International Business Machines Corporation

Industrial Technology Research Institute

Ci-Wei Lan

Chiwen Chang

Kuo-Liang Chou

Tsai-Hsuan Hsieh

Yu Sun

Wen Liu

Jie Hui Xu

Ting Ting Zhang

Xiang Yu Yang

Peter Wu

Ching-Chun Liu

I-Chien Lin

Jen-Hao Hsiao

Dong Ni

Li Yue

Yiping Qu

Tao-Hung Jung

Kate Lin

Tzu-Chen Chao

Chao Zhang

Zhong Fang Yuan

Chih-Hsiung Liu

Tong Liu

De Shuo Kong

Der-Joung Wang

Yu-Siang Chen

Cheng-Fang Lin

Chen Gao

Xin Fang Hao

Tyrone Wilberforce Grandison

Jing Du

Min Luo

Norman Kung

Ya-Ling Chen

Yu-siang Chen

Li-Feng Tseng

Rong Fu He

Hao Chun Hung

Ya-Fan Yeh

Yi-Hui Chen

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

An approach is provided for dynamically identifying a danger zone for a predicted traffic accident and generating a warning about the accident. From a monitoring device at a first location, information about traffic conditions for vehicles at time Tand at least one subsequent time T+t is received. Based on speeds of the vehicles and a fixed distance from the first location, a response time is calculated. Within the response time, a dual artificial intelligence (AI) model using shallow and deep learners applied on historical accident data is employed. Based on the dual AI model and the traffic conditions, an accident involving vehicle(s) in the traffic is predicted to occur in a zone. A warning about the accident is generated and sent to device(s) in the vehicle(s). The warning is presented to driver(s) of the vehicle(s).

Dynamically identifying a danger zone for a predicted traffic accident

In an approach to detecting the transmission of messages, analyzing said messages, calculating a message risk score and transmitting a warning notification, one or more computer processors detect transmission of a message from a user to a selected recipient. The one or more computer processors extract message information from the detected message. The one or more computer processors retrieve one or more historical conversations between the user and the selected recipient of the detected message. The one or more computer processors determine a risk score corresponding to sending the detected message to the selected recipient based on applying the extracted message information and the retrieved historical conversations to a cognitive model.

Mistaken message prevention based on multiple classification layers

A wearable medical device comprising an annular housing configured to attach to a wrist of a patient. The wearable medical device having a first receptacle attached to the annular housing for receiving a first portion of a tube of an intravenous delivery system. The wearable medical device comprising a flow regulator attached to the annular housing and in contact with the first portion of the tube, where the flow regulator is configured to modify a geometric characteristic of the first portion of the tube. The wearable medical device further comprising a wireless transmitter for communicating with a user console.

Wearable medical device for monitoring intravenous injection

A system and method for privacy identity control for sharing media on a social media platform includes receiving a digital image encoded with a privacy identification data from a media capturing device for sharing on the social media platform, retrieving a first key based on the privacy identification data for decrypting an encrypted personal privacy protocol, wherein the personal privacy protocol is encrypted using a second key, decrypting the encrypted personal privacy protocol using the first key to obtain a decrypted personal privacy protocol, and displaying the digital image on the social media platform based on the decrypted personal privacy protocol.

Personal privacy protocols for sharing media on social media platforms

A system, method, and computer program product for tracking interactive events. Facial expression data and interactive event data are received. A new facial expression is detected in the facial expression data, and the new facial expression and corresponding interactive event data are recorded. The new facial expression is recognized based on training data, and in response, a definition is assigned to the new facial expression. The corresponding interactive event data is tagged with the definition.

Selective interactive event tracking based on user interest

An approach is provided to provide URLs based on a digital subject matter image (DSMI) received from a requestor. The approach identifies a set of classification labels pertaining to the DSMI and matches the set of classification labels against multiple sets of predefined labels with each of the sets of predefined labels corresponding to a URL. The matching results in a selected URL pertaining to the DSMI with this URL being returned to the requestor. In one embodiment, the approach is performed by a domain name system (DNS).

Image-based domain name system

Embodiments of the present invention provide a method, system and computer program product for telephonic fraud prevention. In an embodiment of the invention, a method of telephonic fraud prevention includes speech recognizing in real-time, audio of a telephone call from a caller to a called party. Once the real-time audio has been speech recognized into text, the text may be parsed into words and the words compared to a hierarchical semantic tree of terms. On the condition that a match is detected between one of the words and a node of the tree, a level of the tree is identified at which the match is detected and the level is correlated to a degree of risk of the telephone call. Finally, an alert is displayed to the called party reflecting the degree of risk.

Cognitive telephone fraud detection

A computer-implemented method includes receiving a data stream, the data stream including one or more driving factors. The computer-implemented method further includes comparing the one or more driving factors to one or more known driving factors to identify a driving scenario. The computer-implemented method further includes monitoring the driving scenario for a risk. Monitoring the driving scenario for a risk further includes detecting the risk. The computer-implemented method further includes generating an intervention, wherein the intervention is generated based on detecting the risk for the driving scenario. A corresponding computer system and computer program product are also disclosed.

Automated intervention to modify driving behaviors

Embodiments are directed to detecting and uploading measurement data of a non-connected medical measuring device. Embodiments include capturing an image of an identification object and a beginning event image of a medical measuring device and extracting identification data from the image of the identification object. Based on detecting that the identification object has been removed, an ending event image of the medical measuring device is captured. Embodiments include determining if a measurement event has occurred by comparing the ending event image and the beginning event image. Based on determining that the measurement event occurred, a measurement data of the ending event image is extracted and upload to a personal health record database.

Uploading measurement data of non-connected medical measuring devices

A method and a system for preserving privacy of a dataset are provided. In the method, a k-anonymity value with respect to a sensitive data field is determined according to at least one first quasi-identifier. Data entries in each group have the same value in the one or more fields of the first quasi-identifier and data entries in different groups have different values in the one or more fields of the first quasi-identifier. A first group and a second group among the plurality of groups are determined according to the reference number Kr, where the first group and the second group are merged into a merging group. The number of data entries in the merging group is not less than a reference number Kr. One or more fields of at least one first quasi-identifier is masked for the merging group.

Method and system for preserving privacy of a dataset

Growing community of inventors

Keelung, Taiwan

Ci-Wei Lan