Automatic Machine Learning Data Modeling for Low-Latency Analysis

Solution Overview

Problem

Existing database analytic tools are inefficient, costly, and require substantial configuration and training, leading to high resource utilization and limited capability in providing data access using machine learning models.

Innovation Solution

A low-latency data access and analysis system that automatically generates and trains machine learning models based on stored data, resolving input data requests in a compatible form and generating executable queries to reduce resource utilization and improve reliability and load balancing.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If existing database analytic tools are used, then data analysis capability is provided, but resource utilization is high and efficiency is low

Engineering Contradiction:

Improvedata analysis efficiencyVSAvoidresource utilization

Core Design Contradiction:

ProductivityVSUse of energy by moving object

Solution Approach 1:

The system automatically generates and trains machine learning models without requiring manual configuration or training by users. The database itself serves the analytical functions by autonomously creating models from stored data, eliminating the need for external analytical tools and reducing resource utilization while improving efficiency.

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The database system performs multiple functions including storage, retrieval, and automatic machine learning model generation. By integrating these functions into a single system, the patent eliminates the need for separate analytical tools, thereby reducing overall resource utilization and improving productivity.

Inventive Principle:

Principle #6Universality (Multi-functionality)

2Ease of operation

If existing database analytic tools are used, then data analysis is performed, but configuration and training requirements are substantial

Engineering Contradiction:

Improveconfiguration and training requirementVSAvoidsystem configuration complexity

Core Design Contradiction:

Ease of operationVSDevice complexity

Solution Approach 1:

The system automatically generates and trains machine learning models without requiring manual configuration or training by users. The database itself serves the analytical functions by autonomously creating models from stored data, eliminating the need for external analytical tools and reducing resource utilization while improving efficiency.

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The system changes the operational parameters by automatically inferring data relationships and generating models based on stored data patterns. This eliminates the need for manual configuration of analytical parameters, significantly reducing the complexity of system setup and operation.

Inventive Principle:

Principle #35Parameter changes

3Measurement precision

If machine learning models are manually configured, then analytical accuracy is achieved, but time consumption increases

Engineering Contradiction:

Improveanalytical accuracyVSAvoidmodel training time

Core Design Contradiction:

Measurement precisionVSLoss of time

Solution Approach 1:

The system performs preliminary actions by automatically pre-processing and preparing data for model generation. It infers data relationships and creates models in advance based on stored data patterns, eliminating the need for manual configuration and significantly reducing the time required to achieve analytical accuracy.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system automatically generates and trains machine learning models without requiring manual configuration or training by users. The database itself serves the analytical functions by autonomously creating models from stored data, eliminating the need for external analytical tools and reducing resource utilization while improving efficiency.

Inventive Principle:

Principle #25Self-service

Data Source

PatentUS12393559B2Automatic machine learning data modeling in a low-latency data access and analysis system

Publication Date: 2025.08.19 THOUGHTSPOT INC

AI summary

Automatic data modeling in includes identifying an analytical object in response to first data expressing usage intent, generating an analytical model generation data query for the analytical object, obtaining a trained analytical model generated in accordance with the analytical model generation query and trained using results data obtained in accordance with the analytical object, generating a resolved request representing second data expressing usage intent and indicating a request for results data obtained using the trained analytical model, generating an analytical model results data query for obtaining the results data in accordance with the trained analytical model and the analytical object, and outputting data for presenting a visualization of the results data obtained by executing the analytical model results data query, wherein a first portion of the results data corresponds with the analytical object and a second portion of the results data corresponds with the trained analytical model.