Predictive contact tracing

Patent metadata

Field	Value
Publication number	US-11705247-B2
Application number	US-202016952219-A
Country	US
Kind code	B2
Filing date	Nov 19, 2020
Priority date	Nov 19, 2020
Publication date	Jul 18, 2023
Grant date	Jul 18, 2023

Abstract

In an approach to predictive contact tracing, a computer receives a query associated with contact tracing of a person with an infection. A computer retrieves timestamped location data associated with the person over a period of time. Based on the retrieved data, a computer creates a contact graph associated with the person, where the contact graph depicts one or more other people that were in contact with the person over the period of time. A computer retrieves medical data associated with the person and the one or more other people that were in contact with the person over the period of time. Based on the retrieved data, a computer builds a probabilistic model. A computer runs the probabilistic model to provide a prediction of a probability of infection of the one or more other people over the period of time as a result of being in contact with the person.

First claim

What is claimed is:

1. A computer-implemented method comprising:
receiving, by one or more computer processors, a query associated with contact tracing of a person with an infection, wherein the query included a future time horizon;
retrieving, by one or more computer processors, timestamped location data associated with the person over a period of time;
based on the retrieved timestamped location data, creating, by one or more computer processors, a contact graph associated with the person;
retrieving, by one or more computer processors, medical data associated with the person and the one or more other people that were in contact with the person over the period of time;
based on the contact graph and on the retrieved medical data, building, by one or more processors, a probabilistic model;
dividing, by one or more computer processors, the future time horizon into a set of equal subsets;
capturing, by one or more computer processors, one or more dependencies between the person and the one or more other people depicted in the contact graph within each subset of the set of equal subsets of the future time horizon using the probabilistic model;
based on a learned transition probability distribution for each of the one or more other people depicted in the contact graph for each subset of the set of subsets of the future time horizon, creating, by one or more computer processors, a unique graphical probabilistic model for each subset of the set of subsets of the future time horizon;
building, by one or more computer processors, a dynamic probabilistic model by stitching together the unique graphical probabilistic models for each subset of the set of subsets of the future time horizon for each of the one or more other people depicted in the contact graph; and
running, by one or more computer processors, the dynamic probabilistic model to provide the prediction of the probability of infection of the one or more other people over the future time horizon.

2. The computer-implemented method of claim 1 , wherein the probabilistic model is a Markov network.

3. The computer-implemented method of claim 1 , further comprising:
based on the prediction of the probability of infection of the one or more other people over the period of time, generating, by one or more computer processors, a report; and
transmitting, by one or more computer processors, the report.

4. The computer-implemented method of claim 1 , further comprising:
learning, by one or more computer processors, the transition probability distribution for each of the one or more other people depicted in the contact graph for each subset of the set of subsets of the future time horizon.

5. The computer-implemented method of claim 1 , wherein the timestamped location data includes global positioning system (GPS) data and credit card transaction data.

6. The computer-implemented method of claim 1 , wherein creating the contact graph further comprises:
determining, by one or more computer processors, the person is within a pre-defined threshold distance of the one or more other people; and
determining, by one or more computer processors, a period of time when the person was within the pre-defined threshold distance of the one or more other people is greater than a pre-defined threshold period of time.

7. The computer-implemented method of claim 1 , wherein the medical data includes testing and associated results for the infection confirmed in the period of time.

8. A computer program product comprising:
one or more computer readable storage media and program instructions collectively stored on the one or more computer readable storage media, the stored program instructions comprising:
program instructions to receive a query associated with contact tracing of a person with an infection, wherein the query included a future time horizon;
program instructions to retrieve timestamped location data associated with the person over a period of time;
based on the retrieved timestamped location data, program instructions to create a contact graph associated with the person;
program instructions to retrieve medical data associated with the person and the one or more other people that were in contact with the person over the period of time;
based on the contact graph and on the retrieved medical data, program instructions to build a probabilistic model;
program instructions to divide the future time horizon into a set of equal subsets;
program instructions to capture one or more dependencies between the person and the one or more other people depicted in the contact graph within each subset of the set of equal subsets of the future time horizon using the probabilistic model;
based on a learned transition probability distribution for each of the one or more other people depicted in the contact graph for each subset of the set of subsets of the future time horizon, program instructions to create a unique graphical probabilistic model for each subset of the set of subsets of the future time horizon;
program instructions to build a dynamic probabilistic model by stitching together the unique graphical probabilistic models for each subset of the set of subsets of the future time horizon for each of the one or more other people depicted in the contact graph; and
program instructions to run the dynamic probabilistic model to provide the prediction of the probability of infection of the one or more other people over the future time horizon.

9. The computer program product of claim 8 , wherein the probabilistic model is a Markov network.

10. The computer program product of claim 8 , the stored program instructions further comprising:
based on the prediction of the probability of infection of the one or more other people over the period of time, program instructions to generate a report; and
program instructions to transmit the report.

11. The computer program product of claim 8 , the stored program instructions further comprising:
program instructions to learn the transition probability distribution for each of the one or more other people depicted in the contact graph for each subset of the set of subsets of the future time horizon.

12. The computer program product of claim 8 , wherein the timestamped location data includes global positioning system (GPS) data and credit card transaction data.

13. The computer program product of claim 8 , wherein the program instructions to create the contact graph comprise:
program instructions to determine the person is within a pre-defined threshold distance of the one or more other people; and
program instructions to determine a period of time when the person was within the pre-defined threshold distance of the one or more other people is greater than a pre-defined threshold period of time.

14. The computer program product of claim 8 , wherein the medical data includes testing and associated results for the infection confirmed in the period of time.

15. A computer system comprising:
one or more computer processors;
one or more computer readable storage media;
program instructions collectively stored on the one or more computer readable storage media for execution by at least one of the one or more computer processors, the stored program instructions comprising:
program instructions to receive a query associated with contact tracing of a person with an infection, wherein the query included a future time horizon;
program instructions to retrieve timestamped location data associated with the person over a period of time;
based on the retrieved timestamped location data, program instructions to create a contact gra

Assignees

• IBM

Inventors

• Marinescu Radu
• Kishimoto Akihiro

Classifications

• G16H50/80 Primary

  for detecting, monitoring or modelling epidemics or pandemics, e.g. flu · CPC title

• G06F16/9024

  Graphs; Linked lists (G06F16/9027 takes precedence) · CPC title

• G06F17/18

  for evaluating statistical data {, e.g. average values, frequency distributions, probability functions, regression analysis (forecasting specially adapted for a specific administrative, business or logistic context G06Q10/04)} · CPC title

• G16H15/00

  ICT specially adapted for medical reports, e.g. generation or transmission thereof · CPC title

• G16H40/67

  for remote operation · CPC title