Context Analysis Or Word Recognition (e.g., Character String) Patents (Class 382/229)
  • Patent number: 11068738
    Abstract: Detection of typed and/or pasted text, caret tracking, and active element detection for a computing system are disclosed. The location on the screen associated with a computing system where the user has been typing or pasting text, potentially including hot keys or other keys that do not cause visible characters to appear, can be identified and the physical position on the screen where typing or pasting occurred can be provided based on the current resolution of where one or more characters appeared, where the cursor was blinking, or both. This can be done by identifying locations on the screen where changes occurred and performing text recognition and/or caret detection on these locations. The physical position of the typing or pasting activity allows determination of an active or focused element in an application displayed on the screen.
    Type: Grant
    Filed: May 4, 2020
    Date of Patent: July 20, 2021
    Assignee: UiPath, Inc.
    Inventor: Vaclav Skarda
  • Patent number: 11061355
    Abstract: An image forming apparatus includes a receiving part that receives multiple page images including a first page image and a second page image, a medium carrying part that carries the recording media, and an image forming part that forms images on the recording media carried by the medium carrying part based on the first and second page images processed by the image processing part. The image processing part determines one edge region of the first page image, which has the highest image density among four edge regions on the first page image, changes the orientation of the first page image such that the one edge region having the highest image density is arranged to be at the trailing side of the first page image, and changes the orientation of the second page image to the same orientation as that of the first page image.
    Type: Grant
    Filed: July 18, 2019
    Date of Patent: July 13, 2021
    Assignee: Oki Data Corporation
    Inventor: Shuichi Suzuki
  • Patent number: 11057621
    Abstract: An image encoding method, decoding method and corresponding device, and intraframe pixel prediction method.
    Type: Grant
    Filed: August 5, 2019
    Date of Patent: July 6, 2021
    Assignee: Tsinghua University
    Inventors: Pin Tao, Lixin Feng, Zheng Wang
  • Patent number: 11042571
    Abstract: Methods and systems for maximizing data utility efficiency to maximize dynamic application of content in a database as applied to a validation are disclosed herein. A system for maximizing data utility efficiency to maximize dynamic application of content in a database as applied to a validation can include a memory having a first database containing information identifying a plurality of topics and a second database containing a plurality of content items. The system can further include a server that can maximize data utility efficiency by identifying multipurpose content items.
    Type: Grant
    Filed: November 9, 2018
    Date of Patent: June 22, 2021
    Assignee: PEARSON EDUCATION, INC.
    Inventors: Yun Jin Rho, Yueh-Mei Chien, Heijung Kim, Ruth Czarnecki-Lichstein, Alicia L. Anderson
  • Patent number: 11030447
    Abstract: Disclosed is an approach of on-device partial recognition that includes performing partial recognition on an image of a document captured by a mobile device to detect and/or recognize a specific area (e.g., barcodes, non-relevant text, etc.) and filling the recognized area with a solid color. Because the solid color area has a maximum compression ratio, this approach can lead to image size reduction and increased network throughput for client-server based data recognition where further processing such as advanced data extraction is performed at the server side. The approach can be enforced with neural network algorithms to exclude non-relevant information (e.g., logos, phrases, words, etc.).
    Type: Grant
    Filed: August 24, 2020
    Date of Patent: June 8, 2021
    Assignee: OPEN TEXT CORPORATION
    Inventors: Mikhail Yurievitch Zakharov, Kirill Vaniukov, Christopher Dale Lund
  • Patent number: 10990814
    Abstract: A system for converting an image of an unstructured table into a structured table is provided. The system may comprise a memory storing machine readable instructions. The system may include a processor to receive an image of a unstructured table and convert the image of the unstructured table into a structured table. Converting the image of the unstructured table into the structured table may include providing cell mapping and low confidence determination to highlight potentially misconverted content. The low confidence determination may be based on a first input and a second input. The processor may export the structured table, upon validation, to an application that supports structured tables.
    Type: Grant
    Filed: December 27, 2018
    Date of Patent: April 27, 2021
    Assignee: MICROSOFT TECHNOLOGY LICENSING, LLC
    Inventors: Gopalakrishnan Venkateswaran, Tumu Sree Bharath, Jeet Mukeshkumar Patel, Ajit Kumar Singh, Milos Lazarevic, Dhiresh Kumar Nagwani, Abhas Sinha, Ivan Vujic, Naresh Jain, Sanjay Krupakar Bhat, Aleksandar Sretenovic, Tamara Paunovic, Aljosa Obuljen, Sasa Vuckovic, Dusan Lukic, Catherine William Neylan, Marko Rakita
  • Patent number: 10984277
    Abstract: An image analysis apparatus includes an extraction section, an acquisition section, an exclusion section, and a recognition section. The extraction section extracts, from a target image, a text area including a character. The acquisition section acquires a predetermined target-object condition. The predetermined target-object condition defines a target object. The exclusion section searches for the target object in the text area and excludes the target object from a target of character recognition. The text area is extracted by the extraction section. The target object satisfies the predetermined target-object condition. The recognition section performs character recognition on the text area. The text area is an area from which the target object is excluded.
