IP Library › Granted Patent US 12,592,826
Granted Patent B2
US 12,592,826 · App. 17/364,044 · Granted Mar 31, 2026

Geospatial-temporal pathogen tracing

Inventors: Daniel Alan Gregory (Cypress, TX); Prithwish Basu (Lowell, MA); Zachary Ratliff (Somerville, MA); Siddharth Pal (Waltham, MA); Kimberly Gavin (Glen Echo, MD); Benjamin Montgomery (Cambridge, MA); Joud Khoury (Boston, MA)
Assignee: RTX BBN TECHNOLOGIES, INC.
H04L9/3221G06N20/00G16H50/20G16H50/80G16H70/60H04L9/3218H04W4/029
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 12,592,826
App. No.
17/364,044
Filed
Jun 30, 2021
Granted
Mar 31, 2026
Kind
B2
Art Unit
1687
USPC
703/11
Abstract

Techniques for geospatial-temporal pathogen tracing include: obtaining, from multiple mobile devices in association with a first time, first contact tracing data including at least first geospatial traffic data and first values of a set of attributes associated with a pathogen; obtaining, from the multiple mobile devices in association with a second time, second contact tracing data including at least second geospatial traffic data and second values of the set of attributes associated with the pathogen; and applying at least the first contact tracing data and the second contact tracing data to a machine learning model, to obtain actionable intelligence associated with the pathogen.

Claims (78)

1 . One or more non-transitory computer-readable media storing instructions that, when executed by one or more processors, cause the one or more processors to perform operations comprising:

obtaining, from a plurality of mobile devices in association with a first time, first contact tracing data comprising at least first geospatial traffic data and first values of a set of attributes associated with a pathogen;

obtaining, from the plurality of mobile devices in association with a second time, second contact tracing data comprising at least second geospatial traffic data and second values of the set of attributes associated with the pathogen;

applying at least the first contact tracing data and the second contact tracing data to a machine learning model;

generating a hypothetical regional graph based on one or more candidate interventions and one or more candidate policies for addressing a test scenario associated with the pathogen, wherein generating the hypothetical regional graph comprises enforcing the one or more candidate policies with respect to addressing the test scenario, and the hypothetical regional graph comprises a plurality of nodes representing respective locations in a geospatial region and a plurality of edges representing a hypothetical traffic flow between the respective locations;

embedding the hypothetical regional graph as a set of points in a latent vector space;

obtaining actionable intelligence associated with the pathogen based on:

applying at least the first contact tracing data and the second contact tracing data to the machine learning model; and

embedding the hypothetical regional graph in the latent vector space,

wherein the actionable intelligence comprises a candidate response to the pathogen and an effect of the candidate response with respect to the pathogen, and the candidate response comprises the one or more candidate interventions or the one or more candidate policies;

providing the actionable intelligence to a notification platform;

transmitting, via the notification platform and based on the actionable intelligence, exposure notifications to a mobile device of a user having a pathogen exposure risk to the pathogen; and

transmitting, via the notification platform, the actionable intelligence to a policymaker responsible for evaluating the candidate response.

2 . The one or more non-transitory computer-readable media of claim 1 , the machine learning model being a temporal self-attention network.

3 . The one or more non-transitory computer-readable media of claim 2 , the operations further comprising:

generating a first regional graph based at least on the first contact tracing data;

embedding the first regional graph as a first set of points in a first latent vector space;

generating a second regional graph based at least on the second contact tracing data;

embedding the second regional graph as a second set of points in a second latent vector space; and

generating the temporal self-attention network based at least on the first latent vector space and the second latent vector space.

4 . The one or more non-transitory computer-readable media of claim 3 , the first regional graph comprising a second plurality of nodes representing respective locations in the geospatial region and a second plurality of edges representing traffic flow between the respective locations.

5 . The one or more non-transitory computer-readable media of claim 1 , the operations further comprising:

based at least on the actionable intelligence, determining a predicted future hotspot for the pathogen.

6 . The one or more non-transitory computer-readable media of claim 1 , the operations further comprising:

based at least on the actionable intelligence, determining a pathogen exposure risk of a user of a mobile device in the plurality of mobile devices.

7 . The one or more non-transitory computer-readable media of claim 1 , obtaining the first contact tracing data comprising using at least one preprocessing zero knowledge succinct non-interactive argument of knowledge (pp-zk-SNARK) to preserve privacy of a plurality of users of the plurality of mobile devices.

