Browse Prior Art Database

A Method and System for Providing an Automated Response by Using a Dynamic Knowledge Base to Augment a Static Knowledge Base

IP.com Disclosure Number: IPCOM000240093D
Publication Date: 2014-Dec-30
Document File: 2 page(s) / 40K

Publishing Venue

The IP.com Prior Art Database

Abstract

Disclosed is a method and system for providing an automated response by using a dynamic knowledge base to augment a static knowledge base. The method and system relies on heuristics to automatically draft a response for a user query.

This text was extracted from a PDF file.
This is the abbreviated version, containing approximately 52% of the total text.

Page 01 of 2

A Method and System for Providing an Automated Response by Using a Dynamic Knowledge Base to Augment a Static Knowledge Base

Traditional auto-reply emails contain static information or can only collect answers from a static knowledge base such as a Frequently Asked Questions (FAQ) repository or a knowledge repository. These traditional solutions often contain outdated information and depend on frequent upkeep/updates of knowledge bases.

Disclosed is a method and system for providing an automated response by using a dynamic knowledge base to augment a static knowledge base.

Initially, when a user receives a query such as an email query, the system drafts a response based on heuristics from previous responses . The heuristics can be defined by comparing other incoming emails and the corresponding responses . The comparison first checks the subject line of the emails and further continues to check keywords in the description to filter the emails and the corresponding responses matching with the received email query. Based on the comparison, a response is automatically drafted and presented to the user . Thereafter, the user can verify the response and edit the drafted response if required . The user can accordingly transmit the verified response. In addition, the latest response of the user is scored for accuracy and added to database for future responses .

For example, when a user submits a query through a web based chat for a service desk, the system parses the query and finds relevant answers to the query from the static knowledge base. Upon receiving the answer from the static knowledge base, the system augments the response by looking at dynamic knowledge sources such as email inbox or open web chats for providing updated answers.

Consider a scenario, where a user raises a query that the user is having problem in resetting a password. The response from static knowledge base can be "Please click on this link for instructions on resetting your password." The response augmented from dynamic knowledge sources can be "The system A is currently experiencing an outage

with an expected restore time of Y. Once the system is up, please click on this link for instructions on resetting your password." Here, open incident tickets are used as a dynamic knowledge source to augment the static response .

Consider another scenario, where a user raises a query that the user is not able to access a printer X. The response from static knowledge base can be "Please ensure the appropriate printer drivers are installed and click on this link for instructions on installing printer drivers." The response augmented from a dynamic knowledge source can be added with a manual sentence before the response . The manual sentence can be based on a current situation, which can be, but need not be limited to, "There have been numerous inquiries about printer X in last 30 minutes". Further, this manual sentence can be continued with a dynamic knowledge source resp...