Fujitsu Corporation

Jun Sun

Satoshi Naoi

Yuan He

Wei Fan

Song Wang

Pan Pan

Shufu Xie

Hao Yu

Liuan Wang

Wei Liu

Yun Zheng

Shenbin Zhang

Bingfeng Pi

Li Sun

Yutaka Katsuyama

Yifeng Pan

Ziqiang Shi

Wensheng Xia

Chaoliang Zhong

Zhongguang Zheng

Xiaoyi Yu

Danian Zheng

Li Long Chen

Meng Zhang

Katsuhito Fujimoto

Hiroaki Takebe

Rujie Liu

Yoshinobu Hotta

Akihiro Minagawa

Lu Fang

Koji Kurokawa

Rong Zhou

Yusaku Fuji

Zhanzhong Pang

Yingju Xia

Yiling Cao

Ruochen Wang

Naoi Satoshi

Jile Jiao

Chunpeng Wu

Xu-Cheng Yin

A method of presenting prompt information by utilizing a neural network which includes a BERT model and a graph convolutional neural network (GCN), comprising: generating a first vector based on a combination of an entity, a context of the entity, a type of the entity and a part of speech of the context by using BERT model; generating a second vector based on each of predefined concepts by using BERT model; generating a third vector based on a graph which is generated based on the concepts and relationships thereamong, by using GCN; generating a fourth vector by concatenating the second and third vectors; calculating semantic similarity between the entity and each concept based on the first and fourth vectors; determining, based on the first vector and the semantic similarity, that the entity corresponds to one of the concepts; and generating the prompt information based on the determined concept.

Method and device for presenting prompt information and storage medium

The present disclosure relates to a method and device for generating a finite state automata for recognizing a chemical name in a text, and a recognition method. According to an embodiment of the present disclosure, the method comprises substituting representation constants of categories of character segments appearing in an organic compound name set into the organic compound name set to obtain a conversion name set; updating the conversion name set based on a conversion name segment which repeatedly appears in the conversion name set; and generating the finite state automata based on the updated conversion name set.

Generating finite state automata for recognition of organic compound names in Chinese

A method and apparatus of accelerating deep learning, and a deep neural network are provided. The method comprises: randomly initializing weights and biases of a deep neural network as n-bit fixed-point numbers; reducing data in a plurality of layers in the deep neural network that have calculation amounts are greater than a first predetermined threshold as m-bit fixed-point numbers, where m and n are integers and m&#x3c;n, and maintaining data in remaining layers among the plurality of layers as n-bit fixed-point numbers; and training the deep neural network after the reducing, until convergence.

Method and apparatus for accelerating deep learning and deep neural network

The present disclosure relates to methods for estimating an accuracy and robustness of a model and devices thereof. According to an embodiment of the present disclosure, the method comprises calculating a parameter representing a possibility that a sample in the first dataset appears in the second dataset; calculating an accuracy score of the model with respect to the sample in the first dataset; calculating a weighted accuracy score of the model with respect to the sample in the first dataset, based on the accuracy score, by taking the parameter as a weight; and calculating, as the estimation accuracy of the model with respect to the second dataset, an adjusted accuracy of the model with respect to the first dataset according to the weighted accuracy score.

Methods for estimating accuracy and robustness of model and devices thereof

A training device and a training method for training a multi-goal model based on goals in a goal space are provided. The training device includes a memory and a processor coupled to the memory. The processor is configured to set the goal space, to acquire a plurality of sub-goal spaces of different levels of difficulty; change a sub-goal space to be processed from a current sub-goal space to a next sub-goal space of a higher level of difficulty; select, as sampling goals, goals at least from the current sub-goal space, and to acquire transitions related to the sampling goals by executing actions; train the multi-goal model based on the transitions, and evaluate the multi-goal model by calculating a success rate for achieving goals in the current sub-goal space.

Training device and training method for training multi-goal model

A method and apparatus of open set recognition, and a computer-readable storage medium are disclosed. The method comprises acquiring auxiliary data and training data of known categories for open set recognition, training a neural network alternately using the auxiliary data and the training data, until convergence; extracting a feature of data to be recognized for open set recognition, using the trained neural network; and recognizing a category of data to be recognized, based on the feature of the data to be recognized.

Method and apparatus of open set recognition and a computer readable storage medium

Disclosed are a method and apparatus for processing information by cooperation of multiple subjects, by submitting an information processing task to first multiple subjects; performing security analysis on information processing results obtained by executing the information processing task by the first multiple subjects, determining an updated processing manner of executing the information processing task based on a result of the security analysis; and submitting the information processing task to second multiple subjects according to the determined updated processing manner. Information processing results of executing the information processing task by the second multiple subjects are obtained, each of the second multiple subjects and each of the first multiple subjects save same information associated with the information processing task, and the information is updated based on the information processing results of executing the information processing task by the second multiple subjects.

