Natural Language Analytics API for Schema-Grounded Query Generation

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Operating an analytics engine becomes challenging due to the complexity of interfacing with diverse data sources and the need for specialized technical knowledge to generate queries, especially when users lack familiarity with the capabilities and output forms provided by the engine.

Innovation Solution

Implementing a Generative Artificial Intelligence (GenAI) within an API handler to translate natural language user inputs into structured queries for the analytics engine, utilizing a grounding database to generate queries compatible with the engine's schema, thereby allowing users to request data without requiring advanced technical knowledge.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of operation

If traditional API interfaces are used for the analytics engine, then data analysis capabilities are provided, but the interface becomes difficult to operate for administrators not familiar with the engine's capabilities and commands

Engineering Contradiction:
Improveease of operationVSAvoidinterface complexity
Core Design Contradiction:
Ease of operationVSDevice complexity

Solution Approach 1:

The patent introduces a natural language processing intermediary layer between the user and the analytics engine API. This intermediary translates simple natural language queries into complex analytical requests, shielding users from the underlying system complexity while maintaining full access to data analysis capabilities.

Inventive Principle:
Principle #24Intermediary (Mediator)

Solution Approach 2:

The patent replaces the mechanical interaction model (learning specific commands and API interfaces) with a linguistic interaction model (natural language processing). Users communicate through language rather than memorizing technical commands, fundamentally changing how the system is operated.

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

2Adaptability or versatility

If comprehensive data analysis capabilities are provided, then insights can be derived from vast amounts of data, but users need specialized technical knowledge to operate the system

Engineering Contradiction:
Improvedata analysis capabilityVSAvoidease of operation
Core Design Contradiction:
Adaptability or versatilityVSEase of operation

Solution Approach 1:

The system provides self-service capabilities by automatically understanding and executing data analysis requests without requiring user expertise. The natural language interface allows users to independently formulate queries and receive insights without needing to understand the complex analytical methods or data structures underlying the system.

Inventive Principle:
Principle #25Self-service

3Adaptability or versatility

If multiple data formats and analysis methods are supported, then flexible data exploration is enabled, but the number of commands and input forms increases

Engineering Contradiction:
Improvedata format supportVSAvoidcommand complexity
Core Design Contradiction:
Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The natural language interface serves as a universal entry point that handles multiple data formats, analysis methods, and query types through a single consistent interaction model. Rather than providing separate interfaces for different functionalities, the system processes diverse analytical requests through unified natural language understanding.

Inventive Principle:
Principle #6Universality (Multi-functionality)

Data Source

PatentUS20250355732A1Flexible analytics engine API using natural language
Publication Date: 2025.11.20 MICROSOFT TECHNOLOGY LICENSING LLC
  • US20250355732A1 patent drawing
  • US20250355732A1 patent drawing
  • US20250355732A1 patent drawing

AI summary

A data processing system includes an Application Programming Interface (API) handler for an analytics engine. The API handler to perform functions of: receiving user input including a natural language description that defines data a user wants from the analytics engine; generating a submission for a generative artificial intelligence (GenAI) based on the user input, the submission including the natural language description, schema of datasets stored in a database of the analytics engine, and an instruction to produce a query for the database; submitting the generated submission to the GenAI and receiving a corresponding query from the GenAI; submitting the query from the GenAI to the database of the analytics engine to generate a result set specific to the natural language description of the user input; and outputting, via an API, the result set.