# US 2026/0065172 A1 · Artificial intelligence query response system with anomaly detection

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

- Number: US 2026/0065172 A1
- Document ID: US20260065172A1
- Status: Published application
- Kind: A1
- Application number: 18/819,307
- Filed: 2024-08-29
- Published: 2026-03-05
- Earliest claimed: 2024-08-29
- Assignees: Dell Products L.P.
- Applicants: Dell Products L.P.
- Inventors: Bijan Kumar Mohanty; Shamik Kacker; Hung T. Dinh
- Web page: https://patentgrep.com/patent/US20260065172A1

## CPC

- G06N 20/20: Ensemble learning
- G06N 3/045: Combinations of networks
- G06N 20/10: using kernel methods, e.g. support vector machines [SVM]
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS

## Abstract

Methods, apparatus, and processor-readable storage media for artificial intelligence query response systems with anomaly detection are provided herein. An example computer-implemented method includes obtaining at least one user query; performing a comparison of the at least one user query to one or more previous user queries contained within at least portions of one or more data structures; performing, based on results of the comparison, anomaly detection analysis on the at least one user query by processing the at least one user query against the one or more previous user queries contained within the at least portions of the data structure(s) using one or more anomaly detection algorithms; and generating, based on results of the anomaly detection analysis, at least one response to the at least one user query by processing, using an artificial intelligence system, the at least one user query and context information related thereto.

## Claims

### Claim 1

A computer-implemented method comprising:
obtaining at least one user query;
performing a comparison of the at least one user query to one or more previous user queries contained within at least portions of one or more data structures;
performing, based at least in part on results of the comparison, anomaly detection analysis on the at least one user query by processing the at least one user query against the one or more previous user queries contained within the at least portions of the one or more data structures using one or more anomaly detection algorithms; and
generating, based at least in part on results of the anomaly detection analysis, at least one response to the at least one user query by processing, using an artificial intelligence system, the at least one user query and context information related to the at least one user query;
wherein the method is performed by at least one processing device comprising a processor coupled to a memory.

### Claim 2 (depends on 1)

The computer-implemented method of claim 1, wherein performing a comparison comprises:
transforming the at least one user query into at least one embedding by processing the at least one user query using at least one neural network encoder; and
using the at least one embedding to perform a semantic search of at least one vector database within the at least portions of the one or more data structures.

### Claim 3 (depends on 1)

The computer-implemented method of claim 1, wherein performing a comparison comprises processing the at least one user query and the one or more previous user queries contained within the at least portions of the one or more data structures using one or more similarity search algorithms.

### Claim 4 (depends on 1)

The computer-implemented method of claim 1, wherein performing anomaly detection analysis comprises processing the at least one user query against the one or more previous user queries contained within the at least portions of the one or more data structures using at least one isolation forest algorithm.

### Claim 5 (depends on 4)

The computer-implemented method of claim 4, wherein processing the at least one user query against the one or more previous user queries contained within the at least portions of the one or more data structures using at least one isolation forest algorithm comprises isolating at least one non-anomalous state point, from the at least portions of the one or more data structures, using at least a first number of splits, and isolating at least one anomalous state point, from the at least portions of the one or more data structures, using at least a second number of splits.

### Claim 6 (depends on 1)

The computer-implemented method of claim 1, wherein performing anomaly detection analysis comprises processing the at least one user query against the one or more previous user queries contained within the at least portions of the one or more data structures using one or more of at least one support vector machine (SVM) algorithm and at least one artificial neural network (ANN).

### Claim 7 (depends on 1)

The computer-implemented method of claim 1, wherein generating at least one response to the at least one user query comprises processing the at least one user query and context information related to the at least one user query using a retrieval augmented generation (RAG) system.

### Claim 8 (depends on 1)

The computer-implemented method of claim 1, wherein generating at least one response to the at least one user query comprises generating the at least one response upon a determination that (i) the at least one user query is below a designated similarity level relative to the one or more previous user queries, and (ii) the at least one user query is below a designated anomaly detection level relative to the one or more previous user queries.

