Patents by Inventor Fandong Meng
Fandong Meng 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
-
Publication number: 20230231117Abstract: A negative electrode material that is used for a negative electrode of a lithium secondary battery containing a non-aqueous electrolyte solution, includes: a first layer that contains lithium metal as a negative electrode active material; and a second layer that is arranged on at least one surface of the first layer. The second layer consists of a compound represented by a general formula MxAy (M is an element selected from a group consisting of Al, In, Mg, Ag, Si, and Sn, and A is an element selected from a group consisting of O, N, P, and F, and 0.3<x/y<3). The second layer has a thickness of 100 nm or less.Type: ApplicationFiled: March 29, 2023Publication date: July 20, 2023Inventors: Yoshiki TAKAYANAGI, Takaya SAITO, Shuntaro MIYAKAWA, Yong CHE, Tsutomu TAKAHASHI, Fandong MENG
-
Patent number: 11681872Abstract: A language sequence labeling method and includes: reading a first embedding representation of a language sequence, the first embedding representation including a character-level word embedding representation, a pre-trained word embedding representation, and a global word embedding representation of the language sequence, the global word embedding representation referring to a global context representation of the language sequence; performing first depth transformation (DT) encoding on the first embedding representation based on a first DT recurrent neural network (RNN), to output a first hidden-layer state representation corresponding to each word in the language sequence; and decoding the first hidden-layer state representations of the language sequence, to obtain a labeling result of one or more elements in the language sequence.Type: GrantFiled: June 22, 2021Date of Patent: June 20, 2023Assignee: TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITEDInventors: Fandong Meng, Yijin Liu, Jinchao Zhang, Jie Zhou, Jinan Xu
-
Publication number: 20230082605Abstract: Disclosed in this application are a visual content dialog method performed by an electronic device. The method includes: acquiring an image feature of an input image and state vectors corresponding to first n rounds of historical question answering dialog, n being a positive integer; acquiring a question feature of a current round of questioning related to the input image; performing multimodal encoding on the image feature of the input image, the state vectors corresponding to the first n rounds of historical question answering dialog, and the question feature of the current round of questioning, to obtain a state vector corresponding to the current round of questioning; and performing multimodal decoding on the state vector corresponding to the current round of questioning and the image feature of the input image, to obtain an actual output answer corresponding to the current round of questioning.Type: ApplicationFiled: November 17, 2022Publication date: March 16, 2023Inventors: Feilong CHEN, Fandong Meng, Peng Li, Jie Zhou
-
Publication number: 20230028944Abstract: A dialogue generation method, a network training method and apparatus, a storage medium, and a device are provided. The method includes: predicting, based on a plurality of a plurality of pieces of candidate knowledge text in a first candidate knowledge set, a preliminary dialogue response of a first dialogue preceding text; processing the first dialogue preceding text based on the preliminary dialogue response to obtain a first dialogue preceding text vector; obtaining a piece of target knowledge text based on a probability value of the piece of target knowledge text of being selected to be used in generating a final dialogue response, the probability value being obtained based on the first dialogue preceding text vector; and generating the final dialogue response based on the first dialogue preceding text and the piece of target knowledge text.Type: ApplicationFiled: September 7, 2022Publication date: January 26, 2023Applicant: TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITEDInventors: Xiuyi CHEN, Fandong MENG, Peng LI, Jie ZHOU
-
Patent number: 11518161Abstract: The present invention discloses beer barrel printing equipment, including a stand, a first matrix and a second matrix, a locating component, a first beer barrel printing device, and a second beer barrel printing device; a plurality of first matrix mounting positions and second matrix mounting positions are respectively arranged on the first beer barrel printing device and the second beer barrel printing device; the first beer barrel printing device and the second beer barrel printing device respectively control one of the first matrix mounting positions and one of the second matrix mounting positions to move; in a state that the locating member of the locating component is inserted into a tooth slot of the locating gear, the first beer barrel printing device is unable to control the first matrix mounting positions to move and/or the second printing device is unable to control the second matrix mounting positions to move.Type: GrantFiled: October 20, 2021Date of Patent: December 6, 2022Assignee: Ningbo Major Draft Beer Equipment Co., Ltd.Inventors: Fandong Meng, Bangcai Luo
