Tencent Technology (shenzhen) Company Limited

Other

Tencent Technology Company Limited

Yang Feng

Yan Zhang

Lin Ma

Jiebo Luo

Jinchao Zhang

Fandong Meng

Chao Wang

Jin Zhang

Yu Zhang

Bairui Wang

Biao Hu

Jiaqiang Zhou

Chengliang Qiu

Erning Zhao

Xiong Xiao

Xueqing Jiang

Mengmeng Wang

Jiao Ou

Baqun Sun

Jingsheng Li

Xinchun Liu

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.

Method and apparatus for training dialog model, computer device, and storage medium

Embodiments of this application disclose a method for training an image caption model, the image caption model including an encoding convolutional neural network (CNN) and a decoding recurrent neural network (RNN). The method includes: obtaining an image eigenvector of an image sample by using the encoding CNN; decoding the image eigenvector by using the decoding RNN, to obtain a sentence used for describing the image sample; determining a matching degree between the sentence obtained through decoding and the image sample and a smoothness degree of the sentence obtained through decoding, respectively; and adjusting the decoding RNN according to the matching degree and the smoothness degree.

Method and apparatus for training image caption model, and storage medium

The present disclosure describes methods, devices, and storage medium for generating a natural language description for a media object. The method includes respectively processing, by a device, a media object by using a plurality of natural language description models to obtain a plurality of first feature vectors corresponding to a plurality of feature types. The device includes a memory storing instructions and a processor in communication with the memory. The method also includes fusing, by the device, the plurality of first feature to obtain a second feature vector; and generating, by the device, a natural language description for the media object according to the second feature vector, the natural language description being used for expressing the media object in natural language. The present disclosure resolves the technical problem that natural language description generated for a media object can only give an insufficiently accurate description of the media object.

Method and apparatus for generating natural language description information

A video query method includes obtaining a media feature of a query media and a static image feature corresponding to a candidate video. The query media includes the target object, and the candidate video includes the moving object. A video feature of the candidate video is determined according to the static image feature and motion time sequence information of the moving object in the candidate video. Whether the moving object in the candidate video is related to the target object in the query media can be determined according to the media feature and the video feature.

Video query method, apparatus, and device, and storage medium

Disclosed is a reverse flow multi-stage sedimentation rake-free thickening device relating to the field of slime water treatment. The device includes a feed assembly, a guide assembly, and a clean coal collection assembly. The guide assembly also includes a central tank body and coal slurry flows from the upper part of the central tank body to the inner side wall of the central tank body through the feed assembly and the medicament, and then flows to the middle of the central tank body through the guide assembly. After the reaction, the bubbles carry the fine coal slime and move up to the clean coal collection assembly. The clean coal collection assembly is located above the outlet of the guide assembly, and the clean coal collection assembly is sequentially provided with a central collection area, a defoaming area, and a diversion settlement area from the middle to the outside.

Reverse flow type multi-stage sedimentation rake-free thickening device

The present disclosure relates to a question recommending method, apparatus, and system. The method includes: constructing, by a server, an interest vector of a user according to a short-term interest, a long-term interest, and a group interest of the user, the interest vector of the user including multiple interest items; acquiring a candidate-for-recommendation question from a set of to-be-resolved questions according to the multiple interest items; estimating, according to a click-through rate (CTR) model, probability of answering the candidate-for-recommendation question by the user, and selecting a to-be-recommended question according to the estimated probability; and sending the to-be-recommended question to a client. In this way, a real-time comprehensive recommendation result can be obtained, and a question answering rate of an interactive question-and-answer platform can also be improved.

Question recommending method, apparatus and system

Growing community of inventors

Shenzhen, China

Yang Feng