Virtual Assistant Response Indicator for Multi-Assistant Systems
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In a multi-virtual assistant environment, users face delays and difficulty in identifying which assistant provided an initial response to a query, especially when seeking a second opinion, due to the lack of clear indication of the responding virtual assistant.
Innovation Solution
An apparatus and method that utilize an audio input device, processor, and memory to receive and process spoken queries, associate virtual assistants with information categories, and present responses with indicators of the providing virtual assistants, allowing users to select preferred assistants based on response quality and category matching.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If the system polls multiple virtual assistants to find the most appropriate response, then the accuracy and quality of the response is improved, but the response time increases
Solution Approach 1:
The system performs preliminary actions by pre-establishing category associations for each virtual assistant and pre-classifying user queries into categories before polling. This allows the system to quickly identify and poll only the most relevant virtual assistants for a given query category, rather than polling all assistants sequentially, thus reducing response time while maintaining response quality.
Solution Approach 2:
The system applies local quality by matching specific query categories with specific virtual assistant expertise areas. Instead of treating all virtual assistants equally, the system identifies which virtual assistants have demonstrated competence in particular categories and prioritizes polling those assistants for category-specific queries, thereby optimizing both response time and quality.
2Reliability
If the system polls multiple virtual assistants for generic queries, then the likelihood of finding an accurate response is improved, but the complexity of the system increases
Solution Approach 1:
The system segments the virtual assistant ecosystem into distinct categories based on expertise areas. Each virtual assistant is associated with one or more categories, and queries are classified into categories before being routed to appropriate assistants. This segmentation simplifies the polling process by reducing the number of assistants that need to be queried for any given query type.
Solution Approach 2:
The system introduces a category classification intermediary layer between the user query and the virtual assistants. This intermediary classifies queries into categories and uses those categories to determine which virtual assistants to poll, acting as a mediator that simplifies the interaction complexity between multiple assistants and diverse queries.
3Ease of operation
If the system does not indicate which virtual assistant provided the response, then the user interface remains simple, but the user's ability to seek second opinions or prefer certain assistants is reduced
Solution Approach 1:
The system uses visual indicators (analogous to color changes) to differentiate responses from different virtual assistants. By displaying indicators that identify which assistant provided which response, the system enables users to distinguish between multiple responses and make informed choices about which assistant they prefer or trust for future queries.
Data Source
AI summary
A method for indicating a responding virtual assistant from one of a plurality of virtual assistants is disclosed. The method includes receiving a spoken query from a user of an electronic device. The method includes determining whether the spoken query addresses a particular one of a plurality of virtual assistants on the electronic device. The method includes polling a first set of the virtual assistants with the spoken query in response to the spoken query not addressing a particular one of the plurality of virtual assistants. The method further includes presenting a response to the spoken query with an indicator of a virtual assistant providing the response. An apparatus and computer program product are also disclosed, which perform the method.