AI-Enabled Device Adaptive Caching for Network Independent Delivery
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional methods for delivering user consumable information on devices like smart TVs and smartphones rely on continuous network connectivity, leading to delayed response times due to network dependency and potential connectivity issues, which clog bandwidth and increase delivery times.
Innovation Solution
An AI-enabled device implements an AI learning model that periodically trains on user preferences and network information to adaptively cache cloud data locally, allowing for independent delivery of user consumable information with minimal reliance on cloud data, even in offline states.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of time
If cloud data retrieval is used for every user request, then data freshness is maintained, but response time increases and network bandwidth is consumed
Solution Approach 1:
The system performs preliminary actions by caching cloud data locally in advance before it is actually needed. The AI learning model predicts which data will be needed and pre-loads it into local storage, so when a user request comes in, the data is already available locally, eliminating the need for real-time cloud retrieval and thus reducing response time while maintaining data availability.
Solution Approach 2:
The system dynamically adjusts the balance between local caching and cloud retrieval based on predicted user needs and data usage patterns. The AI learning model continuously learns from user behavior and optimizes which data to cache locally versus which to retrieve from the cloud, creating a dynamic adaptation strategy that responds to changing conditions rather than following a static approach.
2Reliability
If network connectivity is required for every information delivery, then data accuracy is ensured, but service availability decreases during connectivity issues
Solution Approach 1:
The system introduces a local cache storage as an intermediary between the user and the cloud server. This intermediary layer can serve user requests even when the cloud server is inaccessible, maintaining service availability. The AI learning model manages this intermediary by predicting which data to cache locally, allowing the system to operate independently of continuous network connectivity while still providing accurate information from local caches when needed.
Solution Approach 2:
The system changes the parameter of data location from exclusively cloud-based to a hybrid local-cloud model. By adjusting where data is stored (locally vs. remotely) based on AI predictions of user needs, the system can switch between relying on local cached data for availability and cloud data for freshness, dynamically changing the operational parameters to optimize both service availability and data accuracy.
3Loss of time
If AI learning model caches more data locally, then response time decreases, but device storage requirements increase
Solution Approach 1:
Instead of caching all possible cloud data locally, the system applies partial action by selectively caching only the most frequently accessed or predicted data. The AI learning model analyzes user behavior patterns and caches only the necessary portion of data that will actually be needed, avoiding the excessive storage consumption that would result from caching everything while still achieving significant response time improvements for the most common operations.
Solution Approach 2:
The system changes the parameter of caching strategy from uniform to selective based on AI predictions. Rather than caching data uniformly or in fixed amounts, the AI learning model dynamically determines which data to cache and in what quantities based on predicted user needs, transforming the storage parameter from a static allocation to a dynamic, demand-driven approach that optimizes the balance between response time and storage usage.
Data Source
AI summary
An artificial intelligence-enabled device that handles delivery of user consumable information independent of network connectivity of the AI-enabled device, includes a memory and neural circuitry. The neural circuitry allocates a dedicated cache storage and determines a type of intelligent service on the AI-enabled device, for which first information is to be cached at the dedicated cache storage. The neural circuitry caches first information from a cloud server to a local sub-cache in the dedicated cache storage. The first information of the determined type of service is adaptively cached during at least one of a background activity or a foreground activity of the AI-enabled device, in accordance with an offline state or an online state of the AI-enabled device. The neural circuitry further controls delivery of user consumable information, based on a user input, on the AI-enabled device, based on the local sub-cache and supplemental information retrievable from the cloud server.