公开(公告)号：US20240323313A1

公开(公告)日：2024-09-26

申请号：US18444256

申请日：2024-02-16

申请人： Apple Inc.

发明人： David A. UNDERWOOD ,  Gary W. GEHIERE ,  Michael W. GREINER ,  Amy W. HUNG ,  Scott G. MARNIK ,  David A. TURNER

IPC分类号： H04N5/272 ,  G06F3/0482 ,  G06F40/166 ,  H04N5/268 ,  H04N5/76 ,  H04N23/90

CPC分类号： H04N5/272 ,  G06F3/0482 ,  G06F40/166 ,  H04N5/268 ,  H04N5/76 ,  H04N23/90

摘要： The present disclosure generally relates to providing live video. An example method includes, at a computer system, while in an editing mode for a presentation, receiving, via one or more input devices, a request to insert an object onto a first slide of the presentation, wherein the request includes associating the object with a source for live video; and while in a presentation mode for the presentation, displaying, via a display generation component, the first slide including concurrent display of the object and one or more visual elements, wherein: in accordance with a determination that the object is associated with a camera, the object includes a live video stream from the camera; and in accordance with a determination that the object is associated with a non-camera external device, the object includes a live video stream that mirrors a portion of a display of the non-camera external device.

公开(公告)号：US20240320432A1

公开(公告)日：2024-09-26

申请号：US18447697

申请日：2023-08-10

申请人： Shopify Inc.

发明人： Russ MASCHMEYER ,  Trisha CAUSLEY ,  Daniel BEAUCHAMP

IPC分类号： G06F40/284 ,  G06F40/166 ,  G06F40/40

CPC分类号： G06F40/284 ,  G06F40/166 ,  G06F40/40

摘要： A textual description that includes a body of unstructured text is received. Using a rating model configured to output a rating based on a degree of similarity of the received textual description and each of a set of selected textual descriptions, a rating is generated based on the received textual description. The rating model to also used to generate a suggested modification of the received textual description that, when applied to the received textual descriptions, changes the rating of the received textual description. An indication of the suggested modification can be output to a user.

公开(公告)号：US12100418B2

公开(公告)日：2024-09-24

申请号：US17472511

申请日：2021-09-10

申请人： INSTITUTE OF AUTOMATION, CHINESE ACADEMY OF SCIENCES

发明人： Jianhua Tao ,  Zheng Lian ,  Bin Liu ,  Xuefei Liu

IPC分类号： G10L25/63 ,  G06F18/25 ,  G06F40/166 ,  G06F40/211 ,  G06F40/216 ,  G06F40/284 ,  G06F40/289 ,  G06F40/30 ,  G06N20/00 ,  G06N20/20 ,  G06V20/40 ,  G06V40/16 ,  G10L15/02 ,  G10L15/26 ,  G10L25/30

CPC分类号： G10L25/63 ,  G06F18/253 ,  G06F40/166 ,  G06F40/211 ,  G06F40/216 ,  G06F40/284 ,  G06F40/289 ,  G06F40/30 ,  G06N20/00 ,  G06N20/20 ,  G06V20/41 ,  G06V40/166 ,  G06V40/168 ,  G10L15/02 ,  G10L15/26 ,  G10L25/30

摘要： Disclosed is a dialogue emotion correction method based on a graph neural network, including: extracting acoustic features, text features, and image features from a video file to fuse them into multi-modal features; obtaining an emotion prediction result of each sentence of a dialogue in the video file by using the multi-modal features; fusing the emotion prediction result of each sentence with interaction information between talkers in the video file to obtain interaction information fused emotion features; combining, on the basis of the interaction information fused emotion features, with context-dependence relationship in the dialogue to obtain time-series information fused emotion features; correcting, by using the time-series information fused emotion features, the emotion prediction result of each sentence that is obtained previously as to obtain a more accurate emotion recognition result.

