Chatbot Session State Restoration via Intent Configuration
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Contact centers face challenges in efficiently managing incomplete co-browse sessions with chatbots, leading to disrupted user interactions and increased workload for human agents, as existing systems lack effective methods for asynchronous session restoration and self-learning capabilities.
Innovation Solution
A system and method for asynchronously restoring incomplete co-browse sessions by initiating interactions with chatbots, determining stored session data, retrieving intent configuration files, and performing defined actions to resume sessions, along with self-learning capabilities using machine learning to generate optimal action sequences for chatbots based on human agent interactions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Extent of automation
If chatbots are used to handle co-browse sessions, then automation extent is improved, but reliability deteriorates due to inability to restore incomplete sessions
Solution Approach 1:
The system performs preliminary actions by storing session state data and intent configuration files during active co-browse sessions. When a session is interrupted, these pre-stored elements enable automatic restoration without requiring human intervention, thus maintaining reliability while preserving automation.
Solution Approach 2:
The system creates copies of session state data and intent configuration files that can be stored and later retrieved to restore sessions. This copying mechanism allows the chatbot to reconstruct incomplete sessions accurately, improving reliability while maintaining automated operation.
2Reliability
If human agents manually restore incomplete co-browse sessions, then reliability is improved, but productivity deteriorates due to increased workload
Solution Approach 1:
The system implements self-service by enabling chatbots to automatically restore incomplete co-browse sessions using stored session state data and intent configuration files. This eliminates the need for human agents to manually intervene in session restoration, maintaining reliability while significantly improving productivity by reducing agent workload.
3Reliability
If session data is stored for restoration, then reliability is improved, but device complexity increases due to data storage requirements
Solution Approach 1:
The system extracts and stores only the essential session state data and intent configuration files needed for restoration, rather than storing complete session recordings. This selective extraction maintains reliability for restoration purposes while minimizing the complexity and storage requirements of the infrastructure.
4Productivity
If chatbots perform all co-browse actions, then productivity is improved, but ease of operation deteriorates when sessions cannot be restored
Solution Approach 1:
The system performs preliminary actions by storing session state data and intent configuration files during active co-browse sessions. When a session is interrupted, these pre-stored elements enable automatic restoration without requiring human intervention, thus maintaining reliability while preserving automation.
Solution Approach 2:
The system creates copies of session state data and intent configuration files that can be stored and later retrieved to restore sessions. This copying mechanism allows the chatbot to reconstruct incomplete sessions accurately, improving reliability while maintaining automated operation.
Data Source
AI summary
A method of self-learning actions for an automated co-browse session according to an embodiment include initiating an interaction between a user and a chat bot, determining a user intent of the user based on the interaction between the user and the chat bot, routing the interaction to a human contact center agent for a co-browse session between the user and the human contact center agent, storing a plurality of actions performed by the human contact center agent during the co-browse session to a data store, and performing machine learning to determine an optimal solution for resolving the user intent based on an analysis of the plurality of actions performed by the human contact center agent during the co-browse session.