Method and apparatus for processing information by cooperation of multiple subjects

A method and a device for simulating atomic dynamics includes setting initial positions for multiple specific atoms in a specific scene; calculating, based on the initial positions, positions of the multiple specific atoms at each time in a first time series by utilizing a Large-scale Atomic/Molecular Massively Parallel Simulator (LAMMPS) configured with respect to the specific scene, as real positions; calculating, based on the initial positions, positions of the multiple specific atoms at the same time in the first time series by utilizing a generative adversarial network (GAN), as predicted positions; improving a configuration of the GAN based on the real positions and the predicted positions at a same time. Initial positions are settable for multiple atoms to be simulated in a scene; positions of the multiple atoms to be simulated are calculated at each time in a second time series in the scene by utilizing the improved GAN.

Method and device for simulating atomic dynamics

A device for testing a blockchain network is provided. The device includes a processor. The processor is configured to calculate a matching degree between a configuration of the blockchain network and a template configuration corresponding to application scenario of the blockchain network; calculate performance of the blockchain network; calculate a health degree for the blockchain network; and determine whether the blockchain network is in a stable state based on the matching degree, the performance and the health degree.

Device for testing blockchain network

A device and a method for improving a processing speed of a neural network and applications thereof in the neural network where the device includes a processor configured to perform: determining, according to a predetermined processing speed improvement target, a dimension reduction amount of each of one or more parameter matrixes in the neural network obtained through training; preprocessing each parameter matrix based on the dimension reduction amount of the parameter matrix; and retraining the neural network based on a result of the preprocessing to obtain one or more dimension reduced parameter matrixes so as to ensure performance of the neural network meets a predetermined requirement. According to the embodiments of the present disclosure, it is possible to significantly improve the processing speed of the neural network while ensuring the performance of the neural network meets the predetermined requirement.

Device and method for improving processing speed of neural network

A device and a method for electromagnetic field simulation are provided. The image processing device is to obtain, with a first resolution, a first electromagnetic field simulation result of a simulation region, and to derive a second electromagnetic field simulation result with a second resolution, according to the first electromagnetic field simulation result, using a model trained based on a deep learning method. The second resolution is higher than the first resolution.

Device and method for electromagnetic field simulation

A device for determining a CNN model for a database according to the present disclosure includes: a selecting unit configured to select at least two CNN models from multiple CNN models whose classification capacity is known; a fitting unit configured to fit, based on the classification capacity and first parameters of the at least two CNN models, a curve taking classification capacity and a first parameter as variables; a predicting unit configured to predict, based on the curve, a first parameter of other CNN models; and a determining unit configured to determine a CNN model applicable to the database from the multiple CNN models. With the device and the method according to the present disclosure, there is no need to train all the CNN models, thereby greatly reducing the amount of computation and simplifying the process of designing the CNN model.

Device and method for determining convolutional neural network model for database

Provided are device and method for determining a Convolutional Neural Network (CNN) model. The device for determining the CNN model includes: a first determination unit configured to determine complexity of a database including multiple samples; a second determination unit configured to determine a classification capability of a CNN model applicable to the database based on the complexity of the database; a third determination unit configured to acquire classification capability of each candidate CNN model; and a matching unit configured to determine the CNN model applicable to the database based on the classification capability of each candidate CNN model. With the device and method for determining the CNN module, a design process of CNN model can be simplified.

Device and method for determining convolutional neural network model

A recognition apparatus based on a deep neural network, a training apparatus and methods thereof. The deep neural network is obtained by inputting training samples comprising positive samples and negative samples into an input layer of the deep neural network and training. The apparatus includes: a judging unit configured to judge that a sample to be recognized is a suspected abnormal sample when confidences of positive sample classes in a classification result outputted by an output layer of the deep neural network are all less than a predefined threshold value. Hence, reliability of a confidence of a classification result outputted by the deep neural network may be efficiently improved.

Recognition apparatus based on deep neural network, training apparatus and methods thereof

Disclosed are a method and apparatus for managing effectiveness of an information processing task in a decentralized data management system. The method comprising: sending requests for multiple information processing tasks by a client to multiple execution subjects, transmitting information processing tasks in a sequential information processing task list in an order to the multiple execution subjects; caching the requested information processing tasks to a task cache queue, caching the sequential information processing task list as a whole to the task cache queue; judging whether each information processing task in the task cache queue satisfies a predetermined conflict condition; moving the information processing task to a conflict task queue if it is determined that the task satisfies the predetermined conflict condition, deleting the task from the conflict task queue and caching the task to the task cache queue when the predetermined conflict condition is not satisfied.

Growing community of inventors

Beijing, China

Jun Sun