公开(公告)号：US12301985B2

公开(公告)日：2025-05-13

申请号：US18756310

申请日：2024-06-27

Applicant: Beijing Zitiao Network Technology Co., Ltd.

Inventor： Fengyi Shang ,  Yinghui Wang ,  Shaopan Chen

IPC: H04N23/60 ,  H04N23/63

Abstract: The present disclosure relates to a photographing method and apparatus, and a device, a storage medium and a program product. The method includes: in response to the selection of a scene type, displaying one or more image processing templates corresponding to the selected scene type; in response to a selection operation for the image processing templates, determining image processing information corresponding to a selected image processing template; displaying one or more material information items corresponding to the image processing template; and in response to a received photographing instruction, performing photographing on the basis of the image processing information.

公开(公告)号：US12299822B2

公开(公告)日：2025-05-13

申请号：US18743455

申请日：2024-06-14

Applicant: BEIJING ZITIAO NETWORK TECHNOLOGY CO., LTD.

Inventor： Xin Dong ,  Xijin Zhang

IPC: G06T19/00 ,  G06T7/11 ,  G06T7/13 ,  G06T7/194 ,  G06T7/73

Abstract: The present disclosure provides a virtual clothing changing method, apparatus, electronic device and readable medium. The method comprises: obtaining a source image and a target image, the source image comprising target clothing associated with a first human instance, the target image comprising a second human instance; obtaining first portrait information and first pose information of the source image and second pose information of the target image, respectively, by processing the source image and the target image; obtaining a clothing changed image by changing clothing of the second human instance in the target image to the target clothing in the source image according to the first portrait information, the first pose information and the second pose information.

公开(公告)号：US12299506B1

公开(公告)日：2025-05-13

申请号：US18636946

申请日：2024-04-16

Applicant: Beijing Zitiao Network Technology Co., Ltd.

Inventor： Linlin Wang ,  Junxing Chen

IPC: G06F3/048 ,  G06F3/0481 ,  G06F9/54

Abstract: Embodiments of the disclosure relate to a method, apparatus, device and storage medium for configuring a message card. The method includes: obtaining configuration information for a digital assistant, the configuration information indicating at least one message card for the digital assistant and a data source corresponding to the at least one message card, the configuration information further indicating a mapping relationship between a first data field associated with the at least one message card and a second data field associated with the data source; and controlling the digital assistant to display a message card based on the configuration information. In this way, by configuring the mapping between the message card and the data source, embodiments of the present disclosure may improve the reusability of message cards.

公开(公告)号：US20250150417A1

公开(公告)日：2025-05-08

申请号：US18941931

申请日：2024-11-08

Applicant: Beijing Zitiao Network Technology Co., Ltd.

Inventor： Yiyu HE ,  Jiangwen WANG ,  Qingyu ZHANG ,  Zhong WANG

IPC: H04L51/063 ,  H04L51/02

Abstract: Embodiments of the disclosure provide a method, an apparatus, a device and a storage medium for session interaction. The method includes: presenting, in a session between a user and a digital assistant, a reply message of the digital assistant for a session message of the user, the reply message including a summary content matching the session message; and in response to detecting the detail viewing operation on the summary content, presenting a detail content including an extension to the summary content. In this way, flexible viewing of the summary content and the detail content of the content can be supported in the session with the digital assistant, thereby improving an extended presentation manner of complex content.

公开(公告)号：US20250148829A1

公开(公告)日：2025-05-08

申请号：US18836736

申请日：2023-02-06

Applicant: Beijing Zitiao Network Technology Co., Ltd.

Inventor： Jie WU

IPC: G06V40/20 ,  G06V10/77 ,  G06V10/80 ,  G06V20/40

Abstract: An action recognition method, an electronic device, and a non-transitory storage medium are provided. The action recognition method includes: augmenting an original video to obtain a plurality of augmented video segments; extracting multi-level video features of the plurality of augmented video segments based on a pre-trained action recognition model, and outputting an action recognition result of the original video according to the multi-level video features of the plurality of augmented video segments.

