On-Device Query Answer Cache for Offline Voice Systems
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Vehicle computing systems often fail to provide query answers when out of range of an internet connection, as they rely on remote systems for data retrieval, leading to unavailable information during travel.
Innovation Solution
Implementing a local query answer cache that predicts user queries based on context parameters such as time, location, and historical data, allowing the system to generate responses without an active internet connection by using pre-fetched query answers from a remote cache.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If the system queries a remote computing system for every user query, then the query answers are accurate and up-to-date, but the system cannot provide answers when out of internet range and experiences high latency
Solution Approach 1:
The system performs preliminary actions by fetching and caching query answers from the remote computing system in advance, before the user actually needs them. The cache is populated with predicted queries and their answers during periods of network availability, enabling offline operation when the vehicle is out of range of internet connection.
Solution Approach 2:
A local query answer cache is introduced as an intermediary between the user query and the remote computing system. This cache stores pre-fetched query answers locally on the vehicle's computing system, allowing the system to respond to queries without directly contacting the remote server, thus enabling operation without internet connectivity.
2Loss of information
If the system queries a remote computing system for every user query, then the answers are comprehensive, but the network data usage and latency increase
Solution Approach 1:
The system predicts which queries the user is likely to ask and fetches their answers in advance during periods of network availability. This preliminary action ensures that when the user actually asks these predicted queries, the answers are already available in the local cache, eliminating latency and reducing network data usage during travel.
3Adaptability or versatility
If the system maintains a large local query answer cache, then offline query support is enhanced, but the device storage requirements increase
Solution Approach 1:
Instead of uniformly caching all possible query answers, the system applies local quality by selectively caching only the predicted queries that the user is most likely to ask. The cache contains a curated subset of query answers based on prediction algorithms that analyze user behavior patterns, historical data, and contextual information, optimizing storage usage while maintaining effective offline support.
Data Source
AI summary
Techniques of this disclosure are directed to enable a computing device to process voice queries and provide query answers even when the computing device and vehicle do not have internet connectivity. According to the disclosed techniques, a computing device may detect a query via input devices of the computing device and output a query answer determined based on the detected query. Rather than directly querying a remote computing system, various aspects of the techniques of this disclosure may enable the computing device to use a query answer cache to generate the query answer. The query answer cache may include predicted queries and query answers retrieved from a query answer cache of a remote computing system, thereby enabling the computing device to respond to the detected queries while experiencing unreliable internet connection.