公开(公告)号：US11755848B1

公开(公告)日：2023-09-12

申请号：US16874385

申请日：2020-05-14

申请人： Wells Fargo Bank, N.A.

发明人： Arnab Dan

IPC分类号： G06F40/166 ,  G06F40/56 ,  G06N20/00 ,  G06F21/62 ,  G06F40/295 ,  G06F16/9032 ,  G06F40/30 ,  G06F18/214

CPC分类号： G06F40/56 ,  G06F16/90332 ,  G06F18/2155 ,  G06F21/6245 ,  G06F40/295 ,  G06F40/30 ,  G06N20/00

摘要： This disclosure describes techniques that include identifying sensitive information from any appropriate set of data, such as data produced by operations of a business or organization. In one example, this disclosure describes a method that includes receiving text data containing sensitive information, including structured sensitive information and unstructured sensitive information; applying a rule-based model to identify the structured sensitive information in the text data; applying a machine learning model to identify the unstructured sensitive information in the text data, wherein the machine learning model has been trained to identify unstructured sensitive information in text; and generating output text data from the text data by modifying the structured sensitive information identified by the rule-based model and the unstructured sensitive information identified by the machine learning model.

公开(公告)号：US11755651B2

公开(公告)日：2023-09-12

申请号：US17091868

申请日：2020-11-06

申请人： Agora Intelligence, Inc.

发明人： Kevin Hopkins ,  Jarom Smith

IPC分类号： G06F16/9032 ,  G06F16/9535 ,  G06F16/955 ,  G06F16/951 ,  G06F16/33

CPC分类号： G06F16/90328 ,  G06F16/3338 ,  G06F16/951 ,  G06F16/9535 ,  G06F16/9566

摘要： A method for generating categorical and criterion-based search results from a search query including receiving the search query, generating one or more query fragments, determining a category corresponding to the search query, determining one or more filters applicable to the search query and one or more core search terms applicable to the search query based at least in part on the determined category and the one or more query fragments, generating at least one custom query for at least one target database in the one or more target databases based at least in part on the one or more filters, the one or more core search terms, the determined category, and one or more attributes of the at least one target database, and executing the at least one custom query on the at least one target database to generate a set of search results.

公开(公告)号：US11748415B2

公开(公告)日：2023-09-05

申请号：US16687417

申请日：2019-11-18

申请人： Lenovo (Singapore) Pte. Ltd.

发明人： Russell Speight VanBlon ,  Roderick Echols ,  Ryan Charles Knudson ,  Bradley Park Strazisar

IPC分类号： G06F16/9032 ,  H04N21/422 ,  H04N21/41

CPC分类号： G06F16/90332 ,  H04N21/41265 ,  H04N21/42203 ,  H04N21/42222

摘要： One embodiment provides a method, including: receiving, at an information handling device comprising a digital assistant, a user command, wherein the digital assistant is providing a current output; determining whether an attribute of the current output should be modified, wherein the determining is based on a content type of the current output and a request type of the command; and providing a response to the user command; wherein the providing comprises modifying, responsive to determining that an attribute should be modified, an attribute of the current output during provision of the response, wherein the modification and the attribute to be modified are based on the content type and the request type; and wherein the providing comprises continuing the current output with no modification responsive to determining that an attribute should not be modified. Other aspects are described and claimed.

公开(公告)号：US20230273841A1

公开(公告)日：2023-08-31

申请号：US18312481

申请日：2023-05-04

申请人： CAPITAL ONE SERVICES, LLC

发明人： Austin WALTERS ,  Vincent PHAM ,  Kate KEY ,  Kenneth TAYLOR ,  Anh TRUONG ,  Fardin ABDI TAGHI ABAD ,  Jeremy GOODSITT

