International Business Machines Corporation

De Shuo Kong

Zhong Fang Yuan

Tong Liu

Yao Liang Chen

Yi Ming Wang

Hai B Zou

Zheng Jie

Shu Xia Cao

Xue Feng Gao

Zhi Peng Jia

Zhi Cao

Rong Fu He

Sarbajit Kumar Rakshit

Xin Peng Liu

Lu Yu

Si Bin Fan

Wen Jie Wang

Yuan Yuan Li

Yong Wang

Ye Wy Wang

Yi Chen Zhong

Kun Yan Yin

Lan Luo

Xiang Yu Yang

Wen Rui Zhao

Jing Wu

Hai Ji

Ci-Wei Lan

Chen Gao

Guang Qing Zhong

Ge Liang

Ya Dong Li

Yun He Gao

Peng Yun Sun

Marc Toubia

Shou Qing Liang

Liu Xiaojin

A method includes: receiving, by a computer device, a user question; extracting, by the computer device and from a knowledge base, multiple answers to the user question; detecting, by the computer device, a first relationship entity that exists in a subset of the multiple answers to the user question; determining, by the computer device, that the first relationship entity is a condition, the condition being a relationship entity that has different values in the subset of the multiple answers; generating, by the computer device, a first follow-up question that solicits a value of the condition; receiving, by the computer device, an answer to the first follow-up question; and determining, by the computer device, a number of the subset of the multiple answers that have a value of the condition that matches the answer to the first follow-up question.

Intelligent leading multi-round interactive automated information system

A method, apparatus, system, and computer program product for container migration. A set of processors operates to identify a set of containers for a set of applications for a migration using a set of application performance metrics. The set of processors operates to create a set of tasks following a migration strategy to move the set of containers for the set of applications identified for the migration from a set of current physical host computers to a set of target physical host computers using the set of application performance metrics. The set of processors operates to move the set of containers for the set of applications from the set of current physical host computers to the set of target physical host computers using the set of tasks following the migration strategy.

Automatic container migration system

A first set of features associated with a neural network are parameterized. A decision tree is generated from the first set of features. One or more adjustments for the neural network are received at the decision tree. A second set of features associated with the adjustments at the decision tree are parameterized. The parameterized first and second set of features are combined into a plurality of parameters. From the plurality, an adjusted neural network is generated.

Decision tree interface for neural networks

Embodiments of the present invention relate to methods, systems, and computer program products for managing a plurality of live comments. A plurality of live comments is obtained for a video, the plurality of live comments being associated with a plurality of fragments in the video, respectively. A plurality of features are extracted from the plurality of live comments, respectively. A knowledge base is generated for the plurality of live comments based on the plurality of features. With these embodiments, the live comments may be managed in an effective way. Further, the knowledge base may provide answers to a user query.

Live comment management

A system, method, and computer program product for implementing cognitive natural language processing software framework optimization is provided. The method includes receiving instructions associated with an audible user input of a user. An AI input intention of the user is determined and key information is extracted from the audible user input. The key information is inputted into a generated database table and additional key information is retrieved from a dialog table. A supplementary database table comprising the additional key information is generated and the key information is spliced with the additional key information. A resulting spliced data structure is merged into a final database table and natural language is converted into a request code structure within an SQL structure and an interactive AI interface presenting results of the converting is generated. Operational functionality of an AI device is enabled for audibly presenting results of the conversion.

Cognitive natural language processing software framework optimization

One or more computer processors encode a plurality of time sequenced global position system (GPS) datapoints onto a grided dimensional area; determine a general trajectory between each time sequenced GPS datapoint in the plurality of encoded time sequenced GPS datapoints and a subsequent encoded time sequenced GPS datapoint; cluster the encoded time sequenced GPS datapoints based on a respective determined trajectory with a plurality of encoded historical GPS datapoints; calculate an azimuth for each encoded time sequenced GPS datapoint in the plurality of time sequenced GPS datapoints utilizing a plurality of adjacent historical GPS datapoints contained within a respective cluster; generate a plurality of interpolated GPS datapoints utilizing calculated azimuths, determined general trajectories, and historical GPS datapoints; and aggregate the generated interpolated GPS datapoints with the plurality of time sequenced GPS datapoints into an interpolated route, wherein each GPS datapoint in the interpolated route is within respective azimuth thresholds.

