Enhancing Productivity in Database Management Through AI: A Three-Phase Approach for Database
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866916687638429696 |
|---|---|
| author | Parashar, Kushagra Dev, Ajay Kumar, Aditya Khatri, Darpan |
| author_facet | Parashar, Kushagra Dev, Ajay Kumar, Aditya Khatri, Darpan |
| contents | This paper presents a novel AI-powered framework designed to streamline database management and query optimization for PostgreSQL systems. Structured in three phases: Natural Language to SQL Translation, Query Execution and Analysis, and Insight Generation, the approach empowers users with intuitive, intelligent interaction with databases. By leveraging advanced natural language processing and language models, the system enables non-technical users to extract meaningful insights from complex datasets, reducing the dependency on specialized DBAs. The framework also introduces iterative refinement of queries, automatic report generation, and support for temporal data forecasting. Experimental results demonstrate improved productivity, reduced query latency, and enhanced accuracy, validating the system's effectiveness across diverse business use cases. The solution was developed and evaluated at ABV-IIITM Gwalior, under the guidance of Prof. Dr. Arun Kuma |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_09288 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Enhancing Productivity in Database Management Through AI: A Three-Phase Approach for Database Parashar, Kushagra Dev, Ajay Kumar, Aditya Khatri, Darpan Databases 68T50 (Natural language processing), 68P20 (Information storage and retrieval) I.2.7; H.2.3; H.2.8 This paper presents a novel AI-powered framework designed to streamline database management and query optimization for PostgreSQL systems. Structured in three phases: Natural Language to SQL Translation, Query Execution and Analysis, and Insight Generation, the approach empowers users with intuitive, intelligent interaction with databases. By leveraging advanced natural language processing and language models, the system enables non-technical users to extract meaningful insights from complex datasets, reducing the dependency on specialized DBAs. The framework also introduces iterative refinement of queries, automatic report generation, and support for temporal data forecasting. Experimental results demonstrate improved productivity, reduced query latency, and enhanced accuracy, validating the system's effectiveness across diverse business use cases. The solution was developed and evaluated at ABV-IIITM Gwalior, under the guidance of Prof. Dr. Arun Kuma |
| title | Enhancing Productivity in Database Management Through AI: A Three-Phase Approach for Database |
| topic | Databases 68T50 (Natural language processing), 68P20 (Information storage and retrieval) I.2.7; H.2.3; H.2.8 |
| url | https://arxiv.org/abs/2504.09288 |