Beijing Xiaomi Intelligent Technology Co., Ltd.

Huawei Technologies Co., Limited

Beijing Xiaomi Mobile Software Co., Ltd.

Jianwei Cui

Jing Li

Yuhui Sun

Jialiang Jiang

Fei Yu

Xiaolin Wu

Shikun Xu

Lanhao Chen

An electronic device obtains an included angle between a touchscreen (a curved screen with a radian on a side edge) and a horizontal plane; starts a camera in response to the included angle between the touchscreen and the horizontal plane falling within a first preset angle range; obtains a distance between the electronic device and a user and a face yaw degree of the user in response to the camera collecting a face image; and performs anti-mistouch processing on a preset mistouch operation of the user on the touchscreen in response to the distance between the electronic device and the user being less than a first distance threshold and the face yaw degree falling within a second preset angle range.

Anti-mistouch method of curved screen and electronic device

A method includes: a bidirectional translation model to be trained and training data are acquired, the training data including a source corpus and a target corpus corresponding to the source corpus; the bidirectional translation model is trained for N cycles, each cycle of training including a forward translation process of translating the source corpus into a pseudo target corpus and a reverse translation process of translating the pseudo target corpus into a pseudo source corpus and N being a positive integer greater than 1; a forward translation similarity and a reverse translation similarity are acquired; and when a sum of the forward translation similarity and the reverse translation similarity converges, it is determined that training of the bidirectional translation model is completed, where the training completed bidirectional translation model is used to perform translating.

Method, device and storage medium for training bidirectional machine translation model using sum of forward and reverse translation similarities

A method for compressing a neural network model, includes: obtaining a set of training samples including a plurality of pairs of training samples, each pair of the training samples including source data and target data corresponding to the source data; training an original teacher model by using the source data as an input and using the target data as verification data; training intermediate teacher models based on the set of training samples and the original teacher model, one or more intermediate teacher models forming a set of teacher models; training multiple candidate student models based on the set of training samples, the original teacher model, and the set of teacher models, the multiple candidate student models forming a set of student models; and selecting a candidate student model of the multiple candidate student models as a target student model according to training results of the multiple candidate student models.

Neural network model compression method, corpus translation method and device

A method for information processing, includes: obtaining a bilingual vocabulary containing N original bilingual word pairs, N being a positive integer; obtaining an original bilingual training set containing multiple original bilingual training sentence pairs; selecting at least one original bilingual training sentence pair matching any original bilingual word from the original bilingual training set as a bilingual sentence pair candidate; constructing a generalized bilingual sentence pattern based on at least one bilingual sentence pair candidate; and obtaining an augmented bilingual training set containing multiple augmented bilingual training sentence pairs, based on the bilingual vocabulary and the generalized bilingual sentence pattern.

Growing community of inventors

Beijing, China

Jianwei Cui