公开(公告)号：US20240362792A1

公开(公告)日：2024-10-31

申请号：US18342612

申请日：2023-06-27

申请人： Base64.ai, Inc.

发明人： Ozan Eren Bilgen ,  Alperen Sahin ,  Begum Yalcin ,  Can Korkut ,  Ihsan Soydemir

IPC分类号： G06T7/136 ,  G06F40/103 ,  G06T7/12

CPC分类号： G06T7/136 ,  G06F40/103 ,  G06T7/12 ,  G06T2207/20081 ,  G06T2207/20132 ,  G06T2207/30176

摘要： Systems and methods of the inventive subject matter are directed to artificial intelligence systems that are configured to receive an uploaded file from a user, where that upload contains images of one or more documents. Documents can be, e.g., receipts, identification cards, and so on. Once received, the system converts the image to a tensor to facilitate identifying mask images. The AI system then converts any identified mask images to grayscale before converting the image to black and white. White spaces are identified, and contours are identified that surround the white spaces. Next, white spaces with areas below a threshold size are discarded and white spaces with areas above that threshold have their contours stored. The AI system finds a minimum bounding rectangle for each contour and then crops the image around each white space accordingly. In this way, documents can be found within an image file and segmented to later processing.

公开(公告)号：US20240362397A1

公开(公告)日：2024-10-31

申请号：US18655781

申请日：2024-05-06

申请人： iCIMS, Inc.

发明人： Eoin O'GORMAN ,  Adrian MIHAI

IPC分类号： G06F40/103 ,  G06F18/21 ,  G06F18/214 ,  G06F40/169 ,  G06F40/197 ,  G06N20/00 ,  G06Q10/1053 ,  G06V30/414

CPC分类号： G06F40/103 ,  G06F18/214 ,  G06F18/217 ,  G06F40/169 ,  G06F40/197 ,  G06N20/00 ,  G06Q10/1053 ,  G06V30/414 ,  G06V2201/13

摘要： In some embodiments, a method can include generating a resume document image having a standardized format, based on a resume document having a set of paragraphs. The method can further include executing a statistical model to generate an annotated resume document image from the resume document image. The annotated resume document image can indicate a bounding box and a paragraph type, for a paragraph from a set of paragraphs of the annotated resume document image. The method can further include identifying a block of text in the resume document corresponding to the paragraph of the annotated resume document image. The method can further include extracting the block of text from the resume document and associating the paragraph type to the block of text.

公开(公告)号：US12131667B2

公开(公告)日：2024-10-29

申请号：US17523842

申请日：2021-11-10

申请人： Pencil Learning Technologies, Inc.

发明人： Amogh Asgekar ,  Ayush Agarwal

IPC分类号： G06F40/103 ,  G09B5/12 ,  G09B7/02 ,  H04L67/04

CPC分类号： G09B5/12 ,  G06F40/103 ,  G09B7/02 ,  H04L67/04

摘要： The present disclosure provides systems and methods for generating deeply integrated presentation gadgets. A system can maintain a plurality of application interfaces each having one or more data fields for presenting content. The system can maintain an information resource having data objects. Each of the data objects can have a content attribute. The system can extract each data object from the information resource based on the respective content attribute. The system can generate a presentation data structure having fields for the information resource based on the extracted data objects. The system can select an application interface for presentation with the information resource. The application interface can populate the one or more data fields of the application interface. The system can present the application interface with the information resource at a client device based on the one or more data fields of the application interface.

公开(公告)号：US20240346458A1

公开(公告)日：2024-10-17

申请号：US18633049

申请日：2024-04-11

申请人： Tyco Fire & Security GmbH

发明人： Julie J. Brown ,  Young M. Lee ,  Rajiv Ramanasankaran ,  Sastry KM Malladi ,  Michael Tenbrock ,  Levent Tinaz ,  Samuel A. Girard ,  David S. Elario ,  Juliet A. Pagliaro Herman ,  Miguel Galvez ,  Trent M. Swanson ,  John F. Kuchler ,  Deepak Budhiraja ,  Daniela M. Natali ,  Josip Lazarevski ,  Scott Deering ,  Gary W. Gavin ,  Kristen Sheppard-Guzelaydin ,  James Young ,  Prashanthi Sudhakar ,  Kaleb Luedtke ,  Karl F. Reichenberger ,  Wenwen Zhao ,  Adam R. Grabowski ,  Lauren C. Dern ,  Nicole A. Madison ,  Dana S. Petersen ,  Nevin L. Forry ,  Pedriant Pena ,  Ghassan R. Hamoudeh ,  Ryan G. Danielson