    Type: Grant
    Filed: March 6, 2018
    Date of Patent: April 20, 2021
    Assignee: FUJI XEROX CO., LTD.
    Inventor: Daisuke Tatsumi
  • Patent number: 10970483
    Abstract: An information processing apparatus includes a first extraction part that extracts a value corresponding to a first item, which is an item indicative of a deadline, from a result of character recognition with respect to an image acquired by reading a document which includes an item and a value corresponding to the item; a generation part that generates a second character string of a date format indicative of a date of the deadline based on the result of the character recognition in a case where the value extracted by the first extraction part is a first character string other than the date format; and an output part that outputs the generated second character string as the value corresponding to the first item.
    Type: Grant
    Filed: August 1, 2019
    Date of Patent: April 6, 2021
    Assignee: FUJI XEROX CO., LTD.
    Inventors: Junichi Shimizu, Kunihiko Kobayashi, Daigo Horie
  • Patent number: 10956402
    Abstract: A method for automatically detecting errors in at least one data entry in a database, the at least one data entry including an input string of characters that do not match at least one predefined string of characters. The method includes generating a first image map; generating at least one classification parameter by comparing the first image map to a second image map, the second image map based at least partially on the predefined string of characters; determining that the input string of characters correlates to the predefined string of characters; and modifying the at least one data entry to match the predefined string of characters in response to determining that the input string of characters correlates to the predefined string of characters. Various other methods and systems for automatically detecting errors in at least one data entry in a database are also disclosed.
    Type: Grant
    Filed: April 13, 2018
    Date of Patent: March 23, 2021
    Assignee: Visa International Service Association
    Inventor: Hima Patel
  • Patent number: 10958976
    Abstract: A method is described for selecting and displaying, on or through a television signal receiver apparatus capable of connecting to Internet and of pointing to URL's, television programs transmitted through an Internet network, said method comprises the step of associating at least one URL, or Uniform Resource Locator, corresponding to streaming audio/video of a specific television program, with the same television program of an EPG, or Electronic Program Guide, received by said apparatus via television broadcast, and wherein said association requires that said URL be stored into a memory-type processing circuit of the apparatus to create a link between said specific television program received through said Internet network and the same specific television program of said EPG received by said television receiver apparatus via television broadcast.
    Type: Grant
    Filed: February 25, 2013
    Date of Patent: March 23, 2021
    Assignee: Saronikos Trading and Services, Unipessoal LDA
    Inventor: Ruiz Rodriguez Ezequiel
  • Patent number: 10929657
    Abstract: An apparatus of the invention determines whether or not new scanned image data is similar to past scanned image data based on character string areas and a table area extracted from the new scanned image data, specifies a character string area used to obtain information set to the past scanned image data determined to be similar, detects a target area as a processing target out of the character string areas extracted from the new scanned image data based on the specified character string area, the table included in the past scanned image data determined to be similar, and the table included in the new scanned image data, performs character recognition processing on the detected target area, and sets information to the new scanned image data by using a character obtained as a result of the character recognition processing.
    Type: Grant
    Filed: January 15, 2019
    Date of Patent: February 23, 2021
    Assignee: Canon Kabushiki Kaisha
    Inventor: Yoshitaka Matsumoto
  • Patent number: 10929666
    Abstract: The present document describes a system and method for providing augmented reality interactions with printed media, whereby a user looking at a printed media (physical or electronic) with their portable computing device may view augmented reality interactions on their portable device to enrich the media being viewed. The method includes recognizing pages and using interaction capabilities offered atop the page once recognized. The system is also configured to perform an image recognition process which allows for a very quick detection of a preregistered image from the database which matches the image of the page viewed by the user in order to extract the assets associated with the prestored image and send them to the portable device for display.
    Type: Grant
    Filed: September 12, 2016
    Date of Patent: February 23, 2021
    Inventors: Christophe Bossut, Guy Le Hénaff, Yves Chapelain De La Villeguerin
  • Patent number: 10917587
    Abstract: Implementations generally relate to importing data and presenting the data in a user interface (UI). In some implementations, a method includes capturing an image of an object using a camera, where the object includes text. The method further includes recognizing the text. The method further includes generating a data structure that includes the text. The method further includes generating a graphical image that represents at least a portion of the text. The method further includes displaying the graphical image in a UI in a display screen of a client device.
