公开(公告)号：US20250045638A1

公开(公告)日：2025-02-06

申请号：US18920692

申请日：2024-10-18

Applicant: Lemon Inc.

Inventor： Yukun Ma ,  Nipun Rustagi

IPC: G06N20/00 ,  G06F18/241

Abstract: There are provided methods, devices, and computer program products for data classification. A sample for training a machine learning model is obtained. The sample comprises a prompt and a response for the prompt, the prompt comprises input data, and the response comprises a classification of the input data, and a reason why the input data belongs to the classification. A first sample is determined based on the input data and the classification of the input data, and the first sample comprises a first prompt and a first response. A second sample is determined based on the input data, the classification of the input data, and the reason, and the second sample comprises a second prompt and a second response. The machine learning model is updated based on the first and the second samples. Therefore, the machine learning model may be updated in a more reliable and accurate way.

公开(公告)号：US20250044783A1

公开(公告)日：2025-02-06

申请号：US18713988

申请日：2022-11-07

Applicant: Lemon Inc.

Inventor： Weihao GAO ,  Ce YANG ,  Di WU ,  Chong WANG

IPC: G05B23/02

Abstract: According to embodiments of the present disclosure, there are provided a method, device, medium, and product for state prediction. The method includes: obtaining a neural network, the neural network being trained to determine a state change of a physical system over time, training data of the neural network indicating states of a plurality of physical systems at a plurality of times; obtaining state data corresponding to a state of a target physical system at a first time; determining respective unit feature representations of the physical units in the target physical system based at least on target values of material properties of the physical units; and determining a state of the target physical system at a second time based on the state data by inputting at least the unit feature representations to the neural network. Through the above solution, generalization capability of the neural network can be significantly improved.

公开(公告)号：US12210877B2

公开(公告)日：2025-01-28

申请号：US18118367

申请日：2023-03-07

Applicant: Lemon Inc. ,  Beijing Youzhuju Network Technology Co., Ltd.

Inventor： Viacheslav Dubeyko ,  Jian Wang

IPC: G06F9/30

Abstract: The present disclosure describes techniques for offloading computation based on an extended instruction set architecture (ISA). The extended ISA may be created based on identifying functions executed multiple times by a central processing unit (CPU). The extended ISA may comprise hashes corresponding to the functions and identifiers of extended operations associated with the functions. The extended operations may be converted from original operations of the functions. The extended operations may be executable by a storage device. The storage device may be associated with at least one computational core. Code may be synthesized based at least in part on the extended ISA. Computation of the synthesized code may be offloaded into the storage device.

公开(公告)号：US12200225B2

公开(公告)日：2025-01-14

申请号：US17809206

申请日：2022-06-27

Applicant: Lemon Inc.

Inventor： Ye-kui Wang

IPC: H04N21/44 ,  H04N7/01 ,  H04N19/132 ,  H04N19/136 ,  H04N19/167 ,  H04N19/169 ,  H04N19/172 ,  H04N19/30 ,  H04N19/46 ,  H04N21/845

Abstract: A method of processing media data. The method includes determining, for a conversion between the media data and a media data file, whether a size and a position of a target picture-in-picture region in a main video are present in the media data file, wherein a supplementary video appears to be overlaid on the target picture-in-picture region when the main video is displayed; and performing the conversion between the media data and the media data file based on the size and the position determined. A corresponding video coding apparatus and non-transitory computer-readable recording medium are also disclosed.

公开(公告)号：US12197302B2

公开(公告)日：2025-01-14

申请号：US18542254

申请日：2023-12-15

Applicant: Lemon Inc.

Inventor： Zhichao Li ,  Heting Liu ,  Zherui Liu ,  Chuanxiong Guo ,  Jian Wang

IPC: G06F11/22

Abstract: The present disclosure provides a prediction method and an apparatus for a faulty GPU, an electronic device and a storage medium. The method includes: acquiring parameter information of each GPU in a plurality of GPUs to obtain a parameter information set; inputting the parameter information set into a plurality of pre-trained prediction models to obtain a prediction result corresponding to each prediction model; and determining a faulty GPU from the plurality of GPUs according to the prediction result.

