Patent Application

App. No. 16/863,665

Abstract

Claims (45)

1 . An information handling system comprising:

one or more processors; and

a non-transitory memory coupled to the one or more processors;

wherein the information handling system is configured to:

receive, from a client information handling system, information indicative of an error;

perform natural language processing of a text associated with the error to determine a set of error tokens;

perform natural language processing of a plurality of items of troubleshooting content to determine, for each item of troubleshooting content, a respective set of troubleshooting tokens;

for each respective set of troubleshooting tokens, determine a similarity score for the corresponding item of troubleshooting content relative to the set of error tokens;

receive user feedback for a selected one of the items of troubleshooting content; and

adjust the similarity score for the selected one based on the received user feedback.

2 . The information handling system of claim 1 , wherein the information indicative of the error further includes a model number and/or a service tag of the client information handling system.

3 . The information handling system of claim 2 , wherein the information handling system is further configured to filter the items of troubleshooting content to remove those items that are not associated with the model number and/or service tag.

4 . The information handling system of claim 1 , wherein the information indicative of the error includes an error code.

5 . The information handling system of claim 1 , wherein the text associated with the error includes remediation instructions.

6 . The information handling system of claim 1 , wherein the error tokens and the troubleshooting tokens comprise single words.

7 . The information handling system of claim 1 , wherein the error tokens and the troubleshooting tokens comprise groupings of words.

8 . A method comprising:

an information handling system receiving, from a client information handling system, information indicative of an error;

the information handling system performing natural language processing of a text associated with the error to determine a set of error tokens;

the information handling system performing natural language processing of a plurality of items of troubleshooting content to determine, for each item of troubleshooting content, a respective set of troubleshooting tokens;

for each respective set of troubleshooting tokens, the information handling system determining a similarity score for the corresponding item of troubleshooting content relative to the set of error tokens;

the information handling system receiving user feedback for a selected one of the items of troubleshooting content; and

the information handling system adjusting the similarity score for the selected one based on the received user feedback.

9 . The method of claim 8 , further comprising transmitting the selected one of the items of troubleshooting content to the user.

10 . The method of claim 8 , further comprising retrieving the text associated with the error from an error database.

11 . The method of claim 8 , wherein performing natural language processing of the text includes calculating term frequency-inverse document frequency (TF-IDF) processing on the text.

12 . The method of claim 8 , wherein the error tokens each have a respective error relevance score, and wherein each troubleshooting token for each item of troubleshooting content has a respective troubleshooting relevance score.

13 . The method of claim 12 , further comprising:

computing an error vector associated with the text, the error vector comprising the respective error relevance score for each error token;

computing troubleshooting vectors associated with each item of troubleshooting content, each troubleshooting vector comprising the respective troubleshooting relevance scores for each associated troubleshooting token.

14 . The method of claim 13 , wherein the similarity score is determined based on a cosine similarity between the error vector and each respective troubleshooting vector.

15 . An article of manufacture comprising a non-transitory, computer-readable medium having computer-executable code thereon that is executable by at least one processor of at least one information handling system for:

receiving, from a client information handling system, information indicative of an error;

performing natural language processing of a text associated with the error to determine a set of error tokens;

performing natural language processing of a plurality of items of troubleshooting content to determine, for each item of troubleshooting content, a respective set of troubleshooting tokens;

for each respective set of troubleshooting tokens, determining a similarity score for the corresponding item of troubleshooting content relative to the set of error tokens;

receiving user feedback for a selected one of the items of troubleshooting content; and

adjusting the similarity score for the selected one based on the received user feedback.

16 . The article of claim 15 , wherein the error tokens include domain-specific groupings of words.

17 . The article of claim 15 , wherein the information indicative of the error further includes a model number and/or a service tag of the client information handling system, and wherein the code is further executable for filtering the items of troubleshooting content to remove those items that are not associated with the model number and/or service tag.

18 . The article of claim 15 , wherein the error tokens each have a respective error relevance score, and wherein each troubleshooting token for each item of troubleshooting content has a respective troubleshooting relevance score.

19 . The article of claim 18 , wherein the code is further executable for:

computing an error vector associated with the text, the error vector comprising the respective error relevance score for each error token;

computing troubleshooting vectors associated with each item of troubleshooting content, each troubleshooting vector comprising the respective troubleshooting relevance scores for each associated troubleshooting token.

20 . The article of claim 19 , wherein the similarity score is determined based on a cosine similarity between the error vector and each respective troubleshooting vector.

Assignments (9)