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.

公开(公告)号：US20240378022A1

公开(公告)日：2024-11-14

申请号：US18654380

申请日：2024-05-03

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

Inventor： Zhilin XU ,  Longfei BAI ,  Qi CHEN ,  Yimin Chen ,  Shan Lu ,  Jian Wang

IPC: G06F7/78 ,  G06F9/30 ,  G06F17/16

Abstract: A data conversion method and apparatus, an electronic device and a storage medium for converting dimensions of a first data combination. The data conversion method includes: reading n elements in the first data combination according to a first-dimension direction to obtain a first processing group, a first element to an n-th element in the first processing group are arranged according to the first-dimension direction, and n is a positive integer; performing a transpose on the first dimension and the third dimension of the first processing group to obtain a second processing group, a first element to an n-th element in the second processing group are arranged in a third-dimension direction; and writing the first element to the n-th element in the second processing group to a first storage.

公开(公告)号：US20240361892A1

公开(公告)日：2024-10-31

申请号：US18644431

申请日：2024-04-24

Applicant: Lemon Inc.

Inventor： Linyi ZHENG ,  Xiaotong MA ,  Xinyu ZHANG ,  Yujie LI ,  Siqi TAN ,  Qilin CHEN

IPC: G06F3/04845 ,  G06F3/0488

CPC classification number: G06F3/04845 ,  G06F3/0488 ,  G06F2203/04806

Abstract: The present disclosure relates to a display method and a display apparatus for image-text content, a storage medium, and a computer program product. The display method for image-text content includes: displaying image-text content in a feed, where the image-text content comprises an image and a truncated text; receiving an operation performed by a user on the image of the image-text content; and displaying a detail page of the image-text content in response to the operation performed by the user on the image of the image-text content being a specified operation, the detail page comprising the image and a full text.

公开(公告)号：US20240354368A1

公开(公告)日：2024-10-24

申请号：US18643872

申请日：2024-04-23

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

Inventor： Longfei BAI ,  Qi CHEN ,  Zhitao YANG ,  Zhilin XU ,  Yimin CHEN ,  Shan LU ,  Jian WANG

IPC: G06F17/16

CPC classification number: G06F17/16

Abstract: A method and a system for performing a matrix multiplication operator using a unit supporting convolution operator operation, an electronic device, and a non-transitory storage medium are provided. The method includes: transforming a first matrix of the matrix multiplication operator to an input data matrix of a convolution operator; transforming a second matrix of the matrix multiplication operator to a weight matrix of the convolution operator, matrix multiplication being performed on the first matrix and the second matrix; and performing a convolution operation on the input data matrix and the weight matrix, which are obtained through transforming, of the convolution operator using the unit supporting convolution operator operation to obtain an operation result of the matrix multiplication operator.

公开(公告)号：US20240348846A1

公开(公告)日：2024-10-17

申请号：US18757292

申请日：2024-06-27

Applicant: Lemon Inc.

Inventor： Yufan XUE ,  Jie HE ,  Ye YUAN ,  Xiaojie LI ,  Yue GAO

IPC: H04N21/2368 ,  H04N21/234 ,  H04N21/439 ,  H04N21/81

CPC classification number: H04N21/2368 ,  H04N21/23418 ,  H04N21/23424 ,  H04N21/4394 ,  H04N21/8113

Abstract: A video generating method includes acquiring video materials from an initial collection which comprises user-related videos, acquiring a target audio material serving as background music, performing image feature extraction on video frames of each video material, and performing segmentation processing according to image feature information corresponding to each video frame to acquire a target video segment corresponding to the video material, and merging the target video segment and the corresponding target audio material to generate a target video. The target video includes video segments which are obtained based on the target video segments respectively, the video segments in the target video are played in order of post time, and time lengths of the video segments are matched with time lengths of corresponding musical phrases in the target audio material.

公开(公告)号：US20240345620A1

公开(公告)日：2024-10-17

申请号：US18634421

申请日：2024-04-12

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

Inventor： Weifeng DONG ,  Jincai YE ,  Yuanlin CHENG ,  Pengfei LIU ,  Xinxia JIA ,  Shan LU ,  Jian WANG

IPC: G06F1/12

CPC classification number: G06F1/12

Abstract: A chip, a chip system, and a timestamp synchronization method. The chip is configured to be in communication connection to another chip, and includes a signal generating module, a first signal response module and a first delay module. The signal generating module is configured to generate a synchronization request signal and transmit the synchronization request signal to the first signal response module and the another chip, so that the another chip records a second timestamp of the another chip in response to receiving the synchronization request signal. The first delay module is configured to perform delay processing on the synchronization request signal to obtain a delayed synchronization request signal. The first signal response module is configured to record a first timestamp of the chip in response to receiving the delayed synchronization request signal, wherein the first timestamp and the second timestamp are used for performing a timestamp synchronization operation.

公开(公告)号：US12113995B2

公开(公告)日：2024-10-08

申请号：US17714024

申请日：2022-04-05

Applicant: Lemon Inc.

Inventor： Yue Li ,  Li Zhang ,  Kai Zhang

IPC: H04N19/436 ,  H04N19/124 ,  H04N19/132 ,  H04N19/157 ,  H04N19/70 ,  H04N19/82

CPC classification number: H04N19/436 ,  H04N19/124 ,  H04N19/132 ,  H04N19/157 ,  H04N19/70 ,  H04N19/82

Abstract: A method of processing video data. The method includes determining that a supplemental enhancement information (SEI) message of a bitstream includes indicators specifying one or more neural network (NN) filter model candidates or selections for a video unit or samples within the video unit, and converting between a video media file comprising the video unit and the bitstream based on the indicators. A corresponding video coding apparatus and non-transitory computer readable medium are also disclosed.

公开(公告)号：US12112573B2

公开(公告)日：2024-10-08

申请号：US17402344

申请日：2021-08-13

Applicant: Lemon Inc.

Inventor： Michael Leong Hou Tay ,  Wanchun Ma ,  Shuo Cheng ,  Chao Wang ,  Linjie Luo

IPC: G06K9/00 ,  G06F18/21 ,  G06T7/246 ,  G06T13/40 ,  G06T13/80 ,  G06V10/24 ,  G06V40/16

CPC classification number: G06V40/176 ,  G06F18/2193 ,  G06T7/251 ,  G06T13/40 ,  G06T13/80 ,  G06V10/242 ,  G06V40/171 ,  G06T2207/20084 ,  G06T2207/30201

Abstract: The present disclosure describes techniques for facial expression recognition. A first loss function may be determined based on a first set of feature vectors associated with a first set of images depicting facial expressions and a first set of labels indicative of the facial expressions. A second loss function may be determined based on a second set of feature vectors associated with a second set of images depicting asymmetric facial expressions and a second set of labels indicative of the asymmetric facial expressions. The first loss function and the second loss function may be used to determine a maximum loss function. The maximum loss function may be applied during training of a model. The trained model may be configured to predict at least one asymmetric facial expression in a subsequently received image.