Multi-Chatbot Query Routing for Accurate Cross-Channel Responses

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing chatbot systems face inefficiencies due to single bot configurations, processing delays, operational inefficiencies from platform-specific content changes, and programming challenges when updating conversation flows across multiple channels, leading to poor performance and user experience.

Innovation Solution

A computing platform trains multiple machine learning models for chatbots, dynamically routes queries to specialized models based on intent, and updates conversation flows without code modifications, using a decentralized network of topic-oriented bots and a centralized knowledge base for content management.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If a single chatbot is configured to respond to all queries, then the chatbot can handle a wide range of queries, but it becomes error-prone and processing inefficient

Engineering Contradiction:

Improvequery handling capabilityVSAvoidresponse accuracy

Core Design Contradiction:

Adaptability or versatilityVSReliability

Solution Approach 1:

The patent divides a single chatbot system into multiple specialized chatbots, each trained on specific datasets for particular domains or tasks. This segmentation allows each chatbot to focus on its specialized area, improving both reliability in its domain and overall system versatility through the collection of specialized bots.

Inventive Principle:

Principle #1Segmentation

2Adaptability or versatility

If a single chatbot is configured to respond to all queries, then the chatbot can handle a wide range of queries, but processing efficiency deteriorates

Engineering Contradiction:

Improvequery handling capabilityVSAvoidprocessing efficiency

Core Design Contradiction:

Adaptability or versatilityVSProductivity

Solution Approach 1:

The patent segments the chatbot system into multiple specialized chatbots that can process queries in parallel. Each chatbot is optimized for specific query types, enabling faster processing times and improved overall productivity while maintaining versatile query handling capabilities.

Inventive Principle:

Principle #1Segmentation

3Adaptability or versatility

If conversation flows are deployed in multiple channels, then the chatbot can serve various platforms, but code updates and redeployment become more complex

Engineering Contradiction:

Improvechannel compatibilityVSAvoiddeployment complexity

Core Design Contradiction:

Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The patent creates chatbots that are universally deployable across multiple channels and platforms. By training chatbots on diverse datasets and making them channel-agnostic, the system achieves multi-functionality where the same chatbot can serve web, mobile, voice, and other channels without requiring separate codebases or complex deployment processes.

Inventive Principle:

Principle #6Universality (Multi-functionality)

4Adaptability or versatility

If content changes are made to chatbot responses, then the chatbot can provide updated information, but operational inefficiencies occur due to code coordination and redeployment

Engineering Contradiction:

Improvecontent update capabilityVSAvoidcontent update efficiency

Core Design Contradiction:

Adaptability or versatilityVSProductivity

Solution Approach 1:

The patent extracts the training data and model training process from the deployment process. Content updates are achieved by simply retraining chatbots with new datasets without requiring code changes or coordination across multiple platforms. This separation of data from code allows independent content updates, dramatically improving productivity.

Inventive Principle:

Principle #2Taking out (Extraction)

5Ease of operation

If a chatbot uses programmed conversation flows with multiple questions, then the chatbot can collect information systematically, but it cannot respond to improperly worded questions and requires manual programming for new responses

Engineering Contradiction:

Improveinformation collection capabilityVSAvoidquery flexibility

Core Design Contradiction:

Ease of operationVSAdaptability or versatility

Solution Approach 1:

The patent enables chatbots to learn and adapt to user queries autonomously through machine learning. Instead of relying on pre-programmed conversation flows, the chatbots use trained models to understand and respond to a wide variety of query formulations, including improperly worded questions. New responses are generated through retraining on new data rather than manual programming.

Inventive Principle:

Principle #25Self-service

Data Source

PatentUS20260111968A1Chatbot system and machine learning modules for query analysis and interface generation

Publication Date: 2026.04.23 ALLSTATE NORTHERN IRELAND LTD

AI summary

Aspects of the disclosure relate to using machine learning methods for chatbot selection. A computing platform may train a plurality of machine learning models, each corresponding to a chatbot. The computing platform may train an additional machine learning model to route queries to the plurality of machine learning models based on contents of the queries. The computing platform may receive a query, and may analyze the query using the additional machine learning model. The computing platform may route, based on the query analysis, the query to the plurality of machine learning models. The computing platform may generate, using the plurality of machine learning models, a response to the query. The computing platform may send the response to the query and one or more commands directing a client device to display the response to the query, which may cause the client device to display the response to the query.