8 . A system comprising:

at least one device including a hardware processor;

the system being configured to perform operations comprising:

obtaining, from a plurality of mobile devices in association with a first time, first contact tracing data comprising at least first geospatial traffic data and first values of a set of attributes associated with a pathogen;

obtaining, from the plurality of mobile devices in association with a second time, second contact tracing data comprising at least second geospatial traffic data and second values of the set of attributes associated with the pathogen;

applying at least the first contact tracing data and the second contact tracing data to a machine learning model;

generating a hypothetical regional graph based on one or more candidate interventions and one or more candidate policies for addressing a test scenario associated with the pathogen, wherein generating the hypothetical regional graph comprises enforcing the one or more candidate policies with respect to addressing the test scenario, and the hypothetical regional graph comprises a plurality of nodes representing respective locations in a geospatial region and a plurality of edges representing a hypothetical traffic flow between the respective locations;

embedding the hypothetical regional graph as a set of points in a latent vector space;

obtaining actionable intelligence associated with the pathogen based on:

applying at least the first contact tracing data and the second contact tracing data to the machine learning model; and

embedding the hypothetical regional graph in the latent vector space,

wherein the actionable intelligence comprises a candidate response to the pathogen and an effect of the candidate response with respect to the pathogen, and the candidate response comprises the one or more candidate interventions or the one or more candidate policies;

providing the actionable intelligence to a notification platform;

transmitting, via the notification platform and based on the actionable intelligence, exposure notifications to a mobile device of a user having a pathogen exposure risk to the pathogen; and

transmitting, via the notification platform, the actionable intelligence to a policymaker responsible for evaluating the candidate response.

9 . The system of claim 8 , the machine learning model being a temporal self-attention network.

10 . The system of claim 9 , the operations further comprising:

generating a first regional graph based at least on the first contact tracing data;

embedding the first regional graph as a first set of points in a first latent vector space;

generating a second regional graph based at least on the second contact tracing data;

embedding the second regional graph as a second set of points in a second latent vector space; and

generating the temporal self-attention network based at least on the first latent vector space and the second latent vector space.

11 . The system of claim 10 , the first regional graph comprising a second plurality of nodes representing respective locations in the geospatial region and a second plurality of edges representing traffic flow between the respective locations.

12 . The system of claim 8 , the operations further comprising:

based at least on the actionable intelligence, determining one or more of a predicted future hotspot for the pathogen or a pathogen exposure risk of a user of a mobile device in the plurality of mobile devices.

13 . The system of claim 8 , obtaining the first contact tracing data comprising using at least one preprocessing zero knowledge succinct non-interactive argument of knowledge (pp-zk-SNARK) to preserve privacy of a plurality of users of the plurality of mobile devices.

14 . A method comprising:

obtaining, from a plurality of mobile devices in association with a first time, first contact tracing data comprising at least first geospatial traffic data and first values of a set of attributes associated with a pathogen;

obtaining, from the plurality of mobile devices in association with a second time, second contact tracing data comprising at least second geospatial traffic data and second values of the set of attributes associated with the pathogen;

applying at least the first contact tracing data and the second contact tracing data to a machine learning model;

generating a hypothetical regional graph based on one or more candidate interventions of and one or more candidate policies for addressing a test scenario associated with the pathogen, wherein generating the hypothetical regional graph comprises enforcing the one or more candidate policies with respect to addressing the test scenario, and the hypothetical regional graph comprises a plurality of nodes representing respective locations in a geospatial region and a plurality of edges representing a hypothetical traffic flow between the respective locations;

embedding the hypothetical regional graph as a set of points in a latent vector space;

obtaining actionable intelligence associated with the pathogen based on:

applying at least the first contact tracing data and the second contact tracing data to the machine learning model; and

embedding the hypothetical regional graph in the latent vector space,

wherein the actionable intelligence comprises a candidate response to the pathogen and an effect of the candidate response with respect to the pathogen, and the candidate response comprises the one or more candidate interventions or the one or more candidate policies;

providing the actionable intelligence to a notification platform;

transmitting, via the notification platform and based on the actionable intelligence, exposure notifications to a mobile device of a user having a pathogen exposure risk to the pathogen; and

transmitting, via the notification platform, the actionable intelligence to a policymaker responsible for evaluating the candidate response.

15 . The method of claim 14 , the machine learning model being a temporal self-attention network.

16 . The method of claim 15 , further comprising:

generating a first regional graph based at least on the first contact tracing data;

embedding the first regional graph as a first set of points in a first latent vector space;

generating a second regional graph based at least on the second contact tracing data;

embedding the second regional graph as a second set of points in a second latent vector space; and

generating the temporal self-attention network based at least on the first latent vector space and the second latent vector space.

