# US 2023/0065854 A1 · Techniques for measurement device calibration management using calibration offset generation machine learning models

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

- Number: US 2023/0065854 A1
- Document ID: US20230065854A1
- Status: Published application
- Kind: A1
- Application number: 17/465,166
- Filed: 2021-09-02
- Published: 2023-03-02
- Earliest claimed: 2021-09-02
- Assignees: Optum Services (Ireland) Limited
- Applicants: Optum Services (Ireland) Limited
- Inventors: Kieran O'Donoghue; Neill Michael Byrne; Michael J. McCarthy
- Web page: https://patentgrep.com/patent/US20230065854A1

## CPC

- G06N 3/044: Recurrent networks, e.g. Hopfield networks
- G06N 3/0442: characterised by memory or gating, e.g. long short-term memory [LSTM] or gated recurrent units [GRU]
- G06N 3/084: Backpropagation, e.g. using gradient descent
- G16H 10/40: for data related to laboratory analysis, e.g. patient specimen analysis
- G16H 40/40: for the management of medical equipment or devices, e.g. scheduling maintenance or upgrades
- G01D 18/008: {with calibration coefficients stored in memory}
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G16H: HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G01D: MEASURING NOT SPECIALLY ADAPTED FOR A SPECIFIC VARIABLE; ARRANGEMENTS FOR MEASURING TWO OR MORE VARIABLES NOT COVERED IN A SINGLE OTHER SUBCLASS; TARIFF METERING APPARATUS; MEASURING OR TESTING NOT OTHERWISE PROVIDED FOR

## Abstract

Various embodiments of the present invention utilize systems, methods, and computer program products that perform measurement device calibration management by utilizing calibration offset generation machine learning models that are generated using a model training routine that comprises, for each measurement environment feature value: (i) determining a plurality of inferred measurements by a measurement device in relation to a ground-truth measurement operation via performing the ground-truth measurement operation under simulated measurement conditions characterized at least in part by varying a measurement environment feature that is associated with the measurement environment feature value across a per-feature spectrum for the measurement environment feature; and (ii) generating the calibration offset generation machine learning model based at least in part on comparing the plurality of inferred measurements and a ground-truth measurement output for the ground-truth measurement operation.

## Claims

### Claim 1

A computer-implemented method for generating a predicted calibration offset for a measurement output of a measurement device, the computer-implemented method comprising:
identifying, using a processor, a plurality of measurement environment feature values of the measurement device, wherein the plurality of measurement environment features values are associated with a measurement operation associated with the measurement output;
determining, using the processor, based at least in part on the plurality of measurement environment feature values and by utilizing a calibration offset generation machine learning model, the predicted calibration offset, wherein the calibration offset generation machine learning model is generated using a model training routine that comprises, for each measurement environment feature value:
determining a plurality of inferred measurements by the measurement device in relation to a ground-truth measurement operation via performing the ground-truth measurement operation under simulated measurement conditions characterized at least in part by varying a measurement environment feature that is associated with the measurement environment feature value across a per-feature spectrum for the measurement environment feature; and
generating the calibration offset generation machine learning model based at least in part on comparing the plurality of inferred measurements and a ground-truth measurement output for the ground-truth measurement operation; and
performing, using the processor, one or more prediction-based actions based at least in part on the predicted calibration offset.

### Claim 2 (depends on 1)

The computer-implemented method of claim 1, wherein the calibration offset generation machine learning model comprises a recurrent neural network.

### Claim 3 (depends on 2)

The computer-implemented method of claim 2, wherein:
the measurement operation is part of a temporal sequence of measurement operations that comprises a plurality of sequenced measurement operations,
the recurrent neural network is configured to, during each current operational timestep that is associated with a sequenced measurement operation, determine a current hidden state for the current operational timestep based at least in part on the plurality of measurement environment feature values for the sequenced measurement operation and a preceding hidden state for a preceding operational timestep, and
the predicted calibration offset for each sequenced measurement operation is determined based at least in part on the current hidden state for the current operational timestamp that is associated with the sequenced measurement operation.

### Claim 4 (depends on 2)

The computer-implemented method of claim 2, wherein the recurrent neural network is a long-short term memory network.

### Claim 5 (depends on 4)

The computer-implemented method of claim 4, wherein the long-short term memory network is a bidirectional long-short term memory network.

### Claim 6 (depends on 5)

The computer-implemented method of claim 5, wherein the bidirectional long-short term memory network is an attention-based bidirectional long-short term memory network with an attention mechanism.

### Claim 7 (depends on 1)

The computer-implemented method of claim 1, wherein performing the one or more prediction-based actions comprises:
determining a calibrated measurement output based at least in part on the measurement output and the predicted calibration offset; and
performing the one or more prediction-based actions based at least in part on the calibrated measurement output.

### Claim 8 (depends on 1)

The computer-implemented method of claim 1, wherein performing the one or more prediction-based actions comprises:
determining whether the predicted calibration offset satisfies a predicted calibration offset threshold; and
in response to determining that the predicted calibration offset satisfies the predicted calibration offset threshold, automatically performing one or more device recalibration operations for the measurement device.

