-
公开(公告)号：WO2022197459A1
公开(公告)日：2022-09-22
申请号：PCT/US2022/018816
申请日：2022-03-04
Applicant: MICROSOFT TECHNOLOGY LICENSING, LLC
Inventor： COTTLE, Aaron D.
IPC: G06F40/171 , G06F3/04883 , G06V30/142 , G06V30/32
Abstract: Systems and methods for converting text to digital ink. One system includes a memory configured to store instructions and an electronic processor coupled to the memory. The electronic processor, through execution of the instructions stored in the memory, is configured to generate an image of text, trace characters within the generated image to establish a plurality of ink points and a plurality of digital strokes, generate a digital ink instance based on the plurality of ink points and the plurality of digital strokes, and provide the digital ink instance within a user interface.
-
公开(公告)号：WO2022180016A1
公开(公告)日：2022-09-01
申请号：PCT/EP2022/054350
申请日：2022-02-22
Applicant: MYSCRIPT
Inventor： PENIN, Thomas , BEDNAROWICZ, Romain
IPC: G06F3/04883 , G06F3/04842 , G06F3/04845 , G06V30/32
Abstract: A computing device and method for performing a modification on digital content of a document, comprising: a display interface configured to display the digital content as a handwritten input or a typeset input; an identification module (MD2) configured to interpret the digital content as one or more objects; a mode type selection module (MD6) configured to select a mode type, wherein said mode type is pixel-mode or object-mode; an input surface (104) configured to detect a modification gesture wherein one or more boundaries of the modification gesture are intersecting with at least part of the digital content; a selection module (MD8) configured to select, at least partially, the digital content according to the selected mode type, and a modification module (MD10) configured to modify at least the selected digital content.
-
公开(公告)号：WO2022125237A1
公开(公告)日：2022-06-16
申请号：PCT/US2021/058506
申请日：2021-11-09
Inventor： ELACHQAR, Oussama , YADAV, Badal , SOLOMON, Oz , DOROSHENKO, Sergey Aleksandrovich , MOHAJERIN, Nima
IPC: G06V30/18 , G06V30/19 , G06V30/32 , G06V30/413
Abstract: Technology is descried herein for parsing an ink document having a plurality of ink strokes. The technology performs stroke-level processing on the plurality of ink strokes to produce stroke-level information, the stroke-level information identifying at least one characteristic associated with each ink stroke. The technology also performs object-level processing on individual objects within the ink document to produce object-level information, the object-level information identifying one or more groupings of ink strokes in the ink document. The technology then parses the ink document into constituent parts based on the stroke-level information and the object-level information. In some implementations, the technology converts the ink stroke data into an ink image. The stroke-level processing and/or the object-level processing may operate on the ink image using one or more neural networks. More specifically the stroke-level processing can classify pixels in the input image, while the object-level processing can identify bounding boxes containing possible objects.
-
4.发明申请
公开(公告)号：WO2022259200A1
公开(公告)日：2022-12-15
申请号：PCT/IB2022/055378
申请日：2022-06-09
Applicant: JIO PLATFORMS LIMITED
Inventor： KRISHNASWAMY, Dilip , BHARDWAJ, Nitish , SRIVASTAVA, Shobhit
Abstract: This present disclosure allows a trusted entity to reach out to stakeholders to seek endorsements, validate the endorsements based on a policy, and also determine consensus associated with the data. It caches digital certificates, IP addresses of stakeholders, and caches policy associated with transactions to enable faster processing, and also performs concurrent processing using available processors to accomplish the tasks. By relying on a single trusted entity to do the work in a permissioned private blockchain setting, the processing costs can be reduced relative to distributed processing and replicated processing across multiple nodes in a blockchain system. The system also allows recursive utilization of the suggested system for transaction authorization and signed consensus processing (TASCP) across users followed by TASCP across nodes. The system may enable quantum-safe consensus processing for utilization in virtualized deployments, particularly for IoT transaction streams.
-
公开(公告)号：WO2022182169A1
公开(公告)日：2022-09-01
申请号：PCT/KR2022/002720
申请日：2022-02-24
Applicant: SAMSUNG ELECTRONICS CO., LTD.
Inventor： SAHU, Pragya Paramita , MITTAL, Paritosh , PANDOTRA, Himanshu , SINGH, Vikrant , AGGARWAL, Kunal , VEERA, Viswanath , VENKATESAN, Shankar M , SOUDAGAR, Afzal Shama , VATSALYA, Vishal
IPC: G06F3/04883 , G06N3/04 , G06V30/32
Abstract: The disclosure relates to a handwritten input-recognition method for an electronic-device. The method comprises: obtaining by the device, at least one first handwriting input representative of at least one object. A context of the at least one first handwriting input is determined based on referring a log of actions performed upon the device. Using a neural network, a positional significance of the at least one first handwriting input is analyzed in relation to the determined context. A description depicting location of the at least one object is generated based on the analyzed positional significance of the at least one first handwriting-input. A command in response to the generated scene description is generated to enable performance of an action, the command referring the location of the at least one object within the scene.