IPC分类号： G06F9/54 ,  G06N20/00 ,  G06F17/16 ,  G06N3/04 ,  G06F11/36 ,  G06N3/088 ,  G06F21/62 ,  G06N5/04 ,  G06F17/15 ,  G06T7/194 ,  G06T7/254 ,  G06T7/246 ,  G06F16/2455 ,  G06F16/22 ,  G06F16/28 ,  G06F16/906 ,  G06F16/93 ,  G06F16/903 ,  G06F16/9038 ,  G06F16/9032 ,  G06F16/25 ,  G06F16/335 ,  G06F16/242 ,  G06F16/248 ,  G06F30/20 ,  G06F40/166 ,  G06F40/117 ,  G06F40/20 ,  G06F8/71 ,  G06F17/18 ,  G06F21/55 ,  G06F21/60 ,  G06N7/00 ,  G06Q10/04 ,  G06T11/00 ,  H04L9/40 ,  H04L67/306 ,  H04L67/00 ,  H04N21/234 ,  H04N21/81 ,  G06N5/00 ,  G06N5/02 ,  G06V30/196 ,  G06F18/22 ,  G06F18/23 ,  G06F18/24 ,  G06F18/40 ,  G06F18/213 ,  G06F18/214 ,  G06F18/21 ,  G06F18/20 ,  G06F18/2115 ,  G06F18/2411 ,  G06F18/2415 ,  G06N3/044 ,  G06N3/045 ,  G06N7/01 ,  G06V30/194 ,  G06V10/98 ,  G06V10/70 ,  G06N3/08

CPC分类号： G06F9/541 ,  G06N20/00 ,  G06F17/16 ,  G06N3/04 ,  G06F11/3628 ,  G06N3/088 ,  G06F21/6254 ,  G06N5/04 ,  G06F17/15 ,  G06F21/6245 ,  G06T7/194 ,  G06T7/254 ,  G06T7/246 ,  G06T7/248 ,  G06F16/24568 ,  G06F16/2237 ,  G06F16/285 ,  G06F16/906 ,  G06F16/93 ,  G06F16/90335 ,  G06F16/9038 ,  G06F16/90332 ,  G06F16/258 ,  G06F16/288 ,  G06F16/283 ,  G06F16/335 ,  G06F16/2264 ,  G06F16/2423 ,  G06F16/248 ,  G06F16/254 ,  G06F30/20 ,  G06F40/166 ,  G06F40/117 ,  G06F40/20 ,  G06F8/71 ,  G06F9/54 ,  G06F9/547 ,  G06F11/3608 ,  G06F11/3636 ,  G06F17/18 ,  G06F21/552 ,  G06F21/60 ,  G06N7/00 ,  G06Q10/04 ,  G06T11/001 ,  H04L63/1416 ,  H04L63/1491 ,  H04L67/306 ,  H04L67/34 ,  H04N21/23412 ,  H04N21/8153 ,  G06N5/00 ,  G06N5/02 ,  G06V30/1985 ,  G06F18/22 ,  G06F18/23 ,  G06F18/24 ,  G06F18/40 ,  G06F18/213 ,  G06F18/214 ,  G06F18/217 ,  G06F18/285 ,  G06F18/2115 ,  G06F18/2148 ,  G06F18/2193 ,  G06F18/2411 ,  G06F18/2415 ,  G06N3/044 ,  G06N3/045 ,  G06N7/01 ,  G06V30/194 ,  G06V10/993 ,  G06V10/768 ,  G06N3/08 ,  G06T2207/20084 ,  G06T2207/10016 ,  G06T2207/20081

摘要： Systems and methods for generating synthetic video are disclosed. For example, a system may include a memory unit and a processor configured to execute the instructions to perform operations. The operations may include receiving video data, normalizing image frames, generating difference images, and generating an image sequence generator model. The operations may include training an autoencoder model using difference images, the autoencoder comprising an encoder model and a decoder model. The operations may include identifying a seed image frame and generating a seed difference image from the seed image frame. The operations may include generating, by the image sequence generator model, synthetic difference images based on the seed difference image. In some aspects, the operations may include using the decoder model to synthetic normalized image frames from the synthetic difference images. The operations may include generating synthetic video by adding background to the synthetic normalized image frames.

公开(公告)号：US11741316B2

公开(公告)日：2023-08-29

申请号：US17823300

申请日：2022-08-30

申请人： Oracle International Corporation

发明人： Boris Galitsky

IPC分类号： G06F40/44 ,  G06F40/35 ,  G06F40/289 ,  G06F16/9032 ,  G06F18/214

CPC分类号： G06F40/44 ,  G06F16/90332 ,  G06F18/214 ,  G06F40/289 ,  G06F40/35

摘要： An autonomous agent creates a first semantic tree from a question and second semantic tree from a candidate answer. The agent identifies, between the first semantic tree and the second semantic tree, common subtrees and calculates a semantic alignment score from a sum of sizes of each of the common subtrees. The agent forms a first syntactic tree for the question and a second syntactic tree for the candidate answer. The agent identifies a number of common syntactic nodes between the first syntactic tree and the second syntactic tree. The agent calculates a syntactic alignment score based on the number of common syntactic nodes. Responsive to determining that a sum of the semantic alignment score and the syntactic alignment score is greater than a threshold, the agent outputs the candidate answer to a device.