17 . The method of claim 16 , the first regional graph comprising a second plurality of nodes representing respective locations in the geospatial region and a second plurality of edges representing traffic flow between the respective locations.

18 . The method of claim 14 , further comprising:

based at least on the actionable intelligence, determining a predicted future hotspot for the pathogen.

19 . The method of claim 14 , further comprising:

based at least on the actionable intelligence, determining a pathogen exposure risk of a user of a mobile device in the plurality of mobile devices.

20 . The method of claim 14 , obtaining the first contact tracing data comprising using at least one preprocessing zero knowledge succinct non-interactive argument of knowledge (pp-zk-SNARK) to preserve privacy of a plurality of users of the plurality of mobile devices.

Assignments (2)
CHANGE OF NAME Recorded Aug 22, 2024
From: RAYTHEON BBN TECHNOLOGIES CORP.
To: RTX BBN TECHNOLOGIES, INC.
Reel/Frame 068748/0419 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Sep 26, 2022
From: GREGORY, DANIEL ALAN; BASU, PRITHWISH; RATLIFF, ZACHARY; PAL, SIDDHARTH; GAVIN, KIMBERLY; MONTGOMERY, BENJAMIN; KHOURY, JOUD
To: RAYTHEON BBN TECHNOLOGIES CORP.
Reel/Frame 061215/0280 →
Continuity (2)
Provisional Application 63046815 · Jul 1, 2020
Related Publication 20220037035A1 · Feb 3, 2022
References Cited (32)
US 10887104B1 · Jayachandran et al. · 2021 [cited by applicant]
US 20160219012A1 · Liao et al. · 2016 [cited by applicant]
US 20210365445A1 · Robell et al. · 2021 [cited by applicant]
US 20220006635A1 · Gregory et al. · 2022 [cited by applicant]
Vazquez-Prokopec GM, Montgomery BL, Horne P, Clennon JA, Ritchie SA. Combining contact tracing with targeted indoor residual spraying significantly reduces dengue transmission. Sci Adv. Feb. 17, 2017;3(2):e1602024. DOI:… [cited by examiner]
Alsdurf, H.; Belliveau, E.; Bengio, Y.; Deleu, T.; Gupta, P.; Ippolito, D.; Janda, R.; Jarvie, M.; Kolody, T.; Krastev, S.; et al. COVI white paper version 1.0. arXiv 2020, arXiv:2005.08502v1, https://arxiv.org/abs/2005… [cited by examiner]
Chan, J, Gollakota, S, Horvitz, E, et al. PACT: privacy sensitive protocols and mechanisms for mobile contact tracing. arXiv 2020, arXiv:2004.03544v4, https://arxiv.org/abs/2004.03544. (Year: 2020). [cited by examiner]
Trieu, N, Shehata K, Saxena, P, Shokri, R, and Song, D. Epione: Lightweight contact tracing with strong privacy. arXiv 2020, arXiv:2004.13293, https://arxiv.org/abs/2004.13293. (Year: 2020). [cited by examiner]
Petkus, M. Why and how zk-SNARK works. arXiv 2019, arXiv: 1906.07221, https://arxiv.org/abs/1906.07221. (Year: 2019). [cited by examiner]
Lin, H., Jia, W., Sun, Y., and You, Y. Spatial-Temporal Self-Attention Network for Flow Prediction. arXiv 2019, arXiv: 1912.07663, https://arxiv.org/abs/1912.07663. (Year: 2019). [cited by examiner]
Ratliff Zachary et al: 11 zkSNARKs to the rescue: proof-of-contact in zero knowledge, arXiv, Jun. 7, 2020 (Jun. 7, 2020), XP055840397, Retrieved from the Internet: URL:https://arxiv.org/pdf/2005.12676v3.pdf. [cited by applicant]
Jean-Franois Biasse et al: Trace-Sigma: 1-15 a privacy-preserving contact tracing app, IACR, International Association for Cryptologic Research vol. 20200627:185311, Jun. 25, 2020 (Jun. 25, 2020), pp. 1-7, XP061036046, … [cited by applicant]
Joseph K Liu et al: Privacy-Preserving COVID-19 Contact Tracing App: A Zero-Knowledge Proof Approach , IACR, International Association for Cryptologic Research, vol. 20200506:134353, May 6, 2020 (May 6, 2020), pp. 1-22,… [cited by applicant]
