Virtual Assistant Interactivity Platform Query Routing

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Virtual assistants face challenges in handling a broad range of user queries without significant increases in processing and data storage resources, and maintaining knowledge bases and competences for products or services not directly produced by the organization is costly and inefficient.

Innovation Solution

A virtual assistant interactivity platform that identifies a subset of virtual assistants based on query topics, generates expert scores, and evaluates answers from multiple assistants using authority and response scores to provide comprehensive responses through semantic analysis.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If a virtual assistant uses a comprehensive knowledge base and programmed competences to handle a broad range of user queries, then the query handling capability is improved, but the processing and data storage resources significantly increase

Engineering Contradiction:
Improvequery handling capabilityVSAvoidprocessing and data storage resources
Core Design Contradiction:
Adaptability or versatilityVSQuantity of substance

Solution Approach 1:

The patent divides the virtual assistant system into multiple specialized virtual assistants, each responsible for specific topics or domains. Instead of one virtual assistant needing to know everything, the system segments knowledge across multiple assistants, reducing the resource burden on each individual assistant while maintaining comprehensive query handling capability through collective expertise.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent introduces a coordination mechanism that acts as an intermediary between user queries and specialized virtual assistants. This mediator routes queries to the appropriate specialists based on topic matching, enabling comprehensive query handling without requiring each virtual assistant to possess all knowledge, thus reducing overall resource requirements.

Inventive Principle:
Principle #24Intermediary (Mediator)

2Adaptability or versatility

If a organization maintains a virtual assistant with knowledge base and programmed competences for products or services not directly produced by it, then the service coverage is improved, but the maintenance cost and efficiency worsen

Engineering Contradiction:
Improveservice coverageVSAvoidmaintenance cost and efficiency
Core Design Contradiction:
Adaptability or versatilityVSEase of manufacture

Solution Approach 1:

The patent creates a universal platform that can host multiple specialized virtual assistants from different organizations or domains. Each virtual assistant maintains its own knowledge base for its specific domain, while the platform provides common infrastructure and coordination services. This allows organizations to leverage external expertise without bearing the full maintenance burden, as the platform handles shared functionality and updates.

Inventive Principle:
Principle #6Universality (Multi-functionality)

Data Source

PatentUS10353906B2Virtual assistant interactivity platform
Publication Date: 2019.07.16 ACCENTURE GLOBAL SERVICES LTD
  • US10353906B2 patent drawing
  • US10353906B2 patent drawing
  • US10353906B2 patent drawing

AI summary

The invention concerns a system having: a virtual assistant interactivity platform (102) including: a processing device; a memory device storing data identifying a plurality of virtual assistants, and one or more topics associated with each virtual assistant; a communication interface configured to receive an input query from a user device (104); and a memory coupled to the processing device and storing executable instructions that, when executed by the processing device, cause the processing device to: assess the input query to identify a subset of at least one of the virtual assistants based on a comparison between at least one topic of the query and the one or more topics associated with each virtual assistant; transmit a query based on the input query to each of the virtual assistants of the subset; evaluate answers to the input query received from the virtual assistants of the subset in order to generate a response comprising one or more of the answers; and transmit the response to the user device.