# US 11,909,579 B2 · Autonomous auditing and remediation of it asset records

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

- Number: US 11,909,579 B2
- Document ID: US11909579B2
- Status: Granted
- Kind: B2
- Application number: 17/533,630
- Filed: 2021-11-23
- Published: 2023-05-25
- Granted: 2024-02-20
- Earliest claimed: 2021-11-23
- Assignees: Adobe Inc.
- Applicants: Adobe Inc.
- Inventors: Lokendra Singh Chauhan; Timothy Ira Scott Burton; Russell Marsh; Aditya Kumar; Sharad Jain; Tonia Erin
- Web page: https://patentgrep.com/patent/US11909579B2

## CPC

- H04L 41/0654: using network fault recovery (ring fault isolation or reconfiguration in loop networks without recovery actions by a network management system H04L12/437)
- H04L 41/145: {involving simulating, designing, planning or modelling of a network}
- G06F 18/24147: {Distances to closest patterns, e.g. nearest neighbour classification}
- H04L 41/082: the condition being updates or upgrades of network functionality
- H04L 41/0869: Validating the configuration within one network element
- H04L 41/0894: Policy-based network configuration management
- H04L 41/12: Discovery or management of network topologies
- H04L 41/16: using machine learning or artificial intelligence
- H04L 41/5003: Managing SLA; Interaction between SLA and QoS
- H04L 41/5074: Handling of user complaints or trouble tickets
- H04L 41/0631: using root cause analysis; using analysis of correlation between notifications, alarms or events based on decision criteria, e.g. hierarchy, tree or time analysis
- H04L 41/22: comprising specially adapted graphical user interfaces [GUI]
- H04L 43/16: Threshold monitoring
- H04L: TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION (arrangements common to telegraphic and telephonic communication H04M)
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)

## Abstract

Embodiments relate to the autonomous remediation of IT asset records in accordance with rules-based asset management policies. An IT asset record associated with an IT asset and having a first piece of IT asset information is received and evaluated for compliance in accordance with defined asset management rules. The asset management rules require the IT asset record to include both the first piece and a second piece of IT asset information. In view of the rules, a determination is made that the IT asset record requires remediation. Based on a determination that the IT asset record requires remediation, a decision-tree machine learning model is utilized to infer, based on IT asset information available in the IT asset record, at least the second piece of IT asset information to place the IT asset record in compliance with the asset management rules.

## Claims

### Claim 1

A non-transitory computer storage medium storing computer-executable instructions that, when executed by a processing device, cause the processing device to:
receive an information technology (IT) asset record associated with a particular IT asset of a plurality of IT assets hosted in a networked computing environment, the IT asset record having at least a first piece of IT asset information associated with the particular IT asset;
determine that a defined set of asset management rules requires at least a second piece of IT asset information in the IT asset record;
determine that the IT asset record requires remediation by adding at least the second piece of IT asset information so that the IT asset record is in compliance with the defined set of asset management rules;
in response to the determination that the IT asset record requires remediation, autonomously generate a ticket associated with the particular IT asset;
determine, utilizing a machine learning model, at least the second piece of IT asset information associated with the particular IT asset based at least in part on the first piece of IT asset information, wherein at least the determined second piece of IT asset information is presented as a suggested remediation action;
update the IT asset record to include the determined second piece of IT asset information based on an acceptance of the suggested remediation action; and
automatically close the ticket in response to the IT asset record being updated to include the second piece of IT asset information.

### Claim 2 (depends on 1)

The computer storage medium of claim 1, wherein the IT asset record is determined to require remediation because the defined set of asset management rules requires that each of the first and second pieces of IT asset information are included in the IT asset record and the second piece of IT asset information is missing from the IT asset record.

### Claim 3 (depends on 1)

The computer storage medium of claim 1, wherein each of the first and second pieces of IT asset information corresponds to one of a plurality of location attributes of the particular IT asset, the plurality of location attributes including an IP address of the particular IT asset, a location name associated with the particular IT asset, or a data center name associated with the particular IT asset.

