公开(公告)号：EP3972269A1

公开(公告)日：2022-03-23

申请号：EP21197100.7

申请日：2021-09-16

Applicant: Lemon Inc.

Inventor： WANG, Ye-Kui

IPC: H04N21/854 ,  H04N21/218

Abstract: Systems, methods and apparatus for processing visual media data are described. One example method includes performing a conversion between visual media data and a visual media file that includes one or more tracks that store one or more bitstreams of the visual media data according to a format rule; wherein the one or more bitstreams include coded subpictures of the visual media data, and wherein the format rule specifies that a container of boxes of subpicture entity groups indicating rules for processing the coded subpictures is included in a file-level box.

公开(公告)号：EP4557180A1

公开(公告)日：2025-05-21

申请号：EP23210772.2

申请日：2023-11-17

Applicant: Lemon Inc. ,  Oxford University Innovation Limited

Inventor： TON, Jean-Francois ,  TAUFIQ, Muhammad Faaiz ,  DOUCET, Arnaud ,  CORNISH, John Robert Macaulay

IPC: G06N7/00 ,  G06N20/00

Abstract: A computer-implemented method of policy evaluation for a contextual decision-making policy, wherein the contextual decision-making policy is used to make one or more decisions, where the outcome of each decision depends upon a context in which the decision is made, the method comprising: obtaining an existing contextual decision-making policy; obtaining a first dataset of decisions made using the existing contextual decision-making context, wherein the first dataset further includes the respective outcome and context of each decision; obtaining a to-be-evaluated contextual decision-making policy; using machine learning to train an outcome model for the to-be-evaluated contextual decision-making policy, based on the existing contextual decision-making policy, the to-be-evaluated contextual decision-making policy and the first dataset; and estimating an expectation for the to-be-evaluated contextual decision-making policy, based on the outcome model.

公开(公告)号：EP4533286A1

公开(公告)日：2025-04-09

申请号：EP23816472.7

申请日：2023-05-11

Applicant: Lemon Inc.

Inventor： SINHA, Parth Vijay

IPC: G06F16/48 ,  G06F16/44

公开(公告)号：EP4529645A1

公开(公告)日：2025-04-02

申请号：EP23832013.9

申请日：2023-06-16

Applicant: Lemon Inc.

Inventor： WANG, Han ,  XIONG, Hongyu ,  CHEN, Zheng ,  ZHANG, Tianyu ,  FENG, Yiqi ,  GAO, Yuan ,  ZENG, Xiangyu ,  LI, Rui ,  LU, Qingyi ,  YANG, Yihan ,  ZHANG, Yu ,  LIU, Bin

IPC: G06F16/954 ,  G06F16/958

公开(公告)号：EP4527063A2

公开(公告)日：2025-03-26

申请号：EP23816474.3

申请日：2023-05-24

Applicant: Lemon Inc.

Inventor： DAHLMAN, Dustin

IPC: H04M1/7243 ,  G06F3/0484 ,  G06F16/71 ,  H04L65/40

公开(公告)号：EP4524951A2

公开(公告)日：2025-03-19

申请号：EP23803939.0

申请日：2023-05-08

Applicant: Lemon Inc.

Inventor： ZHANG, Yilin ,  LI, Bochen ,  THIO, Vibert ,  LIU, Shizhu ,  CHEN, Jitong ,  LI, Naihan ,  WANG, Yuping

IPC: G10H1/00 ,  G06F16/683

Abstract: The present disclosure relates to a song generation method, apparatus and system, and a storage medium. The method comprises: acquiring target lyric text input by a user; aligning the target lyric text with a singing melody of an initial song, and determining a correspondence between text units in the target lyric text and notes in the singing melody; performing speech synthesis on the target lyric text on the basis of the correspondence between the text units in the target lyric text and the notes in the singing melody, so as to obtain singing speech in which the target lyric text is sung with the singing melody; and then, combining the singing speech and accompaniment audio of the initial song, so as to generate a target song. Substantively, a user is allowed to write lyrics by himself/herself, and perform song creation on the basis of the lyrics written by the user himself/herself, a singing melody and accompaniment audio, thereby forming a complete and new song. In this way, even if a user does not have professional skills in music creation, the user can generate a song on the basis of lyrics written by the user, such that the efficiency and interest of creating a song by the user are improved.

