-
公开(公告)号：US11010211B2
公开(公告)日：2021-05-18
申请号：US16349522
申请日：2016-11-15
发明人： Xi Chen , Benjamin Sun , Long Ding , Xiaoli Liu , Huifang Ji , Katsumi Take , Yiannis Paniaras , Qu Mo , Sirui Zhou , Qi Zhao
IPC分类号： G06F9/54 , G06F3/0484 , H04L29/08
摘要： In implementations of the subject matter described herein, a new approach for transferring content between applications is proposed. Generally speaking, in operation, a user can select an area on a user interface in order to cover content that the user wants to transfer. In response, the type of the content in the selected area will be identified. One or more options are then provided on the user interface based on the identified type, and each option may link to one or more applications. Upon a user's selection of an option, an application associated with the selected option is launched to process the content. In this way, the content can be effectively and efficiently processed across different applications, which will significantly improve the processing efficiency and user experience.
-
2.发明申请公开(公告)号：US20190370495A1
公开(公告)日：2019-12-05
申请号：US15994106
申请日：2018-05-31
发明人： Xi Chen
摘要： In an example embodiment, submitted confidential data of a certain cohort (e.g., title, region, organization) is augmented by modeling confidential data of a more generalized cohort based on peer organizations. The modeling may be performed using Bayesian modeling and the results used to infer confidential data values for the original cohort. The inferred confidential data values can then be used to generate statistical insights for display in a graphical user interface.
-
公开(公告)号：US10108726B2
公开(公告)日：2018-10-23
申请号：US15189777
申请日：2016-06-22
发明人： Matthew Robert Scott , Huihua Hou , Weipeng Liu , Hao Wei , Chiwei Che , Byron Huntley Changuion , Weijiang Xu , Xi Chen
摘要： An input method editor (IME) described herein couples scenarios of the input of the user with specific network services to offer more relevant and richer candidates for higher input productivity. Data relating to a computer application in which the input candidates are to be input and/or context relating to a user-submitted query is collected and analyzed to determine a scenario. The input candidates may include text candidates and rich candidates. The IME may select a scenario-tuned and type specific engine to identify the text candidates and/or rich candidates. The scenario-tuned text candidate engines leverage scenario-tuned language models and lexicons, and the scenario-tuned rich candidate engines leverage scenario-relevant web services, such as image, mapping, and video search, when available and appropriate.
-
公开(公告)号：US20240265202A1
公开(公告)日：2024-08-08
申请号：US18562905
申请日：2022-05-23
发明人： Zhiwei YU , Chin-Yew Lin , Xi Chen , Borje Karlsson , Jin-Ge Yao , Shuang Chen
IPC分类号： G06F40/274 , G06F40/279
CPC分类号： G06F40/274 , G06F40/279
摘要： According to implementations of the subject matter described herein, a solution is proposed for auto-suggesting. In this solution, a trigger indication for suggesting is provided based on an input sentence. In response to the trigger indication being confirmed, a suggestion for the sentence is provided and the suggestion comprises one or more rich objects. In response to a selection of the suggestion, supplementary information for supplementing the sentence is provided based on at least one selected rich object. In this way, various auto-suggestions comprising rich objects may be provided, and thus rich supplementary information may be provided to supplement the input sentence to enhance the user experience.
-
公开(公告)号：US11093560B2
公开(公告)日：2021-08-17
申请号：US16138587
申请日：2018-09-21
发明人： Kuang-Huei Lee , Gang Hua , Xi Chen , Houdong Hu , He Xiaodong
摘要： The present concepts relate to matching data of two different modalities using two stages of attention. First data is encoded as a set of first vectors representing components of the first data, and second data is encoded as a set of second vectors representing components of the second data. In the first stage, the components of the first data are attended by comparing the first vectors and the second vectors to generate a set of attended vectors. In the second stage, the components of the second data are attended by comparing the second vectors and the attended vectors to generate a plurality of relevance scores. Then, the relevance scores are pooled to calculate a similarity score that indicates a degree of similarity between the first data and the second data.
-
公开(公告)号：US20200349605A1
公开(公告)日：2020-11-05
申请号：US16401832
申请日：2019-05-02
发明人： Sahin C. Geyik , Florian Raudies , Xi Chen , Yu Wang , Wen Pu
摘要： The disclosed embodiments provide a system for performing calibration of response rates. During operation, the system obtains a position of a content item in a ranking of content items generated for delivery to a member of an online system and a predicted response rate by the member to the content item. Next, the system determines an updated response rate by the member to the content item based on the position of the content item in the ranking and dimensions associated with the predicted response rate and the ranking. The system then outputs the updated response rate for use in managing delivery of the content item.
-
7.发明授权公开(公告)号：US10719626B2
公开(公告)日：2020-07-21
申请号：US15994106
申请日：2018-05-31
发明人： Xi Chen
摘要： In an example embodiment, submitted confidential data of a certain cohort (e.g., title, region, organization) is augmented by modeling confidential data of a more generalized cohort based on peer organizations. The modeling may be performed using Bayesian modeling and the results used to infer confidential data values for the original cohort. The inferred confidential data values can then be used to generate statistical insights for display in a graphical user interface.
-
公开(公告)号：US10235355B2
公开(公告)日：2019-03-19
申请号：US15664631
申请日：2017-07-31
发明人： Dong Li , Xi Chen , Yoshiharu Sato , Keita Ooi
IPC分类号： G06F17/00 , G06F17/21 , G06F17/22 , G06F17/24 , G06F17/25 , G06F17/26 , G06F17/27 , G06F17/28 , G06F17/30 , G06F3/00 , G06F3/048
摘要： An input method editor (IME) is associated with a local user. Memory stores local data and a processor, coupled to the memory, is configured to receive input from a local, first user, obtain shared data associated with at least a remote, second user from a remote server and generate prediction candidates and conversion candidates based on the input provided by the local, first user and correlation of the input and the obtained shared data.
-
公开(公告)号：US20200349604A1
公开(公告)日：2020-11-05
申请号：US16401822
申请日：2019-05-02
发明人： Sahin C. Geyik , Xi Chen , Yu Wang , Keqing Liang , Wen Pu
摘要： The disclosed embodiments provide a system that performs pacing for balanced delivery. During operation, the system obtains predicted response rates associated with impressions of a content item delivered within an online system and a cost per action (CPA) for the content item. Next, the system determines an impression-based spending for the content item based on the predicted response rates and the CPA. The system then calculates a pacing score for the content item based on the impression-based spending. Finally, the system adjusts subsequent interactions with the content item based on the pacing score.
-
公开(公告)号：US20200019628A1
公开(公告)日：2020-01-16
申请号：US16036224
申请日：2018-07-16
发明人： Xi Chen , Houdong Hu , Li Huang , Jiapei Huang , Arun Sacheti , Linjun Yang , Rui Xia , Kuang-Huei Lee , Meenaz Merchant , Sean Chang Culatana
摘要： Representative embodiments disclose mechanisms to perform visual intent classification or visual intent detection or both on an image. Visual intent classification utilizes a trained machine learning model that classifies subjects in the image according to a classification taxonomy. The visual intent classification can be used as a pre-triggering mechanism to initiate further action in order to substantially save processing time. Example further actions include user scenarios, query formulation, user experience enhancement, and so forth. Visual intent detection utilizes a trained machine learning model to identify subjects in an image, place a bounding box around the image, and classify the subject according to the taxonomy. The trained machine learning model utilizes multiple feature detectors, multi-layer predictions, multilabel classifiers, and bounding box regression.
-
-
-
-
-
-
-
-
-
搜索结果
23 条记录 (耗时 0.025 秒)
