公开(公告)号：US20240248794A1

公开(公告)日：2024-07-25

申请号：US18582524

申请日：2024-02-20

Applicant: Lemon Inc.

Inventor： Peng XU ,  Fei LIU ,  Kyoungryun BAE ,  Hao WANG ,  Ming LIN ,  Wei TANG ,  Sheng QIU ,  Yang LIU

IPC: G06F11/10

CPC classification number: G06F11/1004 ,  G06F11/1068

Abstract: A computing device for verifying data integrity is provided, comprising a memory controller configured to receive a plurality of original data blocks. Each original data block has an associated initial CRC value. The memory controller then segments and recombines the received data blocks into logic blocks, and calculates a new logic block CRC value for each logic block. The logic blocks are transmitted with their respective new logic block CRC values to a storage device, and the logic blocks are written to non-volatile memory of the storage device in a write operation. After the write operation, a combined CRC value is calculated for the logic blocks and a combined CRC value for the original data blocks, and compare the combined CRC values. The memory controller determines whether the combined CRC values match. When they match, the memory controller generates a verification response verifying the integrity of the write operation.

公开(公告)号：US20240233350A1

公开(公告)日：2024-07-11

申请号：US18408967

申请日：2024-01-10

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

Inventor： Xiaojie JIN ,  Fan MA ,  Jiashi FENG ,  Heng WANG ,  Jingjia HUANG

IPC: G06V10/80 ,  G06F40/284 ,  G06V10/774 ,  G06V20/40

CPC classification number: G06V10/806 ,  G06F40/284 ,  G06V10/774 ,  G06V20/46

Abstract: The embodiments of the disclosure provides a processing method, apparatus, electronic device and non-transitory computer-readable storage medium for multimodal data, wherein the method includes: obtaining data to be processed of an original modality; determining result data of a target modality corresponding to the data to be processed by processing the data to be processed with a target processing model; wherein the target processing model comprises a multimodal submodel, and the pre-training task of the multimodal submodel includes a task of locating local data that matches second modal data from first modal data; wherein when the first modal data belongs to the original modality, the second modal data belongs to the target modality; when the first modal data belongs to the target modality, the second modal data belongs to the original modality.

公开(公告)号：US20240233070A1

公开(公告)日：2024-07-11

申请号：US18406910

申请日：2024-01-08

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

Inventor： Xiaojie JIN ,  Bowen ZHANG ,  Jiashi FENG

IPC: G06T3/40 ,  G06V10/77 ,  G06V10/82

CPC classification number: G06T3/40 ,  G06V10/7715 ,  G06V10/82

Abstract: Embodiments of the disclosure disclose a method, apparatus, electronic device and storage medium for multi-modal data processing, wherein the method includes: acquiring data of original modality; and processing the data of the original modality by a target processing model to determine data of target modality corresponding to the data of the original modality; wherein the target processing model comprises a multi-modal pre-trained sub-model and a multi-modal feature correction sub-model; a training process of the target processing model comprises training the multi-modal feature correction sub-model with parameters of the multi-modal pre-training sub-model fixed.

公开(公告)号：USD1034640S1

公开(公告)日：2024-07-09

申请号：US29818922

申请日：2021-12-10

Applicant: Lemon Inc.

Designer： Tianzi Yuan ,  Ling Zhong

Abstract: FIG. 1 is a front view of a first image in a sequence for a display screen or portion thereof with an animated graphical user interface showing the new design;
FIG. 2 is a front view of a second image thereof; and,
FIG. 3 is a front view of a third image thereof.
The outermost broken line rectangle illustrates a display screen or portion thereof and forms no part of the claimed design. The remaining broken lines illustrate portions of the animated graphical user interface that form no part of the claimed design.
The appearance of the transitional image sequentially transitions between the images shown in FIGS. 1-3. The process or period in which one image transitions to another forms no part of the claimed design.

公开(公告)号：US20240220641A1

公开(公告)日：2024-07-04

申请号：US18565962

申请日：2022-07-15

Applicant: Lemon Inc.

Inventor： Jiankai SUN ,  Xin YANG ,  Aonan ZHANG ,  Weihao GAO ,  Junyuan XIE ,  Chong WANG

IPC: G06F21/60 ,  G06N20/00

CPC classification number: G06F21/602 ,  G06N20/00

Abstract: The present disclosure relates to a data protection method, apparatus, medium and electronic device. The method comprises: obtaining a specified batch of reference samples of an active participant of a joint training model; determining generation gradient information of the first reference sample; determining target gradient information sent to the passive participant according to the generation gradient information, and sending the target gradient information to the passive participant, to update, by the passive participant, parameters of the joint training model according to the target gradient information. Through the above solution, the influence of the generated data on the training process and model performance of the joint training model is avoided as much as possible, and the privacy and security of data are improved.

