B2B Chat Routing via Business Lookup and CRM Integration

Solution Overview

Problem

Manual routing of business-to-business (B2B) chats to human chat agents is time-consuming, error-prone, and often results in delays and loss of customer history due to the inability of generalist agents to accurately identify and associate chat requests with the correct business accounts.

Innovation Solution

A B2B chatbot system that obtains user-supplied business information, performs business lookups using a business lookup service, evaluates confidence scores, and routes chats to the appropriate human agent, minimizing human involvement and ensuring accurate account association.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If manual routing by generalist chat agents is used, then human involvement in routing is achieved, but routing accuracy and speed deteriorate due to inability to know all customer aliases and variants

Engineering Contradiction:

Improverouting accuracyVSAvoidautomation level

Core Design Contradiction:

ReliabilityVSExtent of automation

Solution Approach 1:

The patent introduces an automated routing system that acts as an intermediary between the chat request and the human chat agent. This system uses machine learning models to analyze chat content, extract business identifiers, and match requests with appropriate business accounts, thereby eliminating the need for generalist agents to manually know all customer aliases while maintaining high routing accuracy.

Inventive Principle:

Principle #24Intermediary (Mediator)

Solution Approach 2:

The patent replaces the manual mechanical process of human agents reviewing and routing chat requests with an automated electronic system. The machine learning-based routing system processes chat content, identifies business identifiers, and routes requests automatically, substituting the mechanical human decision-making process with an electronic automated system that operates faster and more accurately.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

2Productivity

If manual routing by generalist chat agents is used, then flexibility in handling diverse chat requests is maintained, but time consumption and delays increase

Engineering Contradiction:

Improverouting speedVSAvoidrouting delay

Core Design Contradiction:

ProductivityVSLoss of time

Solution Approach 1:

The patent replaces the manual mechanical process of human agents reviewing and routing chat requests with an automated electronic system. The machine learning-based routing system processes chat content, identifies business identifiers, and routes requests automatically, substituting the mechanical human decision-making process with an electronic automated system that operates faster and more accurately.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The system performs preliminary action by pre-processing chat content to extract business identifiers and pre-matching requests with potential business accounts before human agents are involved. This preliminary automated processing reduces the time burden on human agents and accelerates the overall routing process.

Inventive Principle:

Principle #10Preliminary action

3Reliability

If manual routing is used, then human judgment can be applied, but error rates increase and chat records may be linked to incorrect accounts

Engineering Contradiction:

Improveaccount association accuracyVSAvoidcustomer history loss

Core Design Contradiction:

ReliabilityVSLoss of information

Solution Approach 1:

The patent introduces an automated routing system that acts as an intermediary between the chat request and the human chat agent. This system uses machine learning models to analyze chat content, extract business identifiers, and match requests with appropriate business accounts, thereby eliminating the need for generalist agents to manually know all customer aliases while maintaining high routing accuracy.

Inventive Principle:

Principle #24Intermediary (Mediator)

Solution Approach 2:

The system implements feedback mechanisms to verify and confirm account associations. By analyzing chat content and comparing extracted business identifiers with known business profiles, the system can confirm correct matches or request clarification, reducing error rates and preventing incorrect account linkages that would result in loss of customer history.

Inventive Principle:

Principle #23Feedback

Data Source

PatentUS11979362B2Business-to-business chat routing

Publication Date: 2024.05.07 ORACLE INT CORP

AI summary

Techniques for business-to-business (B2B) chat routing are disclosed, including: receiving, by a B2B chatbot during a chat session with a user, user input including a user-supplied business name; performing a business lookup based at least on the user-supplied business name, to obtain a canonical business name and a unique business identifier associated with the canonical business name; performing a customer relationship management (CRM) system lookup based at least on the unique business identifier, to identify a corresponding business account; routing the chat session from the B2B chatbot to a human chat agent assigned to the corresponding business account.