Patents by Inventor JUNJIE ZHAI
JUNJIE ZHAI has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).
-
Patent number: 11900069Abstract: A translation model training method for a computer device includes obtaining a training sample set, the training sample set including a plurality of training samples. Each training sample is a training sample pair having a training input sample in a first language and a training output sample in a second language. The method also includes determining a disturbance sample set corresponding to each training sample in the training sample set, the disturbance sample set comprising at least one disturbance sample, and a semantic similarity between the disturbance sample and the corresponding training sample being greater than a first preset value; and training an initial translation model by using the plurality of training samples and the disturbance sample set corresponding to each training sample to obtain a target translation model, such that the training output sample remains same for the disturbance sample and the corresponding training sample.Type: GrantFiled: August 7, 2020Date of Patent: February 13, 2024Assignee: TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITEDInventors: Yong Cheng, Zhaopeng Tu, Fandong Meng, Junjie Zhai, Yang Liu
-
Patent number: 11710054Abstract: The present disclosure discloses a method, apparatus, and server for information recommendation. Search behavior data, browsing behavior data, and click behavior data on recommended content of a specified user in a forum are acquired. A preprocessing on the search behavior data, the browsing behavior data, and the click behavior data on recommended content is performed respectively to obtain a first recommendation result, a second recommendation result, and a third recommendation result. Distribution and integration on the first recommendation result, the second recommendation result, and the third recommendation result are performed according to weights to obtain recommended content to be recommended to the specified user. Search behavior data, browsing behavior data, and click behavior data on recommended content are taken into comprehensive consideration, data used in recommendation is enriched, and accuracy of recommendation is improved.Type: GrantFiled: February 28, 2019Date of Patent: July 25, 2023Assignee: TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITEDInventors: Conglei Yao, Junjie Zhai, Liang Wang, Quan Wen, Yanan Li
-
Publication number: 20210181142Abstract: Various embodiments are directed to an electrochemical vinyl chloride sensor configured to detect a volume of vinyl chloride present within the volume of ambient gas. The electrochemical vinyl chloride sensor comprises a housing comprising an opening configured to receive a volume of ambient gas and an interior reservoir fluidly connected to the opening; and a plurality of electrodes fixedly disposed within the interior reservoir of the housing. The plurality of electrodes comprises a sensing electrode, a counter electrode, and a reference electrode, at least one of which comprises a catalytic material having an amorphous structure. A bias voltage of at least approximately less than 300 mV (e.g., 200 mV) applied between the sensing electrode and the reference electrode. The plurality of electrodes comprises a three-electrode stack configured such that the counter electrode is disposed between the sensing electrode and the reference electrode.Type: ApplicationFiled: September 25, 2020Publication date: June 17, 2021Inventors: Lei Xiao, Yifan Ye, Junjie Zhai, Gary Arthur Norval Paxton, Fang Wang, Yan Zhou
-
Publication number: 20200364412Abstract: A translation model training method for a computer device includes obtaining a training sample set, the training sample set including a plurality of training samples. Each training sample is a training sample pair having a training input sample in a first language and a training output sample in a second language. The method also includes determining a disturbance sample set corresponding to each training sample in the training sample set, the disturbance sample set comprising at least one disturbance sample, and a semantic similarity between the disturbance sample and the corresponding training sample being greater than a first preset value; and training an initial translation model by using the plurality of training samples and the disturbance sample set corresponding to each training sample to obtain a target translation model, such that the training output sample remains same for the disturbance sample and the corresponding training sample.Type: ApplicationFiled: August 7, 2020Publication date: November 19, 2020Inventors: Yong CHENG, Zhaopeng TU, Fandong MENG, Junjie ZHAI, Yang LIU
-
