# US 12,117,891 B2 · Deducing a root cause analysis model from augmented reality peer assistance sessions

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

- Number: US 12,117,891 B2
- Document ID: US12117891B2
- Status: Granted
- Kind: B2
- Application number: 17/195,751
- Filed: 2021-03-09
- Published: 2022-09-15
- Granted: 2024-10-15
- Earliest claimed: 2021-03-09
- Assignees: International Business Machines Corporation
- Applicants: International Business Machines Corporation
- Inventors: Adi Raz Goldfarb; Oded Dubovsky; Erez Lev Meir Bilgory
- Web page: https://patentgrep.com/patent/US12117891B2

## CPC

- G06F 11/079: {Root cause analysis, i.e. error or fault diagnosis (in a hardware test environment G06F11/22; in a software test environment G06F11/36)}
- G06F 18/214: Generating training patterns; Bootstrap methods, e.g. bagging or boosting
- G06F 18/2431: Multiple classes
- G06N 5/022: Knowledge engineering; Knowledge acquisition
- G06N 20/00: Machine learning
- G06T 19/006: {Mixed reality (object pose determination, tracking or camera calibration for mixed reality G06T7/00)}
- G06N 5/02: Knowledge representation; Symbolic representation
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL

## Abstract

In an approach for deducing a root cause analysis model, a processor trains a classifier based on labeled data to identify entities. A processor trains the classifier with first taxonomy and ontology. A processor uses the classifier to classify each component from one or more augmented reality peer assistance sessions into a class. A processor generates a root cause analysis model based on the identified entities and the classified components.

## Claims

### Claim 1

A computer-implemented method comprising:
correlating information exchanged between two or more parties during a remote assistance session to one or more data labels;
labeling the correlated information with corresponding data labels to create labeled data components;
training a classifier based on the labeled data components to identify entities, wherein the step of training further comprises:
extracting the labeled data components ordered by time from the correlated information;
augmenting the trained classifier with a taxonomy and a pre-defined domain ontology;
using the augmented classifier to classify each labeled data component into a class selected from the classes: (a) symptom; (b) root cause; (c) instruction; and (d) miscellaneous; and
generating a root cause analysis (RCA) model based on the identified entities and the classified labeled data components.

### Claim 2 (depends on 1)

The computer-implemented method of claim 1, further comprising:
augmenting the classifier based on a second taxonomy and a second domain-specific ontology; and
augmenting the classifier based on additional labeled data from a user.

### Claim 3 (depends on 1)

The computer-implemented method of claim 1, further comprising:
using the classifier to classify the remote assistance session stored in the customer enterprise asset management system; and
adjusting the RCA model based on the remote assistance session.

### Claim 4 (depends on 1)

The computer-implemented method of claim 1, further comprising:
augmenting the entities in a domain ontology based on customer-specific entities; and
training the classifier based on the augmented entities.

### Claim 5 (depends on 1)

The computer-implemented method of claim 1, wherein the labeled data includes annotated texts, captioned conversations, and augmented reality annotations.

### Claim 6 (depends on 1)

The computer-implemented method of claim 1, wherein the class is selected from the group consisting of: a symptom, a root cause, an instruction, and a miscellaneous item.

### Claim 7 (depends on 1)

The computer-implemented method of claim 1, wherein each component is selected from the group consisting of: an utterance, an augmented reality annotation, a voice, an image, and a video.

### Claim 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 program instructions comprising:
program instructions to correlate information exchanged between two or more parties during a remote assistance session to one or more data labels;
program instructions to label the correlated information with corresponding data labels to create labeled data components;
program instructions to train a classifier based on the labeled data components to identify entities, wherein the step of training further comprises:
program instructions to extract the labeled data components ordered by time from the correlated information;
program instructions to augment the trained classifier with a taxonomy and a pre-defined domain ontology;
program instructions to use the augmented classifier to classify each labeled data component into a class selected from the classes: (a) symptom; (b) root cause; (c) instruction; and (d) miscellaneous; and
program instructions to generate a root cause analysis (RCA) model based on the identified entities and the classified labeled data components.

### Claim 9 (depends on 8)

The computer program product of claim 8, the program instructions further comprising:
program instructions to augment the classifier based on second taxonomy and ontology; and
program instructions to augment the classifier based on additional labeled data from a user.

### Claim 10 (depends on 8)

The computer program product of claim 8, the program instructions further comprising:
program instructions to use the classifier to classify the remote assistance session stored in the customer enterprise asset management system; and
program instructions to adjust the RCA model based on the stored remote assistance session.

### Claim 11 (depends on 8)

The computer program product of claim 8, the program instructions further comprising:
program instructions to augment the entities in a domain ontology based on customer-specific entities; and
program instructions to train the classifier based on the augmented entities.

### Claim 12 (depends on 8)

The computer program product of claim 8, wherein the labeled data includes annotated texts, captioned conversations, and augmented reality annotations.

### Claim 13 (depends on 8)

The computer program product of claim 8, wherein the class is selected from the group consisting of: a symptom, a root cause, an instruction, and a miscellaneous item.

### Claim 14 (depends on 8)

The computer program product of claim 8, wherein each component is selected from the group consisting of: an utterance, an augmented reality annotation, a voice, an image, and a video.

### Claim 15

A computer system comprising:
one or more computer processors, one or more computer readable storage media, and program instructions stored on the one or more computer readable storage media for execution by at least one of the one or more computer processors, the program instructions comprising:
program instructions to correlate information exchanged between two or more parties during a remote assistance session to one or more data labels;
program instructions to label the correlated information with corresponding data labels to create labeled data components;
program instructions to train a classifier based on the labeled data components to identify entities, wherein the step of training further comprises:
program instructions to extract the labeled data components ordered by time from the correlated information;
program instructions to augment the trained classifier with a taxonomy and a pre-defined domain ontology;
program instructions to use the augmented classifier to classify each labeled data component into a class selected from the classes: (a) symptom; (b) root cause; (c) instruction; and (d) miscellaneous; and
program instructions to generate a root cause analysis (RCA) model based on the identified entities and the classified labeled data components.

### Claim 16 (depends on 15)

The computer system of claim 15, the program instructions further comprising:
program instructions to augment the classifier based on second taxonomy and ontology; and
program instructions to augment the classifier based on additional labeled data from a user.

### Claim 17 (depends on 15)

The computer system of claim 15, the program instructions further comprising:
program instructions to use the classifier to classify the remote assistance session in the customer enterprise asset management system; and
program instructions to adjust the RCA model based on the remote assistance session.

### Claim 18 (depends on 15)

The computer system of claim 15, the program instructions further comprising:
program instructions to augment the entities in a domain ontology based on customer-specific entities; and
program instructions to train the classifier based on the augmented entities.

### Claim 19 (depends on 15)

The computer system of claim 15, wherein the labeled data includes annotated texts, captioned conversations, and augmented reality annotations.

### Claim 20 (depends on 15)

The computer system of claim 15, wherein the class is selected from the group consisting of: a symptom, a root cause, an instruction, and a miscellaneous item.