IPC分类号： G06Q10/20 ,  G06F40/103

CPC分类号： G06Q10/20 ,  G06F40/103

摘要： A method includes receiving, by one or more processors, an unstructured service report corresponding to a service request handled by one or more technicians for servicing building equipment. The unstructured service report may include unstructured data not conforming to a predetermined format or conforming to a plurality of different predetermined formats. The method may include extracting, by the one or more processors, a set of standards from one or more technical documents associated with the building equipment. The method may include automatically generating, by the one or more processors using a generative AI model, a structured service report in the predetermined format for delivery to a customer associated with the building equipment. Generating the structured service report may include standardizing the structured service report to comply with the set of standards extracted from the one or more technical documents associated with the building equipment.

公开(公告)号：US20240346228A1

公开(公告)日：2024-10-17

申请号：US18753645

申请日：2024-06-25

申请人： IpLContent, LLC

发明人： Chi Fai Ho ,  Peter P. Tong

IPC分类号： G06F40/106 ,  G06F15/02 ,  G06F40/103 ,  G06F40/114 ,  G06F40/169

CPC分类号： G06F40/106 ,  G06F15/0291 ,  G06F40/103 ,  G06F40/114 ,  G06F40/169

摘要： One embodiment includes an apparatus, with materials having a text sub file with texts, an illustration sub file with illustrations, and a logic sub file with instructions for presenting at least a part of the materials. One embodiment includes materials with a logic sub file that can analyze an attribute of, and provide a response to, a user. Another embodiment is applicable to apparatus and methods using a limited voice recognition dictionary at least tailored for a piece of materials that includes illustrations. The piece of materials includes instructions. The another embodiment can also use a limited image dictionary. The apparatus can include a headset, and the illustrations can include a piece of audio. The apparatus can be implemented in a vehicle.

公开(公告)号：US12118686B2

公开(公告)日：2024-10-15

申请号：US18464203

申请日：2023-09-09

申请人： Sana Rezgui

发明人： Sana Rezgui

IPC分类号： G06F30/20 ,  G06F30/347 ,  G06F30/39 ,  G06F40/103 ,  G06F40/137 ,  G06T19/00 ,  G06F111/18

CPC分类号： G06T19/006 ,  G06F30/20 ,  G06F30/347 ,  G06F30/39 ,  G06F40/103 ,  G06F40/137 ,  G06F2111/18

摘要： An integrated platform is provided that enables the various steps of development operations from design to sales, the virtualization, the visualization and the interpretation of a device so it may be fully created (designed), viewed, manipulated, packaged, simulated, tested, published and marketed right from within the platform. The resulting virtual device (VD) may be a multi-layered, -dimensional, -angular, -disciplinary, -documentarian, -service, manipulated and used in multiple ways. The provided VD may include visual representations of the VD via a traditional display device in a non-immersive environment and/or within an immersive environment via new virtual-reality (VR) devices. For instance, a user may create, manipulate, in real-time, layered multi-dimensional views of a VD in a virtual-reality, augmented-reality (AR), augmented virtual-reality (AVR), and/or mixed-reality (MR) environments.

