公开(公告)号：US12229517B2

公开(公告)日：2025-02-18

申请号：US17209572

申请日：2021-03-23

Applicant: Hewlett Packard Enterprise Development LP

Inventor： Mainak Das ,  Sean Charles Lennon ,  Salman Mumin Ahmed ,  Richard Shelby Dunlap

IPC: G06F40/35 ,  G06F16/332 ,  G06F16/35 ,  G06F40/284 ,  G06N20/00 ,  G06Q30/01 ,  H04L51/02

Abstract: Embodiments described herein are generally directed to training of classification models and their use by a chatbot to identify a customer-specified product support issue and provide appropriate troubleshooting guidance. According to an example, text describing an issue associated with a product line of a vendor is received via the chatbot. A vector representation of the issue is created using a word association model corresponding to the product line and trained based on a set of historical support cases relating to multiple supported issue categories for the product line. It is determined whether the issue matches a category within the supported issue categories for the product line by applying a classification model to the vector representation. When the determination is affirmative, an automated, interactive, conversational troubleshooting dialog is initiated with the user via the chatbot and guided based on a decision tree for the category within the product line.

公开(公告)号：US12154117B2

公开(公告)日：2024-11-26

申请号：US17343972

申请日：2021-06-10

Applicant: Hewlett Packard Enterprise Development LP

Inventor： Mainak Das ,  Sean Charles Lennon ,  Salman Mumin Ahmed ,  Richard Shelby Dunlap

IPC: G06Q30/016 ,  G06F40/284 ,  G06F40/35 ,  H04L51/02

Abstract: Embodiments described herein are generally directed to use of a chatbot to identify a customer-specified product support issue and provide appropriate troubleshooting guidance. According to an example, free text input describing an issue associated with a product line of a vendor is received from a user via a chatbot. A vector representation of the issue is created by tokenizing and vectorizing the free text input using a word association model corresponding to the product line. It is determined whether the issue matches at least one category within multiple issue categories for the product line by performing similarity scoring between the vector representation and multiple vectors created based on top words per issue category of the multiple issue categories. Responsive to an affirmative determination, an automated, interactive, conversational troubleshooting dialog is initiated with the user via the chatbot and guided based on a decision tree for the at least one category.

公开(公告)号：US20220398598A1

公开(公告)日：2022-12-15

申请号：US17343972

申请日：2021-06-10

Applicant: Hewlett Packard Enterprise Development LP

Inventor： Mainak Das ,  Sean Charles Lennon ,  Salman Mumin Ahmed ,  Richard Shelby Dunlap

IPC: G06Q30/00 ,  G06F40/284 ,  H04L12/58 ,  G06F40/35

Abstract: Embodiments described herein are generally directed to use of a chatbot to identify a customer-specified product support issue and provide appropriate troubleshooting guidance. According to an example, free text input describing an issue associated with a product line of a vendor is received from a user via a chatbot. A vector representation of the issue is created by tokenizing and vectorizing the free text input using a word association model corresponding to the product line. It is determined whether the issue matches at least one category within multiple issue categories for the product line by performing similarity scoring between the vector representation and multiple vectors created based on top words per issue category of the multiple issue categories. Responsive to an affirmative determination, an automated, interactive, conversational troubleshooting dialog is initiated with the user via the chatbot and guided based on a decision tree for the at least one category.

公开(公告)号：US20220309250A1

公开(公告)日：2022-09-29

申请号：US17209572

申请日：2021-03-23

Applicant: Hewlett Packard Enterprise Development LP

Inventor： Mainak Das ,  Sean Charles Lennon ,  Salman Mumin Ahmed ,  Richard Shelby Dunlap

IPC: G06F40/35 ,  H04L12/58 ,  G06N3/08 ,  G06N3/04 ,  G06Q30/00 ,  G06F40/284

Abstract: Embodiments described herein are generally directed to training of classification models and their use by a chatbot to identify a customer-specified product support issue and provide appropriate troubleshooting guidance. According to an example, text describing an issue associated with a product line of a vendor is received via the chatbot. A vector representation of the issue is created using a word association model corresponding to the product line and trained based on a set of historical support cases relating to multiple supported issue categories for the product line. It is determined whether the issue matches a category within the supported issue categories for the product line by applying a classification model to the vector representation. When the determination is affirmative, an automated, interactive, conversational troubleshooting dialog is initiated with the user via the chatbot and guided based on a decision tree for the category within the product line.