Huawei Technologies Co., Limited

Zhengdong Lu

Hang Li

Qiang Yang

Wing Ki Leung

Lifeng Shang

Yangqiu Song

Yibo Zhang

Zhaopeng Tu

Xin Jiang

Shan He

Xiaohua Liu

Qiang Jiang

Piji Li

A method includes: obtaining a text entered by a user; determining at least one topic related to the text; determining a target dialogue robot from the plurality of dialogue robots based on the at least one topic related to the text and a predefined mapping relationship between a dialogue robot and a topic, where a target topic corresponding to the target dialogue robot is some or all of the at least one topic related to the text; allocating the text to the target dialogue robot; and obtaining a reply for the text from the target dialogue robot, where the reply is generated by the target dialogue robot based on at least one semantic understanding of the text.

Human-computer dialogue method and apparatus

A method for processing information by an intelligent agent and the intelligent agent, where the method comprises: a first intelligent agent sends a request message to a second intelligent agent, where the request message includes an invitation message or a recommendation message; the first intelligent agent receives a decision message fed back by the second intelligent agent, where the decision message is determined according to the invitation message or the recommendation message and a knowledge model of the second intelligent agent; and the first intelligent agent updates, according to the decision message, a knowledge model of the first intelligent agent or sends a notification message to a first user account corresponding to the first intelligent agent. By using these technical solutions, information on a social network may be learned and processed by means of interaction with another intelligent agent, thereby implementing mining of data on the social network.

Method for processing information by intelligent agent and intelligent agent

A method and neural network system for human-computer interaction, and user equipment are disclosed. According to the method for human-computer interaction, a natural language question and a knowledge base are vectorized, and an intermediate result vector that is based on the knowledge base and that represents a similarity between a natural language question and a knowledge base answer is obtained by means of vector calculation, and then a fact-based correct natural language answer is obtained by means of calculation according to the question vector and the intermediate result vector. By means of this method, a dialog and knowledge base-based question-answering are combined by means of vector calculation, so that natural language interaction can be performed with a user, and a fact-based correct natural language answer can be given according to the knowledge base.

Method and neural network system for human-computer interaction, and user equipment

A deep learning based dialog method, apparatus, and device are provided and belong to the field of artificial intelligence. The method includes: obtaining a to-be-replied statement, encoding the to-be-replied statement to obtain a first vector , where the first vector is a representation of the to-be-replied statement; obtaining dialog history information corresponding to the to-be-replied statement, and the attention vector is used to represent search intent; making each dialog statement interact with the attention vector, so as to extract information related to the search intent from the dialog statement to obtain a plurality of result vectors, generating a to-be-decoded vector based on the plurality of result vectors, and decoding the to-be-decoded vector to obtain a next word in the reply statement. In the method, the reply statement refers to a dialog history.

Deep learning based dialog method, apparatus, and device

An apparatus is pre-equipped with a plurality of dialogue robots, and each dialogue robot is configured to conduct a human-computer dialogue based on at least one topic. The method includes: obtaining a text entered by a user; determining at least one topic related to the text, and determining a target dialogue robot from the plurality of dialogue robots based on the at least one topic related to the text and a predefined mapping relationship between a dialogue robot and a topic, where a target topic corresponding to the target dialogue robot is some or all of the at least one topic related to the text; and allocating the text to the target dialogue robot and obtaining a reply for the text from the target dialogue robot, where the reply is generated by the target dialogue robot based on at least one semantic understanding of the text.

The present application relates to natural language processing and discloses a sequence conversion method. The method includes: obtaining a source sequence from an input signal; converting the source sequence into one or more source context vectors; obtaining a target context vector corresponding to each source context vector; combining the target context vectors to obtain the target sequence; and outputting the target sequence. A weight vector is applied on a source context vector and a reference context vector, to obtain a target context vector, wherein the weight of one or more elements in the source context vector associated with notional words or weight of a function word in the target context vector is increased. The source sequence and the target sequence are representations of natural language contents. The claimed process improves faithfulness of converting the source sequence to the target sequence.

Sequence conversion method and apparatus in natural language processing based on adjusting a weight associated with each word

A method and an apparatus for determining a semantic matching degree, where the method includes acquiring a first sentence and a second sentence, dividing the first sentence and the second sentence into x and y sentence fragments, respectively, performing a convolution operation on word vectors in each sentence fragment of the first sentence and word vectors in each sentence fragment of the second sentence to obtain a three-dimensional tensor, performing integration or screening on adjacent vectors in the one-dimensional vectors of x rows and y columns, until the three-dimensional tensor is combined into a one-dimensional target vector, and determining a semantic matching degree between the first sentence and the second sentence according to the target vector.

Method and apparatus for determining semantic matching degree

A multi-document summary generation method includes obtaining a candidate sentence set, training each candidate sentence in the candidate sentence set using a cascaded attention mechanism and an unsupervised learning model in a preset network model, to obtain importance of each candidate sentence, selecting, based on the importance of each candidate sentence, a phrase that meets a preset condition from the candidate sentence set as a summary phrase set, and obtaining a summary of a plurality of candidate documents based on the summary phrase set.

Multi-document summary generation method and apparatus, and terminal

A method and an apparatus for determining a semantic matching degree. The method includes acquiring a first sentence and a second sentence, dividing the first sentence and the second sentence into x and y sentence fragments, respectively, performing a convolution operation on word vectors in each sentence fragment of the first sentence and word vectors in each sentence fragment of the second sentence, to obtain a three-dimensional tensor, performing integration and/or screening on adjacent vectors in the one-dimensional vectors of x rows and y columns, until the three-dimensional tensor is combined into a one-dimensional target vector, and determining a semantic matching degree between the first sentence and the second sentence according to the target vector.

A reply information recommendation method and apparatus provides recommended reply information suitable for a context that can be quickly and accurately calculated when a user replies to information. A specific solution is: acquiring information to be replied to received by a user and pre-reply information that is input by the user and corresponding to the information to be replied to; performing segmentation processing on the information to be replied to, to obtain a segmentation processing result; learning a stored text interaction history set of the user to obtain a reply model; obtaining candidate reply information with reference to the segmentation processing result of the information to be replied to and the reply model; and calculating a set of recommended reply information with reference to the candidate reply information and the pre-reply information. The embodiments of present invention are used for reply information recommendation.

Growing community of inventors

Shenzhen, China

Zhengdong Lu