### Claim 4 (depends on 1)

The computer storage medium of claim 1, wherein each of the first and second pieces of IT asset information corresponds to one of a plurality of service attributes of the particular asset, the plurality of service attributes including a unique device identifier of the particular IT asset, a hostname of the particular IT asset, a device name of the particular IT asset, an IP address of the particular IT asset, or a device service identifier associated with the particular IT asset.

### Claim 5 (depends on 1)

The computer storage medium of claim 1, wherein the instructions further cause the processing device to:
receive an input that corresponds to a first graphical user interface (GUI) element to accept the determined second piece of IT asset information, wherein the IT asset record is updated to include the determined second piece of IT asset information based on the received input.

### Claim 6 (depends on 1)

The computer storage medium of claim 1, wherein the machine learning model is trained utilizing a dataset of IT asset records and a set of features selected from the dataset based on a determined non-biased distribution of values for each feature of the dataset and determined correlational strengths between feature pairs of the dataset.

### Claim 7

A computer-implemented method for autonomously remediating information technology (IT) asset records, the method comprising:
receiving, into a machine learning model, a dataset of IT asset records and a set of features selected from the dataset based on a determined non-biased distribution of values for each feature of the dataset and on determined correlational relationships there between; and
training the machine learning model based on the dataset and the selected set of features to generate a trained decision-tree machine learning model that is employable to determine that an IT asset record associated with a particular IT asset and having a first piece of IT asset information is not in compliance with a defined set of asset management rules, and further determine at least a second piece of IT asset information for autonomous updating of the IT asset record to place the IT asset record into compliance with the defined set of asset management rules.

### Claim 8 (depends on 7)

The method of claim 7, further comprising:
obtaining a plurality of IT asset records, each IT asset record of the plurality of IT asset records having a plurality of features and a plurality of corresponding values;
determining the correlational relationships between each feature of the plurality of features; and
selecting the set of features based on the determined correlational relationships of each feature of the plurality of features.

### Claim 9 (depends on 8)

The method of claim 8, wherein the dataset is a randomly-selected portion of the plurality of IT asset records, and the set of features is selected based further on a determined distribution of values for each feature in the set of features.

### Claim 10 (depends on 8)

The method of claim 8, further comprising:
determining that a portion of the plurality of corresponding values includes non-numerical values; and
tokenizing the portion of the plurality of corresponding values into semantic units.

### Claim 11 (depends on 10)

The method of claim 10, further comprising:
label encoding the tokenized portion of the plurality of corresponding values to give the non-numerical values unique numerical values.

### Claim 12

A system comprising:
a processing device, and
a memory component coupled to the processing device, the processing device to perform operations comprising:
receiving an information technology (IT) asset record associated with a particular IT asset of a plurality of IT assets hosted in a computing environment, the IT asset record having at least a first piece of IT asset information associated with the particular IT asset;
determining that a set of asset management rules requires at least a second piece of IT asset information in the IT asset record;
determining that the IT asset record needs remediation by adding at least the second piece of IT asset information so that the IT asset record is in compliance with the set of asset management rules;
in response to the determination that the IT asset record requires remediation, autonomously generate a ticket associated with the particular IT asset;
determining, utilizing a machine learning model, at least the second piece of IT asset information associated with the particular IT asset based at least in part on the first piece of IT asset information, wherein at least the determined second piece of IT asset information is presented as a suggested remediation action;
updating the IT asset record to include the determined second piece of IT asset information based on an acceptance of the suggested remediation action; and
automatically close the ticket in response to the IT asset record being updated to include the second piece of IT asset information.

### Claim 13 (depends on 12)

The system of claim 12, wherein the machine learning model is trained utilizing a dataset of IT asset records and a set of features selected from a plurality of features in the dataset based on a determined non-biased distribution of values for each feature of the plurality of features.

### Claim 14 (depends on 13)

The system of claim 13, wherein the set of features is selected from the plurality of features based further on determined correlational strengths between feature pairs of the dataset.

### Claim 15 (depends on 13)

The system of claim 13, wherein at least a portion of the plurality of features is tokenized into semantic units and then label encoded to assign unique numerical values thereto.