### Claim 9 (depends on 1)

The computer-implemented method of claim 1, wherein obtaining at least one user query comprises classifying the at least one user query based at least in part on one or more of user role and user-related domain.

### Claim 10 (depends on 1)

The computer-implemented method of claim 1, further comprising:
automatically outputting the at least one response to one or more systems associated with the at least one user query.

### Claim 11

A non-transitory processor-readable storage medium having stored therein program code of one or more software programs, wherein the program code when executed by at least one processing device causes the at least one processing device:
to obtain at least one user query;
to perform a comparison of the at least one user query to one or more previous user queries contained within at least portions of one or more data structures;
to perform, based at least in part on results of the comparison, anomaly detection analysis on the at least one user query by processing the at least one user query against the one or more previous user queries contained within the at least portions of the one or more data structures using one or more anomaly detection algorithms; and
to generate, based at least in part on results of the anomaly detection analysis, at least one response to the at least one user query by processing, using an artificial intelligence system, the at least one user query and context information related to the at least one user query.

### Claim 12 (depends on 11)

The non-transitory processor-readable storage medium of claim 11, wherein performing a comparison comprises:
transforming the at least one user query into at least one embedding by processing the at least one user query using at least one neural network encoder; and
using the at least one embedding to perform a semantic search of at least one vector database within the at least portions of the one or more data structures.

### Claim 13 (depends on 11)

The non-transitory processor-readable storage medium of claim 11, wherein performing anomaly detection analysis comprises processing the at least one user query against the one or more previous user queries contained within the at least portions of the one or more data structures using at least one isolation forest algorithm.

### Claim 14 (depends on 11)

The non-transitory processor-readable storage medium of claim 11, wherein generating at least one response to the at least one user query comprises processing the at least one user query and context information related to the at least one user query using a retrieval augmented generation (RAG) system.

### Claim 15 (depends on 11)

The non-transitory processor-readable storage medium of claim 11, wherein generating at least one response to the at least one user query comprises generating the at least one response upon a determination that (i) the at least one user query is below a designated similarity level relative to the one or more previous user queries, and (ii) the at least one user query is below a designated anomaly detection level relative to the one or more previous user queries.

### Claim 16

An apparatus comprising:
at least one processing device comprising a processor coupled to a memory;
the at least one processing device being configured:
to obtain at least one user query;
to perform a comparison of the at least one user query to one or more previous user queries contained within at least portions of one or more data structures;
to perform, based at least in part on results of the comparison, anomaly detection analysis on the at least one user query by processing the at least one user query against the one or more previous user queries contained within the at least portions of the one or more data structures using one or more anomaly detection algorithms; and
to generate, based at least in part on results of the anomaly detection analysis, at least one response to the at least one user query by processing, using an artificial intelligence system, the at least one user query and context information related to the at least one user query.

### Claim 17 (depends on 16)

The apparatus of claim 16, wherein performing a comparison comprises:
transforming the at least one user query into at least one embedding by processing the at least one user query using at least one neural network encoder; and
using the at least one embedding to perform a semantic search of at least one vector database within the at least portions of the one or more data structures.

### Claim 18 (depends on 16)

The apparatus of claim 16, wherein performing anomaly detection analysis comprises processing the at least one user query against the one or more previous user queries contained within the at least portions of the one or more data structures using at least one isolation forest algorithm.

### Claim 19 (depends on 16)

The apparatus of claim 16, wherein generating at least one response to the at least one user query comprises processing the at least one user query and context information related to the at least one user query using a retrieval augmented generation (RAG) system.

### Claim 20 (depends on 16)

The apparatus of claim 16, wherein generating at least one response to the at least one user query comprises generating the at least one response upon a determination that (i) the at least one user query is below a designated similarity level relative to the one or more previous user queries, and (ii) the at least one user query is below a designated anomaly detection level relative to the one or more previous user queries.