-
Patent Agency Ranking
公开(公告)号：WO2022103519A1
公开(公告)日：2022-05-19
申请号：PCT/US2021/053447
申请日：2021-10-05
Applicant: MICROSOFT TECHNOLOGY LICENSING, LLC
Inventor： CHEN, Tianyi , GANESAN, Gowtham , FANG, Biyi , YI, Sheng
Abstract: A data processing system for performing a semantic analysis of digital ink stroke data implements obtaining the digital ink stroke data representing handwritten text, drawings, or both; analyzing the digital ink stroke data to extract path signature feature information from the digital ink stroke data; analyzing the path signature feature information using a convolutional neural network (CNN) trained to perform a pixel-level sematic analysis of the digital ink stroke data and to output a pixel segmentation map with semantic prediction information for each pixel of digital ink stroke data; analyzing the pixel segmentation map to generate stroke-level semantic information using a pixel-to-stroke conversion model; and processing the digital ink stroke data based on the stroke-level semantic information.
-
公开(公告)号：WO2023086151A1
公开(公告)日：2023-05-19
申请号：PCT/US2022/042822
申请日：2022-09-08
Applicant: MICROSOFT TECHNOLOGY LICENSING, LLC.
Inventor： FANG, Biyi , YI, Sheng , CHEN, Tianyi
IPC: G06V30/226 , G06F3/04883 , G06V30/32
Abstract: Systems and methods for performing spatial line grouping on digital ink stokes. The system includes an electronic processor configured to access a set of hypothetical lines in an electronic document and determine a set of hypothetical line pairings. The electronic processor is also configured to determine, via a gradient boosting tree model, a merge confidence score for each hypothetical line pairing and compare a first merge confidence score with a merge threshold. The first merge confidence score is associated with a first hypothetical line and a first neighboring hypothetical line. The electronic processor is also configured to, in response to the first merge confidence score satisfying the merge threshold, merge the first hypothetical line and the first neighboring hypothetical line to form a first line grouping. The electronic processor is also configured to perform a digital ink stroke analysis on the electronic document based on the first line grouping.
-
公开(公告)号：WO2022197442A1
公开(公告)日：2022-09-22
申请号：PCT/US2022/018410
申请日：2022-03-02
Applicant: MICROSOFT TECHNOLOGY LICENSING, LLC
Inventor： COTTLE, Aaron D.
IPC: G06V30/32
Abstract: Systems and methods for providing answers to digitally inked questions within an electronic document. One system includes an electronic processor configured to receive detected interactions between a touchscreen and a digital pen representing one or more digital strokes within a canvas and determine whether the one or more digital strokes match a predetermined signifier. The electronic processor is also configured to, in response to determining that the one or more digital strokes match the predetermined signifier, determine a digital ink instance included in the canvas based on a position of the one or more digital strokes within the canvas, extract text from the digital ink instance, submit the extracted text to an answer service as a query, receive a text-based answer to the query from the answer service, convert the text-based answer to digital ink, and add the digital ink to the canvas.
-
公开(公告)号：WO2022169123A1
公开(公告)日：2022-08-11
申请号：PCT/KR2022/000402
申请日：2022-01-10
Applicant: 주식회사 네오랩컨버전스
IPC: G06V30/32 , G06V30/146 , G06T3/60
Abstract: 필기 데이터를 수신하고, 수신된 필기 데이터의 회전 각도를 추출하고, 추출된 회전 각도에 기초하여 수신된 필기 데이터를 회전하여, 회전된 필기 데이터를 문자 인식하는 필기 데이터 문자 인식 방법 및 그 장치가 개시되어 있다.
-
公开(公告)号：WO2022094036A1
公开(公告)日：2022-05-05
申请号：PCT/US2021/056992
申请日：2021-10-28
Applicant: ANCESTRY.COM OPERATIONS INC.
Inventor： LEE, Jinsol , VENI, Gopalkrishna Balkrishna , FUJIMOTO, Masaki Stanley , YU, Yen-yun
Abstract: Systems and methods for handwriting recognition using language modeling facilitate improved results by using a trained language model (276) to improve results from a handwriting recognition machine learning model (204). The language model (276) may be a character-based language model trained on a dataset pertinent to field values on which the handwriting recognition model (204) is to be used. A loss prediction module (256) may be trained with the handwriting recognition model (204) and/or the language model (276) and used to determine whether a prediction (210) from the handwriting recognition model (204) should be refined by passing the prediction (210) through the trained language model (276).
-
-
-
-
-
-
-
-
-
Search Results
16
records
(took 0.015 seconds)
