-
公开(公告)号：US11501431B2
公开(公告)日：2022-11-15
申请号：US16905079
申请日：2020-06-18
Inventor： Fen Xiao , Jia Chang , Xuan Zhou , Ke Zhou Yan , Cheng Jiang , Kuan Tian , Jian Ping Zhu
Abstract: An image processing method performed by a terminal is provided. A molybdenum target image is obtained, and a plurality of candidate regions are extracted from the molybdenum target image. In the molybdenum target image, a target region is marked in the plurality of candidate regions by using a neural network model obtained by deep learning training, a probability that a lump comprised in the target region is a target lump being greater than a first threshold, a probability that the target lump is a malignant tumor being greater than a second threshold, and the neural network model being used for indicating a mapping relationship between a candidate region and a probability that a lump comprised in the candidate region is the target lump.
-
公开(公告)号：US10580394B2
公开(公告)日：2020-03-03
申请号：US15824495
申请日：2017-11-28
Inventor： Fen Xiao
IPC: A63H5/00 , G10H1/36 , G11B27/031 , G11B27/10
Abstract: The present disclosure discloses a method, a client and a computer storage medium for processing information, wherein the method includes: triggering a first operation; downloading a first audio file and a first text file matching the first audio file in response to the first operation; partly truncating the first audio file to obtain a first audio clip according to first indication information for identifying a truncating start position and second indication information for identifying a truncating end position; triggering a second operation; playing the first audio clip and dynamically displaying a text information part in the first text file corresponding to the first audio clip synchronously in response to the second operation; acquiring voice information of a user while playing the first audio chip; and synthesizing the first audio clip and the voice information into a first acquisition result.
-
3.发明授权Method, device, and system for interacting with a virtual character in smart terminal 有权用于与智能终端中的虚拟角色交互的方法，设备和系统公开(公告)号：US09345967B2
公开(公告)日：2016-05-24
申请号：US14222550
申请日：2014-03-21
Inventor： Zhenwei Zhang , Ling Wang , Fen Xiao , Zhehui Wu
IPC: A63F13/12 , A63F13/211 , A63F13/65 , A63F13/216 , A63F13/213 , A63F13/332
CPC classification number: A63F13/211 , A63F13/213 , A63F13/216 , A63F13/332 , A63F13/65 , A63F2300/204 , A63F2300/8082 , G06F3/011 , H04W4/025
Abstract: A method, device, and system for interacting with a virtual character in a smart terminal are provided. The method can shoot and display a user reality scene image on a screen of the smart terminal, and superimpose the virtual character on the user reality scene image; acquire position of the smart terminal during movement; and determine whether change of the position of the smart terminal exceeds a preset threshold value, and if the change of the position of the smart terminal exceeds the preset threshold value, the method moves the virtual character in the user reality scene image according to the current position of the smart terminal. The interaction scene between the user and the virtual character is not a virtual scene but a true reality scene, both numbers and contents of the scenes are not limited, and the interaction efficiency in this manner is higher.
Abstract translation: 提供了一种用于与智能终端中的虚拟角色交互的方法，设备和系统。 该方法可以在智能终端的屏幕上拍摄和显示用户现实场景图像，并将虚拟角色叠加在用户现实场景图像上; 在运动期间获得智能终端的位置; 并且确定智能终端的位置的改变是否超过预设的阈值，并且如果智能终端的位置的改变超过预设的阈值，则该方法根据当前的用户现实场景图像移动虚拟角色 智能终端的位置。 用户和虚拟角色之间的交互场景不是虚拟场景，而是真实场景，场景的数量和内容都不受限制，以这种方式的交互效率更高。
-
公开(公告)号：US10553003B2
公开(公告)日：2020-02-04
申请号：US15189508
申请日：2016-06-22
Inventor： Zhenwei Zhang , Fen Xiao , Jingjing Liu , Wenpei Hou , Ling Wang , Zhehui Wu , Xinlei Zhang
IPC: G06T11/60 , G06F3/0484 , H04L12/58 , G06K9/00 , H04W84/12
Abstract: The present invention is applicable to the field of Internet, and provides an interactive method and apparatus based on a web picture. The method includes: obtaining a web picture including a human image; determining a region where a specific part of the human image in the web picture is located; receiving an interactive instruction in the region where the specific part is located, and generating the interactive information corresponding to the specific part. When receiving the interactive instruction in the region where the specific part is located, generating the interactive information corresponding to the specific part by determining the region where the specific part of the human image in the obtained web picture including the human image is located. The interactive method provided by the embodiment of the present invention is simple to operate, and the interactive manners are various.
-
公开(公告)号：US10127736B1
公开(公告)日：2018-11-13
申请号：US16034130
申请日：2018-07-12
Inventor： Zhenwei Zhang , Ling Wang , Fen Xiao , Zhehui Wu
Abstract: A method for performing interaction based on augmented reality is performed at a first mobile terminal. While rendering a real-time scene photographed by its camera, the first mobile terminal submits its current location a remote server and then receives, from the remote server, information of multiple mobile terminals. After calculating the distance and orientation relationships between the multiple mobile terminals and itself, the first mobile terminal selects a second mobile terminal whose distance and orientation relationship with the first mobile terminal satisfies a preset requirement and then renders one or more interactive icons of the second mobile terminal near a portion of the real-time scene corresponding to the second location of the second mobile terminal. Finally, the first mobile terminal performs a respective interaction with the second mobile terminal in response to a user selection of a respective one of the one or more interactive icons.