公开(公告)号：US20240311551A1

公开(公告)日：2024-09-19

申请号：US18675520

申请日：2024-05-28

申请人： Canva Pty Ltd

发明人： Declan Robin Vong ,  Michelle Munn Wai Seeto ,  Desiree Isabelle Surjadi ,  Suganth Sengottuvelappan ,  Cayden Joel Meyer

IPC分类号： G06F40/166 ,  G06F40/106 ,  G06F40/109 ,  G06F40/14

CPC分类号： G06F40/166 ,  G06F40/106 ,  G06F40/109 ,  G06F40/14

摘要： A computer implemented method includes displaying a design creation user interface operable by a user to create or edit a design document comprising a plurality of design elements. Data identifying each of the plurality of design elements and data identifying attributes of the plurality of design elements is maintained. A processor determines, based on the attributes, that at least one rule with an associated diagnostic is invoked and indicia is displayed corresponding to the diagnostic associated with the at least one rule.

公开(公告)号：US12095834B2

公开(公告)日：2024-09-17

申请号：US18377452

申请日：2023-10-06

申请人： Zazzle Inc.

发明人： Robert I. Beaver, III ,  Jeffrey J. Beaver ,  Sean Narvasa ,  Leslie Young Harvill ,  Petar S. Ivanov ,  Parker H. Bossier ,  Christopher Collette

IPC分类号： H04L65/401 ,  G06F40/166 ,  H04L9/40 ,  H04L65/402 ,  H04L65/403 ,  H04L67/306

CPC分类号： H04L65/4015 ,  G06F40/166 ,  H04L63/101 ,  H04L63/102 ,  H04L65/4025 ,  H04L65/403 ,  H04L67/306

摘要： In some embodiments, a method for generating customized products in collaboration with live designers is disclosed. The method comprises: receiving, at a computer collaboration computer, a request, from a first user interface that executes on a first user device associated with a first user, for assistance in collaborating on an interactive design; wherein the request comprises collaboration parameters; in response to receiving the request, automatically determining one or more designer profiles, each designer profile satisfying one or more of the collaboration parameters; in response to selecting a particular designer profile from the one or more designer profiles: automatically enabling a collaboration on the interactive design between the first user and a second user who has the particular designer profile; wherein the collaboration between the first user and the second user comprises automatically generating and updating product description data having a plurality of key-values pairs associated with the interactive design.

公开(公告)号：US12094584B2

公开(公告)日：2024-09-17

申请号：US17879784

申请日：2022-08-03

申请人： FUJIFILM Corporation

发明人： Keigo Nakamura

IPC分类号： G16H15/00 ,  G06F3/0482 ,  G06F40/166 ,  G06T7/00 ,  G06V20/70

CPC分类号： G16H15/00 ,  G06F3/0482 ,  G06F40/166 ,  G06T7/0012 ,  G06V20/70 ,  G06T2207/10081 ,  G06T2207/20081 ,  G06T2207/30096 ,  G06V2201/03

摘要： An analysis unit (13) specifies properties of a feature portion included in an image for each of a plurality of predetermined property items. A text generation unit (14) generates a plurality of texts such that a combination of the property items is different between the plurality of texts. In a case where any one of the plurality of texts is selected, an association data generation unit (16) generates association data in which a selection item, which is a property item corresponding to the property described in the selected text, and a property specifying result are associated with each other. In a case where the specified property and the property specifying result included in the association data match, the text generation unit (14) generates a priority text describing the property specified for the same property item as the selection item associated with the property specifying result as one of the plurality of texts.

公开(公告)号：US12093639B2

公开(公告)日：2024-09-17

申请号：US18239710

申请日：2023-08-29

申请人： BEIJING ZITIAO NETWORK TECHNOLOGY CO., LTD.

发明人： Wei Chen ,  Qing Zeng

IPC分类号： G06F40/00 ,  G06F3/16 ,  G06F40/106 ,  G06F40/166

CPC分类号： G06F40/166 ,  G06F3/167 ,  G06F40/106

摘要： Provided in the present disclosure are an electronic document processing method and apparatus, a terminal, and a storage medium. The electronic document processing method comprises: in a current display interface, in response to a document content determination operation, determining target content from the document content of a first document (S11); and, in the current display interface, in response to a document creation operation, creating a second document having an association relationship with the first document (S12), wherein the second document is associated with the first document on the basis of the target content. The method provided in the embodiments of the present disclosure can rapidly generate a second document having an association relationship with the content in a first document, so that there is no need for the user to repeatedly perform copy and paste and association operations, thereby greatly improving the usage experience of the user.