Hannah Alsdurf et al: “COVI White Paper”, 1-15 arxiv.org, Cornell University Library, 201 Olin Library Cornell University Ithaca, NY, 14853, May 18, 2020 (May 18, 2020), XP081671734, pp. 8,23, pp. 35-42. [cited by applicant]
Ye Xia et al: “How to Return to Normalcy: 1-15 Fast and Comprehensive Contact Tracing of COVID-19 through Proximity Sensing Using Mobile Devices”, arxiv.org, Cornell University Library, 201 Olin Library Cornell Universi… [cited by applicant]
Xueping Peng et al: “Temporal 1-15 Self-Attention Network for Medical Concept Embedding”, arxiv.org, Cornell University Library, 201 Olin Library Cornell University Ithaca, NY, 14853, Sep. 15, 2019 (Sep. 15, 2019), XP08… [cited by applicant]
European Search Report for application EP21182938 dated Nov. 18, 2021. [cited by applicant]
Canetti; Ran et al. “Anonymous Collocation Discovery: Harnessing Privacy to Tame the Coronavirus” [online] Arxiv, Apr. 7, 2020 [retrieved May 20, 2023]. Retrieved from the Internet: URL: https://arxiv.org/pdf/2003.13670… [cited by applicant]
Ben-Sasson; Eli et al. “Scalable Zero Knowledge via Cycles of Elliptic Curves” [online] IACR, Sep. 18, 2016 [retrieved May 20, 2023]. Retrieved from the Internet: URL: https://eprintiacrorg/2014/595.pdf (Year: 2016). [cited by applicant]
Dijour; Dean “NOVID: Anonymous Contact Tracing with Ultrasound” [online] Wevolver, May 12, 2020 [retrieved May 20, 2023].Retrieved from the Internet. URL: https://www.wevolvercom/article/novid.anonymous.contact.tracing.… [cited by applicant]
Xie; Tiancheng et al. “Libra: Succinct Zero-Knowledge Proofs with Optimal Prover Computation” [onlines] IACR, Dec. 24, 2019 [retrieved May 20, 2023]. Retrieved from the Internet: URL: https://eprint.iacr.org/archive/201… [cited by applicant]
Trieu; Ni et al. “Epione: Lightweight Contact Tracing with Strong Privacy” [online] arxiv, May 2, 2020 [retrieved May 20, 2023]. Retrieved from the Internet: URL: https://arxiv.org/pdf/2004.13293.pdf (Year: 2020). [cited by applicant]
Chiesa; Alessandro et al. “Marlin: Preprocessing zkSNARKs with Universal and Updatable SRS” [online] IACR, Jan. 1, 2020 [retrieved May 20, 2023]. Retrieved from the Internet: URL: https://eprintiacrorg/archive/2019/1047… [cited by applicant]
Groth, Jens “On the Size of Pairing-base Non-interactive Arguments” [online] IACR, May 31, 2016 [retrieved May 20, 2023]. Retrieved from the Internet: URL: https://eprint.iacr.org/2016/260.pdf (Year: 2016). [cited by applicant]
Zhang, “Graph deep learning model for network-based predictive hotspot mapping of sparse spatio-temporal events”; Elsevier; Computer, Environment and Urban Systems 79, 2019; 12 pages. [cited by applicant]
Liao, L., He, X., Zhang, H. and Chua, T.S., 2018. Attributed social network embedding. IEEE Transactions on Knowledge and Data Engineering, 30(12), pp. 2257-2270. [cited by applicant]
R. Canetti, Y. T. Kalai, A. Lysyanskaya, R. L. Rivest, A. Shamir, E. Shen, A. Trachtenberg, M. Varia, and D. J. Weitzner, “Privacy-preserving automated exposure notification,” Cryptology ePrint Archive, Report 2020/863,… [cited by applicant]
Alsdurf et al., “COVI white paper” arXiv preprint arXiv:2005.08502 (2020) pp. 1-63. [cited by applicant]
Chan et al., “PACT: privacy sensitive protocols and mechanisms for mobile contact tracing” (Year 2020) pp. 1-22. [cited by applicant]
Lin et al., “Spatial-Temporal Self-Attention Network for Flow Prediction” arXiv preprint arXiv:1912.07663 (2019) pp. 1-8. [cited by applicant]
Petkus “Why and how zk-SNARK works: Definitive Explanation” arXiv preprint arXiv:1906.07221 (2019) pp. 1-65. [cited by applicant]
Vazquez-Prokopec et al., “Combining contact tracing with targeted indoor residual spraying significantly reduces dengue transmission” Sci Adv. Feb. 17, 2017; 3(2): e1602024 (Year 2017) pp. 1-9. [cited by applicant]