Prediction Engine Reduces Query Latency in Travel Search
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing travel search engines face significant latency in returning query results due to the need to query multiple databases associated with travel service providers, leading to delayed and inaccurate information for users.
Innovation Solution
The use of predictive techniques, combined with cached or live data, to quickly estimate prices and other information for travel reservations, allowing for the generation of live travel data predictions before all live data is received.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If multiple databases are queried to ensure accurate and current travel information, then data accuracy is improved, but query latency increases
Solution Approach 1:
The system performs preliminary actions by generating predictions using machine learning models before the actual database queries complete. The prediction engine creates estimated travel data (prices, availability, provider information) in advance, allowing the system to return results to users while still gathering live data from multiple databases. This resolves the contradiction by providing accurate-looking results immediately while maintaining data accuracy through subsequent validation against live sources.
Solution Approach 2:
The prediction engine acts as an intermediary between the user query and the multiple databases. Instead of directly querying all databases sequentially (which causes latency), the system uses the prediction engine to generate intermediate results that approximate the final output. These predictions are then refined or validated against actual database responses, achieving both speed and accuracy.
2Reliability
If live data is retrieved from multiple providers to ensure current information, then data currency is improved, but response time deteriorates
Solution Approach 1:
The system performs preliminary data preparation by using the prediction engine to generate current travel information estimates before the live data retrieval process completes. This allows the system to provide users with timely responses that reflect current conditions, while the actual live data from multiple providers is still being fetched in the background to ensure data currency.
Solution Approach 2:
The system performs partial action by using the prediction engine to generate sufficient results for immediate user display, even though complete live data from all providers is not yet available. The predictions provide enough information to satisfy user needs temporarily, while the full live data retrieval continues in parallel, ensuring eventual data currency without compromising response time.
Data Source
AI summary
Disclosed are methods, systems, and computer-readable medium to perform operations including: receiving a query specifying one or more criteria for a travel reservation, transmitting, over a network, one or more requests for live travel data satisfying the one or more criteria, determining one or more query results that satisfy the one or more criteria, retrieving cached travel data for at least one of the one or more query results, and while responses to the one or more requests for live travel data are still being received over the network, generating, using a prediction engine, live travel data predictions for the one or more query results based at least in part on the cached travel data.