公开(公告)号：US20240233223A1

公开(公告)日：2024-07-11

申请号：US18339263

申请日：2023-06-22

申请人： INTERNATIONAL BUSINESS MACHINES CORPORATION

发明人： Nikolaos Livathinos ,  Maksym Lysak ,  Ahmed Samy Nassar ,  Peter Willem Jan Staar

IPC分类号： G06T11/60 ,  G06F40/174 ,  G06F40/177 ,  G06F40/186 ,  G06F40/205 ,  G06F40/284 ,  G06V10/774 ,  G06V30/412

CPC分类号： G06T11/60 ,  G06F40/174 ,  G06F40/177 ,  G06F40/186 ,  G06F40/205 ,  G06F40/284 ,  G06V10/774 ,  G06V30/412

摘要： The present disclosure relates to a method for automatically generating table images. The method includes determining a table configuration including a number of rows of the table, a number of columns of the table and a spanning area of the table, the spanning area indicating a fraction of spanning cells in the table. The table may be generated in accordance with the table configuration. Content may be inserted into cells of the table using a selected content template. An image table of an appearance of the table may be created and the image table may be provided.

公开(公告)号：US20240232505A1

公开(公告)日：2024-07-11

申请号：US18615813

申请日：2024-03-25

申请人： Google LLC

发明人： Alexander James Faaborg ,  Brett Barros

IPC分类号： G06F40/106 ,  G06F3/01 ,  G06F18/21 ,  G06F18/214 ,  G06F40/30 ,  G06V30/10 ,  G06V30/412 ,  G10L13/02

CPC分类号： G06F40/106 ,  G06F3/013 ,  G06F18/214 ,  G06F18/217 ,  G06F40/30 ,  G06V30/412 ,  G10L13/02 ,  G06V30/10

摘要： Gaze data collected from eye gaze tracking performed while training text was read may be used to train at least one layout interpretation model. In this way, the at least one layout interpretation model may be trained to determine current text that includes words arranged according to a layout, process the current text with the at least one layout interpretation model to determine the layout, and output the current text with the words arranged according to the layout.

公开(公告)号：US12032605B2

公开(公告)日：2024-07-09

申请号：US18054787

申请日：2022-11-11

申请人： SparkCognition, Inc.

发明人： William McNeill

IPC分类号： G06F16/31 ,  G06F40/117 ,  G06F40/137 ,  G06F40/284 ,  G06F40/30 ,  G06V30/412 ,  G06V30/414

CPC分类号： G06F16/316 ,  G06F40/117 ,  G06F40/137 ,  G06F40/284 ,  G06F40/30 ,  G06V30/412 ,  G06V30/414

摘要： A method includes obtaining, at a device, a hierarchical structure representing a graphical layout of content items of an electronic document, the content items including at least text. The method also includes generating a word embedding representing a word of the electronic document. The method further includes determining position information of a location of the word in the electronic document. The method also includes determining a descriptor that indicates a relationship of the location to the hierarchical structure. The method further includes providing input data to a machine learning model to generate a semantic region category label of a semantic region of the electronic document. The semantic region includes the word. The input data includes the word embedding, the position information, and the descriptor.

公开(公告)号：US20240220468A1

公开(公告)日：2024-07-04

申请号：US18605550

申请日：2024-03-14

申请人： nference, Inc.

发明人： Ashim Prasad ,  Melwin Babu ,  Dibakar Saha

IPC分类号： G06F16/22 ,  G06F16/21 ,  G06F16/28 ,  G06F18/214 ,  G06N3/08 ,  G06V10/22 ,  G06V10/82 ,  G06V30/19 ,  G06V30/412

CPC分类号： G06F16/221 ,  G06F16/21 ,  G06F16/2282 ,  G06F16/287 ,  G06F18/214 ,  G06N3/08 ,  G06V10/235 ,  G06V10/82 ,  G06V30/19173 ,  G06V30/412

摘要： An apparatus and method for populating a structured database based on an image representation of a data table, wherein the apparatus includes a processor and a memory containing instructions configuring the processor to receive an image representation having pixel data representing a data table, extract a plurality of content objects comprising at least a graphical sequence object from the data table as a function of the pixel data, wherein extracting the plurality of content objects includes identifying a content object location for each content object using a neural network model and identifying a plurality of cell locations based on the content object locations, extract sequence information associated with the at least a graphical sequence object, and populate a structured database with the plurality of content objects as a function of the sequence information and the plurality of cell locations.

公开(公告)号：US12025627B2

公开(公告)日：2024-07-02

申请号：US17372550

申请日：2021-07-12

申请人： FUJIFILM CORPORATION

发明人： Kazuhiro Hirota ,  Yoshihiro Seto ,  Takeya Meguro ,  Kaku Irisawa ,  Hirotaka Watano ,  Taiji Iwasaki ,  Tatsuyuki Denawa ,  Haruyasu Nakatsugawa

IPC分类号： G01N35/00 ,  G06V20/00 ,  G06V20/62 ,  G06V30/412

CPC分类号： G01N35/00732 ,  G01N35/0092 ,  G06V20/00 ,  G06V20/62 ,  G06V30/412 ,  G01N2035/00831

摘要： A management system including at least one processor, wherein the processor is configured to acquire a captured image obtained by imaging an outer surface of each of plural sample containers which contains a sample and in which discrimination information for discriminating a subject from whom the sample is collected is given to the outer surface, and associate a test result related to the sample contained in each of the sample containers with a test order in which information of a discrimination image including the discrimination information is registered in advance for each subject, based on the captured image and the test order.

