公开(公告)号：US20240404170A1

公开(公告)日：2024-12-05

申请号：US18354546

申请日：2023-07-18

Applicant: Lemon Inc.

Inventor： Kin Chung Wong ,  Blake Garrett Fuselier ,  Jason Yang ,  Yizhe Zhu

IPC: G06T15/04 ,  G06Q50/00 ,  G06T5/00 ,  G06T7/90 ,  G06T15/50 ,  G06V10/56

Abstract: A computing system provides a social media platform. The computing system includes one or more processors configured to execute instructions stored in associated memory to receive a base image including a human face and receive an image mask defining a region for inpainting to occur and a region for inpainting to not occur. The region for inpainting to not occur includes at least an eye region. The one or more processors are configured to receive a user text prompt and generate, at an artificial intelligence (AI) model, a face decoration texture using the base image, the image mask, and the user text prompt as input.

公开(公告)号：US20240403125A1

公开(公告)日：2024-12-05

申请号：US18803132

申请日：2024-08-13

Applicant: LEMON INC. ,  BEIJING YOUZHUJU NETWORK TECHNOLOGY CO., LTD.

Inventor： Yuanlong CHEN ,  Bowen ZHU ,  Bing XIA ,  Yichuan WANG ,  Reza MADAD ,  Xudong ZHANG ,  He XIAO

IPC: G06F9/50

Abstract: Embodiments of the present disclosure provide a method, device, and medium for placing information. The method comprises obtaining a plurality of pairs of consumption limits and actual consumptions within a period of time, where the consumption limits in the plurality of pairs are not monotonic in a case that the plurality of pairs are sorted by actual consumptions. The method further comprises adjusting the consumption limits in the plurality of pairs such that the adjusted consumption limits are monotonic in the case that the plurality of pairs are sorted by the actual consumptions. In addition, the method further comprises allocating a target consumption limit for placement of target information based on the adjusted plurality of pairs of consumption limits and actual consumptions.

公开(公告)号：US20240402971A1

公开(公告)日：2024-12-05

申请号：US18205378

申请日：2023-06-02

Applicant: Lemon Inc.

Inventor： Koken Ishii

IPC: G06F3/14 ,  G06F3/01 ,  G06F3/04815 ,  G06F3/0486

Abstract: A connection may be established between an extended reality (XR) device and a non-XR device. User input may be received via one of the XR device and the non-XR device. Position information associated with the user input may be captured by the one of the XR device and the non-XR device. The position information associated with the user input may be converted to be executable by the other device of the XR device and the non-XR device. The other device of the XR device and the non-XR device may perform an action in response to the user input received by the one of the XR device and the non-XR device.

公开(公告)号：US20240402894A1

公开(公告)日：2024-12-05

申请号：US18679217

申请日：2024-05-30

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

Inventor： Lijuan YU ,  Kewei CHEN ,  Kexin LIN ,  Qingyu CHEN ,  Haishan LIU ,  Shengru WANG

IPC: G06F3/04845 ,  G06F3/0482

Abstract: An effect processing method and apparatus, an electronic device, and a storage medium. The processing method includes: displaying an effect processing page, the effect processing page displaying an image to be processed; in response to an addition trigger operation for an effect processing identifier in the effect processing page, determining an effect processing tool corresponding to the effect processing identifier, and determining an effect processing mode corresponding to the effect processing tool; and, in response to a plurality of effect processing modes existing, generating an effect processing item corresponding to each of the plurality of effect processing modes, displaying the effect processing item in the effect processing page, and displaying an effect image obtained by applying effect processing modes corresponding to a plurality of effect processing items to the image to be processed.

公开(公告)号：US20240402885A1

公开(公告)日：2024-12-05

申请号：US18731107

申请日：2024-05-31

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

Inventor： Xin Xie ,  Junyuan Qi ,  Bowen Shen ,  Yibing Zhu

IPC: G06F3/0483 ,  G06F3/0484 ,  G06F9/451

Abstract: According to the embodiments of the present disclosure, a method, apparatus, device, and storage medium for information processing are provided. The method includes in the presence of a first page collection, receiving a first instruction from a user through an interaction window between the user and a digital assistant, the first page collection comprising at least one page; and performing a target operation corresponding to the first instruction based on the first page collection. Therefore, the digital assistant can be applied in scenarios where there is a page collection, in order to provide users with convenient and efficient services.

公开(公告)号：US20240395367A1

公开(公告)日：2024-11-28

申请号：US18694101

申请日：2022-09-20

Applicant: Lemon Inc.