公开(公告)号：US20250148681A1

公开(公告)日：2025-05-08

申请号：US18837573

申请日：2023-02-07

Applicant: Beijing Zitiao Network Technology Co., Ltd.

Inventor： Yixin CHEN

IPC: G06T13/40 ,  G06T7/70 ,  G06T17/00 ,  G06V40/16

Abstract: A video image processing method and apparatus, and an electronic device and a storage medium are provided. The method includes: in response to an effect triggering operation, displaying a target virtual object model, and acquiring an image to be processed containing a target object, wherein the target virtual object model is played according to a preset basic animation effect; determining at least one overlay animation effect being triggered according to a face image in the image to be processed; overlaying the at least one overlay animation effect for the target virtual object model to obtain a target video frame and display the target video frame.

公开(公告)号：US20250148008A1

公开(公告)日：2025-05-08

申请号：US18837580

申请日：2023-02-08

Applicant: Beijing Zitiao Network Technology Co., Ltd.

Inventor： Xiaowei HU ,  Ying WANG ,  Cheng YANG

IPC: G06F16/74 ,  G06F3/0482 ,  G06F3/0484 ,  G06F16/735

Abstract: The embodiments of the present disclosure provide a video display method and apparatus, an electronic device and a storage medium. The method comprising: in response to a first media item comprising a first preset object being played, determining whether a second preset object associated with the first media item meets a preset condition; in response to the second preset object associated with the first media item meeting the preset condition, displaying a preset identifier on a playing screen of the first media item; and in response to a triggering acting on the preset identifier, displaying at least one second media item, wherein the at least one second media item is at least one media item associated with the first preset object, which is determined based on associated information of the first media item.

公开(公告)号：US20250139358A1

公开(公告)日：2025-05-01

申请号：US18634768

申请日：2024-04-12

Applicant: Beijing Zitiao Network Technology Co., Ltd.

Inventor： Xuewei Jia

IPC: G06F40/20

Abstract: A query-processing system processes an input audio stream that represents a succession of queries spoken by a user. The query-processing system listens continuously to the input audio stream, parses queries and takes appropriate actions in mid-stream. In some embodiments, the system processes queries in parallel, limited by serial constraints. In some embodiments, the system parses and executes queries while a previous query's execution is still in progress. To accommodate users who tend to speak slowly and express a thought in separate parts, the query-processing system halts the outputting of results corresponding to a previous query if it detects that a new speech utterance modifies the meaning of the previous query.

公开(公告)号：US20250138993A1

公开(公告)日：2025-05-01

申请号：US18636963

申请日：2024-04-16

Applicant: Beijing Zitiao Network Technology Co., Ltd.

Inventor： Xuewei Jia

IPC: G06F11/36

Abstract: Embodiments of the disclosure provide a method, apparatus, device, and storage medium for debugging a digital assistant. The method includes: receiving a debugging request of a user based on a natural language input; displaying, on a user interface, at least one of: a determination process of one or more function blocks of the digital assistant related to the debugging request, a call process of the one or more function blocks, or a call result of the one or more function blocks; and displaying, on the user interface, a debugging result for the debugging request. By providing a modular and simple input digital assistant debugging solution, users may easily and quickly debug digital assistants with different capabilities without requiring coding skills.

公开(公告)号：US20250138891A1

公开(公告)日：2025-05-01

申请号：US18636927

申请日：2024-04-16

Applicant: Beijing Zitiao Network Technology Co., Ltd.

Inventor： Yuyang Pan

IPC: G06F9/50

Abstract: A method, apparatus, device, and medium for managing a workflow are provided. In one method, in response to receiving a creation request, a page for creating the workflow is presented. The workflow is used to define a plurality of sequential operations in a predetermined task. The page comprises: a first region for providing a plurality of nodes, and a second region for providing a content of the workflow. The plurality of nodes comprises a model node for calling a machine learning model. In response to receiving an interaction request for the page, the workflow is managed based on the interaction request. The model node allows the powerful processing power of a machine learning model to be called in the workflow to complete predetermined tasks of the digital assistant.