-
公开(公告)号：US10810379B2
公开(公告)日：2020-10-20
申请号：US16286444
申请日：2019-02-26
Applicant: Alibaba Group Holding Limited
Inventor： Xiaodong Zeng , Weihua Luo , Feng Lin
IPC: G06F17/28 , G06F40/44 , G06F40/30 , G06F40/55 , G06F40/205
Abstract: A statistics-based machine translation method is disclosed. The method generates probabilities of translation from a sentence to be translated to candidate translated texts based on features of the candidate translated texts that affect the probabilities of translation and a pre-generated translation probability prediction model. The features that affect probabilities of translation include at least degrees of semantic similarity between the sentence to be translated and the candidate translated texts. A preset number of candidate translated texts with highly ranked probabilities of translation are selected to serve as translated texts of the sentence to be translated. The method is able to go deep into a semantic level of a natural language when a machine translation model is constructed to avoid a semantic deviation of a translated text from an original text, thereby achieving the effect of improving the quality of translation.
-
公开(公告)号：US20200234077A1
公开(公告)日：2020-07-23
申请号：US16841467
申请日：2020-04-06
Applicant: Alibaba Group Holding Limited
Inventor： Linqing Wang , Xiaodong Zeng , Hong Zhang , Feng Lin
Abstract: A method includes: receiving, at a server and from an augmented reality device, user information of a user using the augmented reality device; generating, by the server, a picture feature sample sub-library corresponding to the user information, including screening out, from a preset picture feature sample library, picture feature samples associated with the user information; and providing, to the augmented reality device, the picture feature sample sub-library, wherein the picture feature sample sub-library can be configured to be used by the augmented reality device to perform, during image scanning of an offline environment of the user, image recognition of images scanned from the offline environment by comparing the scanned images to picture features in the picture feature sample sub-library.
-
公开(公告)号：US10706874B2
公开(公告)日：2020-07-07
申请号：US16380609
申请日：2019-04-10
Applicant: Alibaba Group Holding Limited
Inventor： Lei Jiao , Yanchu Guan , Xiaodong Zeng , Feng Lin
Abstract: An audio signal is obtained by a user terminal. The audio signal is divided into a plurality of short-time energy frames based on a frequency of a predetermined voice signal. Energy of each short-time energy frame is determined. Based on the energy of each short-time energy frame, whether the audio signal includes a voice signal is determined.
-
公开(公告)号：US10437973B2
公开(公告)日：2019-10-08
申请号：US15782747
申请日：2017-10-12
Applicant: Alibaba Group Holding Limited
Inventor： Jun Wu , Xiaodong Zeng , Huanmi Yin , Feng Lin
Abstract: Interaction characteristics of a user interacting with a virtual reality (VR) terminal are obtained through preset sensing hardware in response to a request for execution of a target task requiring user identity verification. The obtained interaction characteristics of the user are compared with preset interaction characteristics of an authorized user of the VR terminal to verify identity of the user. The target task is executed and the user is authenticated as an identity-verified user of the VR terminal based on a successful user identity verification.
-
公开(公告)号：US20190278997A1
公开(公告)日：2019-09-12
申请号：US16422798
申请日：2019-05-24
Applicant: Alibaba Group Holding Limited
Inventor： Huanmi Yin , Xiaodong Zeng , Feng Lin , Jun Wu
Abstract: A method for offline-service multi-user interaction based on augmented reality (AR) includes scanning, by an AR client terminal of a user, an offline service label at an offline service site. Information of the offline service label is transmitted to a server terminal. Based on the information of the offline service label, the server terminal establishes a service group including the user and a second user that scanned the offline service label. In response to transmitting the information of the offline service label, service data is received from the server terminal. The service data includes information related to the user and information related to the second user. Based on the service data, a service interactive interface is outputted. The service interactive interface displays the information related to the user and the information related to the second user at a position corresponding to the offline service label in an AR scene.