公开(公告)号：US20240303416A1

公开(公告)日：2024-09-12

申请号：US18665707

申请日：2024-05-16

申请人： Gal EHRLICH

发明人： Gal EHRLICH

IPC分类号： G06F40/166 ,  G06F3/0484 ,  G06F40/123 ,  G06Q50/18

CPC分类号： G06F40/166 ,  G06F3/0484 ,  G06F40/123 ,  G06Q50/184

摘要： A method and system for drafting a patent application. The method comprising (a) inputting a short description of an inventive concept into an AI machine; (b) querying the AI machine to draft one or more patent claims based on the short description; (c) inputting the drafted patent claims into a second query; and (d) requesting the second query to draft a patent application based on the drafted patent claims. The system comprising (a) an AI machine configured to receive a short description of an inventive concept and draft one or more patent claims based on the short description; (b) A second query interface configured to receive the drafted patent claims and draft a patent application based on the claims; and (c) a user interface through which a user can input the short description and receive the drafted patent application.

公开(公告)号：US12086192B2

公开(公告)日：2024-09-10

申请号：US17365798

申请日：2021-07-01

申请人： NORTH FORK HOLDINGS, LLC

发明人： John Yih-Jung Hu ,  Qing Xia ,  Venkatchalapathi Madheswaran

IPC分类号： G06F16/23 ,  G06F16/25 ,  G06F16/93 ,  G06F40/166 ,  G06Q10/10 ,  G06Q20/40 ,  G06Q30/04 ,  G06Q40/12

CPC分类号： G06F16/93 ,  G06F16/2379 ,  G06F40/166 ,  G06Q10/10 ,  G06F16/254 ,  G06F16/258 ,  G06Q20/405 ,  G06Q30/04 ,  G06Q40/12

摘要： An exception handling machine is configured to receive a first document from a source document processing system and provide a first revised document to a destination document processing system. The exception handling machine is configured to detect an exception flag in at least one data field of the first document and determine at least one exception handling rule for the first document based on at least one other data field in the first document and the exception flag, determine an exception code corresponding to the exception handling rule, insert the exception code into the first document to generate the first revised document, and provide the first revised document to the destination document processing system. The destination document processing system is programmed to respond to the exception code inserted in the revised first document by providing the first revised document to a client device connected to the destination document processing system.

公开(公告)号：US20240296425A1

公开(公告)日：2024-09-05

申请号：US18328667

申请日：2023-06-02

申请人： Microsoft Technology Licensing, LLC

发明人： Thomas Rosenkranz ,  Asim Anis ,  Andrew Chimka ,  Daniel K. Hewlett ,  Cho Won Kim ,  Zixin Li ,  Hang Li ,  Pierre Monestie ,  Jianqiang Shen ,  Deanne Moree Chan

IPC分类号： G06Q10/1053 ,  G06F16/9535 ,  G06F40/166 ,  G06F40/194 ,  G06F40/197 ,  G06F40/40

CPC分类号： G06Q10/1053 ,  G06F16/9535 ,  G06F40/166 ,  G06F40/194 ,  G06F40/197 ,  G06F40/40

摘要： Embodiments of the described technologies receive, via a user interface, an input associated with a first user of a user connection network. The input identifies first position data related to a position capable of being filled by a hiring of a person. In response to validating the first position data, second position data different from the first position data is extracted from the user connection network, based on the first position data. A first prompt is formulated based on the first position data and the second position data. The first prompt is sent to a generative language model. A first piece of writing is received from the generative language model. The first piece of writing includes a position description output by the generative language model based on the first prompt. The position description is sent to the user interface in response to the input.