公开(公告)号：US11869260B1

公开(公告)日：2024-01-09

申请号：US18092164

申请日：2022-12-30

申请人： Kargo Technologies Corporation

发明人： Bingyan Liu ,  Pengxiang Hu ,  Maxwell C. Goldberg ,  Taylor Harwin

IPC分类号： G06V30/18 ,  G06V30/19 ,  G06V30/12 ,  G06V20/62 ,  G06V30/412 ,  G06V30/10 ,  G06K7/14

CPC分类号： G06V30/18019 ,  G06V20/63 ,  G06V30/10 ,  G06V30/12 ,  G06V30/19013 ,  G06V30/1916 ,  G06V30/19093 ,  G06V30/412 ,  G06K7/1413

摘要： A series of steps may be performed to automatically extract structured data from an image. First, anchor points may be extracted from the image, representing areas of the image that potentially contain information of interest. The arrangement of anchor points may be used to identify a template. A transform may be generated, to facilitate mapping between particular points in the selected template and corresponding points in the image. The transform may then be used to automatically read visual information from the image and extract structured data from the visual information.

公开(公告)号：US11868717B2

公开(公告)日：2024-01-09

申请号：US17940777

申请日：2022-09-08

申请人： Open Text Corporation

发明人： Ming Fung Ho

IPC分类号： G06F40/226 ,  G06F40/174 ,  G06V30/413 ,  G06V30/416 ,  G06V30/10

CPC分类号： G06F40/226 ,  G06F40/174 ,  G06V30/413 ,  G06V30/416 ,  G06V30/10

摘要： Techniques to capture document data are disclosed. It is determined that a sequence of pages in a stream of document page images comprise a single multi-page document. Data is extracted from two or more different pages included in the sequence. The data extracted from two or more different pages included in the sequence of pages is used to populate a data entry form associated with the multi-page document.

公开(公告)号：US11861496B2

公开(公告)日：2024-01-02

申请号：US17247283

申请日：2020-12-07

申请人： AVEVA Software, LLC

发明人： Tim Sowell ,  Colm McCarthy

IPC分类号： G06N20/00 ,  G06V30/422 ,  G06N3/08 ,  G06F18/214 ,  G06V10/82 ,  G06V30/10 ,  G06V30/18

CPC分类号： G06N3/08 ,  G06F18/214 ,  G06N20/00 ,  G06V10/82 ,  G06V30/422 ,  G06V30/10 ,  G06V30/18029

摘要： A system that includes artificial intelligence (AI) configured to identify text and images within an industrial reference. Example industrial references include electrical drawings and P&IDs. The system includes a method for training artificial intelligence model to recognize text characters and strings in addition to industrial images using a limited sample set. The use of a limited sample set improves computer performance by relying on a smaller dataset to train the model.

公开(公告)号：US11861253B2

公开(公告)日：2024-01-02

申请号：US18114223

申请日：2023-02-25

申请人： SHARP KABUSHIKI KAISHA

发明人： Tatsuya Fujisaki

IPC分类号： G06F3/12 ,  G06V30/10

CPC分类号： G06F3/1255 ,  G06F3/1205 ,  G06F3/1238 ,  G06F3/1279 ,  G06V30/10

摘要： According to an embodiment, an image processing apparatus includes: a character recognition processor which reads an image of a document and extracts text information in the document; a setting manager which manages settings including a setting to allow or prohibit a function of character recognition; a job controller which controls job execution related to reading of the document; and an operation controller which provides a setting menu to receive a setting of at least one item related to the job execution and receives a setting, in which when the function of the character recognition is set to be prohibited, the operation controller hides a function that requires the character recognition from the setting menu or indicates that the function is not to be set, and when the function that requires the character recognition has already been set, the operation controller enables the function to be replaced by another function.

公开(公告)号：US20230421602A1

公开(公告)日：2023-12-28

申请号：US18219552

申请日：2023-07-07

申请人： Darktrace Holdings Limited

发明人： John Anthony Boyer ,  Matthew Dunn

IPC分类号： H04L9/40 ,  G06N20/10 ,  G06N20/00 ,  G06F21/36 ,  H04L43/045 ,  G06F16/2455 ,  G06F3/04842 ,  G06F3/0486 ,  H04L41/22 ,  G06F40/40 ,  H04L51/42 ,  H04L51/212 ,  G06F21/55 ,  G06F18/23 ,  G06F18/232 ,  G06V30/10 ,  H04L51/224

CPC分类号： H04L63/1441 ,  G06N20/10 ,  H04L63/1425 ,  G06N20/00 ,  H04L63/1416 ,  H04L63/20 ,  H04L63/14 ,  G06F21/36 ,  H04L43/045 ,  H04L63/101 ,  G06F16/2455 ,  G06F3/04842 ,  G06F3/0486 ,  H04L41/22 ,  H04L63/0209 ,  H04L63/0428 ,  H04L63/1433 ,  G06F40/40 ,  H04L63/1483 ,  H04L51/42 ,  H04L51/212 ,  G06F21/554 ,  G06F21/556 ,  G06F18/23 ,  G06F18/232 ,  G06V30/10 ,  H04L51/224 ,  G06N20/20

摘要： The cyber security appliance can have at least the following components. A phishing site detector that has a segmentation module to break up an image of a page of a site under analysis into multiple segments and then analyze each segment of the image to determine visually whether a key text-like feature exists in that segment. A signature creator creates a digital signature for each segment containing a particular key text-like feature. The digital signature for that segment is indicative of a visual appearance of the particular key text-like feature. Trained AI models compare digital signatures from a set of key text-like features detected in the image of that page under analysis to digital signatures of a set of key text-like features from known bad phishing sites in order to output a likelihood of maliciousness of the unknown site under analysis.