-
Patent Agency Ranking
公开(公告)号：US10255275B2
公开(公告)日：2019-04-09
申请号：US15247690
申请日：2016-08-25
Applicant: Alibaba Group Holding Limited
Inventor： Kai Song , Feng Lin , Weihua Luo
Abstract: Implementations herein relate to methods and devices for generating candidate translations and for quantizing text as well as words. A method may include generating, by a computing device, pending candidate translations of text to be translated based on predetermined translation rules. The computing device may generate translation probabilities from the text to be translated to the pending candidate translations based on features having impacts on translation probabilities of the pending candidate translations and a predetermined translation probability prediction model. The computing device may then select a predetermined number of pending candidate translations that have the translation probabilities higher than other pending candidate translations in the pending candidate translations to be the candidate translations of the text to be translated. In implementations, the features having impacts on the translation probabilities may include degrees of semantic similarity between the text to be translated and the candidate translations.
-
公开(公告)号：US10180940B2
公开(公告)日：2019-01-15
申请号：US15273509
申请日：2016-09-22
Applicant: Alibaba Group Holding Limited
Inventor： Hongfei Jiang , Jun Lu , Weihua Luo , Feng Lin
Abstract: A translation method is disclosed herein. The method includes determining a target object to be translated, the target object including a plurality of elements; dividing the target object to be translated according to a language correspondence relationship to obtain at least one element set; determining a weight value of a second object corresponding to each first object in each element set according to the language correspondence relationship; determining a comparison value associated with each element set according to the determined weight value and selecting an element set with the maximum comparison value; determining a second object with the maximum weight value corresponding to each first object in the selected element set according to the correspondence relationship, combining all the determined second objects to form a translation content of the target object.
-
公开(公告)号：US10108607B2
公开(公告)日：2018-10-23
申请号：US15223950
申请日：2016-07-29
Applicant: Alibaba Group Holding Limited
Inventor： Kai Song , Weihua Luo , Feng Lin
Abstract: A machine translation method includes determining source language text to be translated and obtaining a translation rule table, which has been trained in advance, that includes multiple translation rules associated with the target language text and the source language text in multiple languages; determining candidate results of the target language text; and determine the target language text to be output based on the candidate results. During the translation, a specific language of the source language text need not to be specified by a user. The implementations improve accuracy of the translation, and avoid errors introduced from the process of language identification during recognizing unknown languages. The implementations avoid developing a translation engine for an individual source language of text to be translated for a certain target language, and therefore save development costs and computing resources.
-
公开(公告)号：US20180107816A1
公开(公告)日：2018-04-19
申请号：US15782747
申请日：2017-10-12
Applicant: Alibaba Group Holding Limited
Inventor： Jun Wu , Xiaodong Zeng , Huanmi Yin , Feng Lin
CPC classification number: G06F21/32 , G02B27/017 , G06F3/011 , G06F3/012 , G06F3/013 , G06F3/017 , G06F21/31 , G06F21/36 , G06F21/62 , H04L63/0861 , H04W12/00508
Abstract: Interaction characteristics of a user interacting with a virtual reality (VR) terminal are obtained through preset sensing hardware in response to a request for execution of a target task requiring user identity verification. The obtained interaction characteristics of the user are compared with preset interaction characteristics of an authorized user of the VR terminal to verify identity of the user. The target task is executed and the user is authenticated as an identity-verified user of the VR terminal based on a successful user identity verification.
-
公开(公告)号：US20180107814A1
公开(公告)日：2018-04-19
申请号：US15782672
申请日：2017-10-12
Applicant: Alibaba Group Holding Limited
Inventor： Jun Wu , Xiaodong Zeng , Huanmi Yin , Feng Lin
Abstract: A method for user identity authentication using virtual reality includes presenting one or more virtual elements on a virtual reality (VR) scenario of a VR application for initiating a service, identifying, using one or more sensors communicably coupled to the VR device, one or more interactive operations of a user of the VR device with the one or more virtual elements, determining whether the one or more interactive operations match one or more predetermined operations for selecting the one or more virtual elements to initiate the service and trigger biometric authentication for user identity authentication, invoking biometric authentication if the one or more interactive operations match one or more predetermined operations, presenting a virtual guidance in the VR scenario for guiding the user to perform the biometric authentication, and presenting a service interface to the user if the biometric authentication is successful.
-
-
-
-
-
-
-
-
-
Search Results
66
records
(took 0.032 seconds)
