# US 2026/0073293 A1 · Real time detection, prediction and remediation of machine learning model drift in asset hierachy based on 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 2026/0073293 A1
- Document ID: US20260073293A1
- Status: Published application
- Kind: A1
- Application number: 19/106,168
- Filed: 2022-08-24
- Published: 2026-03-12
- Earliest claimed: 2022-08-24
- Assignees: Hitachi Vantara, Ltd.
- Applicants: Hitachi Vantara LLC
- Inventors: Yongqiang ZHANG; Wei LIN
- Web page: https://patentgrep.com/patent/US20260073293A1

## CPC

- G06N 20/00: Machine learning
- 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)}
- G06F 18/10: Pre-processing; Data cleansing
- G06F 18/217: {Validation; Performance evaluation; Active pattern learning techniques}
- G06F 18/22: Matching criteria, e.g. proximity measures
- G06F 18/2321: using statistics or function optimisation, e.g. modelling of probability density functions
- G06N 3/044: Recurrent networks, e.g. Hopfield networks
- G06F 2123/02: in the time domain, e.g. time-series data
- G06N 3/09: Supervised learning
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)

## Abstract

Model drift management of one or more machine learning models deployed across one or more physical systems, including executing a first process configured to detect model drift occurring on the one or more deployed machine learning models in real time, the first process configured to intake time series sensor data of one or more physical systems and one or more labels associated with the time series sensor data to output detected model drift detected from the one or more deployed machine learning models; and executing a second process configured to predict model drift from the one or more deployed machine learning models, the second process configured to intake the output model drifts from the first machine learning model and the time series sensor data to output predicted model drift of the one or more deployed machine learning models, wherein the second process is another machine learning model.

## Claims

### Claim 1

A method for model drift management of one or more machine learning models deployed across one or more physical systems, the method comprising:
executing a first process configured to detect model drift occurring on the one or more deployed machine learning models in real time, the first process configured to intake time series sensor data of one or more physical systems and one or more labels associated with the time series sensor data to output detected model drift detected from the one or more deployed machine learning models; and
executing a second process configured to predict model drift from the one or more deployed machine learning models, the second process configured to intake the output detected model drifts from the first process and the time series sensor data to output predicted model drift of the one or more deployed machine learning models.

### Claim 2 (depends on 1)

The method of claim 1, further comprising executing a remediation process configured to correct model drift on the one or more deployed machine learning models based on the output detected model drift and the output predicted model drift.

### Claim 3 (depends on 1)

The method of claim 1, wherein the first process comprises:
parsing the time series sensor data into training data and testing data;
determining a statistical significance test score for each value in the training data;
clustering the training data based on the statistical significance test score to generate a plurality of clusters;
applying the plurality of clusters to the testing data;
executing one or more of Population Stability Index (PSI) or statistical testing to determine distribution change over time based on the applying of the plurality of clusters to the testing data; and
providing the output detected model drift based on the distribution change exceeding a threshold.

### Claim 4 (depends on 1)

The method of claim 1, wherein, for the first process providing the output detected model drift indicative of an occurrence of model drift, executing a third process to modify the output detected model drift comprising:
calculating, from similar sensors associated with the time series sensor data, similarity scores across a plurality of windows;
executing an anomaly detection process to the similarity scores to generate an anomaly score; and
modifying the output detected model drift for the anomaly score not exceeding a threshold.

### Claim 5 (depends on 1)

The method of claim 1, wherein the first process comprises:
calculating, from similar sensors associated with the time series sensor data, similarity scores across a plurality of windows;
executing an anomaly detection process to the similarity scores to generate an anomaly score; and
providing the output detected model drift based on the anomaly score exceeding a threshold.

### Claim 6 (depends on 1)

The method of claim 1, further comprising parsing the time series sensor data into training data and testing data;
wherein the first process is another machine learning model trained against the training data and configured to input the time series sensor data and the labels to determine model performance of the one or more deployed machine learning models against a ground truth derived from the testing data;
wherein for the first process determining that a first model performance of the one or more deployed machine learning models against the testing data is worse than a second model performance of the one or more deployed machine learning models against the training data, providing the output detected model drift.

