# US 2022/0037020 A1 · Modeling external event effects upon system variables

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2022/0037020 A1
- Document ID: US20220037020A1
- Status: Published application
- Kind: A1
- Application number: 16/942,842
- Filed: 2020-07-30
- Published: 2022-02-03
- Earliest claimed: 2020-07-30
- Assignees: International Business Machines Corporation
- Applicants: International Business Machines Corporation
- Inventors: Debarun Bhattacharjya; Tian Gao; Nicholas Scott Mattei; Karthikeyan Shanmugam; Dharmashankar Subramanian; Kush Raj Varshney
- Web page: https://patentgrep.com/patent/US20220037020A1

## CPC

- G16H 50/20: for computer-aided diagnosis, e.g. based on medical expert systems
- G06F 18/29: {Graphical models, e.g. Bayesian networks}
- G06F 30/27: using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
- G06N 7/01: Probabilistic graphical models, e.g. probabilistic networks
- G06N 20/20: Ensemble learning
- G16H 50/70: for mining of medical data, e.g. analysing previous cases of other patients
- G05B 2219/24075: Predict control element state changes, event changes
- G16H: HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G05B: CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS (systems for controlling or regulating non-electric variables G05D; systems for regulating electric or magnetic variables G05F; control devices or systems insofar as characterised by mechanical features only G05G)

## Abstract

Analyzing complex systems by receiving labeled event data describing events occurring in association with a complex system, generating a first machine learning model according to the distribution of labeled event data, receiving state variable transition data describing state variable transitions occurring in association with a complex system, training a second machine learning model according to a combination of a distribution of state variable transitions and the first machine learning model, and using the second machine learning model to predict the effects of events upon state variables within the complex system according to new state variable transition and new labeled event data.

## Claims

### Claim 1

A computer implemented method for analyzing complex systems, the method comprising:
receiving, by one or more computer processors, labeled event data describing events occurring in association with a complex system;
generating, by the one or more computer processors, a first machine learning model according to a distribution of the labeled event data;
receiving, by the one or more computer processors, state variable transition data describing state transitions occurring in association with the complex system;
generating, by the one or more computer processors, a second machine learning model according to a combination of a distribution of state transition data and the first machine learning model; and
using, by the one or more computer processors, the second machine learning model to predict effects of events upon state variables within the complex system according to new state variable transition data and new labeled event data.

### Claim 2 (depends on 1)

The computer implemented method according to claim 1, wherein the first machine learning model comprises a graphical model considering labeled event history during a time duration.

### Claim 3 (depends on 1)

The computer implemented method according to claim 1, wherein the second machine learning model comprises a Bayesian network model considering state variable transitions during a time duration.

### Claim 4 (depends on 1)

The computer implemented method according to claim 1, wherein the complex system comprises a health-related system.

### Claim 5 (depends on 1)

The computer implemented method according to claim 1, wherein the state variable transition data and the labeled event data are time stamped.

### Claim 6 (depends on 1)

The computer implemented method according to claim 1, further comprising computing, by the one or more computer processors, event injections to achieve desired state variable transitions.

### Claim 7 (depends on 1)

The computer implemented method according to claim 1, further comprising predicting, by the one or more computer processors, state variable transitions according to real-time labeled event data.

### Claim 8

A computer program product for analyzing complex system, the computer program product comprising one or more computer readable storage devices and collectively stored program instructions on the one or more computer readable storage devices, the stored program instructions comprising:
program instructions to receive labeled event data describing events occurring in association with a complex system;
program instructions to generate a first machine learning model according to a distribution of the labeled event data;
program instructions to receive state variable transition data describing events occurring in association with the complex system;
program instructions to generate a second machine learning model according to a combination of a distribution of state variable transition data, and the first machine learning model; and
program instructions to use the second machine learning model to predict effects of events upon state variables within the complex system according to new state variable transition and new labeled event data.

### Claim 9 (depends on 8)

The computer program product according to claim 8, wherein the first machine learning model comprises a graphical model considering labeled event history during ae time duration.

### Claim 10 (depends on 8)

The computer program product according to claim 8, wherein the second machine learning model comprises a Bayesian network model considering state variable transitions during a time duration.

### Claim 11 (depends on 8)

The computer program product according to claim 8, wherein the complex system comprises a health-related system.

### Claim 12 (depends on 8)

The computer program product according to claim 8, wherein the state variable transition and the labeled event data are time stamped.

### Claim 13 (depends on 8)

The computer program product according to claim 8, the stored program instructions further comprising program instructions to compute event injections to achieve desired state variable transitions.

### Claim 14 (depends on 8)

The computer program product according to claim 8, the stored program instructions further comprising program instructions to predict state variable transitions according to real-time labeled event data.

### Claim 15

A computer system for analyzing complex systems, the computer system comprising:
one or more computer processors;
one or more computer readable storage devices; and
stored program instructions on the one or more computer readable storage devices for execution by the one or more computer processors, the stored program instructions comprising:
program instructions to receive labeled event data describing events occurring in association with a complex system;
program instructions to generate a first machine learning model according to a distribution of the labeled event data;
program instructions to receive state variable transition data describing state variable transitions occurring in association with the complex system;
program instructions to generate a second machine learning model according to a combination of a distribution of the state variable transitions and the first machine learning model; and
program instructions to use the second machine learning model to predict effects of events upon state variables within the complex system according to new state variable transition data and new labeled event data.

### Claim 16 (depends on 15)

The computer system according to claim 15, wherein the first machine learning model comprises a graphical model considering labeled event data history during a time duration.

### Claim 17 (depends on 15)

The computer system according to claim 15, wherein the second machine learning model comprises a Bayesian network model considering state variable transitions during a time duration.

### Claim 18 (depends on 15)

The computer system according to claim 15, wherein the state variable transition data and the labeled event data are time stamped.

### Claim 19 (depends on 15)

The computer system according to claim 15, the stored program instructions further comprising program instructions to compute event injections to achieve desired state variable transitions.

### Claim 20 (depends on 15)

The computer system according to claim 15, the stored program instructions further comprising program instructions to predict state variable transitions according to real-time labeled event data.
