# US 12,118,061 B2 · Computerized methods and systems for machine-learned multi-output multi-step forecasting of time-series data

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

- Number: US 12,118,061 B2
- Document ID: US12118061B2
- Status: Granted
- Kind: B2
- Application number: 18/224,097
- Filed: 2023-07-20
- Published: 2023-11-16
- Granted: 2024-10-15
- Earliest claimed: 2019-03-29
- Assignees: Cigna Intellectual Property, Inc.
- Applicants: Cigna Intellectual Property, Inc.
- Inventors: Armand E. Prieditis; John E. Paton
- Web page: https://patentgrep.com/patent/US12118061B2

## CPC

- G06F 17/18: 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)}
- G01W 1/10: Devices for predicting weather conditions (computers per se G06; display devices G09)
- G06F 7/24: Sorting, i.e. extracting data from one or more carriers, rearranging the data in numerical or other ordered sequence, and rerecording the sorted data on the original carrier or on a different carrier or set of carriers {sorting methods in general}(G06F7/36 takes precedence)
- G06F 17/16: Matrix or vector computation {, e.g. matrix-matrix or matrix-vector multiplication, matrix factorization (matrix transposition G06F7/78)}
- G16H 40/67: for remote operation
- G16H 50/20: for computer-aided diagnosis, e.g. based on medical expert systems
- G16H 50/30: for calculating health indices; for individual health risk assessment
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G01W: METEOROLOGY (radar, sonar, lidar or analogous systems, designed for meteorological use G01S13/95, G01S15/88, G01S17/95)
- G16H: HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA

## Abstract

A method includes, in response to receiving a forecasting request from a user device via a web portal, determining a measure of uncertainty associated with an input vector specified by the forecasting request. The measure of uncertainty includes a compact representation of uncertainty associated with future time intervals specified by the forecasting request. The method includes obtaining a set of historical data from a time-series data store. The method includes generating a forecast model using the set of historical data, the input vector, and the measure of uncertainty to predict outcomes incrementally for the future time intervals. The method includes determining a predicted outcome using the forecast model at an end of the future time intervals. The method includes, in response to the predicted outcome exceeding a threshold, generating a graphical user interface. The graphical user interface illustrates the mean vector and a magnitude of the predicted uncertainty measure.

## Claims

### Claim 1

A forecasting system comprising:
a processor circuit; and
a memory circuit coupled to the processor circuit,
wherein the memory circuit stores:
a time-series data store including historical data; and
instructions for execution by the processor circuit,
wherein the instructions include:
displaying, on a user device, a graphical user interface of a web portal, and
in response to receiving a forecasting request from the user device via the graphical user interface of the web portal;
determining a measure of uncertainty associated with an input vector specified by the forecasting request, wherein the measure of uncertainty includes a compact representation of uncertainty associated with future time intervals specified by the forecasting request;
obtaining a set of historical data from the time-series data store;
generating a forecast model using the set of historical data, the input vector, and the measure of uncertainty to predict outcomes incrementally for the future time intervals, wherein:
the forecast model is configured to generate a mean vector and a predicted uncertainty measure,
the predicted uncertainty measure is generated based on the compact representation of uncertainty,
the mean vector includes mean values corresponding respectively to the future time intervals, and
the compact representation of uncertainty is carried forward for the future time intervals;
determining a predicted outcome using the forecast model at an end of the future time intervals; and
in response to the predicted outcome exceeding a threshold, updating, via the web portal, the graphical user interface at the user device to display:
the mean vector and a magnitude of the predicted uncertainty measure, and
a communication indicating a proposed action associated with the input vector, the set of historical data, the mean vector, and the magnitude of the predicted uncertainty measure.

### Claim 2 (depends on 1)

The system of claim 1 wherein the predicted outcome is multi-output and multi-step.

### Claim 3 (depends on 1)

The system of claim 1 wherein the forecast model is configured to generate the mean vector and the predicted uncertainty measure based on a linear function.

### Claim 4 (depends on 1)

The system of claim 1 wherein the measure of uncertainty is carried forward for each of the future time intervals of the forecasting request.

### Claim 5 (depends on 4)

The system of claim 4 wherein the measure of uncertainty includes, for each future time interval of the future time intervals of the forecasting request, a compact representation of uncertainty for the future time interval.

### Claim 6 (depends on 1)

The system of claim 1 wherein the graphical user interface is configured to illustrate the magnitude of the predicted uncertainty measure using error bars representing values of the predicted uncertainty measure.

### Claim 7 (depends on 1)

The system of claim 1 wherein the set of historical data is associated with the proposed action.

