-
公开(公告)号:US20250166667A1
公开(公告)日:2025-05-22
申请号:US18775954
申请日:2024-07-17
Inventor: Yan Zeng , Guoqiang Wei , Hang Li
IPC: G11B27/036 , G06F40/40 , G06V20/40
Abstract: Provided are a method, apparatus, device and medium for generating a video. In one method, a plurality of images for respectively describing a plurality of target images in a target video are received. A text for describing a content of the target video is received. The target video is generated based on the plurality of images and the text according to a generation model. With exemplary implementations of the present disclosure, the plurality of images received can serve as guiding data to determine a development direction of a story in the video, which contributes to the generation of a richer and more realistic dynamic video.
-
2.
公开(公告)号:US20250165263A1
公开(公告)日:2025-05-22
申请号:US18837055
申请日:2023-02-13
Inventor: Lv HE
IPC: G06F9/445 , G06F16/9535
Abstract: Provided are an application starting method and apparatus, an electronic device, a storage medium, a computer program product and a computer program, which relate to terminal device technologies. The method includes: in response to a start instruction of an application, obtaining historical browsing information of the application, wherein the historical browsing information includes information generated during a user's browsing of an application; determining a target channel in each channel of the application based on the historical browsing information, and displaying the target channel of the application. Provided are an application start method and apparatus, an electronic device, a storage medium and a program product. Based on historical browsing information about a user corresponding to an application, a target channel preferred by the user in various channels of the application may be presumed, and after the application is started, the electronic device directly displays the target channel, thereby reducing the operations required by the user for switching to the preferred channel, and improving the user experience.
-
公开(公告)号:US20250157237A1
公开(公告)日:2025-05-15
申请号:US18730493
申请日:2023-01-04
Inventor: Xiaofei MAO , Can HUANG
IPC: G06V30/12 , G06V20/62 , G06V30/148
Abstract: The disclosure relates to a method, apparatus, readable storage medium and electronic device of image processing. The method includes: performing text recognition on a target image, to obtain a recognized text; performing segmentation processing on the recognized text; and obtaining, based on a text segment obtained from the segmentation processing, a target text by correcting the recognized text through a pre-trained language model.
-
公开(公告)号:US20250156657A1
公开(公告)日:2025-05-15
申请号:US18942104
申请日:2024-11-08
Applicant: Lemon Inc. , Beijing Youzhuju Network Technology Co., Ltd.
Inventor: Zhichao HUANG , Rong YE , Yu Ting KO , Qianqian DONG , Shanbo CHENG , Mingxuan WANG , Hang LI
IPC: G06F40/58
Abstract: Embodiments of the present disclosure relate to a method and apparatus for speech translation, an electronic device, and a medium. The method includes obtaining an audio in a source language, where the audio includes a specific type of information. The method further includes obtaining prompt content related to a target language. In addition, the method further includes generating, based on the audio and the prompt content, a target-language text corresponding to the audio, where the target-language text includes a punctuation mark corresponding to the specific type of the information.
-
公开(公告)号:US20250156656A1
公开(公告)日:2025-05-15
申请号:US18941556
申请日:2024-11-08
Applicant: Lemon Inc. , Beijing Youzhuju Network Technology Co., Ltd.
Inventor: Zhichao Huang , Rong Ye , Yu Ting Ko , Qianqian Dong , Shanbo Cheng , Mingxuan Wang , Hang Li
Abstract: Embodiments of the present disclosure relate to a speech translation method, an apparatus, an electronic device, and a medium. The method includes generating a speech representation corresponding to a source-language audio based on the audio. The method also includes obtaining prompt content related to a target language. In addition, the method also includes generating a target-language text corresponding to the audio based on the speech representation and the prompt content.
-
公开(公告)号:US20250156109A1
公开(公告)日:2025-05-15
申请号:US19021790
申请日:2025-01-15
Inventor: Yunfeng SHI , Jun ZHOU , Jian WANG
IPC: G06F3/06
Abstract: A processor chip, a method for flexibly accessing data in the processor chip, an electronic device, and a non-transitory storage medium are provided. The chip includes: a memory, configured to store read-in tensor data from outside the processor chip; a storage control unit, configured to control reading elements from the memory according to the tensor operation of the operator to send the elements to a computing unit, where the storage control unit includes an address computing module, and the address computing module computes addresses in the memory in one-layer read loop or multi-layer read loop nest according to the parameter configured that is received by the interface, so as to read the elements from computed addresses and send the elements to the computing unit; and the computing unit, configured to perform the tensor operation of the operator by using the elements received.
-
7.
公开(公告)号:US20250147564A1
公开(公告)日:2025-05-08
申请号:US19013433
申请日:2025-01-08
Inventor: Hangjian YUAN , Liyang LIU , Dongming YANG , Yunfeng SHI , Jian WANG
Abstract: A method for optimizing computing power of a neural network module, a chip, an electronic device, and a medium are provided. The method includes: obtaining, by the chip, a computational graph of the neural network module having respective operators; performing at least one of adjustments below at least 1 time on a first operator in the computational graph according to specific operation of each operator: counterchanging a position of the first operator with a subsequent operator or a preceding operator in the computational graph, splitting the first operator into more than two identical operators, and inserting a plurality of first operators that are capable of canceling each other out; determining a second operator adjacent to the adjusted first operator in the computational graph according to the specific operations of each operator; and performing merge or cancellation, by the chip, on the adjusted first operator and the second operator.
-
公开(公告)号:US20250142774A1
公开(公告)日:2025-05-01
申请号:US19004084
申请日:2024-12-27
Inventor: Ting TIAN , Bing GAO , Xiaoliang GUO , Tangbo JING , Jian WANG
IPC: H05K7/20
Abstract: Embodiments of the disclosure provide a cooling system including an air cooling part including a first cooler and a first circulation pipeline, the first cooler being configured to cool a coolant inside it with an external liquid, and the first circulation pipeline including a first liquid outlet pipe and a first liquid return pipe; a liquid cooling part including a second cooler and a second circulation pipeline, the second cooler being configured to cool a coolant inside it with an external gas, and the second circulation pipeline including a second liquid outlet pipe and a second liquid return pipe; and a guide assembly connected between the first circulation pipeline and the second circulation pipeline.
-
公开(公告)号:US20250130854A1
公开(公告)日:2025-04-24
申请号:US19002531
申请日:2024-12-26
Inventor: Yu DA , Tao LI , Haizhao LUO , Yongsu ZHANG , Kairui SHE , Yu ZHANG , Jian WANG
Abstract: Embodiments of the present disclosure relate to a method for task scheduling and an electronic device. The method comprises: determining whether there is a task to be scheduled in an online task set of a waiting queue; and if there is the task to be scheduled in the online task set, scheduling the task to be scheduled in the online task set based on a preset online scheduling mode, wherein the preset online scheduling mode is a sequential mode, a throughput mode, or a round-robin mode.
-
公开(公告)号:US20250118338A1
公开(公告)日:2025-04-10
申请号:US18832049
申请日:2023-01-04
Inventor: Jia SUN , Zehuan YUAN
IPC: G11B27/036 , G06V20/40 , G06V20/62 , G06V30/19
Abstract: The present disclosure relates to a video processing method, device, readable medium and electronic equipment. The method includes: obtaining key information corresponding to a video to be processed; extracting one or more target video clips from the video to be processed based on the key information; and obtaining a target video by adding the target video clip to a position preceding a specified video frame in the video to be processed, the specified video frame being any video frame of a preset number of video frames in the video to be processed.
-
-
-
-
-
-
-
-
-