System and method for generation of self-guided recovery procedures and suggestions

Patent metadata

Field	Value
Publication number	US-12423710-B2
Application number	US-202217667176-A
Country	US
Kind code	B2
Filing date	Feb 8, 2022
Priority date	Feb 8, 2022
Publication date	Sep 23, 2025
Grant date	Sep 23, 2025

Abstract

A self-guided troubleshooting guide generation method includes: receiving a first assistance request from the user; in response to receiving the first assistance request, scanning a first user interface (UI) through which the first assistance request is transmitted and extracting text from the first UI; parsing the extracted text and identifying an error message in the extracted text; comparing, after the identifying, the error message to data stored in an assistance request database; and generating, based on the comparing, solution information for resolving the error message and displaying the solution information on a display displaying the first UI.

First claim

What is claimed is:

1. A self-guided troubleshooting guide generation method comprising:
receiving a first assistance request from a user using a first display;
in response to receiving the first assistance request, scanning a first user interface (UI) displayed on the first display;
extracting, using a user interface parsing engine and the scanning, all text from the first UI displayed on the first display to obtain extracted text;
parsing, using the user interface parsing engine, the extracted text and identifying an error message in the extracted text;
receiving, at a text matching engine, the error message:
searching, via the text matching engine and after the receiving, data stored in an assistance request database by:
comparing the error message to data stored in the assistance request database, wherein the comparing comprises:
approximating a Jaccard similarity coefficient for each of a plurality of key-value pairs stored in the assistance request database; and
finding a set of potential matches for the error message using the Jaccard similarity coefficient for each of the plurality of key-value pairs and a min-hash function;

generating, based on the comparing and using the set of potential matches, solution information for resolving the error message;
displaying the solution information as part of the self-guided troubleshooting guide on the first display, by automatically displaying the set of potential matches in an order from most commonly used to least commonly used;
automatically generating and populating a service request using the solution information and displaying the service request on the first display;
tracking, via system data logs, user interactions with the displayed solution to detect resolution success or failure;
receiving, after displaying the solution, feedback from the user directed to the solution, wherein the feedback comprises the user interactions; and
updating, in real-time and in response to receiving the feedback and using the feedback, the data in the assistance request database.

2. The method of claim 1 , wherein the data in the assistance request database is compiled using information from release notes, install/upgrade guides, administrator guides, knowledge base (KB) articles, service requests, and known error codes.

3. The method of claim 1 , wherein the method further comprises:
receiving a second assistance request from the user;
in response to receiving the second assistance request, scanning a second UI through which the second assistance request is transmitted and extracting text from the second UI;
parsing the extracted text from the second UI and identifying no error messages in the extracted text of the second UI;
retrieving, in response to identifying no error messages in the extracted text of the second UI, one or more predefined keywords associated with a content of the text shown on the second UI;
comparing, after the retrieving, the one or more predefined keywords with the data stored in the assistance request database; and
generating, based on the comparing, tutorial information associated with the content of the text shown on the second UI and displaying the tutorial information on a display displaying the second UI.

4. The method of claim 3 ,
wherein the data stored in the assistance request database further comprises a plurality of product tutorials and a plurality of product keywords, wherein tutorial information is one of the plurality of product tutorials, and
wherein comparing the one or more predefined keywords with the data stored in the assistance request database comprises parsing the assistance request database to find a product keyword among the plurality of product keywords having a highest match with the one or more predefined keywords.

5. The method of claim 4 ,
wherein the plurality of product tutorials and the plurality of product keywords are stored in the assistance request database in a key-value pair format, and
wherein a product tutorial, among the plurality of product tutorials, associated in the key-value pair format with the product keyword having the highest match with the one or more predefined keywords is transmitted as the tutorial information.

6. A non-transitory computer readable medium (CRM) comprising computer readable program code, which when executed by a computer processor enables the computer processor to perform a self-guided troubleshooting guide generation method, the method comprising:
receiving a first assistance request from a user using a first display;
in response to receiving the first assistance request, scanning a first user interface (UI) displayed on the first display;
extracting, using a user interface parsing engine and the scanning, all text from the first UI displayed on the first display to obtain extracted text;
parsing, using the user interface parsing engine, the extracted text and identifying an error message in the extracted text;
receiving, at a text matching engine, the error message:
searching, via the text matching engine and after the receiving, data stored in an assistance request database by:
comparing the error message to data stored in the assistance request database, wherein the comparing comprises:
approximating a Jaccard similarity coefficient for each of a plurality of key-value pairs stored in the assistance request database; and
finding a set of potential matches for the error message using the Jaccard similarity coefficient for each of the plurality of key-value pairs and a min-hash function;

generating, based on the comparing and using the set of potential matches, solution information for resolving the error message;
displaying the solution information as part of the self-guided troubleshooting guide on the first display, by automatically displaying the set of potential matches in an order from most commonly used to least commonly used;
automatically generating and populating a service request using the solution information and displaying the service request on the first display;
tracking, via system data logs, user interactions with the displayed solution to detect resolution success or failure;
receiving, after displaying the solution, feedback from the user directed to the solution, wherein the feedback comprises the user interactions; and
updating, in real-time and in response to receiving the feedback and using the feedback, the data in the assistance request database.

7. The CRM of claim 6 , wherein the data in the assistance request database is compiled using information from release notes, install/upgrade guides, administrator guides, knowledge base (KB) articles, service requests, and known error codes.

8. A system comprising:
a memory; and
a processor coupled to the memory, wherein the processor is configured to generate a self-guided troubleshooting guide by:
receiving a first assistance request from a user using a first display;
in response to receiving the first assistance request, scanning a first user interface (UI) displayed on the first display;
extracting, using a user interface parsing engine and the scanning, all text from the first UI displayed on the first display to obtain extracted text;
parsing, using the user interface parsing engine, the extracted text and identifying an error message in the extracted text;
receiving, at a text matching engine, the error message:
searching, via the text matching engine and after the receiving, data stored in an assistance request database by:
comparing the error message to data stored in the assistance request database, wherein the comparing comprises:
approximating a Jaccard similarity coefficient for each of a plurality of key-value pairs stored in the assistance request database; and
finding

Assignees

• Dell Products Lp

Inventors

• Sampath Kapil
• Gupta Veenu
• Vishwakarma Rahul Deo

Classifications

• G06F40/205

  Parsing · CPC title

• G06F40/279

  Recognition of textual entities · CPC title

• G06F16/3329

  Natural language query formulation · CPC title

• G06F40/30

  Semantic analysis · CPC title

• G06Q30/016 Primary

  After-sales · CPC title