# US 2026/0094033 A1 · Dynamic explainable artificial intelligence pipeline composability and customization

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

- Number: US 2026/0094033 A1
- Document ID: US20260094033A1
- Status: Published application
- Kind: A1
- Application number: 19/111,676
- Filed: 2023-03-30
- Published: 2026-04-02
- Earliest claimed: 2022-09-15
- Assignees: Intel Corporation
- Applicants: Intel Corporation
- Inventors: Ria Cheruvu; Harsha Bajpai; Arshad Mehmood; Saima Sharmin
- Web page: https://patentgrep.com/patent/US20260094033A1

## CPC

- G06N 5/045: Explanation of inference; Explainable artificial intelligence [XAI]; Interpretable artificial intelligence
- G06N 3/063: using electronic means
- G06N 3/08: Learning methods
- G06N 20/00: Machine learning
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS

## Abstract

Various systems and methods are described for explainable artificial intelligence (AI) operations, workflows, and implementing systems are discussed. In an example, explainable AI operations are coordinated in a computing system, by: receiving a schema for the explainable AI operations, the schema corresponding to a persona role used to evaluate an AI model; coordinating or performing the explainable AI operations, the explainable AI operations including: data analysis on output data produced from the AI model, and model analysis on performance of the AI model; and outputting explanation data from the explainable AI operations, the explanation data customized based on the schema. The explanation data may include a variety of data metrics and values used for reports, deployment, and monitoring.

## Claims

### Claim at position 1

-21. (canceled)

### Claim 22

A computing device configured to coordinate explainable artificial intelligence (AI) operations, comprising:
processing circuitry; and
a memory device including instructions embodied thereon, wherein the instructions, which when executed by the processing circuitry, configure the processing circuitry to cause operations that:
receive a schema for the explainable AI operations, the schema corresponding to a persona role used to evaluate an AI model;
control the explainable AI operations, the explainable AI operations including:
data analysis on output data produced from the AI model, and model analysis on performance of the AI model; and
output explanation data based on the explainable AI operations, wherein the explanation data is customized to the persona role based on the schema.

### Claim 23 (depends on 22)

The computing device of claim 22, wherein the data analysis includes data slicing of the output data based on data quality metrics, and wherein the model analysis includes performance metrics for the AI model based on the data slicing.

### Claim 24 (depends on 23)

The computing device of claim 23, wherein the explanation data is a visualization, and wherein the visualization provides a representation of the performance metrics that correspond to a cohort analysis.

### Claim 25 (depends on 23)

The computing device of claim 23, wherein image data is provided as input data to the AI model, and wherein the AI model performs object detection on the image data;
wherein the data quality metrics correspond to one or more of: data slicing by size sensitivity level, data slicing by occlusion level, or data slicing by lighting level;
wherein the performance metrics are provided for each slice per object detection class, and wherein the explanation data corresponds to metrics per data attribute per slice.

### Claim 26 (depends on 22)

The computing device of claim 22, wherein the explainable AI operations include reliability scoring based on a processing of input data by the AI model;
wherein the explanation data includes a robustness score for the AI model, and wherein the robustness score is produced based on the reliability scoring.

### Claim 27 (depends on 22)

The computing device of claim 22, wherein the instructions configure the processing circuitry to cause operations that:
perform retraining of the AI model, based on the explanation data.

### Claim 28 (depends on 22)

The computing device of claim 22, wherein the instructions configure the processing circuitry to cause operations that:
identify, based on the explanation data, a plurality of AI models; and
select a particular model from the plurality of AI models for subsequent data processing.

### Claim 29 (depends on 22)

The computing device of claim 22, wherein the explanation data includes a model card for the AI model, wherein the model card includes multiple data quality metrics and multiple performance metrics;
wherein the data quality metrics relate to at least one of size sensitivity, occlusion analysis, or instances per class produced from object detection of the AI model; and
wherein the performance metrics relate to at least one of a confusion matrix, performance per class, or a saliency map produced from the object detection of the AI model.

### Claim 30 (depends on 22)

The computing device of claim 22, wherein the explanation data includes a natural language explanation of the output data produced from the AI model, and wherein the instructions configure the processing circuitry to cause operations that:
generate, based on the explanation data, at least one report that includes data from at least one data analysis mechanism, wherein the at least one report is customized to the persona role;
wherein the persona role is associated with: a regulator, a software development operations architect, a solutions architect, or a domain expert.

### Claim 31

A method for explainable artificial intelligence (AI) operations, performed by processing circuitry of a computing system, the method comprising:
receiving a schema for the explainable AI operations, the schema corresponding to a persona role used to evaluate an AI model;
controlling a workflow with the explainable AI operations, the explainable AI operations including: data analysis on output data produced from the AI model, and model analysis on performance of the AI model; and
outputting explanation data based on the explainable AI operations, wherein the explanation data is customized to the persona role based on the schema.

### Claim 32 (depends on 31)

The method of claim 31, wherein the data analysis includes data slicing of the output data based on data quality metrics, and wherein the model analysis includes performance metrics for the AI model based on the data slicing.

### Claim 33 (depends on 32)

The method of claim 32, wherein the explanation data is a visualization, and wherein the visualization provides a representation of the performance metrics that correspond to cohort analysis.

### Claim 34 (depends on 32)

The method of claim 32, wherein image data is provided as input data to the AI model, and wherein the AI model performs object detection on the image data;
wherein the data quality metrics correspond to one or more of: data slicing by size sensitivity level, data slicing by occlusion level, or data slicing by lighting level;
wherein the performance metrics are provided for each slice per object detection class, and wherein the explanation data corresponds to metrics per data attribute per slice.

### Claim 35 (depends on 31)

The method of claim 31, wherein the explainable AI operations include reliability scoring based on a processing of input data by the AI model;
wherein the explanation data includes a robustness score for the AI model, and wherein the robustness score is produced based on the reliability scoring.

### Claim 36 (depends on 31)

The method of claim 31, further comprising:
performing retraining of the AI model, based on the explanation data.

### Claim 37 (depends on 31)

The method of claim 31, further comprising:
identifying, based on the explanation data, a plurality of AI models; and
selecting a particular model from the plurality of AI models for subsequent data processing.

### Claim 38 (depends on 31)

The method of claim 31, wherein the explanation data includes a model card for the AI model, wherein the model card includes multiple data quality metrics and multiple performance metrics;
wherein the data quality metrics relate to at least one of size sensitivity, occlusion analysis, or instances per class produced from object detection of the AI model; and
wherein the performance metrics relate to at least one of a confusion matrix, performance per class, or a saliency map produced from the object detection of the AI model.

### Claim 39 (depends on 31)

The method of claim 31, wherein the explanation data includes a natural language explanation of the output data produced from the AI model.

### Claim 40 (depends on 31)

The method of claim 31, further comprising:
generating, based on the explanation data, at least one report that includes data from at least one data analysis mechanism, wherein the at least one report is customized to the persona role;
wherein the persona role is associated with: a regulator, a software development operations architect, a solutions architect, or a domain expert.

### Claim 41

At least one non-transitory machine-readable medium capable of storing instructions for explainable artificial intelligence (AI) operations, wherein the instructions when executed by at least one processor cause the at least one processor to:
receive a schema for the explainable AI operations, the schema corresponding to a persona role used to evaluate an AI model;
control the explainable AI operations, the explainable AI operations including: data analysis on output data produced from the AI model, and model analysis on performance of the AI model; and
output explanation data based on the explainable AI operations, wherein the explanation data is customized to the persona role based on the schema.