公开(公告)号：US20240203149A1

公开(公告)日：2024-06-20

申请号：US18590472

申请日：2024-02-28

申请人： Informed, Inc.

发明人： Jatin Agrawal ,  Ashwin Kannan ,  Harshil Prajapati ,  Bharath Rengarajan ,  Eric Harvey ,  Emma Wei

IPC分类号： G06V30/416 ,  G06F40/226 ,  G06F40/289 ,  G06F40/30 ,  G06V30/10 ,  G06V30/412 ,  G06V30/414

CPC分类号： G06V30/416 ,  G06F40/226 ,  G06F40/289 ,  G06F40/30 ,  G06V30/412 ,  G06V30/414 ,  G06V30/10

摘要： A system and method for domain aware document classification and information extraction from consumer documents are disclosed. A particular embodiment is configured to: establish, by use of a data processor and a data network, a data connection with at least one applicant platform; receive an upload of documents from the applicant platform via the data network; classify each document as being of a particular document type; determine an information extraction strategy based on a document type classification of a particular document; and extract information from the particular document based on the information extraction strategy.

公开(公告)号：US12002276B2

公开(公告)日：2024-06-04

申请号：US17208223

申请日：2021-03-22

申请人： Bill.com, LLC

发明人： Xin Geng Kelly ,  Sangammohan Harimohan Singh ,  Derek Chan ,  Eitan Anzenberg

IPC分类号： G06K9/00 ,  G06F16/93 ,  G06N3/049 ,  G06N20/00 ,  G06V30/412 ,  G06V30/416 ,  G06Q30/04

CPC分类号： G06V30/416 ,  G06F16/93 ,  G06N3/049 ,  G06N20/00 ,  G06V30/412 ,  G06Q30/04

摘要： The accuracy of existing machine learning models, software technologies, and computers are improved by estimating whether a particular page belongs to a same document as another page or whether the page belongs to a different document. Such document distinguishing can be based on deriving relationship information between a first feature vector representing the page and a second feature vector representing the other page. This also improves the user experience and model building experience, among other things.

公开(公告)号：US11989693B2

公开(公告)日：2024-05-21

申请号：US17043360

申请日：2019-03-26

申请人： NEC CORPORATION

发明人： Yuichi Nakatani ,  Katsuhiko Kondoh ,  Satoshi Segawa ,  Michiru Sugimoto ,  Yasushi Hidaka ,  Junya Akiyama

IPC分类号： G06Q10/10 ,  G06N20/00 ,  G06V10/10 ,  G06V30/412 ,  G06V30/414 ,  G06V30/416

CPC分类号： G06Q10/10 ,  G06N20/00 ,  G06V10/10 ,  G06V30/412 ,  G06V30/414 ,  G06V30/416

摘要： An image-processing device includes: an acquisition unit configured to acquire form image data generated as an optical reading result of a form image; a group-specifying unit configured to determine whether kinds of groups into which the form image data is grouped are specifiable; and a work target determination unit configured to determine that the form image data is the form image data on which checking work for the kinds of groups is required when the kinds of groups of the form image data are determined to be unspecifiable.

公开(公告)号：US20240160616A1

公开(公告)日：2024-05-16

申请号：US18415062

申请日：2024-01-17

申请人： Coupa Software Incorporated

发明人： Hongyang Yu ,  Hanieh Borhanazad ,  Sandip Mandlecha

IPC分类号： G06F16/22 ,  G06F16/93 ,  G06F18/213 ,  G06N3/045 ,  G06V30/412 ,  G06V30/414

CPC分类号： G06F16/2282 ,  G06F16/93 ,  G06F18/213 ,  G06N3/045 ,  G06V30/412 ,  G06V30/414

摘要： Embodiments of the disclosed technologies provide solutions for automatically reading digital electronic documents that contain tables and correctly extracting table data, rows and columns from the documents with high accuracy and high throughput. Embodiments are capable of converting a table portion of a read-only document to a searchable, editable data record using text rectangle (TR)-level numerical data that indicates probabilities of TRs belonging to canonicals and at least one convolutional neural network (CNN) that processes the TR-level numerical data to produce table-level numerical data.

公开(公告)号：US11972627B2

公开(公告)日：2024-04-30

申请号：US17552542

申请日：2021-12-16

申请人： Accenture Global Solutions Limited

发明人： Loganathan Muthu ,  Rahul Kotnala ,  Srinivasan Krishnan Rajagopalan ,  Peter Ashly Gopalan ,  Manikandan Chandran ,  Anand Yesuraj Prakash ,  Simantini Deb ,  Vijay Dhandapani ,  Harbhajan Singh ,  RBSanthosh Kumar ,  Lokesh Venkatappa ,  Ramakrishnan Raman

IPC分类号： G06V30/414 ,  G06V30/19 ,  G06V30/412 ,  G06V30/413 ,  G06V30/416

CPC分类号： G06V30/414 ,  G06V30/19107 ,  G06V30/19147 ,  G06V30/412 ,  G06V30/413 ,  G06V30/416

摘要： A system and method for automating and improving data extraction from a variety of document types, including both unstructured, structured, and nested content, is disclosed. The system and method incorporate an intelligent machine learning model that is designed to intelligently identify chunks of text, map the fields in the document, and extract multi-record values. The system is designed to operate with little to no human intervention, while offering significant gains in accuracy, data visualization, and efficiency. The architecture applies customized techniques including density-based adaptive text clustering, tabular data extraction based on hierarchical intelligent keyword searches, and natural language processing-based field value selection.