본 자료는 자연어 처리(NLP) 분야의 전 세계 영어 논문 및 특허를 엄선하여 정리한 것으로, 다양한 온라인 과학 저널에 게재된 자료들을 자연어 처리, 토큰화, 어간 추출, 표제어 추출, 품사 구분, 개체명 인식 및 감정 분석에 초점을 맞춰 분류했습니다.
Hardware security module implementation as edge devices in a networked system
Patent published on the 2026-06-04 in US under Ref US20260154449 by BANK OF AMERICA CORP [US] (Dande Pratap [us], Dos Santos Gilberto [us], Murugan Jayabalaji [in], Medeiros Patricia A [us])
Abstract: Hardware security modules (HSM) may be implemented at distributed edge devices to provide faster and dynamic processing of data. HSM-implemented edge devices may be used to process data to enhance data security. For example, HSM edge devices may provide encryption, decryption, data masking, tokenization, or anonymization. The HSM edge devices may interface with one or more blockchains to invoke smart contracts, and to record data transaction events. In some examples, smart contracts may be used [...]
Our summary: HSMs can be implemented in edge devices to enhance data processing and security. They enable encryption, decryption, and data masking among other functions. Additionally, HSM edge devices can interact with blockchains to manage smart contracts and track data transactions.
Hardware Security Module, Edge Devices, Data Security, Smart Contracts
Patent
Machine learning aspect based sentiment analysis
Patent published on the 2026-06-04 in US under Ref US20260154506 by ORACLE INT CORPORATION [US] (Phani Sai Ganesh Didugu [in], Baviskar Akash [in], Ramanathan Krishnan [in], Agrawal Vikas [in])
Abstract: [0000] Embodiments evaluate performance by receiving a plurality of training performance reviews. Embodiments extract from the training performance reviews, using a first machine learning model, a plurality of features comprising a training aspect, a training sentiment, and a corresponding training evidence. Embodiments use the extracted plurality of features to train a second machine learning model. Embodiments receive a first performance review and extract from the first performance review one[...]
Our summary: The process involves evaluating performance through training performance reviews. It extracts features like training aspect and sentiment using a first machine learning model. A second model predicts sentiment scores for aspects in new performance reviews.
sentiment analysis, machine learning, performance reviews, feature extraction
Patent
Anomaly detection engine in a security management system
Patent published on the 2026-06-03 in EP under Ref EP4752764 by MICROSOFT TECHNOLOGY LICENSING LLC [US] (Vinay Vaishali [us], Mangal Anjali [us])
Abstract: [0001] Methods, systems, and computer storage media for providing anomaly detection using an anomaly detection engine of a security management system are described. The anomaly detection engine supports anomaly detection that refers to the process of identifying command-line activities that deviate from established patterns of normal behavior within a large-scale environment, such as data centers. The anomaly detection engine operates based on an advanced framework specifically designed to enhan[...]
Our summary: The anomaly detection engine identifies command-line activities that deviate from normal behavior in large-scale environments. It employs advanced models for pattern recognition and integrates global and local context analysis. The system features a dual-layer detection architecture and supports scalable anomaly detection with continuous compliance monitoring.
anomaly detection, security management, pattern recognition, distributed computing
Patent
Systems and methods for optimized fingerprinting and tokenization in server drift analysis
Patent published on the 2026-05-28 in US under Ref US20260149639 by BANK OF AMERICA CORP [US] (Alizzi Jason A [us], Lozes John Andres [us], Yu Chia-ho [us], Maniotis Daniel M [us], Bosi Robert [us], Jain Amit [us], Misra Pravesh K [us], Carlson Kevin Roy [us], Simon Matthew E [us], Badawy Tamer [us], Nair Sreeni R [us], Gupta Dharmendra Kumar [in],)
Abstract: Systems, computer program products, and methods are described herein for optimized fingerprinting and tokenization in server drift analysis. The present disclosure is configured to detect configuration drift across entire computer servers by utilizing distributed agents that collect and analyze metadata such as file modification dates, sizes, and cryptographic hashes. These agents sanitize sensitive information and conditionally tokenize environment-specific values, such as server names, IP addr[...]