公开(公告)号：US12026198B2

公开(公告)日：2024-07-02

申请号：US17384576

申请日：2021-07-23

Applicant: LEMON INC.

Inventor： Minz Won ,  Keunwoo Choi ,  Yuanjian Feng

IPC: G06F17/00 ,  G06F16/65 ,  G06F16/683 ,  G06N3/08 ,  G10G1/00 ,  G10H1/00

CPC classification number: G06F16/683 ,  G06F16/65 ,  G06N3/08 ,  G10G1/00 ,  G10H1/0025

Abstract: The present disclosure describes techniques for identifying music attributes. The described techniques comprises receiving audio data of a piece of music; determining at least one attribute of the piece of music based on the audio data of the piece of music using a model; the model comprising a convolutional neural network and a transformer; the model being pre-trained using training data, wherein the training data comprise labelled data associated with a first plurality of music samples and unlabelled data associated with a second plurality of music samples, the labelled data comprise audio data of the first plurality of music samples and label information indicative of attributes of the first plurality of music samples, and the unlabelled data comprise audio data of the second plurality of music samples.

公开(公告)号：USD1029870S1

公开(公告)日：2024-06-04

申请号：US29815601

申请日：2021-11-15

Applicant: Lemon Inc.

Designer： Yining Zhou ,  Yue Chen ,  Ling Zhong

Abstract: The FIGURE is a front view of a display screen or portion thereof with a graphical user interface showing our new design.
The outermost broken line rectangle illustrates a display screen or portion thereof and forms no part of the claimed design. The remaining broken lines illustrate portions of the graphical user interface that form no part of the claimed design.

公开(公告)号：US12002491B2

公开(公告)日：2024-06-04

申请号：US17566342

申请日：2021-12-30

Applicant: Lemon Inc.

Inventor： Maryyann Crichton ,  Nite Luo ,  Xinglun Liang ,  Josiah John Serrano ,  Lakshminarayanan Vijayaraghavan ,  Deepak Ramalingam

IPC: G06F3/048 ,  G06F9/445 ,  G06T19/00 ,  G11B27/031

CPC classification number: G11B27/031 ,  G06F9/44505 ,  G06T19/006

Abstract: The present disclosure describes techniques for designing effects. A first window comprising a first copy of a first scene may be created. The first scene comprises a first visual effect. A second window comprising a second copy of the first scene may be created. The first window and the second window are configured to enable testing and comparison of different versions of the first visual effect in the first scene at an approximately same time. The first copy of the first scene in the first window may be modified based on a first change to at least one attribute of the first visual effect in the first copy of the first scene. The second copy of the first scene in the second window may be modified based on a second change to at least one attribute of the first visual effect in the second copy of the first scene.

公开(公告)号：US20240170103A1

公开(公告)日：2024-05-23

申请号：US18185760

申请日：2023-03-17

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

Inventor： Hung Pham ,  Dingshun Lv

IPC: G16C10/00 ,  G06N10/70

CPC classification number: G16C10/00 ,  G06N10/70

Abstract: Example embodiments of the present disclosure relate to a solution for ph-AFQMC with direct product multi-Slater determinants trial. Multiple active spaces of a molecular system may be obtained and multiple coefficient tensors may be determined respectively. A composite coefficient tensor may be determined based on a tensor product of the multiple coefficient tensors of the multiple active spaces, and a trial wave function may be further determined based on the composite coefficient tensor and a cutoff value. As such, the multiple coefficient tensors for the multiple active spaces may be determined, thus the computation can be reduced. Additionally, since a cutoff value is used, the composite coefficient tensor is a sparse tensor and the number of Slater determinants may be reduced. Further, the determined trial wave function may be further used in a ph-AFQMC algorithm, and a balance between accuracy and efficiency may be achieved.

公开(公告)号：US20240169479A1

公开(公告)日：2024-05-23

申请号：US18056444

申请日：2022-11-17

Applicant: Lemon Inc.

Inventor： Wei Min Wang ,  Daquan Zhou ,  Jiashi Feng

IPC: G06T3/40

CPC classification number: G06T3/4007 ,  G06T3/4053

Abstract: The present disclosure provides systems and methods for video generation using latent diffusion machine learning models. Given a text input, video data relevant to the text input can be generated using a latent diffusion model. The process includes generating a predetermined number of key frames using text-to-image generation tasks performed within a latent space via a variational auto-encoder, enabling faster training and sampling times compared to pixel space-based diffusion models. The process further includes utilizing two-dimensional convolutions and associated adaptors to learn features for a given frame. Temporal information for the frames can be learned via a directed temporal attention module used to capture the relation among frames and to generate a temporally meaningful sequence of frames. Additional frames can be generated via a frame interpolation process for inserting one or more transition frames between two generated frames. The process can also include a super-resolution process for upsampling the frames.