Interested in licensing this patent?
MTEC can help explore whether this patent might be available for licensing for your application.
Publication Number
US-12353410-B2
Publication Date
2025-07-08
Expiration Date
Abstract
Predicting cacheable queries is provided. For example, a system integrates one or more processors with a cache store to execute one or more microservices. The system receives a first request including an identifier and a set of key-value pairs. The system predicts a set of requests based on the identifier and the set of key-value pairs. The system identifies based on a comparison with a threshold metric, a subset of predicted requests from the set of requests indicative of one or more subsequent requests. The system constructs a set of labels. The system retrieves, via the set of labels and from a data repository remote from the client service, data for the subset of predicted requests. The system transmits a cache value from the cache store that corresponds to the subsequent request.
Core Innovation
A system with one or more processors coupled with a cache store receives a first request that includes an identifier and a set of key-value pairs. The system uses a machine learning model to predict a plurality of requests indicative of one or more subsequent requests based on the identifier and the set of key-value pairs from the first request, and based on a comparison with a threshold metric identifies a subset of predicted requests and determines predicted request identifiers and corresponding predicted key-value pairs.
The system constructs, using the machine learning model and based on the predicted request identifiers and the corresponding predicted key-value pairs, a set of labels comprising classifications for the subset of predicted requests. Using the set of labels, the system retrieves data for the subset of predicted requests from a database and configures the cache store by storing the set of labels as cache keys and the data retrieved for the subset of predicted requests as cache values.
Responsive to receipt of a subsequent request that matches one of the subset of predicted requests, the system transmits a cache value from the cache store that corresponds to the subsequent request. The same sequence is performed in a method form by one or more processors coupled with the cache store, and in a non-transitory computer-readable medium form as instructions to cause the processors to perform the receive, predict, select by threshold metric, label, retrieve, configure cache keys and values, and transmit upon matching subsequent request.
Claims Coverage
The partial content includes three independent claims: a system, a method, and a non-transitory computer-readable medium. Across these independent claims, the same core inventive features recur, including the threshold metric comparison, label or classification to cache-key mapping, database retrieval for the labeled subset, caching as cache keys and cache values, and serving the matching subsequent request from the cache store.
Machine-learning prediction of subsequent requests from request identifier and key-value pairs
Predict, using a machine learning model, a plurality of requests indicative of one or more subsequent requests based on the identifier and the set of key-value pairs from the first request.
Threshold metric selection of a subset of predicted requests
Identify, using the machine learning model and based on a comparison with a threshold metric, a subset of predicted requests from the plurality of predicted requests, the subset of predicted requests comprising predicted request identifiers and corresponding predicted key-value pairs.
Label construction as classifications for selected predicted requests
Construct, using the machine learning model and based on the predicted request identifiers and the corresponding predicted key-value pairs, a set of labels comprising classifications for the subset of predicted requests.
Database retrieval using labels
Retrieve, using the set of labels and from a database, data for the subset of predicted requests.
Cache store configuration mapping labels to cache keys and retrieved data to cache values
Configure, in the cache store, the set of labels as cache keys and the data retrieved for the subset of predicted requests as cache values.
Serving cached values upon subsequent request match
Transmit, responsive to receipt of a subsequent request that matches one of the subset of predicted requests, a cache value from the cache store that corresponds to the subsequent request.
The independent claims consistently cover predicting subsequent requests from a first request’s identifier and key-value pairs using a machine learning model, selecting a subset by comparing predicted requests to a threshold metric, generating labels or classifications for the subset, retrieving corresponding data from a database, caching that data keyed by the labels, and transmitting the cached cache value when a subsequent matching request is received.
Stated Advantages
Documented Applications
No documented applications found
Interested in licensing this patent?