    Type: Grant
    Filed: August 31, 2017
    Date of Patent: February 9, 2021
    Assignee: Oracle International Corporation
    Inventors: Reginald Hansbrough, Sergio Acosta, Victor Medina, Lakshmi Dontamsetti
  • Patent number: 10902183
    Abstract: A computer-implemented method of tagging a text, comprises: determining a value for each of a plurality of locations in a first vector; processing (402), by a trained first neural network component, the first vector to generate a second vector; processing (404), at a trained second neural network component, the second vector to generate a probability score for each of at least ten predetermined tags; determining (406) if each probability score meets a criterion; if the criterion is met, assigning (408) the tag corresponding to the probability score to the text. Each of the locations may correspond to a respective predetermined word, each value relating to existence and/or frequency of the corresponding word in the text, and the number of locations may be between 600 and 20000. The number of locations in the second vector may be fewer than the number of locations in the first vector and is from 100 to 5000.
    Type: Grant
    Filed: January 17, 2018
    Date of Patent: January 26, 2021
    Assignee: DIGITAL GENIUS LIMITED
    Inventors: Bohdan Maksak, Conan McMurtrie, Jose Marcos Rodriguez Fernandez, Mahyar Bordbar, Yoram Bachrach
  • Patent number: 10891474
    Abstract: Techniques for providing improved optical character recognition (OCR) for receipts are discussed herein. Some embodiments may provide for a system including one or more servers configured to perform receipt image cleanup, logo identification, and text extraction. The image cleanup may include transforming image data of the receipt by using image parameters values that optimize the logo identification, and performing logo identification using a comparison of the image data with training logos associated with merchants. When a merchant is identified, a second image clean up may be performed by using image parameter values optimized for text extraction. A receipt structure may be used to categorize the extracted text. Improved OCR accuracy is also achieved by applying on format rules of the receipt structure to the extracted text.
    Type: Grant
    Filed: January 22, 2019
    Date of Patent: January 12, 2021
    Assignee: GROUPON, INC.
    Inventors: Stephen Clark Mitchell, Pavel Melnichuk
  • Patent number: 10887576
    Abstract: A method for reducing the parameters defining an acquired light field ray which enables only the colour associated with the light field ray to be stored instead of 4 light field co-ordinates (x,y,i,j) and its associated colour.
    Type: Grant
    Filed: September 16, 2016
    Date of Patent: January 5, 2021
    Assignee: INTERDIGITAL VC HOLDINGS, INC.
    Inventors: Valter Drazic, Guillaume Boisson, Mozhdeh Seifi
  • Patent number: 10878088
    Abstract: Examples relate to identifying randomly generated character strings. In one example, a computing device may: receive a character string that includes two or more characters; identify a number of character transitions included in the character string, each character transition being a change in character type within an n-gram of the character string, where n is a positive integer; and determine, based on the number of character transitions, whether the character string was randomly generated.
    Type: Grant
    Filed: February 7, 2018
    Date of Patent: December 29, 2020
    Assignee: Trend Micro Incorporated
    Inventors: Richard Andrew Lawshae, Josiah Dede Hagen, Mathew Robert Powell, Elvis Collado, Jonathan Edward Andersson, Stephen David Povolny
  • Patent number: 10878173
    Abstract: In some embodiments, a computing system computes tags for an electronic document. The computing system identifies sets of objects for the electronic document by applying a set of object-recognition rules to the electronic document, with each object-recognition rule generating a set of identified objects. The computing system generates feature maps that represent a set of identified objects. The computing system generates a heat map that identifies attributes of the electronic document including object candidates of the electronic document by applying a page-segmentation machine-learning model to the electronic document. The computing system computes a tag by applying a fusion deep learning module to the feature map and the heat map to correlate a document object identified by the feature map with an attribute of the electronic document identified by the heat map. The computing system generates the tagged electronic document by applying the tag to the electronic document.
    Type: Grant
    Filed: November 29, 2018
    Date of Patent: December 29, 2020
    Assignee: Adobe Inc.
    Inventors: Vlad Morariu, Rajiv Jain, Nishant Sankaran
  • Patent number: 10862833
    Abstract: A message processing method and an electronic device for supporting the same are provided. The electronic device includes a communication interface configured to receive a message including a plurality of pages, and a control module configured to process the received message, wherein, if undefined data exists among data contained in a specific page of the plurality of pages, the control module combines at least a part of data contained in a next page that is sequential to the specific page with the undefined data.
    Type: Grant
    Filed: June 19, 2019
    Date of Patent: December 8, 2020
    Assignee: Samsung Electronics Co., Ltd.
    Inventors: Kyu Hyun Kim, Min O Kim, In Soo Kim, Jun Ho You, Sang Min Bae
  • Patent number: 10861068
    Abstract: Methods and systems to supplement search results returned to a buyer of parts are described. The system receives a first query from a buyer. The first query includes keywords. The system identifies at least one compatibility keyword included in the keywords. The system further infers that the other keywords in the query are item information that describes a part that is sought for on a network-based marketplace. The system further infers the part has a compatibility based on the compatibility keywords. Next, the system searches a data storage device based on the item information and the compatibility keywords to identify a first listing as matched. Finally, the system presents the first listing describing the matched part. The matched part is indicated as compatible by supplementing the presentation of the first listing with the compatibility keywords from the first query.
