-
公开(公告)号：US20210319185A1
公开(公告)日：2021-10-14
申请号：US16953426
申请日：2020-11-20
Inventor： Jun XU , Zeyang LEI , Zhengyu NIU , Hua WU , Haifeng WANG
IPC: G06F40/30
Abstract: A method for generating a conversation, an electronic device and a storage medium, which relate to the field of artificial intelligence, are disclosed. The method may include: acquiring conversation content to be replied; determining an event node matched with the conversation content from an event graph, the event graph being a pre-constructed directed graph and including event nodes corresponding to different events respectively, and sides between the event nodes indicating logical relationships between the different events; determining an event node for guiding reply generation from the event graph according to the matched event node and the connection mode among the event nodes; and generating conversation reply content according to the event node for guiding reply generation. With the technical solution, dialog coherent, informative, and engaging multi-turn conversation may be generated.
-
公开(公告)号：US20210287044A1
公开(公告)日：2021-09-16
申请号：US17104165
申请日：2020-11-25
Inventor： Long LI , Haifeng WANG , Weibao GONG
Abstract: A method for updating a parameter of a model, a distributed training system, and an electric device are related to a field of deep learning technologies. The method includes: obtaining a batch training period of batch training data to be trained for a model; increasing priorities of tasks ranked at the bottom in a sequence of gradient communication tasks for parameters of the model when the batch training period is greater than or equal to a preset period threshold; and performing a communication of gradients of the parameters and updating the parameters based on priorities of the gradient communication tasks for the parameters in the model.
-
公开(公告)号：US20210232775A1
公开(公告)日：2021-07-29
申请号：US17031569
申请日：2020-09-24
Inventor： Han ZHANG , Dongling XIAO , Yukun LI , Yu SUN , Hao TIAN , Hua WU , Haifeng WANG
IPC: G06F40/56
Abstract: The present disclosure proposes a language generation method and apparatus. The method includes: performing encoding processing on an input sequence by using a preset encoder to generate a hidden state vector corresponding to the input sequence; in response to a granularity category of a second target segment being a phrase, decoding a first target segment vector, the hidden state vector, and a position vector corresponding to the second target segment by using N decoders to generate N second target segments; determining a loss value based on differences between respective N second target segments and a second target annotated segment; and performing parameter updating on the preset encoder, a preset classifier, and the N decoders based on the loss value to generate an updated language generation model for performing language generation.
-
公开(公告)号：US20210192147A1
公开(公告)日：2021-06-24
申请号：US16868426
申请日：2020-05-06
Inventor： Ruiqing ZHANG , Chuanqiang ZHANG , Hao XIONG , Zhongjun HE , Hua WU , Zhi LI , Haifeng WANG
IPC: G06F40/40
Abstract: Embodiments of the present disclosure provide a method and an apparatus for translating a polysemy, and a medium. The method includes: obtaining a source language text; identifying and obtaining the polysemy from the source language text; inquiring related words corresponding to each interpretation of the polysemy; determining a target interpretation corresponding to the related words contained in the source language text; and translating the polysemy into the target interpretation.
-
公开(公告)号：US20220100786A1
公开(公告)日：2022-03-31
申请号：US17407320
申请日：2021-08-20
Inventor： Yuchen DING , Yingqi QU , Jing LIU , Kai LIU , Dou HONG , Hua WU , Haifeng WANG
Abstract: The present application discloses a method and apparatus for training a retrieval model, device and computer storage medium that relate to intelligent search and natural language processing technologies. An implementation includes: acquiring initial training data; performing a training operation using the initial training data to obtain an initial retrieval model; selecting texts with the correlation degrees with a query in the training data meeting a preset first requirement from candidate texts using the initial retrieval model; performing a training operation using the updated training data to obtain a first retrieval model; and selecting texts with the correlation degrees with the query in the training data meeting a preset second requirement from the candidate texts using the first retrieval model; and/or selecting texts with the correlation degrees with the query meeting a preset third requirement; and performing a training operation using the expanded training data to obtain a second retrieval model.
