AI-Powered Personal Memory Assistant with Context-Aware Smart Reminders and Multimodal Information Extraction

References

[1] Du, Y., et al. (2023). "According to Me: Long-Term Personalized Referential Memory QA." Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV).

[2] Hirschberg, J., & Manning, C. D. (2015). "Advances in natural language processing." Science, 349(6245), 261-266. (Establishes the NLP baseline utilized in the Conversational Interface module).

[3] Jones, W. (2007). Keeping Found Things Found: The Study and Practice of Personal Information Management. Morgan Kaufmann. (Foundational literature on human cognitive offloading and folder vs. search retrieval).

[4] Minaee, S., et al. (2024). "Large Language Models: A Survey." arXiv preprint,arXiv:2402.06196. (Comprehensive review of LLMs like Google Gemini and their zero-shot capabilities in data extraction).

[5] Grinbaum, A., & Adomavicius, G. (2022). "Privacy and Security in Intelligent Personal Assistants: A Comprehensive Review." IEEE Transactions on Secure and Dependable Computing. (Explores the necessity of cryptographic measures, like Fernet encryption, in personal AI).

[6] Paliwal, S. et al. (2023). "Post-OCR Error Correction Using Large Language Models." Proceedings of SPIE Document Recognition and Retrieval. (Highlights how LLMs surpass traditional OCR engines in extracting structure from messy text).

[7] Subramani, S. et al. (2021). "A survey on recent advances in named entity recognition." Springer Artificial Intelligence Review. (Relates directly to recognizing "Event Types" and "Object Locations" using NER algorithms).

[8] Wang, Z., et al. (2023). "ProactiveAgent: Personalized Context-Aware Reminder System." Adjunct Proceedings of the 36th Annual ACM Symposium on User Interface Software and Technology (UIST '23).

[9] Whittaker, S. (2011). "Personal information management: from information consumption to curation." Annual Review of Information Science and Technology, 45(1), 1-62.

[10] Zhang, H., et al. (2024). "OmniQuery: A Multimodal Interactive Memory Assistant." ACM/ArXiv Repository Computing Frameworks. (Analyzes multimodal vision-and-text memory retrieval).

[11] Zhong, W., et al. (2024). "MemoryBank: Enhancing Large Language Models with Long-Term Memory." Proceedings of the AAAI Conference on Artificial Intelligence.

[12] Honnibal, M., & Montani, I. (2017). "spaCy 2: Natural language understanding with Bloom embeddings, convolutional neural networks and incremental parsing." To appear. (Technical reference for algorithmic NLP fuzzy-matching and tokenization).

[13] Li, Y., & Singh, M. (2024). "Evaluating Vision-Language Models for Document Understanding Scale." IEEE International Conference on Systems, Man, and Cybernetics (SMC). (Details the exact mechanism your Gemini OCR Module uses to categorize tickets and prescriptions).

[14] W3C Web Speech API Specification. (2022). World Wide Web Consortium (W3C) Draft Technical Report. (Standardized reference detailing the architecture behind your microphone speech-to-text module).

@article{1715480,
      author = {K Bharath, Dr. K Ponmozhi},
      title = {AI-Powered Personal Memory Assistant with Context-Aware Smart Reminders and Multimodal Information Extraction},
      journal = {Iconic Research And Engineering Journals},
      year = {2026},
      volume = {9},
      number = {9},
      pages = {2229-2236},
      issn = {2456-8880},
      url = {https://www.irejournals.com/formatedpaper/1715480.pdf},
      abstract = {Human memory limitations often lead to everyday challenges such as misplacing essential items, forgetting important deadlines, and losing track of valuable digital information. To address these issues, this study presents an AI-powered Personal Memory Assistant designed to support and enhance daily cognitive tasks. The system is developed as a secure, full-stack web application using the Flask framework and incorporates Fernet encryption to ensure data privacy. It enables users to store, organize, and retrieve both physical object locations (such as keys or documents) and digital content (such as links and articles) through a user-friendly, natural language chatbot interface. The proposed system integrates two key intelligent components. The Smart Predictive Reminder Engine analyzes user behavior patterns to identify frequently misplaced items and proactively suggests reminders, thereby helping users build consistent routines. Additionally, the Intelligent Document Reminder System utilizes Optical Character Recognition (OCR) to extract and interpret information from uploaded images, such as medical prescriptions, tickets, or bills. By understanding the context such as event type, urgency, and recurrence the system automatically generates appropriate reminders. Overall, the solution provides a practical and accessible approach to reducing cognitive load, improving personal organization, and minimizing the risk of human error in everyday memory-related tasks.},
      keywords = {Artificial Intelligence (AI), Cognitive Augmentation, Personal Memory Systems, Natural Language Processing (NLP), Optical Character Recognition (OCR), Context-Aware Computing, Predictive Reminder Systems, Pattern Recognition, Flask-Based Web Application, End-to-End Encryption, Human–Computer Interaction (HCI), Intelligent Assistive Systems},
      month = {March},
      doi = {https://doi.org/10.64388/IREV9I9-1715480}
  }