Inventor： Yuwei YANG ,  Siqi OUYANG ,  Hao ZHOU ,  Lei LI ,  Hang LI

IPC: G16C20/50 ,  G06F30/27

Abstract: According to the embodiments of the disclosure, a method, apparatus, device, storage media, and program products for designing ligand molecules is provided. The methods described herein include: editing a first molecular structure with an editing model to determine a second molecular structure, the editing at least comprising deleting a fragment from the first molecular structure or adding a fragment to the first molecular structure; in response to determining that an evaluation of the second molecular structure is better than the first molecular structure, training the editing model based on the editing, the evaluation at least indicating binding capacity between the second molecular structure and a target molecule; and determining a target structure of the ligand molecule for the target molecule with the trained editing model and based on the second molecular structure.

公开(公告)号：US20240394507A1

公开(公告)日：2024-11-28

申请号：US18714656

申请日：2022-11-04

Applicant: Lemon Inc.

Inventor： Yibo ZHU ,  Yangrui CHEN ,  Jun HE ,  Yanghua PENG ,  Chuanxiong GUO ,  Jian WANG

IPC: G06N3/042 ,  G06N5/01

Abstract: The disclosure relates to a method, apparatus, system, medium and electronic device for graph neural network generation. The method includes: obtaining a subgraph structure, the subgraph structure being configured to reflect a graph structure of a corresponding subgraph, and the subgraph comprising a plurality of nodes and edges between the plurality of nodes; obtaining, based on the subgraph structure and according to a predetermined priority, node features of the plurality of nodes and edge features of the edges from a plurality of memories; the predetermined priority being obtained by sorting the plurality of memories in accordance with memory size in an ascending order; fusing, based on the subgraph structure, the node features of the plurality of nodes and the edge features of the edges to obtain subgraph data; and training, based on the subgraph data, the graph neural network.

公开(公告)号：US20240385860A1

公开(公告)日：2024-11-21

申请号：US18786237

申请日：2024-07-26

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

Inventor： Yiguo WANG ,  Yang LIU ,  Bowen ZHAO ,  Yingdi SUN ,  Yibing ZHU

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

Abstract: According to embodiments of the present disclosure, methods for information interaction and device and storage medium are provided. In the method for information interaction, a first interactive window for a first user to interact with a digital assistant is displayed in response to an operation of invoking the digital assistant in a first page, and one or more plug-ins selected by default are displayed in the first interactive window, wherein the one or more plug-ins selected by default have a first association relationship with the first page, and each plug-in is configured to perform a corresponding function. Thus, the plug-ins may be selected for a user by default in the interactive window. In this way, diversified operations may be completed efficiently by means of the plug-ins during the user interactions with the digital assistant.

公开(公告)号：US20240380949A1

公开(公告)日：2024-11-14

申请号：US18314019

申请日：2023-05-08

Applicant: Lemon Inc.

Inventor： Linjie YANG ,  Heng WANG ,  Yuhan SHEN ,  Longyin WEN ,  Haichao YU

IPC: H04N21/488 ,  H04N21/2389 ,  H04N21/84

Abstract: A system and a method are provided that include a processor executing a caption generation program to receive an input video, sample video frames from the input video, extract video frames from the input video, extract video embeddings and audio embeddings from the video frames, including local video tokens and local audio tokens, respectively, input the local video tokens and the local audio tokens into at least a transformer layer of a cross-modal encoder to generate multi-modal embeddings, and generate video captions based on the multi-modal embeddings using a caption decoder.

公开(公告)号：US20240378453A1

公开(公告)日：2024-11-14

申请号：US18658582

申请日：2024-05-08

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

Inventor： Yegor KLOCHKOV ,  Jean-Francois TON ,  Ruocheng GUO ,  Yang LIU ,  Hang LI

IPC: G06N3/094

Abstract: A system for removing a concept from a trained neural network for executing a classification task, the system comprising: the trained neural network, wherein the trained neural network comprises a hidden layer; and a classifier applied at a layer of the hidden layer, wherein: the classifier defines a representation vector at the layer of the hidden layer, wherein the representation vector classifies instances of the concept and non-instances of the concept at the layer; the classifier defines a concept activation vector, wherein the concept activation vector is a normal vector to the representation vector and the concept activation vector comprises an adversarial penalty objective to reduce the instances of the concept at the layer; and a loss function of the trained neural network is optimised based on a downstream loss of the classification task and the adversarial penalty objective.