Semantic Classification for Natural Language Database Queries

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Conventional databases face challenges in efficiently processing queries and storing data due to the need for predefined structures and terminology, limitations in accessing unstructured data, and the manual effort required for data reorganization and conversion between different data formats.

Innovation Solution

Implementing a database system that uses semantic classification and interpretation to store and retrieve data, allowing for natural language queries and efficient retrieval of implicit information by converting unstructured data into structured annotations, which can be searched using compatible annotation models.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If conventional databases use predefined structures and terminology to organize data, then data storage and retrieval follow established patterns, but the system cannot efficiently process natural language queries or access unstructured data

Engineering Contradiction:

Improvequery processing capabilityVSAvoiddata structure requirements

Core Design Contradiction:

Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The patent introduces an intermediary layer between the user's natural language query and the database structure. This intermediary processes the query through semantic interpretation to convert it into database-compatible search criteria, enabling natural language queries without requiring changes to the underlying database schema or user education on predefined structures

Inventive Principle:

Principle #24Intermediary (Mediator)

Solution Approach 2:

The patent replaces manual mechanical processes of data reorganization and conversion with automated semantic interpretation engines. Instead of requiring users to manually reorganize data or convert between formats, the system automatically processes queries and retrieves implicit information through semantic analysis

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

2Adaptability or versatility

If manual data reorganization and conversion between formats is performed, then data can be accessed in different formats, but significant manual effort and time are required

Engineering Contradiction:

Improvedata format compatibilityVSAvoidmanual processing time

Core Design Contradiction:

Adaptability or versatilityVSLoss of time

Solution Approach 1:

The patent implements self-service through automated semantic interpretation. The system automatically processes data conversion and format transformation without human intervention. When data needs to be accessed in different formats or from different sources, the semantic interpretation engine automatically handles the conversion and retrieval processes

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The patent performs preliminary processing of data by pre-establishing semantic interpretations and classifications. This preliminary action prepares the data in advance so that when queries are made, the system can quickly retrieve and convert information without requiring manual reorganization at query time

Inventive Principle:

Principle #10Preliminary action

3Adaptability or versatility

If unstructured data is stored in databases, then more flexible data storage is achieved, but the data cannot be efficiently searched or accessed without predefined structures

Engineering Contradiction:

Improvedata storage flexibilityVSAvoiddata retrieval efficiency

Core Design Contradiction:

Adaptability or versatilityVSProductivity

Solution Approach 1:

The patent introduces semantic interpretation as an intermediary layer that bridges unstructured data storage and efficient retrieval. This intermediary processes queries and converts them into search criteria that can effectively query unstructured data, enabling both flexible storage and efficient access simultaneously

Inventive Principle:

Principle #24Intermediary (Mediator)

Solution Approach 2:

The patent changes the parameters of data representation by introducing semantic classifications and interpretations. Instead of searching for exact keyword matches in unstructured data, the system uses semantic parameters to retrieve relevant information, transforming the search process to work effectively with unstructured data formats

Inventive Principle:

Principle #35Parameter changes

Data Source

PatentUS9239872B2Data store organizing data using semantic classification

Publication Date: 2016.01.19 MICROSOFT TECHNOLOGY LICENSING LLC

AI summary

Data stores that store content units and annotations regarding the content units derived through a semantic interpretation of the content units. When annotations are stored in a database, different parts of an annotation may be stored in different tables of the database. For example, one or more tables of the database may store all semantic classifications for the annotations, while one or more other tables may store content of all of the annotations. A user may be permitted to provide natural language queries for searching the database. A natural language query may be semantically interpreted to determine one or more annotations from the query. The semantic interpretation of the query may be performed using the same annotation model used to determine annotations stored in the database. Semantic classifications and format of the annotations for a query may be the same as one or more annotations stored in the database.