    Type: Grant
    Filed: June 13, 2018
    Date of Patent: December 8, 2020
    Assignee: eBay Inc.
    Inventors: Adam Bursey, Jennifer M. Dante, Brian M. Johnson
  • Patent number: 10846482
    Abstract: A document processing system is configured to identify, for each accessed electronic document in a first set of multiple electronic documents, a set of identified multi-word phrases determined to be in ordered text information in the accessed electronic document, each multi-word phrase of the set of identified multi-word phrases including adjacent words in the ordered text information; and determine, for each accessed electronic document in the first set of multiple electronic documents, a selected document type from the first set of document types based at least on an analysis of the set of identified multi-word phrases with respect to multi-word-phrase characteristics identified by a first definition and associated with each document type in a first set of document types associated with a first document-set type.
    Type: Grant
    Filed: September 19, 2019
    Date of Patent: November 24, 2020
    Assignee: CLOUDDOCS.COM, LLC
    Inventor: John Frank Walsh
  • Patent number: 10814661
    Abstract: A system and a method for verifying authenticity of a physical copy and a digital copy of a document are disclosed. The method comprises registering a document in a repository by storing details related to the document in a location of the repository. A symbology for the document is generated. The symbology is an identifier of the location of the repository comprising the document. The symbology is associated with either a physical or a digital copy of the document. The digital copy of the document is printed to generate a printed copy. The printed copy or the physical copy of the document is scanned to generate a scanned image. The document and the details related to the document present at the location of the repository are accessed. The scanned image is compared with the document stored in the repository to determine the authenticity of either the physical copy or the digital copy of the document.
    Type: Grant
    Filed: December 6, 2017
    Date of Patent: October 27, 2020
    Inventor: Leigh M. Rothschild
  • Patent number: 10785188
    Abstract: Disclosed is a domain filter capable of determining an n-gram distance between a seed domain and each of a plurality of candidate domains. The domain filter loads a seed domain n-gram for the seed domain and a candidate domain n-gram for each candidate domain in memory, compares the seed domain n-gram and the candidate domain n-gram to identify any identical grams, removes any identical grams from the seed domain n-gram, and determines how many grams are left in the seed domain n-gram, representing the n-gram distance between the seed domain and the candidate domain. The domain filter then compares n-gram distances thus determined with a predetermined threshold, eliminates any candidate domain having an n-gram distance from the seed domain that exceeds the predetermined threshold, and provides remaining candidate domains to a downstream computing facility such as a user interface or an analytical module operating in an enterprise computing environment.
    Type: Grant
    Filed: May 22, 2018
    Date of Patent: September 22, 2020
    Assignee: Proofpoint, Inc.
    Inventors: Harold Nguyen, Ali Mesdaq, Kevin Dedon, Michael Fox, Gaurav Dalal
  • Patent number: 10755043
    Abstract: The present invention relates to a method for revising an error, wherein a user inputs a desired character string for revision so as to calculate a correlation between the desired character string for revision and previously inputted character strings, so that a character string with a high correlation is replaced with the desired character string for revision. A characteristic configuration of the present invention is in a step for deciding a correlation.
    Type: Grant
    Filed: November 28, 2013
    Date of Patent: August 25, 2020
    Assignee: NAVER Corporation
    Inventor: Min Chul Kim
  • Patent number: 10755090
    Abstract: Disclosed is an approach of on-device partial recognition that includes performing partial recognition on an image of a document captured by a mobile device to detect and/or recognize a specific area (e.g., barcodes, non-relevant text, etc.) and filling the recognized area with a solid color. Because the solid color area has a maximum compression ratio, this approach can lead to image size reduction and increased network throughput for client-server based data recognition where further processing such as advanced data extraction is performed at the server side. The approach can be enforced with neural network algorithms to exclude non-relevant information (e.g., logos, phrases, words, etc.).
    Type: Grant
    Filed: September 17, 2018
    Date of Patent: August 25, 2020
    Assignee: OPEN TEXT CORPORATION
    Inventors: Mikhail Yurievitch Zakharov, Kirill Vaniukov, Christopher Dale Lund
  • Patent number: 10749802
    Abstract: Embodiments include techniques for channeling elements in an analytics engine environment, techniques include analyzing a current process, and identifying critical data element types associated with the current process. The techniques also include receiving a real-time data stream including a plurality of data elements, and pre-filtering the plurality of data elements, wherein the pre-filtering determines one or more of the plurality of data elements are associated with the critical data element type. The technique includes selecting a channel of a plurality of channels to fast-path the one or more of the plurality of data elements based at least in part on the pre-filtering, and increasing a confidence level corresponding to the current process and the critical data element type based on a state of the current process.