### Claim 9

An apparatus for generating a predicted calibration offset for a measurement output of a measurement device, the apparatus comprising at least one processor and at least one memory including program code, the at least one memory and the program code configured to, with the processor, cause the apparatus to at least:
identify a plurality of measurement environment feature values of the measurement device, wherein the plurality of measurement environment features values are associated with a measurement operation associated with the measurement output;
determine, based at least in part on the plurality of measurement environment feature values and by utilizing a calibration offset generation machine learning model, the predicted calibration offset, wherein the calibration offset generation machine learning model is generated using a model training routine that comprises, for each measurement environment feature value:
determine a plurality of inferred measurements by the measurement device in relation to a ground-truth measurement operation via performing the ground-truth measurement operation under simulated measurement conditions characterized at least in part by varying a measurement environment feature that is associated with the measurement environment feature value across a per-feature spectrum for the measurement environment feature; and
generate the calibration offset generation machine learning model based at least in part on comparing the plurality of inferred measurements and a ground-truth measurement output for the ground-truth measurement operation; and
perform one or more prediction-based actions based at least in part on the predicted calibration offset.

### Claim 10 (depends on 9)

The apparatus of claim 9, wherein the calibration offset generation machine learning model comprises a recurrent neural network.

### Claim 11 (depends on 10)

The apparatus of claim 10, wherein:
the measurement operation is part of a temporal sequence of measurement operations that comprises a plurality of sequenced measurement operations,
the recurrent neural network is configured to, during each current operational timestep that is associated with a sequenced measurement operation, determine a current hidden state for the current operational timestep based at least in part on the plurality of measurement environment feature values for the sequenced measurement operation and a preceding hidden state for a preceding operational timestep, and
the predicted calibration offset for each sequenced measurement operation is determined based at least in part on the current hidden state for the current operational timestamp that is associated with the sequenced measurement operation.

### Claim 12 (depends on 10)

The apparatus of claim 10, wherein the recurrent neural network is a long-short term memory network.

### Claim 13 (depends on 12)

The apparatus of claim 12, wherein the long-short term memory network is a bidirectional long-short term memory network.

### Claim 14 (depends on 13)

The apparatus of claim 13, wherein the bidirectional long-short term memory network is an attention-based bidirectional long-short term memory network with an attention mechanism.

### Claim 15 (depends on 9)

The apparatus of claim 9, wherein performing the one or more prediction-based actions comprises:
determining a calibrated measurement output based at least in part on the measurement output and the predicted calibration offset; and
performing the one or more prediction-based actions based at least in part on the calibrated measurement output.

### Claim 16 (depends on 9)

The apparatus of claim 9, wherein performing the one or more prediction-based actions comprises:
determining whether the predicted calibration offset satisfies a predicted calibration offset threshold; and
in response to determining that the predicted calibration offset satisfies the predicted calibration offset threshold, automatically performing one or more device recalibration operations for the measurement device.

### Claim 17

A computer program product for generating a predicted calibration offset for a measurement output of a measurement device, the computer program product comprising at least one non-transitory computer-readable storage medium having computer-readable program code portions stored therein, the computer-readable program code portions configured to:
identify a plurality of measurement environment feature values of the measurement device, wherein the plurality of measurement environment features values are associated with a measurement operation associated with the measurement output;
determine, based at least in part on the plurality of measurement environment feature values and by utilizing a calibration offset generation machine learning model, the predicted calibration offset, wherein the calibration offset generation machine learning model is generated using a model training routine that comprises, for each measurement environment feature value:
determine a plurality of inferred measurements by the measurement device in relation to a ground-truth measurement operation via performing the ground-truth measurement operation under simulated measurement conditions characterized at least in part by varying a measurement environment feature that is associated with the measurement environment feature value across a per-feature spectrum for the measurement environment feature; and
generate the calibration offset generation machine learning model based at least in part on comparing the plurality of inferred measurements and a ground-truth measurement output for the ground-truth measurement operation; and
perform one or more prediction-based actions based at least in part on the predicted calibration offset.

### Claim 18 (depends on 17)

The computer program product of claim 17, wherein the calibration offset generation machine learning model comprises a recurrent neural network.

### Claim 19 (depends on 18)

The computer program product of claim 18, wherein:
the measurement operation is part of a temporal sequence of measurement operations that comprises a plurality of sequenced measurement operations,
the recurrent neural network is configured to, during each current operational timestep that is associated with a sequenced measurement operation, determine a current hidden state for the current operational timestep based at least in part on the plurality of measurement environment feature values for the sequenced measurement operation and a preceding hidden state for a preceding operational timestep, and
the predicted calibration offset for each sequenced measurement operation is determined based at least in part on the current hidden state for the current operational timestamp that is associated with the sequenced measurement operation.

### Claim 20 (depends on 18)

The computer program product of claim 18, wherein the recurrent neural network is a long-short term memory network.
