IP Library › Granted Patent US 12,693,928

Granted Patent B2

US 12,693,928 · App. 18/476,847 · Granted Jul 28, 2026

Automated help desk

Inventors: Kannan Parthasarathy (Palo Alto, CA); Arijit Pathak (Karnataka, IN); Hayden Davis (Denver, CO)

Assignee: Omnissa, LLC

G06F11/0793 G06F11/0766 G06F16/3344

View Patent ↗

Loading inventors, assignments & file history…

Monitor This Case

Get email alerts when status or documents change.

Order Certified Copies

Most orders are placed with the USPTO same day — all within 24 business hours.

Order via The Patent Place →

Pre-filled with this patent's details

Quick Facts

Patent No.: US 12,693,928
App. No.: 18/476,847
Granted: Jul 28, 2026
Kind: B2

External Links

USPTO Patent Center↗ Full Patent PDF↗

Abstract

Disclosed are various embodiments for automating IT help desk services by utilizing historical IT help desk data to identify potential solutions for incidents. First, a ticket associated with an incident on a client device can be received. Next, a ticket record can be generated by extracting information from the ticket using natural language processing techniques. Next, using the ticket record as a key, a graph database can be queried for one or more similar ticket records. In response to obtaining similar ticket records from the graph database, the graph database can be further queried for solution records related to the similar ticket records by edges. The solution can comprise a set of machine-readable instructions which can resolve the incident when executed.

Claims (64)

1 . A system, comprising:

a computing device comprising a processor and a memory; and

a first set of machine-readable instructions stored in the memory that, when executed by the processor, cause the computing device to at least:

receive a ticket associated with an incident on a first client device of a plurality of client devices;

generate a ticket record by extracting information from the ticket using natural language processing techniques and generating a vector representation of the extracted information, wherein the ticket record stores the vector representation;

using the vector representation of the ticket record, query a graph database for one or more similar ticket records, the graph database comprising a plurality of typed nodes including ticket nodes, incident nodes, and solution nodes, wherein the ticket record is stored as a ticket node associated with the vector representation in the graph database; and

in response to obtaining the one or more similar ticket records from the graph database based on vector similarity of the ticket nodes storing the one or more similar ticket records to the ticket node storing the ticket record, query the graph database for one or more solution nodes storing one or more solution records related to the ticket nodes storing the one or more similar ticket records by one or more edges in the graph database, wherein the one or more solution records comprise a second set of machine-readable instructions which, when executed on the first client device, resolve the incident.

2 . The system of claim 1 , wherein the first set of machine-readable instructions, when executed, further cause the computing device to at least push the second set of machine-readable instructions to the first client device to be executed.

3 . The system of claim 1 , wherein the first set of machine-readable instructions, when executed, further cause the computing device to at least send, in response to obtaining the one or more solution records, a notification to an administrative computing device, wherein the notification indicates that a solution has been identified.

4 . The system of claim 1 , wherein the first set of machine-readable instructions, when executed, further cause the computing device to at least send, in response to a failure to obtain the one or more solution records, a troubleshoot notification to an administrative computing device.

5 . The system of claim 1 , wherein the first set of machine-readable instructions, when executed, further cause the computing device to at least:

obtain, from the first client device, a diagnostic report corresponding in time to the incident;

generate an incident record comprising the diagnostic report;

store the incident record in the graph database as an incident node of the incident nodes; and

add an edge connecting the incident node to the ticket node.

6 . The system of claim 5 , wherein the first set of machine-readable instructions, when executed, further cause the computing device to at least:

query the graph database for one or more similar incident nodes containing one or more similar incident records; and

in response to obtaining the one or more similar incident nodes containing the one or more similar incident records from the graph database, query the graph database for one or more solution nodes containing one or more solution records related to the similar incident nodes by one or more edges in the graph database.

7 . The system of claim 5 , wherein the first set of machine-readable instructions, when executed, further cause the computing device to at least:

obtain a plurality of diagnostic reports from the plurality of client devices;

execute a similarity detection algorithm which compares individual diagnostic reports of the plurality of diagnostic reports to the diagnostic report from the first client device, the similarity detection algorithm configured to identify one or more similar diagnostic reports;

identify one or more affected client devices from the plurality of client devices, the one or more affected client devices corresponding to the one or more similar diagnostic reports; and

push the second set of machine-readable instructions to the one or more affected client devices.

8 . A method, comprising:

receiving, by a computing device, a ticket associated with an incident on a first client device of a plurality of client devices;

generating, by the computing device, a ticket record by extracting information from the ticket using natural language processing techniques and generating a vector representation of the extracted information, wherein the ticket record stores the vector representation;

using the vector representation of the ticket record, querying, by the computing device, a graph database for one or more similar ticket records, the graph database comprising a plurality of typed nodes including ticket nodes, incident nodes, and solution nodes, wherein the ticket record is stored as a ticket node associated with the vector representation in the graph database; and

in response to obtaining the one or more similar ticket records from the graph database based on vector similarity of the ticket nodes storing the one or more similar ticket records to the ticket node storing the ticket record, querying, by the computing device, the graph database for one or more solution nodes storing one or more solution records related to the ticket nodes storing the one or more similar ticket records by one or more edges in the graph database, wherein the one or more solution records comprise a set of machine-readable instructions which, when executed on the first client device, resolve the incident.

9 . The method of claim 8 , further comprising pushing the set of machine-readable instructions to the first client device to be executed.

10 . The method of claim 8 , further comprising sending, in response to obtaining the one or more solution records, a notification to an administrative computing device, wherein the notification indicates that a solution has been identified.

11 . The method of claim 8 , further comprising sending, in response to a failure to obtain the one or more solution records, a troubleshoot notification to an administrative computing device.

12 . The method of claim 8 , further comprising:

obtaining, from the first client device, a diagnostic report corresponding in time to the incident;

generating an incident record comprising the diagnostic report;

storing the incident record in the graph database as an incident node of the incident nodes; and

adding an edge connecting the incident node to the ticket node.

13 . The method of claim 12 , further comprising:

querying the graph database for one or more similar incident nodes containing one or more similar incident records; and

in response to obtaining the one or more similar incident nodes containing the one or more similar incident records from the graph database, querying the graph database for one or more solution nodes containing one or more solution records related to the similar incident nodes by one or more edges in the graph database.

14 . The method of claim 12 , further comprising:

obtaining a plurality of diagnostic reports from the plurality of client devices;

executing a similarity detection algorithm which compares individual diagnostic reports of the plurality of diagnostic reports to the diagnostic report from the first client device, the similarity detection algorithm configured to identify one or more similar diagnostic reports;

identifying one or more affected client devices from the plurality of client devices, the one or more affected client devices corresponding to the one or more similar diagnostic reports; and

pushing the set of machine-readable instructions to the one or more affected client devices.

15 . A non-transitory, computer-readable medium, comprising a first set of machine readable instructions that, when executed by a processor of a computing device, cause the computing device to at least:

receive a ticket associated with an incident on a first client device of a plurality of client devices;

16 . The non-transitory, computer-readable medium of claim 15 , wherein the machine-readable instructions further cause the computing device to at least push the second set of machine-readable instructions to the first client device to be executed.

17 . The non-transitory, computer-readable medium of claim 15 , wherein the machine-readable instructions further cause the computing device to at least send, in response to obtaining the one or more solution records, a notification to an administrative computing device, wherein the notification indicates that a solution has been identified.

18 . The non-transitory, computer-readable medium of claim 15 , wherein the machine-readable instructions, when executed, further cause the computing device to at least: