Alibaba Group Holding Limited

Advanced New Technologies Co., Ltd.

Alipay (hangzhou) Information Technology Co., Ltd.

Zhejiang University

Boe Technology Group Co., Ltd.

Baidu Online Network Technology (beijing) Co., Ltd.

Hefei Xinsheng Optoelectronics Technology Co., Ltd.

Hefei Boe Optoelectronics Technology Co., Ltd.

Acbel Polytech Inc.

Ant Blockchain Technology (shanghai) Co., Ltd.

Beijing Techshino Technology Co., Ltd.

Jun Zhou

Chaochao Chen

Xiaolong Li

Shaosheng Cao

Xinxing Yang

Li Wang

Fei Liu

Longfei Li

Peilin Zhao

Longfei Zheng

Jiangang Shen

Wenwen Kong

Yanhong Li

Han Guo

Yingting Liu

Jianting Zhu

Jinrong Wang

Gang Wang

Bin Yang

Yong He

Hui Fang

Peng Li

Yuliang Wang

Zhiming Wang

Rui Yang

Daeyoung Choi

Yufei Liu

Wenjuan Zhang

Licui Gao

Xianglong Meng

Zengli Liu

Daojie Li

Xiao-Lin Ma

Jinming Cui

Youhao Sun

Yunxiao Zhang

Fei Al

Bing Guo

Wenjing Fang

Yinggui Wang

Yilun Lin

Hongjun Yin

Shenquan Qu

Ziqi Liu

Yongming Ding

Jie Jiao

Mengyuan Chen

Riqun Ni

Xiangyu Lu

Chunlin Yang

Fushui Yu

Lei Feng

Chengkun Shan

The present disclosure provides a crop yield estimation method and system based on level identification and weighted decision fusion. The method includes: inputting an obtained visible light image of a target crop field at maturity into a yield level classification model, to obtain yield level output values corresponding to all yield levels of the visible light image of the target crop field at maturity, where the yield levels are determined according to a yield level rule; calculating a confidence score corresponding to each of the yield level output values, and sorting the confidence scores in descending order; selecting the first m confidence scores, and performing normalization on the first m confidence scores to obtain m yield level weights; and respectively multiplying the m yield level weights and corresponding yield levels, and adding up all products, to obtain an estimated yield of the target crop field at maturity.

Crop yield estimation method and system based on grade identification and weight decision-making

One or more embodiments of the present specification provide privacy protection-based multicollinearity detection methods, apparatuses, and systems. Data alignment is performed by a member device on respective local feature data with other member devices to construct a joint feature matrix. Privacy protection-based multi-party matrix multiplication computation is performed to compute a product matrix of a transposed matrix of the joint feature matrix and the joint feature matrix. An inverse matrix of the product matrix is determined based on respective submatrices of the product matrix. A variance inflation factor of each attribute feature is determined by the member device with the other member devices using respective submatrices of the inverse matrix and the respective local feature data. Multicollinearity is determined by the member device with the other member devices based on fragment data of the variance inflation factor of each attribute feature.

Privacy protection-based multicollinearity detection methods, apparatuses, and systems

The present disclosure provides a method and a system for training a machine learning system. Multiple pieces of sample data are used for training the machine learning system. The method includes acquiring multiple sample sets, each sample set including sample data in a corresponding sampling time period; setting a sampling rate for each sample set according to the corresponding sampling time period; acquiring multiple sample sets sampled according to set sampling rates; determining importance values of the multiple sampled sample sets; correcting each piece of sample data in the multiple sampled sample sets by using a corresponding importance value to obtain corrected sample data; and inputting the corrected sample data into the machine learning system to train the machine learning system.

Method and system for training machine learning system

A distributed cluster training method and an apparatus thereof are provided. The method includes reading a sample set, the sample set including at least one piece of sample data; using the sample data and current weights to substitute into a target model training function for iterative training to obtain a first gradient before receiving a collection instruction, the collection instruction being issued by a scheduling server when a cluster system environment meets a threshold condition; sending the first gradient to an aggregation server if a collection instruction is received, wherein the aggregation server collects each first gradient and calculates second weights; and receiving the second weights sent by the aggregation server to update current weights. The present disclosure reduces an amount of network communications and an impact on switches, and avoids the use of an entire cluster from being affected.

Distributed cluster training method and apparatus

Disclosed a crop yield prediction method and system based on low-altitude remote sensing information from an unmanned aerial vehicle (UAV). Obtaining a plurality of images taken by the UAV; stitching the plurality of images to obtain a stitched image; performing spectral calibration on the stitched image to obtain the reflectivity of each pixel in the stitched image; using a threshold segmentation method to segment the stitched image, to obtain a target area for crop yield prediction; using a Pearson correlation analysis method to analyze a correlation between the reflectivity of each band and the growth status and yield of the crop to obtain feature bands; constructing yield prediction factors based on the feature bands; and determining a predicted crop yield value of the target area for crop yield prediction based on the yield prediction factors and a crop planting area of the target area for crop yield prediction.

Crop yield prediction method and system based on low-altitude remote sensing information from unmanned aerial vehicle

A client device determines a local user gradient value based on a current user preference vector and a local item gradient value based on a current item feature vector. The client device updates a user preference vector by using the local user gradient value and updates an item feature vector by using the local item gradient value. The client device determines a neighboring client device based on a predetermined adjacency relationship. The local item gradient value is sent by the client device to the neighboring client device. The client device receives a neighboring item gradient value sent by the neighboring client device. The client device updates the item feature vector by using the neighboring item gradient value. In response to the client device determining that a predetermined iteration stop condition is satisfied, the client device outputs the user preference vector and the item feature vector.