    Type: Grant
    Filed: November 9, 2017
    Date of Patent: August 18, 2020
    Assignee: INTERNATIONAL BUSINESS MACHINES CORPORATION
    Inventors: Al Chakra, Alexandre A. Da Silva, Jeremy A. Greenberger, Li Li, Allison M. Moore
  • Patent number: 10747962
    Abstract: Based on a candidate set of translations produced by a neural network based machine learning model, a mapping data structure such as a statistical phrase table is generated. The mapping data structure is analyzed to obtain a quality metric of the neural network based model. One or more operations are initiated based on the quality metric.
    Type: Grant
    Filed: March 12, 2018
    Date of Patent: August 18, 2020
    Assignee: Amazon Technologies, Inc.
    Inventors: Hagen Fuerstenau, Felix Hieber
  • Patent number: 10740603
    Abstract: A structured data processing system includes hardware processors and a memory in communication with the hardware processors. The memory stores a data structure and an execution environment. The data structure includes an electronic document. The execution environment includes a data extraction solver configured to perform operations including identifying a particular page of the electronic document; performing an optical character recognition (OCR) on the page to determine a plurality of alphanumeric text strings on the page; determining a type of the page; determining a layout of the page; determining at least one table on the page based at least in part on the determined type of the page and the determined layout of the page; and extracting a plurality of data from the determined table on the page.
    Type: Grant
    Filed: March 22, 2018
    Date of Patent: August 11, 2020
    Assignee: Drilling Info, Inc.
    Inventors: Chris Randy Larsen Davis, Yenming Mark Lai
  • Patent number: 10740602
    Abstract: Systems and methods for assigning word fragments to lines of text in optical character recognition (OCR) extracted data can include at least one processor obtaining a plurality of word fragments from OCR generated data associated with an image. The at least one processor can determine vertical coordinates of each of the word fragments in the image. The at least one processor can cluster the plurality of word fragments into one or more clusters of word fragments based on the vertical coordinates of the plurality of word fragments. The at least one processor can assign each word fragment of a respective cluster to a corresponding text line based on the clustering.
    Type: Grant
    Filed: April 18, 2018
    Date of Patent: August 11, 2020
    Assignee: Google LLC
    Inventors: Ivan Ordonez, Swaminathan Krishnamurthy, David Paul, Tushar Udeshi, Aiyou Chen
  • Patent number: 10726250
    Abstract: A method for automatically selecting one of a plurality of recognition algorithms for a handwritten input of alphanumeric characters and/or gestures into a selected input field displayed on a screen using a touch-sensitive input apparatus comprises carrying out optical character recognition in a region of the screen which comprises at least the input field and the immediate environment of the input field, or carrying out voice recognition for a voice instruction acoustically output after the selected input field has been displayed. Terms describing field types are searched for in the result of the optical character recognition or the voice recognition, and a recognition algorithm which is adapted to a field type found in the result of the optical character recognition or the voice recognition is selected.
    Type: Grant
    Filed: October 28, 2016
    Date of Patent: July 28, 2020
    Assignee: Continental Automotive GmbH
    Inventor: Bernhard Schild
  • Patent number: 10728151
    Abstract: Embodiments include techniques for channeling elements in an analytics engine environment, techniques include analyzing a current process, and identifying critical data element types associated with the current process. The techniques also include receiving a real-time data stream including a plurality of data elements, and pre-filtering the plurality of data elements, wherein the pre-filtering determines one or more of the plurality of data elements are associated with the critical data element type. The technique includes selecting a channel of a plurality of channels to fast-path the one or more of the plurality of data elements based at least in part on the pre-filtering, and increasing a confidence level corresponding to the current process and the critical data element type based on a state of the current process.
    Type: Grant
    Filed: June 16, 2017
    Date of Patent: July 28, 2020
    Assignee: INTERNATIONAL BUSINESS MACHINES CORPORATION
    Inventors: Al Chakra, Alexandre A. Da Silva, Jeremy A. Greenberger, Li Li, Allison M. Moore
  • Patent number: 10679088
    Abstract: Disclosed is an effective domain name defense solution in which a domain name string may be provided to or obtained by a computer embodying a visual domain analyzer. The domain name string may be rendered or otherwise converted to an image. An optical character recognition function may be applied to the image to read out a text string which can then be compared with a protected domain name to determine whether the text string generated by the optical character recognition function from the image converted from the domain name string is similar to or matches the protected domain name. This visual domain analysis can be dynamically applied in an online process or proactively applied in an offline process to hundreds of millions of domain names.
    Type: Grant
    Filed: February 10, 2017
    Date of Patent: June 9, 2020
    Assignee: Proofpoint, Inc.
