ADOBE had five patents in future of work during Q4 2023. ADOBE Inc filed patents in Q4 2023 for systems and methods for coreference resolution, co-editing management, and music enhancement. The coreference resolution system inserts speaker tags into transcripts to identify speakers, extracts entity mentions, and generates coreference information. The co-editing management method detects modification operations on sequential data structures, generates tree structures, and sends updates to a co-editing server. The music enhancement system processes input mel spectrograms of musical instrument recordings using machine learning models to generate enhanced mel spectrograms and acoustic waveforms without artifacts. GlobalData’s report on ADOBE gives a 360-degreee view of the company including its patenting strategy. Buy the report here.

ADOBE grant share with future of work as a theme is 40% in Q4 2023. Grant share is based on the ratio of number of grants to total number of patents.

Recent Patents

Application: Systems and methods for coreference resolution (Patent ID: US20230403175A1)

The patent filed by ADOBE Inc. describes systems and methods for coreference resolution, focusing on inserting speaker tags into transcripts to indicate the corresponding speaker, encoding candidate spans, extracting entity mentions, and generating coreference information. The method involves utilizing machine learning models with encoder, mention extractor, and mention linker networks to process the transcript data and identify coreferences between entity mentions. Various techniques such as span length identification, token encoding, attention vector generation, mention scoring, and span vector combination are employed to enhance the coreference resolution process.

Additionally, the patent outlines a method for training the machine learning model using training data comprising text, mention annotation data, and coreference annotation data. The training process involves updating parameters of the mention extractor network based on entity mentions and mention annotation data in the first phase, followed by updating the mention linker network using coreference information and coreference annotation data in the second phase. The apparatus for coreference resolution includes the machine learning model with encoder, mention extractor, and mention linker networks, along with a preprocessing component for inserting speaker tags and a training component for parameter updates, showcasing a comprehensive approach to improving coreference resolution in textual data.

To know more about GlobalData’s detailed insights on ADOBE, buy the report here.

Premium Insights

From

The gold standard of business intelligence.

Blending expert knowledge with cutting-edge technology, GlobalData’s unrivalled proprietary data will enable you to decode what’s happening in your market. You can make better informed decisions and gain a future-proof advantage over your competitors.

GlobalData

GlobalData, the leading provider of industry intelligence, provided the underlying data, research, and analysis used to produce this article.

GlobalData Patent Analytics tracks bibliographic data, legal events data, point in time patent ownerships, and backward and forward citations from global patenting offices. Textual analysis and official patent classifications are used to group patents into key thematic areas and link them to specific companies across the world’s largest industries.