Publication number: 20190197416Abstract: The present disclosure discloses a method, apparatus, and server for information recommendation. Search behavior data, browsing behavior data, and click behavior data on recommended content of a specified user in a forum are acquired. A preprocessing on the search behavior data, the browsing behavior data, and the click behavior data on recommended content is performed respectively to obtain a first recommendation result, a second recommendation result, and a third recommendation result. Distribution and integration on the first recommendation result, the second recommendation result, and the third recommendation result are performed according to weights to obtain recommended content to be recommended to the specified user. Search behavior data, browsing behavior data, and click behavior data on recommended content are taken into comprehensive consideration, data used in recommendation is enriched, and accuracy of recommendation is improved.Type: ApplicationFiled: February 28, 2019Publication date: June 27, 2019Inventors: CONGLEI YAO, JUNJIE ZHAI, LIANG WANG, QUAN WEN, YANAN LI
-
Patent number: 10268960Abstract: The present disclosure discloses a method, apparatus, and server for information recommendation. Search behavior data, browsing behavior data, and click behavior data on recommended content of a specified user in a forum are acquired. A preprocessing on the search behavior data, the browsing behavior data, and the click behavior data on recommended content is performed respectively to obtain a first recommendation result, a second recommendation result, and a third recommendation result. Distribution and integration on the first recommendation result, the second recommendation result, and the third recommendation result are performed according to weights to obtain recommended content to be recommended to the specified user. Search behavior data, browsing behavior data, and click behavior data on recommended content are taken into comprehensive consideration, data used in recommendation is enriched, and accuracy of recommendation is improved.Type: GrantFiled: April 3, 2015Date of Patent: April 23, 2019Assignee: TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITEDInventors: Conglei Yao, Junjie Zhai, Liang Wang, Quan Wen, Yanan Li
-
Patent number: 9241242Abstract: An information recommendation method is provided for a terminal. The method includes obtaining at least one keyword, obtaining geographical location information corresponding to the keyword, and searching, within a range of a map interface display area, recommendation information relevant to geographical locations adjacent to the geographical location corresponding to the geographical location information. The method also includes displaying, according to the range of the map interface display area, geographical location information corresponding to the keyword, as well as the map interface having the recommendation information.Type: GrantFiled: May 18, 2014Date of Patent: January 19, 2016Assignee: TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITEDInventors: Gang Cheng, Xuan Pan, Ziming Zhuang, He Li, Fang Lu, Gudan Wang, Yiyang Liu, Junjie Zhai, Boyu Qiu, Jianqun Chen
-
Publication number: 20150213368Abstract: The present disclosure discloses a method, apparatus, and server for information recommendation. Search behavior data, browsing behavior data, and click behavior data on recommended content of a specified user in a forum are acquired. A preprocessing on the search behavior data, the browsing behavior data, and the click behavior data on recommended content is performed respectively to obtain a first recommendation result, a second recommendation result, and a third recommendation result. Distribution and integration on the first recommendation result, the second recommendation result, and the third recommendation result are performed according to weights to obtain recommended content to be recommended to the specified user. Search behavior data, browsing behavior data, and click behavior data on recommended content are taken into comprehensive consideration, data used in recommendation is enriched, and accuracy of recommendation is improved.Type: ApplicationFiled: April 3, 2015Publication date: July 30, 2015Inventors: CONGLEI YAO, JUNJIE ZHAI, LIANG WANG, QUAN WEN, YANAN LI
-
Publication number: 20140315584Abstract: An information recommendation method is provided for a terminal. The method includes obtaining at least one keyword, obtaining geographical location information corresponding to the keyword, and searching, within a range of a map interface display area, recommendation information relevant to geographical locations adjacent to the geographical location corresponding to the geographical location information. The method also includes displaying, according to the range of the map interface display area, geographical location information corresponding to the keyword, as well as the map interface having the recommendation information.Type: ApplicationFiled: May 18, 2014Publication date: October 23, 2014Applicant: TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITEDInventors: GANG CHENG, XUAN PAN, ZIMING ZHUANG, HE LI, FANG LU, GUDAN WANG, YIYANG LIU, JUNJIE ZHAI, BOYU QIU, JIANQUN CHEN