Digital Assistant Query Routing for Low-Latency Response Handling
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing digital assistants face inefficiencies in routing queries to appropriate components and processing complex user queries, leading to increased latency and power consumption.
Innovation Solution
Implementing a system that determines the type of query and routes it to the most efficient digital assistant component, utilizing large language models and multiple handling agents to process queries efficiently, and adjusting queries based on contextual data.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Device complexity
If a single digital assistant component processes all queries, then the system structure is simple, but processing latency increases and power consumption increases
Solution Approach 1:
The patent segments the digital assistant system into multiple specialized components: a query routing component that classifies incoming queries by type, and multiple query handling agents (first query handling agent, second query handling agent) that process specific query types. This segmentation allows queries to be routed to the most appropriate handler, reducing processing latency while maintaining manageable system complexity through modular architecture.
2Ease of operation
If a single digital assistant component processes all queries, then the system is easy to manage, but power consumption increases
Solution Approach 1:
The system is divided into specialized query handling agents that process specific query types, allowing the device to optimize power consumption by activating only the necessary agents for each query type rather than running a single component for all queries.
Solution Approach 2:
The query routing component changes the processing parameters by analyzing query characteristics and dynamically selecting the appropriate handling agent based on query type, enabling efficient resource allocation and reduced power consumption.
3Measurement precision
If contextual data is retrieved and queries are rewritten for all queries, then response accuracy improves, but processing time increases
Solution Approach 1:
The system performs preliminary actions by retrieving contextual data and rewriting queries only when necessary, based on the query type determined by the routing component. This selective approach maintains response accuracy for complex queries while avoiding unnecessary processing time for simpler queries.
Data Source
AI summary
Systems and processes for operating an intelligent automated assistant are provided. An example method includes, at a computer system that is configured to communicate with a display generation component and an input device: detecting an audio input including a query; in response to detecting the audio input including the query: retrieving contextual data related to the query; in accordance with a determination that the query includes a request of a first type: converting the query to a rewritten query based on the contextual data related to the query; and providing the rewritten query to a first digital assistant component; and in accordance with a determination that the query includes a request of a second type different from the request of the first type, providing the query and the contextual data related to the query to a second digital assistant component different from the first digital assistant component.