Alibaba Group Holding Limited

Advanced New Technologies Co., Ltd.

Alipay (hangzhou) Information Technology Co., Ltd.

Wei Chu

Xu Yang

Xiaoyan Jiang

Bin Dai

Shen Li

Wei Zhang

Yuan Qi

Xing Shi

Shaomeng Wang

Zihao Fu

Feng Xie

Xudong Mao

Mengli Cheng

Wenmeng Zhou

Qingpei Guo

Ke Zhang

Shukun Xie

A computer-implemented system for encoding includes an encoding layer and at least one joint encoding unit. The encoding layer encodes a received first modal initial feature vector and a received second modal initial feature vector, to generate, respectively, a first modal feature vector and a second modal feature vector, joint encoded by the at least one joint encoding unit, where the at least one joint encoding unit includes an encoding module and a modal input switching module. The modal input switching module processes the first modal feature vector and the second modal feature vector, to obtain, respectively a first modal switching encoding vector and a second modal switching encoding vector. The encoding module processes the first modal switching encoding vector and the second modal switching encoding vector, to generate, respectively a first target modal fusion vector and a second target modal fusion vector.

Encoding apparatuses, and data processing methods and apparatuses

The present disclosure provides multi-sampling model training methods and devices. One exemplary training method includes: performing multi-sampling on samples to obtain a training set and a validation set in each sampling; using the training set and the validation set obtained in each sampling as a group, and performing model training and obtaining a trained model using the training set in each group; evaluating the trained model using the training set and the validation set in each group separately; eliminating or retaining the trained model based on the evaluation results and a predetermined elimination criterion; obtaining prediction results of the samples using retained models; and obtaining a final model by performing combined model training on the retained models using the prediction results. The final model obtained using embodiments of the present disclosure can be more robust and stable, and can provide more accurate prediction results, thus greatly improving efficiency of modeling.

Multi-sampling model training method and device

Embodiments of the present disclosure provide a method and system for training a model by using training data. The training data includes a plurality of samples, each sample includes N features, and features in the plurality of samples form N feature columns, and the method includes: determining an importance value of each of the N feature columns; determining whether the importance value of each of the N feature columns satisfies a threshold condition; performing a dimension reduction on M feature columns to generate P feature columns in response to the determination that the importance values of the M feature columns do not satisfy the threshold condition, wherein M&#x3c;N and P&#x3c;M; merging (N&#x2212;M) feature columns having importance values that satisfy the threshold condition and the generated P feature columns to obtain (N&#x2212;M+P) feature columns; and training the model based on the training data including the (N&#x2212;M+P) feature columns.

Method and system for training model by using training data

The present disclosure provides methods and an apparatuses for building a data identification model. One exemplary method for building a data identification model includes: performing logistic regression training using training samples to obtain a first model, the training samples comprising positive and negative samples; sampling the training samples proportionally to obtain a first training sample set; identifying the positive samples using the first model, and selecting a second training sample set from positive samples that have identification results after being identified using the first model; and performing Deep Neural Networks (DNN) training using the first training sample set and the second training sample set to obtain a final data identification model. The methods and the apparatuses of the present disclosure improve the stability of data identification models.

Methods and apparatuses for building data identification models

The present disclosure provides feature data processing methods and devices. One exemplary feature data processing method comprises: classifying features into an important feature set and an auxiliary feature set according to information attribute values of the features; converting features in the auxiliary feature set to hash features; and combining the hash features with features in the important feature set, and setting the combined features as fingerprint features. Training and prediction of to-be-processed data can be performed based on the fingerprint features. With the embodiments of the present disclosure, training dimensions can be more controllable and the amount training data amount can be reduced. Therefore, the efficiency of data processing can be improved.

Feature data processing method and device

A computer-implemented method includes: obtaining a sample picture and corresponding mark data, in which the mark data includes a first damage mark outline, and in which the first damage mark outline frames a damaged object in the sample picture; determining a segmentation type for a plurality of pixels in the sample picture based on the first damage mark outline, to generate segmentation mark data; inputting the sample picture to a weak segmentation damage detection model, in which the weak segmentation damage detection model includes an outline prediction branch and a segmentation prediction branch, in which the outline prediction branch outputs outline prediction data including a damage prediction outline, the damage prediction outline framing a predicted damaged object in the sample picture, and in which the segmentation prediction branch includes segmentation prediction data including a predicted segmentation type of each pixel of the plurality of pixels.

Segmentation-based damage detection

A character recognition method and apparatus are disclosed, relate to the field of image recognition technologies, reduce a calculation time, and increase character recognition efficiency. The method includes: obtaining picture data (); performing calculation on the picture data by using calculation layers shared by a first classifier and a second classifier, to obtain a first result, where the first classifier is a classifier for recognizing a specific character in the picture data, and the second classifier is a classifier for recognizing whether the picture data is a character picture (); performing calculation by bringing the first result into remaining calculation layers other than the shared calculation layers in the first classifier, to obtain a first probability corresponding to each character (); performing calculation by bringing the first result into remaining calculation layers other than the shared calculation layers in the second classifier, to obtain a second probability (); calculating, based on the first probability and the second probability, a confidence value that the picture data is recognized as each character (); and outputting a character recognition result based on the confidence ().

Growing community of inventors

Hangzhou, China

Wei Chu