Fujitsu Corporation

Fujitsu Semiconductor Limited

Fujistu Limited

Wei-Peng Chen

Chenxi Zhu

Mehdi Bahrami

Lei Liu

Jonathan Russell Agre

Junhee Park

Takuki Kamiya

Masato Okuda

Dorin Gheorghe Viorel

Daisuke Mashima

Takao Naito

Ying Liu

Hui Zeng

Akira Ito

Yuji Kojima

Ahmed Ragab Elsherif

Sanam Mirzazad Barijough

Jagan N Seshadri

Jorjeta Gueorguieva Jetcheva

Ryusuke Masuoka

Sung Ho Lee

Koji Yoshimura

Ching-Fong Su

Ulrich Herberg

Dawei He

Qinghan Xue

Mostafa Majidpour

Vishwanath Ramamurthi

Chetan Ramaiah

Hiroyuki Seki

Samir Parikh

Yoichi Koyanagi

Hiroyuki Kiyanagi

Golnaz Farhadi

Takeo Hamada

Pranav Mahesh Makhijani

Changqin Huo

Nien-Tai Kai Mao

Abhilash Ugaonkar

Teng-Sheng Moh

Rohisha Adke

Sarthak Arora

Mehdi Assefi

Athar Sefid

Oussama Chafiqui

Shrikanth Narayanaswamy Chandrasekaran

Manisha Mukherjee

Qiyu Zhi

Michel Ferreira Abdalla

Kiyoshi Nakayama

According to an aspect of an embodiment, operations for deep parameter learning for code synthesis are provided. The operations may include receiving a source code file and generating an abstract syntax tree (AST). The operations may further include determining a set of classes, and functions/procedures from the computer-executable code and extracting metadata associated to each component. The operations may further include selecting a subset of functions for which descriptions in the extracted metadata satisfy filtering criteria and updating the computer-executable code by filtering lines of code (LoCs) corresponding to the subset of functions/procedures. The operations may further include generating a dataset of code features and respective metadata features that includes a deep connection between parameters and its usage based on the updated computer-executable code and the metadata generation task. The operations may further include training a language model on a sequence-to-sequence generation task, based on the dataset.

Deep parameter learning for code synthesis

According to an aspect of an embodiment, operations for code enrichment through metadata for code synthesis are provided. The operations include acquiring package data that include source code files and package metadata. The operations further include extracting additional metadata associated with software package and preparing metadata features based on the package metadata and the additional metadata. The operations further include identifying a set of target portions of a source code included in the source code files and updating one or more source code files using the metadata features. Such files are updated by performing at least one of a revision of existing code comments, and an addition of new code comments for the target portions. The operations further include generating a dataset of natural language (NL) text features and respective code features and training a language model on a sequence-to-sequence generation task.

Code enrichment through metadata for code synthesis

According to an aspect of an embodiment, operations for code enrichment for training language models on tasks related to computer programming are provided. The operations include receiving source code data including a computer-executable code and a natural language (NL) text. The operations further include determining blocks of code from the computer-executable code. The operations further include extracting a set of features related to components of the source code data from the blocks of code. The extraction is performed by parsing the blocks of code using Abstract Syntax Tree (AST) data of the blocks of code. The operations further include revising the AST data. The operations further include updating the source code data based on the revised AST data and generating a dataset of NL and abstracted code features as training data based on the updated source code data and further training a language model on a sequence-to-sequence generation task.

Code enrichment for training language models relating to computer programming

According to an aspect of an embodiment, operations include receiving a set of NL descriptors and a corresponding set of PL codes. The operations further include determining a first vector associated with each NL descriptor and a second vector associated with each PL code, using language models. The operations further include determining a number of a set of semantic code classes to cluster the set of PL codes into the set of semantic code classes, based on the number, the first vector, and the second vector. The operations further include training a multi-class classifier model to predict a semantic code class, from the set of semantic code classes, corresponding to an input NL descriptor. The operations further include selecting an intra-class predictor model based on the predicted semantic code class. The operations further include training the intra-class predictor model to predict a PL code corresponding to the input NL descriptor.

Code retrieval based on multi-class classification

According to an aspect of an embodiment, operations for detection of API compatibility across software versions are provided. The operations may include receiving an input associated with a software application. The operations may further include determining first information. The operations may further include extracting a set of data from one or more web-based sources based on the determined first information. The operations may further include executing a set of operations including one or more pattern searching operations on the extracted set of data to generate a compatibility result. The operations may further include controlling a display device based on the generated compatibility result. The display device may be controlled to display assistive information which informs about a compatibility of the one or more APIs or the functions used in the source code of the software application with respect to the second version of the software.

Detection of API backward compatibility across software versions

A method includes extracting, from a web application programming interface (API) repository, first information associated with a plurality of web APIs and constructing an initial dataset associated with the plurality of web APIs by performing a first set of information processing operations on the extracted first information. The method further includes constructing a training dataset by performing a second set of information processing operations on the constructed initial dataset and obtaining a Machine Learning (ML) model based on the constructed training dataset. The method further includes receiving an input natural language query via an electronic user interface (UI) and providing the received input natural language query to the obtained ML model. The method further includes outputting a set of recommendation results based on the provided input natural language query to the obtained ML model. Each recommendation result includes a specific API name and a specific endpoint.