-
Patent Agency Ranking
公开(公告)号：US20220019744A1
公开(公告)日：2022-01-20
申请号：US17319189
申请日：2021-05-13
Inventor： Fei YU , Jiji TANG , Weichong YIN , Yu SUN , Hao TIAN , Hua WU , Haifeng WANG
Abstract: A multi-modal pre-training model acquisition method, an electronic device and a storage medium, which relate to the fields of deep learning and natural language processing, are disclosed. The method may include: determining, for each image-text pair as training data, to-be-processed fine-grained semantic word in the text; masking the to-be-processed fine-grained semantic words; and training the multi-modal pre-training model using the training data with the fine-grained semantic words masked.
-
公开(公告)号：US20210255896A1
公开(公告)日：2021-08-19
申请号：US17076346
申请日：2020-10-21
Inventor： Daxiang DONG , Haifeng WANG , Dianhai YU , Yanjun MA
Abstract: Embodiments of the present disclosure disclose a method for processing tasks in parallel, a device and a storage medium, and relate to a field of artificial intelligent technologies. The method includes: determining at least one parallel computing graph of a target task; determining a parallel computing graph and an operator scheduling scheme based on a hardware execution cost of each operator task of each of the at least one parallel computing graph in a cluster, in which the cluster includes a plurality of nodes for executing the plurality of operator tasks, and each parallel computing graph corresponds to at least one operator scheduling scheme; and scheduling and executing the plurality of operator tasks of the determined parallel computing graph in the cluster based on the determined parallel computing graph and the determined operator scheduling scheme.
-
公开(公告)号：US20210192151A1
公开(公告)日：2021-06-24
申请号：US16861750
申请日：2020-04-29
Inventor： Haifeng WANG , Hua Wu , Zhongjun He , Hao Xiong
Abstract: The present disclosure provides a method, apparatus, electronic device and readable storage medium for translation and relates to translation technologies. In the embodiments of the present disclosure, the at least one knowledge element is obtained according to associated information of content to be translated, and respective knowledge element in the at least one knowledge element comprise an element of the first language type and an element of the second language type so that the at least one knowledge element can be used to obtain a translation result of the content to be translated. Since the at least one knowledge element obtained in advance is taken as global information of the translation task of this time, it can be ensured that the translation result of the same content to be translated is consistent, thereby improving the quality of the translation result.
-
公开(公告)号：US20210192150A1
公开(公告)日：2021-06-24
申请号：US16926197
申请日：2020-07-10
Inventor： Ruiqing ZHANG , Chuanqiang ZHANG , Hao XIONG , Zhongjun HE , Hua WU , Haifeng WANG
IPC: G06F40/55 , G06F40/58 , G06F40/211
Abstract: Embodiments of the present disclosure provide a language conversion method and apparatus based on syntactic linearity and a non-transitory computer-readable storage medium. The method includes: encoding a source sentence to be converted by using a preset encoder to determine a first vector and a second vector corresponding to the source sentence; determining a current mask vector according to a preset rule, in which the mask vector is configured to modify vectors output by the preset encoder; determining a third vector according to target language characters corresponding to source characters located before a first source character; and decoding the first vector, the second vector, the mask vector, and the third vector by using a preset decoder to generate a target character corresponding to the first source character.
-
30.发明申请公开(公告)号：US20180321994A1
公开(公告)日：2018-11-08
申请号：US16039144
申请日：2018-07-18
Inventor： Yu MA , Weide ZHANG , Wei HE , Haifeng WANG , Yibing LIANG , Zhuo CHEN
CPC classification number: G06F9/546 , G06F11/3024 , G06F11/3055 , G06F2209/508 , Y10S901/50
Abstract: This disclosure discloses a method and apparatus for monitoring a message transmission frequency in a robot operating system. A specific implementation of the method includes: writing to-be-transmitted messages, into a pre-allocated memory; obtaining time points when the to-be-transmitted messages are written into the memory, and recording the time points in a preset time point list; determining a message transmission frequency within a preset time interval based on the time points in the time point list; and comparing the message transmission frequency with a preset message transmission frequency threshold, and generating monitoring information based on a comparing result. This implementation monitors the message transmission frequency of a process to thereby avoid information codes related to monitoring of each application from being added to the application so as to reduce the program debuging cost, and improve the monitoring efficiency.
-
-
-
-
-
-
-
-
-
Search Results
30
records
(took 0.032 seconds)