-
Publication number: 20220309088Abstract: A computer device acquires, based on a prior network and a posterior network of a dialogue model, at least two first dialogue features and at least two second dialogue features of a first dialogue. The computer device outputs, using the prior network, a probability distribution of dialogue features in accordance with the acquired dialogue features and estimates, using the posterior network, the probability distribution of the dialogue features output by the prior network. The computer device updates the dialogue model and updates the posterior network based on dialogue features of the first dialogue. The computer device also updates a discriminator in the dialogue model based on at least two first dialogue features and at least two second dialogue features of a second dialogue. In accordance with a determination that the dialogue model has satisfied a training end condition, the computer device determines that the dialogue model is a trained model.Type: ApplicationFiled: April 7, 2022Publication date: September 29, 2022Inventors: Jiao OU, Jinchao ZHANG, Yang FENG, Fandong MENG
-
Publication number: 20220266588Abstract: The present invention discloses beer barrel printing equipment, including a stand, a first matrix and a second matrix, a locating component, a first beer barrel printing device, and a second beer barrel printing device; a plurality of first matrix mounting positions and second matrix mounting positions are respectively arranged on the first beer barrel printing device and the second beer barrel printing device; the first beer barrel printing device and the second beer barrel printing device respectively control one of the first matrix mounting positions and one of the second matrix mounting positions to move; in a state that the locating member of the locating component is inserted into a tooth slot of the locating gear, the first beer barrel printing device is unable to control the first matrix mounting positions to move and/or the second printing device is unable to control the second matrix mounting positions to move.Type: ApplicationFiled: October 20, 2021Publication date: August 25, 2022Inventors: Fandong Meng, Bangcai Luo
-
Publication number: 20220245365Abstract: A computer device acquires a semantic association graph associated with n source statements belonging to different modals. The semantic association graph includes n semantic nodes of the different modals, a first connecting edge used for connecting the semantic nodes of a same modal and a second connecting edge used for connecting the semantic nodes of different modals. The computer device extracts a plurality of first word vectors from the semantic association graph. The device encodes the plurality of first word vectors to obtain n encoded feature vectors. The device also decodes the n encoded feature vectors to obtain a translated target statement.Type: ApplicationFiled: April 12, 2022Publication date: August 4, 2022Inventors: Fandong MENG, Yongjing YIN, Jinsong SU, Jie ZHOU
-
Patent number: 11346745Abstract: A fatigue test assessment method for assessing a suspension point of a cylinder block by means of a fatigue test includes: fixing a suspension point of a cylinder block test piece by using a power assembly installation approach; applying a load to the suspension point of the cylinder block test piece in a preset direction; and determining whether the suspension point of the cylinder block fails. The method can ascertain, by means of assessment during a stage of parts testing, whether the structural strength of a suspension point of a cylinder block meets user requirements, so as to predict and prevent breakage of and faults in the suspension point of the cylinder block, thereby enhancing overall test validity.Type: GrantFiled: September 3, 2018Date of Patent: May 31, 2022Assignee: WEICHAI POWER CO., LTD.Inventors: Fandong Meng, Tao Wei, Shuai Teng
-
Publication number: 20210319181Abstract: A language sequence labeling method and includes: reading a first embedding representation of a language sequence, the first embedding representation including a character-level word embedding representation, a pre-trained word embedding representation, and a global word embedding representation of the language sequence, the global word embedding representation referring to a global context representation of the language sequence; performing first depth transformation (DT) encoding on the first embedding representation based on a first DT recurrent neural network (RNN), to output a first hidden-layer state representation corresponding to each word in the language sequence; and decoding the first hidden-layer state representations of the language sequence, to obtain a labeling result of one or more elements in the language sequence.Type: ApplicationFiled: June 22, 2021Publication date: October 14, 2021Inventors: Fandong MENG, Yijin LIU, Jinchao ZHANG, Jie ZHOU, Jinan XU
-