公开(公告)号：US11741314B2

公开(公告)日：2023-08-29

申请号：US16952702

申请日：2020-11-19

申请人： DIRECTV, LLC

发明人： Huy Q Tran ,  Vlad Zarney ,  Kapil Chaudhry ,  Douglas T. Kuriki ,  Todd T. Tran ,  David K Homan ,  An T. Lam ,  Michael E. Yan ,  Ashley B. Tarnow

IPC分类号： G06F17/00 ,  G06F40/40 ,  G06F16/632 ,  G06F16/332 ,  G06F16/9032 ,  H04N21/422 ,  H04N21/439 ,  H04N21/482 ,  H04N21/4147 ,  H04N21/433 ,  H04N21/472 ,  H04N21/4722 ,  H04N21/488 ,  H04N21/61 ,  G06F3/16 ,  G08C17/02 ,  H04N21/4415 ,  H04N21/475 ,  G10L15/26 ,  G06F3/04842 ,  H04N21/41 ,  G06F3/0482 ,  G06F3/0488 ,  G10L15/22 ,  G10L15/06 ,  G10L15/30 ,  H04N21/458 ,  H04N21/222

CPC分类号： G06F40/40 ,  G06F3/0482 ,  G06F3/0488 ,  G06F3/04842 ,  G06F3/165 ,  G06F3/167 ,  G06F16/3325 ,  G06F16/3329 ,  G06F16/632 ,  G06F16/90332 ,  G08C17/02 ,  G10L15/22 ,  G10L15/26 ,  H04N21/4147 ,  H04N21/41265 ,  H04N21/4222 ,  H04N21/42203 ,  H04N21/42204 ,  H04N21/42209 ,  H04N21/42222 ,  H04N21/42224 ,  H04N21/4334 ,  H04N21/4394 ,  H04N21/4398 ,  H04N21/4415 ,  H04N21/475 ,  H04N21/4722 ,  H04N21/4753 ,  H04N21/47214 ,  H04N21/4828 ,  H04N21/4882 ,  H04N21/6143 ,  H04N21/6175 ,  G08C2201/31 ,  G10L15/063 ,  G10L15/30 ,  G10L2015/0638 ,  H04N21/2221 ,  H04N21/4583 ,  H04N21/47211

摘要： A system and method for operating the same includes a language processing module generating a search request text signal and determining identified data from the search request text signal. A search module generates search results in response to the search request text signal. A dialog manager classifies the search request text signal into a response classification associated with a plurality of templates, selects a first template from the plurality of templates in response to the response classification and corrects search results in response to the identified data and the template to form a corrected response signal. A device receives and displays the corrected response signal.

公开(公告)号：US20230266981A1

公开(公告)日：2023-08-24

申请号：US18096468

申请日：2023-01-12

申请人： GOOGLE LLC

发明人： Mingling Wang ,  Ye Zhou ,  Dina Elhaddad

IPC分类号： G06F9/451 ,  G06F3/0482 ,  H04W4/38 ,  G06F16/9032 ,  G06F9/445 ,  G06F8/61 ,  H04W4/33 ,  H04W4/70 ,  G06F40/10 ,  G06F40/35 ,  G06F40/40 ,  H04M1/72403 ,  H04M1/72454 ,  H04M1/72469

CPC分类号： G06F9/453 ,  G06F3/0482 ,  H04W4/38 ,  G06F16/90332 ,  G06F9/4451 ,  G06F9/445 ,  G06F8/61 ,  H04W4/33 ,  H04W4/70 ,  G06F40/10 ,  G06F40/35 ,  G06F40/40 ,  H04M1/72403 ,  H04M1/72454 ,  H04M1/72469 ,  G06F3/04817

摘要： Methods, apparatus, systems, and computer-readable media are provided for introducing a user to functions of various applications through interactions with an assistant agent. The assistant agent can correspond to an assistant application that can provide a user interface with multiple selectable elements, each of which can correspond to a separate application. When a user selects one of the selectable elements, a function of an application can be demonstrated to the user, in order that the user might become more familiar with functions of the application. In some implementations, a portion of the selectable element can be selected to cause information about the application to be presented to the user. This allows the user to have the option to try out or learn about an application before investing computational resources through downloading and installing the entire application.