Our summary: The system optimizes fingerprinting and tokenization for server drift analysis. It utilizes distributed agents to collect and sanitize metadata for accurate configuration comparisons. This automation enhances efficiency, accuracy, and security in large, dynamic environments.
Fingerprinting, Tokenization, Server Drift, Metadata
Patent
Adaptive modular system and method for ai-driven professional evaluation and benchmarking
Patent published on the 2026-05-28 in US under Ref US20260148174 by NEAL KEVIN [US] (Neal Kevin [us])
Abstract: [0000] This invention relates to an adaptive modular system and method for professional evaluation and benchmarking across multiple industries. The system integrates advanced artificial intelligence and machine learning algorithms within a modular framework to provide personalized, objective, and real-time assessments. Key components include a data ingestion layer for collecting data from diverse sources, a data processing engine for cleaning and transforming data, a feature extraction module, a[...]
Our summary: The invention presents an adaptive modular system for professional evaluation and benchmarking. It utilizes AI and machine learning to deliver real-time, personalized assessments across various industries. Key features include data ingestion, processing, and tailored evaluation modules for enhanced customization and scalability.
Adaptive, Modular, AI, Benchmarking
Patent
Electronic device, method, and non-transitory computer-readable storage medium for training language model
Patent published on the 2026-05-21 in WO under Ref WO2026105889 by NCSOFT CORP [KR] (Kim Kuntae [kr], Jang Cheolhun [kr])
Abstract: An electronic device is provided. The electronic device may comprise: a memory for storing instructions; and at least one processor comprising a processing circuit. The instructions, when executed individually or collectively by the at least one processor, may cause the electronic device to: identify first probability data obtained by applying input data to a first trained model usable for natural language processing; identify a first score according to a value in the first probability data; ide[...]
Our summary: The electronic device trains a language model using input data and probability scores. It identifies scores from two trained models and applies weights to enhance training. The process improves the second model s performance based on the first model s outputs.
language model, electronic device, natural language processing, training method
Patent
Attention-guided transformer architecture for fine-grained style representation in design systems
Published on 2026-05-01 by @OXFORD
Abstract: AbstractInterior design style recognition presents a challenging computational problem due to fine-grained inter-style similarities, complex spatial arrangements, and strong variability in materials, lighting, and layout. From a computational design and engineering perspective, accurately modelling such stylistic variations is essential not only for classification, but also for enabling semantic representation, retrieval, and analysis of design cases within data-driven design systems. However, e[...]
Our summary: This study introduces InDes, a curated dataset for interior design style recognition with 3826 images across five styles. It presents AT3, an attention-guided transformer architecture that enhances feature extraction and global context modeling. The proposed method achieves significant performance improvements in classification accuracy and supports downstream design-oriented tasks.
Attention-guided, transformer architecture, interior design, style recognition
Publication
Signatures of broken symmetries in the excitations of a periodic 2DEG coupled to a cylindrical photon cavity
Published on 2026-04-02 by Vidar Gudmundsson, Vram Mughnetsyan, Hsi-Sheng Goan, Jeng-Da Chai, Nzar Rauf Abdullah, Chi-Shung Tang, Wen-Hsuan Kuan, Valeriu Moldoveanu and Andrei Manolescu @IOP SCIENCE
Abstract: In a two-dimensional electron gas in a periodic lateral superlattice subjected to an external homogeneous magnetic field and in a cylindrical far-infrared photon cavity we search for effects of broken symmetries: Static ones, stemming from the unit cell of the system, and the external magnetic field together with the dynamic ones caused by the vector potential of the cavity promoting magnetic types of transitions, and the chirality of the excitation pulse. The Coulomb interaction of the electron[...]
Our summary: The study investigates broken symmetries in a periodic two-dimensional electron gas (2DEG) coupled to a cylindrical photon cavity. It employs density functional theory and configuration interaction to analyze static and dynamic effects of external magnetic fields and electron-photon interactions. Weak chiral effects are observed, revealing a connection between para- and diamagnetic interactions influenced by the system s symmetry.
2DEG, broken symmetry, electron-photon interaction, density functional theory
Publication