公开(公告)号：US11854246B2

公开(公告)日：2023-12-26

申请号：US17201733

申请日：2021-03-15

申请人： BEIJING BAIDU NETCOM SCIENCE AND TECHNOLOGY CO., LTD.

发明人： Yulin Li ,  Ju Huang ,  Xiameng Qin ,  Junyu Han

IPC分类号： G06N3/08 ,  G06V30/413 ,  G06V30/414 ,  G06N3/047 ,  G06V10/82 ,  G06V30/18 ,  G06V30/19 ,  G06V30/412 ,  G06V30/16 ,  G06V30/10

CPC分类号： G06V10/82 ,  G06N3/047 ,  G06N3/08 ,  G06V30/18057 ,  G06V30/19173 ,  G06V30/412 ,  G06V30/413 ,  G06V30/414 ,  G06V30/10 ,  G06V30/1607

摘要： A method, apparatus, device and storage medium for recognizing a bill image may include: performing text detection on a bill image, and determining an attribute information set and a relationship information set of each text box of at least two text boxes in the bill image; determining a type of the text box and an associated text box that has a structural relationship with the text box based on the attribute information set and the relationship information set of the text box; and extracting structured bill data of the bill image, based on the type of the text box and the associated text box that has the structural relationship with the text box.

公开(公告)号：US11853684B2

公开(公告)日：2023-12-26

申请号：US18068955

申请日：2022-12-20

申请人： Palantir Technologies Inc.

发明人： Suchan Lee ,  Jon Paek

IPC分类号： G06F3/0482 ,  G06F40/117 ,  G06F9/451 ,  G06F16/51 ,  G06F16/583 ,  G06F16/93 ,  G06F40/109 ,  G06F40/134 ,  G06V10/40 ,  G06V30/10

CPC分类号： G06F40/117 ,  G06F9/451 ,  G06F16/51 ,  G06F16/5846 ,  G06F16/93 ,  G06F40/109 ,  G06F40/134 ,  G06V10/40 ,  G06V30/10

摘要： A computing system accesses an image-based document and a text document having text extracted from the image-based document and provides a user interface displaying at least a portion of the image-based document. In response to selection of a text portion of the image-based document, the system determines an occurrence of the text portion within at least a portion of the image-based document and then applies a search model on the text document to identify the same occurrence of the text portion. Once matched, alignment data indicating a relationship between a selected tag and both the text portion of the image-based document and the text portion of the text document is stored.

公开(公告)号：US11853406B2

公开(公告)日：2023-12-26

申请号：US18055293

申请日：2022-11-14

申请人： Capital One Services, LLC

发明人： Abdelkader M'Hamed Benkreira ,  Joshua Edwards ,  Michael Mossoba

IPC分类号： G06K9/00 ,  G06F21/32 ,  G06V40/16 ,  G06V30/413 ,  G06V30/416 ,  G06V40/40 ,  G06V30/14 ,  G06V30/148 ,  G06V20/62 ,  G06V30/10

CPC分类号： G06F21/32 ,  G06V20/62 ,  G06V30/1444 ,  G06V30/153 ,  G06V30/413 ,  G06V30/416 ,  G06V40/168 ,  G06V40/172 ,  G06V40/40 ,  G06V40/45 ,  G06V30/10

摘要： A system receives an image including a live facial image of the user and an identity document including a photograph of the user. Moreover, the system calculates a facial match score by comparing facial features in the live facial image to facial features in the photograph. The system recognizes data objects and characters in the identity document using optical character recognition (OCR) and computer vision, and then identifies, based on the recognized data objects and characters, a type of the identity document. Further, the system calculates a document validity score by comparing the recognized characters and data objects to character strings and data objects known to be present in the identified type of the identity document. Additionally, the system determines and outputs the user's identity verification status based on comparing the facial match score to a facial match threshold and comparing the document validity score to a document validity threshold.

公开(公告)号：US20230410541A1

公开(公告)日：2023-12-21

申请号：US17843991

申请日：2022-06-18

申请人： KYOCERA Document Solutions Inc.

发明人： Yury Ageev

IPC分类号： G06V30/10 ,  G06F16/36 ,  G06V30/413

CPC分类号： G06V30/10 ,  G06F16/36 ,  G06V30/413

摘要： Systems and methods relate generally to performing a machine learning task on training documents to generate an output. In an example method, a pretrained Sentence Bidirectional Encoder Representational Transformers (“S-BERT”) model is obtained. The training documents are scanned by a plurality of scanners. Content of the training documents is recognized with character recognition. The content is templated responsive to the character recognition. The content is processed with the pretrained S-BERT model for training thereof. A trained S-BERT model is generated from the processing of the content as the output. The trained S-BERT model is configured to automatically categorize and assemble non-training documents into original configurations thereof.

公开(公告)号：US11849240B2

公开(公告)日：2023-12-19

申请号：US17958763

申请日：2022-10-03

申请人： Insight Direct USA, Inc.

发明人： Amol Ajgaonkar

IPC分类号： G11B27/031 ,  G06V30/10 ,  G06V20/40 ,  H04N5/262

CPC分类号： H04N5/2628 ,  G06V20/40 ,  G06V30/10 ,  G11B27/031

摘要： A method of processing first video data of a region of interest from incoming video data includes preprocessing, according to preprocessing parameters defined within a runtime configuration file, incoming video data to create the first video data of the first region of interest and processing, by a computer processor, the first video data to determine at least one output that is indicative of a first inference dependent upon the first video data. The preprocessing parameters that format incoming video data to create the first video data are dependent upon the processing to be performed on the first video data.