Publication number: 20210294972Abstract: A data processing method includes: obtaining a to-be-detected text, and determining a context word set and a candidate substitute word set corresponding to a to-be-detected word in the to-be-detected text to be inputted into a pronoun resolution neural network for feature extraction; performing positive-example iteration processing and negative-example iteration processing on the features corresponding to the context word set and the candidate substitute word set, to obtain a positive-example feature vector length and a negative-example feature vector length, and calculating a substitute probability corresponding to each candidate substitute word in the candidate substitute word set according to the positive-example feature vector length and the negative-example feature vector length; determining a target substitute word according to the substitute probability corresponding to the each candidate substitute word; and inserting the target substitute word into the to-be-detected text according to a position corrType: ApplicationFiled: June 4, 2021Publication date: September 23, 2021Inventors: Jinchao ZHANG, Fandong MENG, Jie ZHOU
-
METHOD AND APPARATUS FOR GENERATING HIDDEN STATE IN RECURRENT NEURAL NETWORK FOR LANGUAGE PROCESSING
Publication number: 20210286953Abstract: A method and apparatus for generating a hidden state in a recurrent neural network for language processing are provided. The method includes: generating regional word vectors of at least two dimensions of a target word vector inputted at a first moment; combining the regional word vectors to obtain combined regional word vectors of at least two dimensions; performing aggregation transformation processing on the combined regional word vectors based on a feedforward neural network, to obtain an aggregated word vector corresponding to the target word vector; and generating a target hidden state corresponding to the target word vector based on the aggregated word vector.Type: ApplicationFiled: May 27, 2021Publication date: September 16, 2021Inventors: Fandong MENG, Jinchao ZHANG, Jie ZHOU -
Publication number: 20210174003Abstract: Embodiments of this disclosure disclose a sentence processing method and device. The method may include performing word segmentation operation on a source sentence to be encoded to obtain m words. The method may further include obtaining an ith word in the m words using an ith encoding processing node in the n encoding processing nodes, and obtaining an (i?1)th word vector from an (i?1)th encoding processing node. The method may further include performing linear operation and non-linear operation on the ith word and the (i?1)th word vector using the first unit of the ith encoding processing node to obtain an ith operation result, and outputting the ith operation result to the at least one second unit for processing to obtain an ith word vector. The method may further include generating, in response to obtaining m word vectors, a sentence vector according to the m word vectors.Type: ApplicationFiled: February 22, 2021Publication date: June 10, 2021Applicant: TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITEDInventors: Fandong MENG, Jinchao ZHANG, Jie ZHOU
-
Publication number: 20210055181Abstract: A fatigue test assessment method for assessing a suspension point of a cylinder block by means of a fatigue test includes: fixing a suspension point of a cylinder block test piece by using a power assembly installation approach; applying a load to the suspension point of the cylinder block test piece in a preset direction; and determining whether the suspension point of the cylinder block fails. The method can ascertain, by means of assessment during a stage of parts testing, whether the structural strength of a suspension point of a cylinder block meets user requirements, so as to predict and prevent breakage of and faults in the suspension point of the cylinder block, thereby enhancing overall test validity.Type: ApplicationFiled: September 3, 2018Publication date: February 25, 2021Inventors: Fandong Meng, Tao Wei, Shuai Teng
-
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: 20170351236Abstract: The present invention discloses a method and system for switching an operating state of a robot. The method comprises the following steps of: providing an excitation device for an opening terminal and an excitation device for a closing terminal on a mask of the robot; transmitting, by the excitation device, a mask state signal to a slave computer processor when the mask is opened or closed; by the slave computer processor, processing the received mask state signal and then transmitting the processed mask state signal to a master computer processor; and controlling, by the master computer processor, the switchover of the operating state of the robot according to the received processed mask state signal. With regard to the technical solutions of the present invention, through the opening and closing of a mask, the system of a robot can be in two operating states and perform different functions.Type: ApplicationFiled: July 22, 2016Publication date: December 7, 2017Applicant: Beijing Evolver Robotics Co., LTDInventors: Qingyun Xu, Ran Wei, Wei Wang, Fandong Meng, Jianhui Li, Jinwen Hou, Tao Qiao