Predictive Model Request Validation With Isolated Execution Layers
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing software solutions face challenges such as system crashes due to invalid inputs and resource monopolization, leading to inefficiencies and slow response times when processing electronic requests for predictive computer models.
Innovation Solution
A system and method that separates the API layer from the model execution layer, with the analytic server validating requests using model specification files and imputing valid values for invalid inputs, and leveraging an integrated development environment for efficient resource allocation and load balancing.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If the API layer loads models from memory or database for each request, then the system can handle different predictive models, but the processing time increases and resource efficiency decreases
Solution Approach 1:
The system pre-loads multiple predictive models into memory before receiving requests. When a request arrives, the API layer can immediately execute the pre-loaded model without waiting for disk I/O, significantly reducing processing time while maintaining the ability to handle different models
2Device complexity
If all models share the same resource pool and environment, then the system is simple to manage, but invalid inputs cause system crashes and segmentation faults
Solution Approach 1:
The system segments the execution environment by creating separate execution contexts for each predictive model. Each model runs in its own isolated environment with dedicated resource allocation, preventing invalid inputs in one model from crashing the entire system or affecting other models
3Device complexity
If only one predictive model runs at a time, then the system is easy to manage, but CPU resources are monopolized and low-priority batch predictions suffer from resource starvation
Solution Approach 1:
The system implements dynamic resource allocation where multiple predictive models can execute simultaneously with flexible CPU resource distribution. The resource manager dynamically adjusts CPU allocation based on model priorities and resource availability, enabling both high-priority real-time predictions and low-priority batch predictions to execute efficiently without monopolization
4Device complexity
If the API layer performs both request receiving and model execution, then the system architecture is simple, but validation failures lead to crashes and memory dumps that cause subsequent request failures
Solution Approach 1:
The system separates the API layer from the model execution layer, with validation performed in the API layer before executing models in a separate execution environment. This segmentation ensures that validation failures are contained and cannot cause system crashes or memory dumps that would affect subsequent requests
Data Source
AI summary
Disclosed herein are embodiments of systems, methods, and products comprises a server for efficiently processing electronic requests. The server receives a plurality of predictive computer models and generates a specification file for each model by parsing the source code of each model. When the server receives an electronic request, the API layer of the server validates the request by verifying the inputs of the request satisfying validation codes in the specification file of the corresponding model. If the electronic request is invalid, the server imputes valid values for the request and sends the imputed values to the model execution layer. Within the model execution layer, the server utilizes an integrated development environment of a third-party server to call the function of the corresponding model. The model execution layer transmits the function's output results back to the API layer, which transmits the output results to the user device.