This is our latest selection of worldwide publications and patents in english on Natural Language Processing (NLP), between many scientific online journals, classified and focused on natural language processing, tokenization, stemming, lemmatization, part-of-speech, named entity recognition and sentiment analysis.
Assessing Collaborative Brainstorming Tasks in Virtual Reality and Desktop Environments
Published on 2026-07-02 by @MIT
Abstract: AbstractCollaboration builds the collective development of new ideas, perspectives, and ways of working. By engaging in shared collaborative tasks, teams can strengthen professional relationships and improve creative outcomes. Since the COVID-19 pandemic, the adoption of digital tools for remote collaboration has grown rapidly, with desktop-based applications now widely used to manage teams, conduct workshops, and support ideation. In parallel, advances in virtual reality (VR) technology and the[...]
Our summary: This study evaluates collaborative brainstorming in VR and desktop environments. Results indicate comparable idea generation and communication levels between both platforms. However, VR users reported higher perceived task effort, suggesting increased workload.
Collaboration, Virtual Reality, Desktop Environments, Brainstorming
Publication
Mobile application and web experience for data collection and logbook creation
Patent published on the 2026-07-02 in US under Ref US20260187161 by JEFF BLOOD FLY FISHING LLC [US] (Blood Jeffrey L [us])
Abstract: [0000] A mobile device receives voice input from a user during a fishing event. The mobile device processes the voice input using natural language processing and natural language understanding to identify trigger words. The mobile device performs actions based on the trigger words. The mobile device may drop a virtual pin on a map to mark a location. The mobile device retrieves data from the internet related to the fishing event. The mobile device may log data points, including GPS coordinates, [...]
Our summary: A mobile device uses voice input to log fishing events through natural language processing. It marks locations on a map and logs various data points related to the fishing activity. The compiled data is stored in an electronic logbook and managed via cloud storage.
Natural Language Processing, Data Collection, Mobile Application, Cloud Storage
Patent
Ai based vendor and customer agnostic framework to improve integration of legacy systems
Patent published on the 2026-07-01 in EP under Ref EP4769174 by INGRAM MICRO INC [US] (Sahoo Sanjib [us])
Abstract: [0001] Systems and methods provide for integrating legacy systems into a unified platform. Embodiments include a system configured to ingest, normalize, and store data from multiple sources using a data layer, analyze and transform data using AI algorithms by a processing layer, and provide a dynamic user interface for data visualization and interaction by a presentation layer. Methods are provided for receiving, by a computing device, data such as email orders, vendor catalogs, CRM data, etc., [...]
Our summary: The framework integrates legacy systems into a unified platform. It utilizes AI algorithms for data analysis and transformation. The system supports real-time insights and manages data workflows effectively.
Integration, Legacy Systems, AI Algorithms, Data Normalization
Patent
Artificial intelligence assisted method for measuring and quantifying physical effort, cognitive effort, and sentiment while performing a task
Patent published on the 2026-06-18 in US under Ref US20260170426 by HARRIS CHRISTOPHER JOHN [US] (Harris Christopher John [us])
Abstract: An AI-assisted method and system for comprehensively measuring and quantifying physical effort, cognitive effort, and sentiment during task performance. The invention utilizes multi-modal video analysis, including screen capture, audio, and webcam recordings, to detect and measure various effort metrics. Unique aspects include the fusion of physical and cognitive effort measurements, sentiment analysis, and the ability to compare task performance across different approaches or platforms. The sys[...]
Our summary: The system measures physical and cognitive effort along with sentiment during task performance. It employs multi-modal video analysis, including screen capture and audio. The method generates detailed reports to optimize user experiences and workflows.
AI-assisted measurement, multi-modal analysis, effort quantification, sentiment analysis
Patent
Data processing device, data processing method, and data processing program
Patent published on the 2026-06-18 in WO under Ref WO2026126305 by NTT INC [JP] (Morikawa Akira [jp])
Abstract: This data processing device: inputs, to a natural language processing model, an instruction to assign, to respective data items in a data group that are candidates for training data of a machine learning model, labels indicating evaluation results for the data items, and an instruction to refer to data related to the data items in the data group when assigning the labels to the data items, thereby causing the natural language processing model to assign, to the data items, the labels indicating t[...]
Our summary: This device inputs instructions to a natural language processing model for labeling training data items. It calculates the certainty of these labels based on predictive probabilities. Finally, it filters and adds data items with high certainty labels to the training data for the machine learning model.
data processing device, natural language processing, machine learning, label assignment
Patent
Systems and methods for identifying intents based on call or chat transcripts
Patent published on the 2026-06-18 in US under Ref US20260170253 by VERIZON PATENT AND LICENSING INC [US] (Jayakrishnasamy Miruna [in], Reddy Nareddy Abhinay Kumar [in], Ranganathan Prakash [in], Singh Dheeraj [in])
Abstract: [0000] A device may receive transcripts associated with calls or chats, and may filter customer utterances from the transcripts. The device may predict intents for the customer utterances, and may filter the intents to generate a set of intents. The device may generate features from the customer utterances and the set of intents using a natural language processing technique, and may assign respective weights to the filtered set of intents based on a comparison between the features and the custom[...]
Our summary: The device analyzes call or chat transcripts to filter and predict customer intents. It generates features from utterances and ranks intents based on assigned weights. Actions are performed based on identified primary and secondary intents and their reasons.
intent recognition, natural language processing, customer interaction, feature extraction
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
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