公开(公告)号：US20240321412A1

公开(公告)日：2024-09-26

申请号：US18124638

申请日：2023-03-22

申请人： INTERNATIONAL BUSINESS MACHINES CORPORATION

发明人： Nikolaos Livathinos ,  Maksym Lysak ,  Ahmed Samy Nassar ,  Peter Willem Jan Staar ,  Valery Weber ,  Gerhard Ingmar Meijer

IPC分类号： G16C20/80 ,  G06F40/103 ,  G06F40/143 ,  G06F40/186

CPC分类号： G16C20/80 ,  G06F40/103 ,  G06F40/143 ,  G06F40/186

摘要： The invention is notably directed to a computer-implemented method to generate a synthetic data set. The synthetic data set comprises a plurality of chemical documents and each of the plurality of chemical documents comprises a respective set of chemical objects. The method comprises a step of receiving configuration data, the configuration data comprising a set of configuration parameters for the data set. The method further comprises performing, in an iterative manner, for each of the plurality of chemical documents the steps of generating, by a structure generation module, a respective document structure for each of the respective chemical documents in accordance with the configuration data, generating, by a content generation module, the respective set of chemical objects for the respective chemical document and arranging the respective set of chemical objects on the respective chemical document.

公开(公告)号：US20240320769A1

公开(公告)日：2024-09-26

申请号：US18731233

申请日：2024-06-01

申请人： Biometrica Systems, Inc.

发明人： Wyly Wade

IPC分类号： G06Q50/18 ,  G06F16/338 ,  G06F16/583 ,  G06F40/103 ,  G06F40/174

CPC分类号： G06Q50/18 ,  G06F16/338 ,  G06F16/583 ,  G06F40/103 ,  G06F40/174

摘要： A system, method, and computer program product for generating Freedom of Information Act (FOIA) requests, including a law enforcement server and database that store, retrieve, and transmit digital information relating to an individual; a FOIA request server and database that receives the digital information from the law enforcement server and automatically generates a FOIA request; and a FOIA request processing server and database that processes the FOIA request, automatically analyzes the received digital information, determines if it includes at least a predetermined percentage of relevant information fields, stores it in the FOIA request database if the percentage is met, triggers automatic pre-population of the FOIA request, and requests missing information if the percentage is not met, and transmits the pre-populated FOIA request for processing.

公开(公告)号：US20240311554A1

公开(公告)日：2024-09-19

申请号：US18183027

申请日：2023-03-13

申请人： Capital One Services, LLC

发明人： Jeremy GOODSITT ,  Galen RAFFERTY ,  Samuel SHARPE ,  Grant EDEN ,  Austin WALTERS

IPC分类号： G06F40/18 ,  G06F16/22 ,  G06F16/25 ,  G06F40/103 ,  G06F40/151

CPC分类号： G06F40/18 ,  G06F16/2282 ,  G06F16/258 ,  G06F40/103 ,  G06F40/151

摘要： In some implementations, a data processing device may receive, from a data source, a set of delimiter-separated values and may divide the set of delimiter-separated values into a plurality of subsets. Each subset may correspond to at least a portion of a column or correspond to at least a portion of a row. The data processing device may generate a plurality of vectors, corresponding to the plurality of subsets, according to an embedding space. The data processing device may compare the plurality of vectors to each other and may select a row or a column of the set of delimiter-separated values as one or more headers based on comparing the plurality of vectors to each other. Accordingly, the data processing device may output a tabular data structure including the one or more headers distinguished from a remainder of the set of delimiter-separated values.

公开(公告)号：US20240296276A1

公开(公告)日：2024-09-05

申请号：US18117314

申请日：2023-03-03

申请人： Microsoft Technology Licensing, LLC

发明人： Poonam Ganesh HATTANGADY ,  Adam Douglas TROY ,  Michael Ivan BORYSENKO ,  Susan Marie GRIMSHAW ,  Caleb WHITMORE

IPC分类号： G06F40/166 ,  G06F3/0484 ,  G06F40/103 ,  G06F40/279 ,  G06F40/58 ,  G06N3/0475 ,  G06N3/09

CPC分类号： G06F40/166 ,  G06F3/0484 ,  G06F40/103 ,  G06F40/279 ,  G06F40/58 ,  G06N3/0475 ,  G06N3/09

摘要： Systems and methods for using a generative artificial intelligence (AI) model to generate a suggested draft reply to a selected message. A message generation system and method are described that optimize input that is provided to the AI model so that it provides the most relevant information. In some examples, input prompts to the AI model are limited in size and latency can be impacted based on the size of the input provided to the AI model. Thus, the method and system identify, include, and format relevant information in an input prompt. The prompt reduces latency by the generative AI model in processing the prompt and may also lead to more relevant results produced by the generative AI model.