Recommending web API's and associated endpoints

A method comprises receiving vehicle data comprising information associated with a plurality of sensors of autonomous vehicle and segmenting the received vehicle data into non-public data and public data. The method further comprises partitioning the public data into a plurality of data partitions and generating a plurality of data levels of the public data. Each data level of the plurality of data levels is generated according to an access level of a plurality of access levels and includes one or more data partitions of the plurality of data partitions in an encrypted form. The method further comprises transmitting the generated plurality of data levels to a group of electronic devices. Each electronic device of the group of electronic devices retrieves, according to one of the plurality of access levels, at least a portion of the public data from the transmitted plurality of data levels.

Multi-level access control in sharing of vehicle data with devices

According to an aspect of an embodiment, operations for trend monitoring of code repositories and related information are provided. The operations include identifying a set of repositories from a collection of repositories hosted on one or more web-based repository hosting systems and collecting repository metadata for each repository. The operations further include generating a set of topic tags by using one or more natural language processing-based methods and collecting a set of statistics associated with each of the generated set of topic tags. The operations further include generating a set of presentation data based on one or more of the identified set of repositories, the collected repository metadata, the generated set of topic tags, and the collected set of statistics. The operations further include controlling a user device to display the generated set of presentation data onto an electronic User Interface of the user device.

Trend monitoring of code repositories and related information

A method may include obtaining training code and extracting features from the training code. The extracted features of the training code may be mapped to natural language code vectors by a deep neural network. A natural language search query requesting source-code suggestions may be received, and the natural language search query may be mapped to a natural language search vector by the deep neural network. The method may include mapping the natural language search query to the natural language search vector in the same or a similar method as mapping the extracted features of the training code to natural language code vectors, and the natural language search vector may be compared to the natural language code vectors. Source code responsive to the natural language search query may be suggested based on the comparison between the natural language search vector and the natural language code vectors.

Source code retrieval

A method may include obtaining machine-readable source code. The method may include parsing the source code for one or more code descriptions and identifying a section of the source code corresponding to each of the code descriptions. The method may include determining a description-code pair including a first element representing the code description and a second element representing the section of the source code corresponding to the code description. The method may include generating an augmented programming language corpus based on the description-code pair, the one or more code descriptions, and the source code. The method may include receiving a natural language search query for source-code recommendations, identifying source code from the augmented programming language corpus responsive to the natural language search query, and responding to the natural language search query with the identified source code.

Semantic code search based on augmented programming language corpus

A method of deploying an unmanned aerial vehicle (UAV) operation system may be provided. A method may include estimating an amount of traffic for one or more routes based on a demand of the one or more routes. The method may also include determining a required number of docking stations for each route of the one or more routes based on the estimated amount of traffic for the route, a distance of the route, and a maximum travel distance for a UAV. Further, the method may include installing the required number of docking stations for each route of the one or more routes, wherein each docking station of the required number of docking stations including at least one of a power supply, a wireless charger, a communication module, a control module, and a camera.

Unmanned aerial vehicle operation systems

A method may include providing access to a first application programming interface (API) provided by a first party and a second API provided by a second party. The method may also include collecting a first set of API data sources related to the first API and a second set of API data sources related to the second API. The method may additionally include using a deep learning model to predict a privacy trustworthiness level for the first API and the second API, and disabling access to the first API based on the privacy trustworthiness level of the first API being below a threshold level.

Privacy trustworthiness based API access

Operations may include obtaining source code describing an optimization problem. The operations may include identifying problem parameters associated with the optimization problem such that a specialized computing system may be enabled to solve the optimization problem. The operations may include extracting one or more first parameters of the problem parameters from the source code. The operations may include identifying one or more second parameters of the problem parameters that are not included in the source code. A user may be prompted via a GUI for input relating to the one or more second parameters. The operations may include compiling the extracted first parameters and the user-provided second parameters as input parameters of the specialized computing system. The operations may include providing the input parameters to the specialized computing system such that the specialized computing system is able to solve the optimization problem.

Community-oriented, cloud-based digital annealing platform

According to an aspect of an embodiment, operations include deploying a trigger function on a computing system for detecting an electronic trigger event associated with a first Application Programming Interface (API) provider. The operations further include deploying a rule function for applying at least one trigger rule on event data and deploying an action function for generating at least one API call to a second API provider based on whether the event data satisfies the at least one trigger rule. The operations further include deploying a set of API gateways for enabling a workflow system to invoke at least one of: the deployed trigger function, the deployed rule function, and the deployed action function. The operations further include generating a workflow template of an API mashup based on information associated with the deployed functions and API gateways and posting the generated workflow template to the workflow system.

API mashup infrastructure generation on computing systems

According to an aspect of an embodiment, operations may include receiving a first input corresponding to a selection of a combinatorial optimization problem and receiving a set of datapoints as input. The operations may further include generating a first quadratic unconstrained binary optimization (QUBO) formulation based on an objective function for the combinatorial optimization problem and the received set of datapoints. The operations may further include selecting a first privacy setting and encoding the first QUBO formulation based on the selected privacy setting to generate a second QUBO formulation. The operations may further include submitting the generated second QUBO formulation to an optimization solver machine and receiving a first solution of the second QUBO formulation. The operations may further include decoding the first solution to produce a second solution and publishing an output of the combinatorial optimization problem on a user device based on the second solution.

Data privacy protection on cloud-based optimization systems

Growing community of inventors

Fremont, CA, United States of America

Wei-Peng Chen