-
Patent Agency Ranking
公开(公告)号：US20180322707A1
公开(公告)日：2018-11-08
申请号：US16034130
申请日：2018-07-12
Inventor： Zhenwei Zhang , Ling Wang , Fen Xiao , Zhehui Wu
CPC classification number: G06T19/006 , G06K9/00671 , G06T11/00 , G06T2207/10004
Abstract: A method for performing interaction based on augmented reality is performed at a first mobile terminal. While rendering a real-time scene photographed by its camera, the first mobile terminal submits its current location a remote server and then receives, from the remote server, information of multiple mobile terminals. After calculating the distance and orientation relationships between the multiple mobile terminals and itself, the first mobile terminal selects a second mobile terminal whose distance and orientation relationship with the first mobile terminal satisfies a preset requirement and then renders one or more interactive icons of the second mobile terminal near a portion of the real-time scene corresponding to the second location of the second mobile terminal. Finally, the first mobile terminal performs a respective interaction with the second mobile terminal in response to a user selection of a respective one of the one or more interactive icons.
-
7.发明申请公开(公告)号：US20160300557A1
公开(公告)日：2016-10-13
申请号：US15187056
申请日：2016-06-20
Inventor： Fen Xiao
IPC: G10H1/36
CPC classification number: G10H1/365 , G10H2210/061 , G10H2210/091 , G10H2220/011 , G10H2220/106 , G11B27/10
Abstract: The present disclosure discloses a method, a client and a computer storage medium for processing information, wherein the method includes: triggering a first operation; downloading a first audio file and a first text file matching the first audio file in response to the first operation; partly truncating the first audio file to obtain a first audio clip according to first indication information for identifying a truncating start position and second indication information for identifying a truncating end position; triggering a second operation; playing the first audio clip and dynamically displaying a text information part in the first text file corresponding to the first audio clip synchronously in response to the second operation; acquiring voice information of a user while playing the first audio chip; and synthesizing the first audio clip and the voice information into a first acquisition result.
Abstract translation: 本公开公开了一种用于处理信息的方法，客户端和计算机存储介质，其中所述方法包括：触发第一操作; 响应于第一操作，下载与第一音频文件匹配的第一音频文件和第一文本文件; 部分地截断第一音频文件以根据用于识别截断开始位置的第一指示信息和用于识别截断结束位置的第二指示信息来获得第一音频剪辑; 触发第二次操作; 播放所述第一音频剪辑并响应于所述第二操作，同步地动态地显示与所述第一音频片段相对应的所述第一文本文件中的文本信息部分; 在播放第一音频芯片时获取用户的语音信息; 以及将所述第一音频剪辑和所述语音信息合成为第一采集结果。
-
公开(公告)号：US10863310B2
公开(公告)日：2020-12-08
申请号：US15791180
申请日：2017-10-23
Inventor： Zhenwei Zhang , Ling Wang , Fen Xiao , Zhehui Wu
Abstract: It is provided a method performed at a terminal for information interaction including the following steps: detecting current position and direction information of the terminal when the terminal shoots a scene image; determining an information search range of the terminal according to an image capture ability of the terminal; sending the current position and direction information and the information search range of the terminal to a server, wherein the server is configured to return, among a plurality of social information items published by one or more terminals on a social network platform, an information collection within the information search range and satisfying the position and direction information of the terminal; obtaining the scene image using the terminal; and displaying the information collection returned by the server along with the scene image.
-
公开(公告)号：US20200320701A1
公开(公告)日：2020-10-08
申请号：US16905079
申请日：2020-06-18
Inventor： Fen Xiao , Jia Chang , Xuan Zhou , Ke Zhou Yan , Cheng Jiang , Kuan Tian , Jian Ping Zhu
Abstract: An image processing method performed by a terminal is provided. A molybdenum target image is obtained, and a plurality of candidate regions are extracted from the molybdenum target image. In the molybdenum target image, a target region is marked in the plurality of candidate regions by using a neural network model obtained by deep learning training, a probability that a lump comprised in the target region is a target lump being greater than a first threshold, a probability that the target lump is a malignant tumor being greater than a second threshold, and the neural network model being used for indicating a mapping relationship between a candidate region and a probability that a lump comprised in the candidate region is the target lump.
-
公开(公告)号：US10049494B2
公开(公告)日：2018-08-14
申请号：US14371996
申请日：2014-07-11
Inventor： Zhenwei Zhang , Ling Wang , Fen Xiao , Zhehui Wu
Abstract: A method for performing interaction based on augmented reality is provided. The method includes obtaining an image of a real scene photographed by a first terminal; obtaining a first location of the first terminal and a second location of a second terminal, the first location including geographical coordinate and orientation of the first terminal; matching the first location with the second location; displaying, on the image of the real scene photographed by the first terminal, information of successfully matched second terminal; and interacting according to the displayed information of the second terminal. By the method, an image is formed by photographing a real scene, and information of the successfully matched second terminal is displayed on the image of the real scene photographed by the first terminal; then interactions are performed according to needs. Furthermore, a system for performing interaction based on augmented reality is provided.
-
-
-
-
-
-
-
-
-
Search Results
13
records
(took 0.018 seconds)