    Inventors: Gaurav Mitesh Dalal, Ali Mesdaq, Sharon Huffner, Harold Nguyen
  • Patent number: 10649608
    Abstract: A non-interactive screen sharing session executing within a computing device can be identified. The device can be communicatively linked to different computing devices of the screen sharing session. The contents of the remote screen buffer can be analyzed to determine a graphical representation of a Uniform Resource Locator (URL) within the contents prior to presenting the contents of the buffer within the device. A visible information item can be extracted and a non-visible reference can be established from the representation. An area surrounding the representation including a position and dimensions of the representation within the contents can be determined. The representation of the URL can be replaced with an interactive element in real-time. The element can include the visible and non-visible reference. The contents of the buffer can be presented within an interface associated with the session of the device, responsive to the replacing.
    Type: Grant
    Filed: September 26, 2017
    Date of Patent: May 12, 2020
    Assignee: International Business Machines Corporation
    Inventors: Quang T. Duong, David M. Gordon, David L. Schmidt, Scott A. Will
  • Patent number: 10635683
    Abstract: The present invention provides a search capability to allow a user to easily locate a preference control, file, folder, control, or other system resource or data item associated with a search result. In one embodiment, a user enters a search term (or a portion thereof) in a search field associated with one or more resource types that may be searched. The user may be presented with a pop-up menu containing a list of likely matches. The user selects the desired preference control from the pop-up menu, and the corresponding preference pane, or other container, containing the selected data item, control, or other resource is displayed. In one aspect, as the user enters the search term (or portion thereof), certain icons are highlighted. Specifically, those icons that represent containers containing matching data items (such as preference panes having controls that match the search term) are highlighted.
    Type: Grant
    Filed: May 22, 2017
    Date of Patent: April 28, 2020
    Assignee: APPLE INC.
    Inventors: Maxym I. Runov, Bas Ording, Steve Ko, Gregory N. Christie, Kevin Tiene
  • Patent number: 10621427
    Abstract: A search area is set on a recognition target image, cutout areas are set at a plurality of positions in the search area, images corresponding to the plurality of set cutout areas are extracted, similarities of candidate characters obtained by comparison between the extracted images and dictionary data is weighted in accordance with the positions of the cutout areas. In such a manner, evaluation values of the candidate characters are obtained, and a candidate character with the highest evaluation value among the obtained candidate characters is output as a recognition result. Further, a search area relating to a next character is set based on position information about the cutout area corresponding to the recognition result.
    Type: Grant
    Filed: November 27, 2017
    Date of Patent: April 14, 2020
    Assignee: Canon Kabushiki Kaisha
    Inventor: Mitsuo Kimura
  • Patent number: 10614109
    Abstract: As disclosed herein, a method for generating a natural language processing query includes receiving one or more documents, wherein each document comprises a set of words, processing the one or more documents and the sets of words to provide a document content matrix V, a word feature matrix W, and a document feature matrix H, forecasting values for each entry of the word feature matrix and the document feature matrix over a selected time interval and a selected set of domains to provide a forecasted word feature matrix W? and a forecasted document feature matrix H?, calculating a set of coefficients for forecasted document feature matrix H? such that V=W? *H?, determining a rank for each word of the sets of words according to the calculated set of coefficients, and generating one or more queries according to the determined ranks for each word of the set of words.
    Type: Grant
    Filed: March 29, 2017
    Date of Patent: April 7, 2020
    Assignee: International Business Machines Corporation
    Inventors: Aaron K. Baughman, Gary F. Diamanti, Mauro Marzorati
  • Patent number: 10592766
    Abstract: An image processing apparatus includes a controller configured to execute: acquiring objective image data representing an objective image which includes a first character and a second character; analyzing first partial image data and specifying the first character in an image represented by the first partial image data; and generating processed image data representing a processed image which includes the first character and the second character by using the objective image data. The objective image data includes the first partial image data in a bitmap format which represents the image including the first character and second partial image data in a vector format which represents an image including the second character. The processed image data includes: first processed data representing an image including the first character; and second processed data representing an image including the second character.
    Type: Grant
    Filed: February 24, 2017
    Date of Patent: March 17, 2020
    Assignee: BROTHER KOGYO KABUSHIKI KAISHA
    Inventor: Kazuhide Sawada
  • Patent number: 10579717
    Abstract: Computer-implemented systems and methods are provided for suggesting emoticons for insertion into text based on an analysis of sentiment in the text. An example method includes: determining a first sentiment of text in a text field; selecting first text from the text field in proximity to a current position of an input cursor in the text field; identifying one or more candidate emoticons wherein each candidate emoticon is associated with a respective score indicating relevance to the first text and the first sentiment based on, at least, historical user selections of emoticons for insertion in proximity to respective second text having a respective second sentiment; providing one or more candidate emoticons having respective highest scores for user selection; and receiving user selection of one or more of the provided emoticons and inserting the selected emoticons into the text field at the current position of the input cursor.