公开(公告)号：US11735180B2

公开(公告)日：2023-08-22

申请号：US17031544

申请日：2020-09-24

申请人： International Business Machines Corporation

发明人： Girmaw Abebe Tadesse ,  Sarbajit K. Rakshit ,  Komminist Weldemariam

IPC分类号： G10L15/22 ,  G06F16/9032 ,  G06F16/903

CPC分类号： G10L15/22 ,  G06F16/90332 ,  G06F16/90335

摘要： Aspects of the present invention disclose a method for synchronizing a voice reply from AI voice assistant based on user activities. The method includes one or more processors identifying a task of a user that corresponds to a voice query of the user. The method further includes generating a sequence of sub-activities of the task corresponding to the voice query of the user. The method further includes determining a completion status of each sub-activity of the sequence of sub-activities of the task corresponding to the voice query of the user based at least in part on activity data received from one or more computing devices in an operating environment of the user. The method further includes synchronizing a voice reply of a computing device with the sequence of sub-activities of the task based at least in part on the completion status of each sub-activity of the sequence.

公开(公告)号：US11734311B1

公开(公告)日：2023-08-22

申请号：US17200212

申请日：2021-03-12

申请人： Google LLC

发明人： Erwin Can Sar ,  Timothy Youngjin Sohn ,  Andrew Tomkins

IPC分类号： G06F16/9032 ,  G06F16/28 ,  G06F16/2455 ,  G06F21/55

CPC分类号： G06F16/284 ,  G06F16/24565 ,  G06F16/90324 ,  G06F21/554

摘要： Methods and apparatus related to determining additional features for a user task entry of a user based on a user habit of the user. For example, one or more aspects of a user task entry of a user may be compared to one or more aspects of a user habit of the user to determine a correlation measure between the task entry and the user habit. If the correlation measure satisfies a threshold, one or more additional features of the user task entry may be determined based on the user habit. For example, the user habit may include one or more trigger indicators that indicate an actual entry or anticipated entry of the user into the user habit, and one or more of the trigger indicators may be utilized to determine task trigger indicators for the user task entry.

公开(公告)号：US11734268B2

公开(公告)日：2023-08-22

申请号：US17358114

申请日：2021-06-25

申请人： Pryon Incorporated

发明人： David Nahamoo ,  Igor Roditis Jablokov ,  Vaibhava Goel ,  Etienne Marcheret ,  Ellen Eide Kislal ,  Steven John Rennie ,  Marie Wenzel Meteer ,  Neil Rohit Mallinar ,  Soonthorn Ativanichayaphong ,  Joseph Allen Pruitt ,  John Pruitt ,  Bryan Dempsey ,  Chui Sung

IPC分类号： G06F16/2452 ,  G06F40/151 ,  G06F40/137 ,  G06F16/957 ,  G06F16/332 ,  G06F16/338 ,  G06F16/335 ,  G06F16/9032 ,  G06F16/93 ,  G06F40/30 ,  G06F16/33 ,  G06F40/247 ,  G06N5/022 ,  G06N5/04 ,  G06F40/131 ,  G06F40/20 ,  G06F40/284 ,  G06N3/08 ,  G06N3/006 ,  G06N3/044 ,  G06N3/045

CPC分类号： G06F16/24522 ,  G06F16/335 ,  G06F16/338 ,  G06F16/3328 ,  G06F16/3329 ,  G06F16/3349 ,  G06F16/9032 ,  G06F16/93 ,  G06F16/9574 ,  G06F40/131 ,  G06F40/137 ,  G06F40/151 ,  G06F40/20 ,  G06F40/247 ,  G06F40/284 ,  G06F40/30 ,  G06N5/022 ,  G06N5/04 ,  G06N3/006 ,  G06N3/044 ,  G06N3/045 ,  G06N3/08

摘要： Disclosed are methods, systems, devices, apparatus, media, design structures, and other implementations, including a method that includes receiving a source document, applying one or more pre-processes to the source document to produce contextual information representative of the structure and content of the source document, and transforming the source document, based on the contextual information, to generate a question-and-answer searchable document.