公开(公告)号：EP4517733A2

公开(公告)日：2025-03-05

申请号：EP23796955.5

申请日：2023-04-27

Applicant: Lemon Inc.

Inventor： XUE, Yufan ,  ZHENG, Qiang ,  NIU, Dong ,  XU, Liangqin ,  WANG, Xiaochan ,  CHEN, Jitong ,  LI, Bochen ,  LI, Naihan

IPC: G10H1/00 ,  G10L13/02 ,  G06F3/048

Abstract: Embodiments of the present disclosure relates to a music generation method, apparatus and system, and a storage medium. In at least some embodiments of the present disclosure, in response to an operation of a user operation of triggering a music generation control, displaying a music generation interface comprising a text input box, a music generation control and a music configuration item, so that the user can input a custom text in the text input box and configure a music melody by means of the music configuration item; then in response to the user operation of triggering the music generation control, generating a voice on the basis of the custom text input by the user, and on the basis of the generated voice and the music melody configured by the user, generating music comprising the voice corresponding to the custom text.

公开(公告)号：EP4513886A1

公开(公告)日：2025-02-26

申请号：EP24736638.8

申请日：2024-05-24

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

Inventor： ZHANG, Bowei ,  LIU, Runyu ,  LI, Xiaokai

IPC: H04N23/667 ,  G06F3/01

Abstract: According to embodiments of the disclosure, a method and an apparatus for eye tracking are provided. The method comprises capturing a first image of an eye by a first camera; capturing a second image of the eye by a second camera; determining, based on information of an eye component in the first image and/or the second image, one of the first camera and the second camera as a main camera and the other one as an auxiliary camera; and controlling the main camera to operate at a power higher than that of the auxiliary camera. Therefore, the power consumption during the eye tracking may be reduced by switching between the main camera and the auxiliary camera.

公开(公告)号：EP4495785A1

公开(公告)日：2025-01-22

申请号：EP24184940.5

申请日：2024-06-27

Applicant: BEIJING YOUZHUJU NETWORK TECHNOLOGY CO. LTD. ,  Lemon Inc.

Inventor： XU, Zhilin ,  CHEN, Qi ,  BAI, Longfei ,  CHEN, Yimin ,  WANG, Jian

IPC: G06F12/04 ,  G06F5/01 ,  G06F7/06 ,  G06F7/26

Abstract: The present disclosure provides a data processing method and apparatus, an electronic device, and a storage medium. The data processing provided by the present disclosure includes: receiving a first request message (104) from a first device (101), where the first request message (104) includes a first address aligned with a first data length and a first size in a unit of the first data length; converting the first address into a second address aligned with a second data length, where the second data length is greater than the first data length; converting the first size into a second size in a unit of the second data length; and sending a second request message (105) to a second device (103), where the second request message (105) includes the second address and the second size. Based on the data processing method, format conversion is performed on a processing request, so that the processing request can be easily switched between different hardware, to improve overall processing efficiency.

公开(公告)号：EP4488879A1

公开(公告)日：2025-01-08

申请号：EP23183596.8

申请日：2023-07-05

Applicant: Lemon Inc.

Inventor： TON, Jean-Francois ,  YANG, Mengyue

IPC: G06N3/045 ,  G06N3/0455 ,  G06N3/047 ,  G06N3/088 ,  G06N3/094 ,  H04N21/482 ,  G06Q30/0241

Abstract: Present approach includes methods, computer readable medium, systems, devices for debiasing data. Debiased data is received by or for training a recommendation system. The present approach includes steps of receiving data comprising sensitive-correlated information; obtaining sensitivity representations of the sensitive-correlated information from the data using a plurality of neural networks trained in relation to a set of predetermined context features; deriving a learned representation from the sensitivity representations; and generating a balanced fair prediction from the recommendation system based on the learned representation.