AI Data Table Semantics for Automated Quality Management

Solution Overview

Problem

Current data quality management in enterprises is inefficient and labor-intensive, relying on manual data checking and cleaning, which is time-consuming and lacks automation.

Innovation Solution

A data quality management method and apparatus utilizing AI models for semantic extraction and processing solution generation, enabling automated data quality management through user input of data tables and tasks, with feedback loops for model fine-tuning based on user corrections.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If manual data checking and cleaning is performed, then data quality management can be conducted, but the process is time-consuming and labor-intensive

Engineering Contradiction:

Improvedata quality management capabilityVSAvoidtime consumption

Core Design Contradiction:

ReliabilityVSLoss of time

Solution Approach 1:

The patent replaces manual mechanical data checking and cleaning operations with an automated AI model system. The processing solution generation model automatically generates executable code for data quality tasks, substituting human labor with intelligent automation that performs semantic extraction, task understanding, and solution generation without manual intervention.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The system enables self-service data quality management where the AI model autonomously generates processing solutions based on user inputs. The model automatically creates executable code, executes it, and iteratively improves through feedback loops without requiring manual programming or intervention, making the system self-sufficient in performing data quality tasks.

Inventive Principle:

Principle #25Self-service

2Reliability

If manual data checking and cleaning is performed, then data quality management can be conducted, but the process is labor-intensive

Engineering Contradiction:

Improvedata quality management capabilityVSAvoidefficiency

Core Design Contradiction:

ReliabilityVSProductivity

Solution Approach 1:

The patent replaces manual mechanical data checking and cleaning operations with an automated AI model system. The processing solution generation model automatically generates executable code for data quality tasks, substituting human labor with intelligent automation that performs semantic extraction, task understanding, and solution generation without manual intervention.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The system enables self-service data quality management where the AI model autonomously generates processing solutions based on user inputs. The model automatically creates executable code, executes it, and iteratively improves through feedback loops without requiring manual programming or intervention, making the system self-sufficient in performing data quality tasks.

Inventive Principle:

Principle #25Self-service

3Productivity

If AI models are used for automated data quality management, then efficiency is improved, but model precision needs continuous optimization

Engineering Contradiction:

Improvedata quality management efficiencyVSAvoidmodel precision

Core Design Contradiction:

ProductivityVSMeasurement precision

Solution Approach 1:

The patent implements a feedback mechanism where user corrections and modifications to generated processing solutions are fed back to the AI model. This feedback loop allows the model to learn from errors and improvements, continuously optimizing its precision while maintaining high automation efficiency. The system tracks user interactions and uses them to refine future solution generation.

Inventive Principle:

Principle #23Feedback

Data Source

PatentUS20260030225A1Data quality management method and apparatus, and computer-readable storage medium

Publication Date: 2026.01.29 HUAWEI CLOUD COMPUTING TECHNOLOGIES CO LTD

AI summary

Example data quality management methods and apparatus are described. In one example method, a computing device obtains a data table input or selected by a user. The computing device inputs the data table into a data table semantic extraction model, and uses semantics output by the data table semantic extraction model as semantics of the data table. Then, the computing device obtains a task of performing quality management on the data table input or selected by the user, and inputs the semantics of the data table and the quality management task into a processing solution generation model. A processing solution output by the processing solution generation model is used as a processing solution of the quality management task. The computing device executes the processing solution to obtain a task execution result, and feeds back the task execution result to the user.