Automated Assistant Session Restoration via Context Snapshotting

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Automated assistance systems, such as chatbots, face inefficiencies due to interruptions, requiring users to restart conversations and repeat information after unplanned outages, leading to increased customer response time and frustration.

Innovation Solution

Implementing a method to save session contexts with reentry points, allowing the system to resume interrupted conversations by matching user metadata and reconnecting users to the previous session, eliminating the need to repeat previously discussed information.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If automated assistance systems are used to provide virtual assistants, then productivity is improved, but reliability deteriorates due to unplanned outages and interruptions

Engineering Contradiction:

Improveautomation efficiencyVSAvoidsession continuity

Core Design Contradiction:

ProductivityVSReliability

Solution Approach 1:

The system performs preliminary actions by saving session contexts and identifying reentry points during normal operation, so that when an interruption occurs, the session can be restored without requiring users to repeat information. This proactive data preservation enables seamless resumption of interrupted sessions.

Inventive Principle:

Principle #10Preliminary action

2Loss of time

If session restoration is implemented, then loss of time is reduced, but device complexity increases

Engineering Contradiction:

Improvecustomer response timeVSAvoidsession management complexity

Core Design Contradiction:

Loss of timeVSDevice complexity

Solution Approach 1:

The system creates copies of session contexts that can be stored and retrieved independently. Instead of maintaining complex real-time session state, the system captures and stores session snapshots that can be quickly restored, simplifying the management of session restoration while reducing time loss.

Inventive Principle:

Principle #26Copying

3Loss of information

If session context is saved and restored, then loss of information is reduced, but manufacturing precision requirements increase

Engineering Contradiction:

Improveconversation context retentionVSAvoidsession matching accuracy

Core Design Contradiction:

Loss of informationVSManufacturing precision

Solution Approach 1:

The system uses feedback mechanisms to verify session restoration accuracy by comparing user metadata with saved session contexts. This ensures that the correct session is restored and that the context information is accurately retrieved, maintaining high precision in session matching while minimizing information loss.

Inventive Principle:

Principle #23Feedback

Data Source

PatentUS10824520B2Restoring automated assistant sessions

Publication Date: 2020.11.03 KYNDRYL INC

AI summary

Disclosed embodiments provide techniques for restoring an interrupted automated assistance session. Session contexts including pertinent metadata are periodically saved for each session, including a session reentry point. When a user calls an automated response system, metadata is collected from the user and compared with metadata from saved session contexts. If the user is determined to be associated with a saved session context, the user is connected to a conversation starting at the session reentry point, thereby eliminating the need to repeat the entirety of previously provided information.