Natural Language Query Processing with Analytics Intent

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing natural language query systems are unable to process queries with an analytic intent, limiting their ability to handle queries that include analytics functions.

Innovation Solution

The system processes natural language queries by applying domain reasoning using predefined grammars to assign analytics functions to categories, instantiate them with arguments and actions, and interpret them within a domain ontology to generate executable queries.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If existing natural language query systems are used, then simple point queries and keyword queries can be processed, but queries with analytic intent cannot be handled

Engineering Contradiction:

Improvequery processing capabilityVSAvoidanalytics function processing

Core Design Contradiction:

Adaptability or versatilityVSReliability

Solution Approach 1:

The system extends natural language query processing to handle multiple query types (point queries, keyword queries, and analytics queries) through a unified framework. The grammar-based parsing system and domain ontology interpretation layer enable the same system architecture to process diverse query intents, making the system universal rather than specialized for single query types.

Inventive Principle:

Principle #6Universality (Multi-functionality)

Solution Approach 2:

The patent introduces intermediate processing layers including grammar-based parsing, domain reasoning, and ontology interpretation that mediate between the raw natural language input and the executable query generation. These intermediary components enable the system to understand and process analytic intent by breaking down complex queries into structured representations before execution.

Inventive Principle:

Principle #24Intermediary (Mediator)

2Adaptability or versatility

If domain reasoning and predefined grammar are applied to categorize analytics functions, then queries with analytic intent can be processed, but system complexity increases

Engineering Contradiction:

Improveanalytics query processingVSAvoidsystem architecture

Core Design Contradiction:

Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The system segments the query processing pipeline into distinct modular components: natural language input reception, grammar-based parsing, domain reasoning layer, ontology interpretation, and executable query generation. Each component handles a specific aspect of the processing, making the overall complex system manageable through clear separation of concerns and independent module development.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The system uses parameter-based grammar rules and domain ontology parameters to control the processing behavior. By changing and configuring parameters in the grammar definitions and ontology structures, the system can adapt to different domain requirements without redesigning the entire architecture, managing complexity through parameterization rather than structural changes.

Inventive Principle:

Principle #35Parameter changes

3Manufacturing precision

If analytics functions are instantiated with predefined arguments and actions, then accurate executable queries are generated, but processing time increases

Engineering Contradiction:

Improvequery generation accuracyVSAvoidquery processing time

Core Design Contradiction:

Manufacturing precisionVSLoss of time

Solution Approach 1:

The system performs preliminary actions by pre-defining grammar rules, argument structures, and action sequences for common analytics function patterns. During query processing, the system matches incoming queries against these pre-prepared templates and applies the corresponding predefined arguments and actions, avoiding the need to construct everything from scratch and reducing processing time while maintaining accuracy.

Inventive Principle:

Principle #10Preliminary action

Data Source

PatentUS11586619B2Natural language analytics queries

Publication Date: 2023.02.21 INTERNATIONAL BUSINESS MACHINE CORPORATION

AI summary

Methods, systems, and computer program products for processing natural language analytics queries are provided herein. A computer-implemented method includes obtaining a natural language query comprising an analytics function; applying domain reasoning using a predefined grammar for a plurality of different predefined categories of analytics functions to assign the analytics function of the natural language query into a given analytics function category; identifying predefined arguments and a predefined sequence of actions associated with the given analytics function category; instantiating the analytics function using the predefined arguments and the predefined sequence of actions; interpreting the instantiated analytics function in the context of a domain ontology to generate a target executable query to implement the instantiated analytics function; and executing the predefined sequence of actions for the given analytics function class on a result of the target executable query to obtain an answer to the natural language query.