Low-sampling rate GPS trajectory learning

Provided is a method, computer program product, and system for fusing knowledge graphs to generate a larger knowledgebase for responding to cross document questions. A processor may extract contextual information from a plurality of documents. The processor may generate, based on the extracted contextual information, a knowledge graph for each document of the plurality of documents. The processor may analyze each knowledge graph to determine if one or more entities of each knowledge graph are linked. The processor may fuse, in response to an entity in a first knowledge graph being linked to an entity in a second knowledge graph, the first knowledge graph with the second knowledge graph to create a fused knowledge graph.

Knowledge graph fusion

Pint with an american football ball shape inside

An approach for extracting non-textual data from an electronic document is disclosed. The approach includes receiving a request to extract a file and converting the file into pixels. The approach creates a pixel map of the converted file and determines one or more density clusters of the pixel map based on image clustering method. Furthermore, the approach determines one or more coordinates of the one or more density clusters and determines one or more candidate information regions based on the one or more coordinates, density of the one or more density clusters. Finally, the approach extracts one or more textual data based on the one or more candidate information regions and outputs the extracted one or more textual data.

Extracting non-textual data from documents via machine learning

Systems and methods of computer program code or business process design pattern recognition are provided. In embodiments, a method includes identifying, by the computing device, predefined elements and relationships between the elements in a digital industry product based on stored rules; generating, by the computing device, a diagram based on stored image rules, the diagram including graphical notations and text-based information representing the elements and the relationships between the elements; removing, by the computing device, the text-based information from the diagram to produce a modified diagram; and determining, by the computing device, that the modified diagram includes at least one predetermined pattern from a plurality of stored patterns using image object detection.

Pattern recognition

Embodiments of the present invention provide methods, computer program products, and systems to for dynamically modifying a generated route that enables peer to peer navigation. Embodiments of the present invention can be used to receive input that specifies one or more terms pertaining to a target that is a location of interest from a user. Embodiments of the present invention can pair the user with the target of interest; generating a route to the target and dynamically modify the generated route to the target according to positional information of the location and changes in positional information of the user.

Peer to peer route guidance

In embodiments, a method includes receiving a first user input to a chat managed by a multiple-round dialogue system, receiving a second user input to the chat, the second user input following the first user input, and embedding the first and second user inputs into first and second nodes, respectively, each node including a multi-dimensional vector. The method further includes determining, based at least in part on the first node and the second node, if a context of the second user input is the same as a context of the first user input, and, based on the determination, generating a chat reply to the second user input.

Cognitive management of context switching for multiple-round dialogues

A method and system for generating test cases of different types for testing an application. A functional flow of the application is created. The test cases are generated, based on at least one test case generation rule and additional test information corresponding to different stages of the functional flow with respect to at least two test types.

Test cases generation for different test types

The present invention provides methods and systems for saving and querying context data for an online application. The context data of an online application related to pages visited by a user are collected, where the context data is associated with page identifiers of the visited pages. A step-by-step path is generated based on the page identifiers of the pages visited by the user, and a context data record is generated and saved based on the collected context data and the step-by-step path. According to the methods and systems, a query term is further generated using on the collected context data and the step-by-step path, for performing query to the context data. By applying the methods and systems of the present invention to different contexts, the user is able to easily save and later reference the previous actual running data of some functional contexts.

Method and system of saving and querying context data for online applications

A method, and associated data processing system and computer program product, for generating test cases of different types for testing an application. A functional flow of the application is created based on a system design of the application. Additional test information corresponding to different stages of the functional flow with respect to a test types is generated. The generation of additional test information includes utilizing templates associated with the test types. The test cases are generated based on the additional test information and at least one test case generation rule. The test cases of different types are associated with one another.

Growing community of inventors

Beijing, China

De Shuo Kong