公开(公告)号：US20250014251A1

公开(公告)日：2025-01-09

申请号：US18763893

申请日：2024-07-03

Applicant: Beijing Zitiao Network Technology Co., Ltd. ,  Lemon Inc.

Inventor： Jiacheng Liu ,  Fan Zhang

IPC: G06T13/00 ,  G06T7/20

Abstract: There are provided a method for displaying a virtual object, apparatus, device, readable storage medium and product. The method includes: obtaining an effect processing request triggered by a user, the effect processing request comprising identification information of target effect; displaying, in a media content generating page, at least one target image frame and a virtual object associated with the target effect; determining a first motion parameter of the virtual object in a first direction based on the at least one target image frame, and determining a second motion parameter of the virtual object in a second direction based on predetermined content associated with the virtual object; and driving, through a predetermined dynamic component, the virtual object to move according to the first motion parameter and the second motion parameter, the predetermined dynamic component being on a skeleton node corresponding to the virtual object.

公开(公告)号：US20250013558A1

公开(公告)日：2025-01-09

申请号：US18762525

申请日：2024-07-02

Applicant: Lemon Inc.

Inventor： Junyu YUE

IPC: G06F11/36

Abstract: The disclosure provides a method, apparatus, device, and medium for modifying a bytecode. The detailed description of the method includes: searching for a bytecode to be tested based on a predetermined annotation and determining a depended object category and a depending object category for dependency injection therefrom; and generating a supplementary bytecode based on the depended object category, inserting the supplementary bytecode into a corresponding part of the depending object category in the bytecode to be tested to obtain a target bytecode. With this method, static dependency injection of code can be implemented in the compilation phase with only a few source code modifications, especially without the need to write a large amount of template code, and the success of the code after dependency injection is guaranteed in the software runtime phase.

公开(公告)号：US20250013479A1

公开(公告)日：2025-01-09

申请号：US18891729

申请日：2024-09-20

Applicant: Beijing Zitiao Network Technology Co., Ltd. ,  Lemon Inc.

Inventor： Junli XIAN ,  Bowen SHEN ,  Xin XIE

IPC: G06F9/451 ,  G06F3/0482 ,  G06F3/0484

Abstract: According to embodiments of the disclosure, a method, an apparatus, a device and a storage medium for processing information are provided. In the method, first information input by a target object to a digital assistant is obtained; and second information is generated as a response of the digital assistant to the first information based at least on the first information and historical interaction information between the target object and at least one service component. Thus, by generating a response of the digital assistant based on the historical interaction information between the target object and the service component, the embodiments of the disclosure can improve the quality of the response content generated by the digital assistant.

公开(公告)号：US12190554B2

公开(公告)日：2025-01-07

申请号：US17666045

申请日：2022-02-07

Applicant: Lemon Inc.

Inventor： Shuo Cheng ,  Peng Wang

IPC: G06V10/25 ,  G06N3/045 ,  G06T7/50 ,  G06T7/70

Abstract: The present disclosure describes techniques for determining a bounding box. An image may be received. An X-frame, a Y-frame, and a normal frame may be estimated based on the image using a first neural network. At least one planar region may be detected from the image using a second neural network. A vanishing point detection may be performed on each of the at least one planar region. Output of the first neural network may be fused with results of the vanishing point detection. A depth value of each pixel in at least one plane corresponding to the at least one planar region may be determined based at least in part on a result of the fusing. A location of a bounding box may be determined based at least in part on the depth value of each pixel in the at least one plane.

公开(公告)号：US12190481B2

公开(公告)日：2025-01-07

申请号：US17807527

申请日：2022-06-17

Applicant: Lemon Inc.

Inventor： Guoxian Song ,  Jing Liu ,  Weihong Zeng ,  Jingna Sun ,  Xu Wang ,  Linjie Luo

IPC: G06T5/50 ,  G06T3/4046 ,  G06V40/16

Abstract: Methods and systems for enlarging a stylized region of an image are disclosed that include receiving an input image, generating, using a first generative adversarial network (GAN) generator, a first stylized image, based on the input image, normalizing the input image, generating, using a second generative adversarial network (GAN) generator, a second stylized image, based on the normalized input image, blending the first stylized image and the second stylized image to obtain a third stylized image, and providing the third stylized image as an output.