### Claim 7 (depends on 1)

The method of claim 1, wherein the second process is a recurrent neural network (RNN) model configured to intake the output detected model drift and a target future time and provide the output predicted model drift at the target future time.

### Claim 8 (depends on 1)

The method of claim 1, wherein the physical systems are configured in an asset hierarchy, wherein the one or more deployed machine learning models are deployed for each one of the physical systems in the asset hierarchy, wherein the first process and the second process are executed from lower level to higher level across the asset hierarchy.

### Claim 9

A non-transitory computer readable medium, storing instructions for model drift management of one or more machine learning models deployed across one or more physical systems, the instructions comprising:
executing a first process configured to detect model drift occurring on the one or more deployed machine learning models in real time, the first process configured to intake time series sensor data of one or more physical systems and one or more labels associated with the time series sensor data to output detected model drift detected from the one or more deployed machine learning models; and
executing a second process configured to predict model drift from the one or more deployed machine learning models, the second process configured to intake the output detected model drifts from the first process and the time series sensor data to output predicted model drift of the one or more deployed machine learning models.

### Claim 10 (depends on 9)

The non-transitory computer readable medium of claim 9, the instructions further comprising executing a remediation process configured to correct model drift on the one or more deployed machine learning models based on the output detected model drift and the output predicted model drift.

### Claim 11 (depends on 9)

The non-transitory computer readable medium of claim 9, wherein the first process comprises:
parsing the time series sensor data into training data and testing data;
determining a statistical significance test score for each value in the training data;
clustering the training data based on the statistical significance test score to generate a plurality of clusters;
applying the plurality of clusters to the testing data;
executing one or more of Population Stability Index (PSI) or statistical testing to determine distribution change over time based on the applying of the plurality of clusters to the testing data; and
providing the output detected model drift based on the distribution change exceeding a threshold.

### Claim 12 (depends on 9)

The non-transitory computer readable medium of claim 9, the instructions, wherein, for the first process providing the output detected model drift indicative of an occurrence of model drift, executing a third process to modify the output detected model drift comprising:
calculating, from similar sensors associated with the time series sensor data, similarity scores across a plurality of windows;
executing an anomaly detection process to the similarity scores to generate an anomaly score; and
modifying the output detected model drift for the anomaly score not exceeding a threshold.

### Claim 13 (depends on 9)

The non-transitory computer readable medium of claim 9, wherein the first process comprises:
calculating, from similar sensors associated with the time series sensor data, similarity scores across a plurality of windows;
executing an anomaly detection process to the similarity scores to generate an anomaly score; and
providing the output detected model drift based on the anomaly score exceeding a threshold.

### Claim 14 (depends on 9)

The non-transitory computer readable medium of claim 9, the instructions further comprising parsing the time series sensor data into training data and testing data;
wherein the first process is another machine learning model trained against the training data and configured to input the time series sensor data and the labels to determine model performance of the one or more deployed machine learning models against a ground truth derived from the testing data;
wherein for the first process determining that a first model performance of the one or more deployed machine learning models against the testing data is worse than a second model performance of the one or more deployed machine learning models against the training data, providing the output detected model drift.

### Claim 15 (depends on 9)

The non-transitory computer readable medium of claim 9, wherein the second process is a recurrent neural network (RNN) model configured to intake the output detected model drift and a target future time and provide the output predicted model drift at the target future time.

### Claim 16 (depends on 9)

The non-transitory computer readable medium of claim 9, wherein the physical systems are configured in an asset hierarchy, wherein the one or more deployed machine learning models are deployed for each one of the physical systems in the asset hierarchy, wherein the first process and the second process are executed from lower level to higher level across the asset hierarchy.

### Claim 17

An apparatus for model drift management of one or more machine learning models deployed across one or more physical systems, the apparatus comprising:
a processor, configured to execute instructions comprising:
executing a first process configured to detect model drift occurring on the one or more deployed machine learning models in real time, the first process configured to intake time series sensor data of one or more physical systems and one or more labels associated with the time series sensor data to output detected model drift detected from the one or more deployed machine learning models; and
executing a second process configured to predict model drift from the one or more deployed machine learning models, the second process configured to intake the output detected model drifts from the first process and the time series sensor data to output predicted model drift of the one or more deployed machine learning models.