    Type: Grant
    Filed: April 25, 2019
    Date of Patent: March 3, 2020
    Assignee: MZ IP Holdings, LLC
    Inventors: Gabriel Leydon, Nikhil Bojja
  • Patent number: 10572780
    Abstract: A printing apparatus comprises: a processor configured to create print data for printing at least one printable character so as to arrange the printable character along a widthwise direction of the print medium based on input data input by a user; and a printhead configured to print on the print medium in accordance with the print data, wherein the processor compares an overall print length of overall data obtained by adding margins to a front end and a rear end of the printable character with a first length of an elongated print medium in the widthwise direction, and, the processor creates the print data including a mark indicating an end portion of the overall data when the overall print length is shorter than the first length.
    Type: Grant
    Filed: May 17, 2018
    Date of Patent: February 25, 2020
    Assignee: CASIO COMPUTER CO., LTD.
    Inventor: Naoki Ogawa
  • Patent number: 10565188
    Abstract: A method including the steps of: receiving a search query containing search terms from a user device; retrieving from one or more data storage devices, search configuration information in response to the received search query, wherein the search configuration information comprises a designated field set; generating a plurality of query partitions based on the received search query; generating one or more internal query clauses based on all possible combinations of sub-phrases of the plurality of query partitions and fields from the designated field set; executing a query on a database based on the one or more internal query clauses; generating query results based on the executed query; calculating match metrics for all query results; determining query results having match metrics that satisfy configured match constraints as legitimate matches; and detecting patterns based on corresponding matched terms and fields of the legitimate matches.
    Type: Grant
    Filed: May 30, 2014
    Date of Patent: February 18, 2020
    Assignee: MACY'S WEST STORES, INC.
    Inventors: Denis Kamotsky, Mariel Vargas
  • Patent number: 10552704
    Abstract: An image processing apparatus includes a controller configured to execute: acquiring objective image data representing an objective image which includes a first character and a second character; analyzing first partial image data and specifying the first character in an image represented by the first partial image data; and generating processed image data representing a processed image which includes the first character and the second character by using the objective image data. The objective image data includes the first partial image data in a bitmap format which represents the image including the first character and second partial image data in a vector format which represents an image including the second character. The processed image data includes: first processed data representing an image including the first character; and second processed data representing an image including the second character.
    Type: Grant
    Filed: February 24, 2017
    Date of Patent: February 4, 2020
    Assignee: BROTHER KOGYO KABUSHIKI KAISHA
    Inventor: Kazuhide Sawada
  • Patent number: 10521435
    Abstract: A method that includes generating, in a query pre-processor, a set of pre-computed materialized sub-graphs by executing a pre-processing dynamic random-walk based search for a bin of terms. The method also includes receiving, in a query processor, a search query having at least one search query term. In response to receiving the search query, the method includes accessing the set of pre-computed materialized sub-graphs. The accessing includes accessing a text index based on the search query term to retrieve a corresponding term group identifier and accessing the corresponding pre-computed materialized sub-graph based on the term group identifier. The method also includes executing a dynamic random-walk based search on only the corresponding pre-computed materialized sub-graph and based on the executing, retrieving nodes in the dataset and transmitting the nodes as results of the query.
    Type: Grant
    Filed: September 21, 2015
    Date of Patent: December 31, 2019
    Assignee: INTERNATIONAL BUSINESS MACHINES CORPORATION
    Inventors: Andrey Balmin, Heasoo Hwang, Erik Nijkamp, Berthold Reinwald
  • Patent number: 10515148
    Abstract: Disclosed is a data driven error model that is based on error patterns found at the morphemes level. A model is generated by error-correct patterns generator and is stored in an error-correct patterns database (ECPD). The ECPD is used in conjunction with a correction candidates' generator (CCG) to provide a list of correction candidates for a given error word. The error model can learn the types and forms of the language patterns from an annotated corpus. The error model can be used to analyze the type of error and can provide candidates corrections for wide ranges of Arabic spelling errors.
    Type: Grant
    Filed: February 8, 2018
    Date of Patent: December 24, 2019
    Assignee: King Fahd University of Petroleum and Minerals
    Inventors: Sabri A. Mahmoud, Wasfi G. Al-Khatib, Tamim Alnethary
  • Patent number: 10482109
    Abstract: One or more embodiments relate to an object indexing method, object indexing device and object indexing system. An object indexing method may include an initializing step of dividing at least one first data container and at least one second data container, and initializing respectively the first and the second data containers by using a first data indexer and a second data indexer; a first indexing step of adding the input feature vector of a specific object into a first data container currently being filled by using the first data indexer; and a second indexing step, when the data size in the first data container being filled has reached a threshold, selecting another first data container as the first data container currently being filled, and in the case of executing the first indexing step, converting bulk data in the first data container previously being filled into one available second data container.