### Claim 8 (depends on 7)

The system of claim 7 wherein the proposed action includes at least one of a method of communication, a frequency of communication, and a desired outcome.

### Claim 9 (depends on 1)

The system of claim 1 wherein the forecasting request includes (i) the input vector and (ii) a number of steps representing a number of future time intervals of the forecasting request.

### Claim 10 (depends on 1)

The system of claim 1 wherein the forecast model is specific to an entity specified by the forecasting request.

### Claim 11 (depends on 10)

The system of claim 10 wherein:
the entity is a patient; and
the time-series data store includes time-series data for at least one of a blood pressure, a heart rate, and a blood glucose level of the patient.

### Claim 12 (depends on 10)

The system of claim 10 wherein the instructions include:
determining a second predicted outcome for the entity using a second proposed action;
calculating a value equal to the predicted outcome less the second predicted outcome; and
based on the value, displaying on the user device a likelihood of success of the proposed action, wherein performing the second proposed action excludes performing the proposed action.

### Claim 13 (depends on 1)

The system of claim 1 wherein the instructions include, in response to the forecasting request from the user device including a set of entities:
for each entity of the set of entities:
determining the predicted outcome, and
adding the predicted outcome to an outcome list;
rearranging the outcome list based on a value of each predicted outcome;
selecting a reduced set of predicted outcomes greater than the threshold;
identifying a reduced set of entities corresponding to each predicted outcome included in the reduced set of predicted outcomes; and
displaying the reduced set of entities to the user device.

### Claim 14 (depends on 1)

The system of claim 1 wherein the predicted uncertainty measure is sized based on a sum of a number of input features of the forecast model and a number of output features of the forecast model.

### Claim 15 (depends on 1)

The system of claim 1 wherein:
the mean vector includes a first piece of data and a second piece of data,
the first piece of data represents data occurring a time interval after the second piece of data,
the first piece of data corresponds to output of the forecast model, and the second piece of data corresponds to input of the forecast model.

### Claim 16 (depends on 1)

The system of claim 1 wherein the predicted uncertainty measure includes:
a first matrix associated with output of the forecast model,
a second matrix associated with input of the forecast model, and
a third matrix associated with an output relationship between outputs of the forecast model and an input relationship between inputs of the forecast model.

### Claim 17

A non-transitory computer-readable medium comprising instructions including:
displaying, on a user device, a graphical user interface of a web portal; and
in response to receiving a forecasting request from the user device via the graphical user interface of the web portal:
determining a measure of uncertainty associated with an input vector specified by the forecasting request, wherein the measure of uncertainty includes a compact representation of uncertainty associated with future time intervals specified by the forecasting request;
obtaining a set of historical data from a time-series data store;
generating a forecast model using the set of historical data, the input vector, and the measure of uncertainty to predict outcomes incrementally for the future time intervals, wherein:
the forecast model is configured to generate a mean vector and a predicted uncertainty measure,
the predicted uncertainty measure is generated based on the compact representation of uncertainty,
the mean vector includes mean values corresponding respectively to the future time intervals, and
the compact representation of uncertainty is carried forward for the future time intervals;
determining a predicted outcome using the forecast model at an end of the future time intervals; and
in response to the predicted outcome exceeding a threshold, updating, via the web portal, the graphical user interface at the user device to display:
the mean vector and a magnitude of the predicted uncertainty measure, and
a communication indicating a proposed action associated with the input vector, the set of historical data, the mean vector, and the magnitude of the predicted uncertainty measure.

### Claim 18

A computer-implemented method comprising:
displaying, on a user device, a graphical user interface of a web portal; and
in response to receiving a forecasting request from the user device via the graphical user interface of the web portal:
determining a measure of uncertainty associated with an input vector specified by the forecasting request, wherein the measure of uncertainty includes a compact representation of uncertainty associated with future time intervals specified by the forecasting request;
obtaining a set of historical data from a time-series data store;
generating a forecast model using the set of historical data, the input vector, and the measure of uncertainty to predict outcomes incrementally for the future time intervals, wherein:
the forecast model is configured to generate a mean vector and a predicted uncertainty measure,
the predicted uncertainty measure is generated based on the compact representation of uncertainty,
the mean vector includes mean values corresponding respectively to the future time intervals, and
the compact representation of uncertainty is carried forward for the future time intervals;
determining a predicted outcome using the forecast model at an end of the future time intervals; and
in response to the predicted outcome exceeding a threshold, updating, via the web portal, the graphical user interface at the user device to display:
the mean vector and a magnitude of the predicted uncertainty measure, and
a communication indicating a proposed action associated with the input vector, the set of historical data, the mean vector, and the magnitude of the predicted uncertainty measure.