Recommendation system construction method and apparatus

An automatic multi-threshold feature filtering method and an apparatus thereof are provided. In an iterative process of training a machine learning model, the feature filtering method calculates a feature filtering threshold and feature correlation values of a current round of iteration based on a result of a previous iteration, and performs feature filtering on samples based on the calculated feature filtering threshold and the calculated feature correlation values. The feature filtering apparatus of the present disclosure includes a calculation module and a feature filtering module. The method and apparatus of the present disclosure can automatically generate different feature filtering thresholds at each iteration, which greatly improves an accuracy of a filtering threshold, and can greatly increase the training speed of automatic machine learning and an accuracy of a machine learning model compared with fixed and single thresholds nowadays.

Automatic multi-threshold feature filtering method and apparatus

Current streaming sample data is received. A current deep learning model is trained based on the current streaming sample data, the training including: obtaining a shallow learning model through training based on historical sample data associated with the current streaming sample data; and initializing parameters of the current deep learning model as the parameters of the shallowing learning model.

Methods, apparatuses, and computing devices for trainings of learning models

A computer-implemented method, medium, and system are disclosed. One example method includes determining multiple model bases by multiple service parties. A respective local service model is constructed by each service party. Respective local training samples are processed by each service party using the respective local service model to determine respective gradient data corresponding to each model basis. The respective gradient data is sent to a server. In response to determining that the first model basis satisfies a gradient update condition, corresponding gradient data of the first model basis received from each service party are combined to obtain global gradient data corresponding to the first model basis. The global gradient data is sent to each service party. Reference parameters in local model basis corresponding to the first model basis are updated by each service party using the global gradient data to train the respective local service model.

Methods, apparatuses, and systems for updating service model based on privacy protection

A computer-implemented method, medium, and system are disclosed. One example computer-implemented method performed by a server includes obtaining training task information from a task party. The training task information includes information about a to-be-pretrained model and information about a to-be-trained target model. A respective task acceptance indication from each of at least one of a plurality of data parties is received to obtain a candidate data party set. The information about the to-be-pretrained model is sent to each data party in the candidate data party set. A respective pre-trained model of each data party is received. A respective performance parameter of the respective pre-trained model of each data party is obtained. One or more target data parties from the candidate data party set is determined. The information about the to-be-trained target model is sent to the one or more target data parties to obtain a target model.

Target data party selection methods and systems for distributed model training

The invention relates to a method and device for predicting a volume median diameter (VMD) in an overlapped spray area of twin nozzles. Placing a single nozzle at different heights to determine a spray area; measuring all VMDs in the spray area to obtain first true measured values; dividing the first true measured values to construct a first calibration set and a first prediction set; establishing a polynomial fitting formula by a REGRESS function; placing twin nozzles at different heights and different nozzle spacing, and measuring VMDs in the overlapped spray area to obtain second true measured values; determining simulated values of the VMDs of first and second nozzles; dividing the simulated values of the VMDs and the second true measured values to construct a second calibration set and a second prediction set; quantitatively calibrating by using a radial basis function neural network (RBFNN) to obtain a prediction model; determining a VMD in the overlapped spray area of twin nozzles.

Method and device for predicting volume median diameter in overlapped spray area of twin nozzles

The present specification discloses a multi-classifier-based recommendation method and device, and an electronic device. In the method, a target sub-classifier is obtained from k sub-classifiers in a multi-classifier based on received data, where the target sub-classifier is a sub-classifier whose data distribution has a highest similarity with feature data in the multi-classifier; the first prediction data obtained after the primary classifier performs prediction on the feature data is obtained, the second prediction data obtained after the target sub-classifier performs prediction on the feature data is obtained, and then the third prediction data is obtained by combining the first prediction data and the second prediction data, so that more accurate prediction data is obtained, thereby resolving the technical problem of low accuracy of data classification prediction in the existing technology; and the feature data is recommended based on the third prediction data, so that the accuracy of data recommendation is improved.

Multi-classifier-based recommendation method and device, and electronic device

One or more embodiments of the present specification relate to a method and system for obtaining a jointly trained model based on privacy protection. An example method includes jointly training a first model, by a first device and with a second device, the first device and the second device each holding respective training data that includes first training data with a sample label, and second training data without the sample label. Jointly training the first model includes privately obtaining the first training data, and performing joint model training using the first training data. The second training data is input to the trained first model to obtain a predicted label for the second training data. Jointly training a second model includes privately obtaining labeled training data, and performing joint model training using the first training data, the second training data, and the labeled training data.

Obtaining jointly trained model based on privacy protection

Methods, systems, and apparatus for facial recognition. An example method includes storing encrypted facial features of a target user that are encrypted by using a first public key; receiving a recognition request from an end-user device of the target user, wherein the recognition request comprises an encrypted facial image and a second public key; performing homomorphic feature processing on the encrypted facial image; obtain obfuscated and encrypted output features; obtain obfuscated and encrypted facial features; transmitting the obfuscated and encrypted output features and the obfuscated and encrypted facial features to the end-user device; receiving from the end-user device a difference between the second intermediate value and the first intermediate value; and determining whether the to-be-recognized facial image corresponds to a facial image of the target user, comprising removing an impact of the first obfuscation and the second obfuscation on the difference.

Facial recognition methods and apparatuses

Growing community of inventors

Hangzhou, China

Jun Zhou