    Type: Grant
    Filed: September 26, 2016
    Date of Patent: November 19, 2019
    Assignee: Canon Kabushiki Kaisha
    Inventors: Cheng Tan, Yaohai Huang, Rongjun Li, Sen Na, Hirotaka Shiiyama, Masahiro Matsushita
  • Patent number: 10474758
    Abstract: A machine translation method and a machine translation apparatus using a neural network model are provided. The machine translation apparatus extracts information associated with a keyword from a source sentence, obtains a supplement sentence associated with the source sentence based on the extracted information associated with the keyword, acquires a first vector value from the source sentence and a second vector value from the supplement sentence using neural network model-based encoders, and outputs a target sentence corresponding to a translation of the source sentence based on any one or any combination of the first vector value and the second vector value using a neural network model-based decoder.
    Type: Grant
    Filed: May 10, 2018
    Date of Patent: November 12, 2019
    Assignee: Samsung Electronics Co., Ltd.
    Inventors: Min-Joong Lee, YoungSang Choi
  • Patent number: 10460192
    Abstract: A method and system are provided for optical character recognition (OCR) of multi-language content. The method includes extracting a text portion from an image received from a user-computing device. The text portion comprises a plurality of keywords associated with a plurality of languages. The method further includes segmenting the plurality of keywords into a plurality of layers. Each layer of the plurality of layers comprises one or more keywords which are associated with a language. The method further comprise generating an OCR output of each of the plurality of layers based on the language associated with the one or more keywords in each of the plurality of layers. The method further comprises generating an electronic document of the received image based on the generated OCR output of each of the plurality of layers. The method further includes transmitting the generated electronic document to the user-computing device.
    Type: Grant
    Filed: October 21, 2016
    Date of Patent: October 29, 2019
    Assignee: XEROX Corporation
    Inventors: Sainarayanan Gopalakrishnan, Rajasekar Kanagasabai, Sudhagar Subbaian
  • Patent number: 10445359
    Abstract: A hardware and software facility for classifying media content units using keywords from a structured vocabulary. Metadata associated with each media content unit is segmented into a series of descriptive phrases. The descriptive phrases are mapped to keywords in a structured vocabulary, and the identified keywords associated with the media content units. Descriptive phrases that are not found in the structured vocabulary are tracked as candidate phrases for later addition to the structured vocabulary. A keyword index to the media content units may be constructed. The index is used to identify specific media content units that are responsive to search queries in a reliable and accurate fashion.
    Type: Grant
    Filed: June 7, 2006
    Date of Patent: October 15, 2019
    Assignee: Getty Images, Inc.
    Inventors: Anna Bjarnestam, Mary Forster, Nate Gandert, Steven F. Heck, Ziji Huang, Monika MacGuffie, Alvin Nance, Thomas M. O'Leary
  • Patent number: 10381045
    Abstract: A system for annotating frames in a media stream 114 includes a pattern recognition system (PRS) 108 to generate PRS output metadata for a frame; an archive 106 for storing ground truth metadata (GTM); a device to merge the GTM and PRS output metadata and thereby generate proposed annotation data (PAD) 110; and a user interface 109 for use by the human annotator HA 118. The user interface 104 includes an editor 111 and an input device 107 used by the HA 118 to approve GTM for the frame. An optimization system 105 receives the approved GTM and metadata output by the PRS 108, and adjusts input parameters for the PRS to minimize a distance metric corresponding to a difference between the GTM and PRS output metadata.
    Type: Grant
    Filed: July 24, 2018
    Date of Patent: August 13, 2019
    Assignee: LiveClips LLC
    Inventors: Eric David Petajan, David Eugene Weite, Douglas W. Vunic
  • Patent number: 10341292
    Abstract: Network session identification information is received. The network session identification information is associated with a destination IP address and a destination network port. An available source network port for a new session to be established for a source IP address is determined based on the destination IP address and the destination network port.
    Type: Grant
    Filed: October 23, 2018
    Date of Patent: July 2, 2019
    Assignee: Avi Networks
    Inventors: Sreeram Iyer, Kiron Haltore, Murali Basavaiah
  • Patent number: 10311139
    Abstract: Computer-implemented systems and methods are provided for suggesting emoticons for insertion into text based on an analysis of sentiment in the text. An example method includes: determining a first sentiment of text in a text field; selecting first text from the text field in proximity to a current position of an input cursor in the text field; identifying one or more candidate emoticons wherein each candidate emoticon is associated with a respective score indicating relevance to the first text and the first sentiment based on, at least, historical user selections of emoticons for insertion in proximity to respective second text having a respective second sentiment; providing one or more candidate emoticons having respective highest scores for user selection; and receiving user selection of one or more of the provided emoticons and inserting the selected emoticons into the text field at the current position of the input cursor.
    Type: Grant
    Filed: June 2, 2017
    Date of Patent: June 4, 2019
    Assignee: MZ IP Holdings, LLC
    Inventors: Gabriel Leydon, Nikhil Bojja