International Business Machines Corporation

Guang Ming Zhang

Yun Ting Wang

Hong Wei Jia

Xin Yang

Shuang Shuang Li

Hai Lei Song

Mo Chi Liu

Shuo Li

Yue Li

Jun Feng Liu

Zhao Li

Qian Li

Yun Bj Wang

Xiaoyang Yang

Zhi Zhu

Pei Pei Liang

Wu Yan

Wenyan Yuan

Jing James Xu

Ke Wei Wei

Yuan Feng

Jun Wang

Yi Dai

Chu Yun Tong

Shuang Ys Yu

Ling Zhuo

Pu Zhu

Zhao Zhong

He Yang

An embodiment generates an initial set of training data from monitoring data. The initial set of training data is generated by combining outputs from a plurality of pretrained classifiers. The embodiment trains a new classification model using the initial set of training data to identify anomalies in monitoring data. The embodiment performs a multiple-level clustering of the data samples resulting in a plurality of clusters of sub-clusters of data samples, and generates a review list of data samples by selecting a representative data sample from each of the clusters. The embodiment receives an updated data sample from the expert review that includes a revised target classification for at least one of the data samples of the expert review list. The embodiment then trains another replacement classification model using a revised set of training data that includes the updated data sample and associated revised target classification.

Intelligent expansion of reviewer feedback on training data

Embodiments of the present disclosure relate to a solution for translation verification and correction. According to the solution, a neural network is trained to determine an association degree among a group of words in a source or target language. The neural network can be used for translation verification and correction. According to the solution, a group of words in a source language and translations of the group of words in a target language are obtained. An association degree among the group of words and an association degree among the translations can be determined by using the trained neural network. Then, whether there is a wrong translation can be determined based on the association degrees. In some embodiments, corresponding methods, systems and computer program products are provided.

Translation verification and correction

A method of operating a shared computing environment includes receiving a client request for an optimized runtime configuration of the shared computing environment for executing a task, receiving runtime data of the task collected from a prior runtime, inferring a runtime configuration from the runtime data, determining a predicted timeseries workload for the shared computing environment, updating the runtime configuration to including the timeseries workload prediction, wherein the updating outputs the optimized runtime configuration, and configuring the shared computing environment according to the optimized runtime configuration in executing the task.

Machine learning based runtime optimization

Systems and methods for computer-automated labeling of data are disclosed. In embodiments, a method includes: identifying technical data assets in lineage data and corresponding business items in User Interface (UI) data of a user, wherein the lineage data includes a data source for the UI data; mapping the technical data assets to the corresponding business items; determining relevant labels to assign to the technical data assets from a label repository based on a similarity analysis of names of the corresponding business items and labels in the label repository; determining that one or more of the relevant labels meet a confidence threshold based on the similarity analysis; and automatically assigning the one or more of the relevant labels to associated ones of the technical data assets based on the determining that the one or more of the relevant labels meet the confidence threshold.

Automated data labeling

A method includes receiving an input from a user, the input including a selection of an object, where the object is contained in a video, identifying, in response to the input, the object in the video, determining an attribute of the object associated with a profile of the user, where the profile contains a preference of the user regarding at least one object to be viewed, and determining, in response to the attribute of the object associated with the profile, a target segment in the video, where the target segment includes the object.

Interactive video generation

A method for curating documents, executed by a computer, includes detecting one or more themes in a document, identifying one or more user interests for a user, presenting a ranked list of the one or more themes to the user, and dynamically updating the ranked list based on user feedback. The ranked list may be ranked according to the one or more user interests. A computer program product and computer system corresponding to the above method are also disclosed herein.

Document curation

As disclosed herein a method, executed by a computer, includes monitoring proximate automobiles using a camera, receiving a request to transmit a communication connection request to a selected automobile, and determining observed attributes corresponding to the selected automobile based on images from the camera. The method further includes broadcasting, over a network, the observed attributes to the proximate automobiles, and requesting disclosed attributes and a connection identifier from the proximate automobiles that match the observed attributes, receiving at least one response from the proximate automobiles that match the observed attributes, and determining which response is a best match to the selected automobile. The method further includes transmitting the communication connection request to the selected automobile over the network using the connection identifier corresponding to the best match. A computer program product corresponding to the above method is also disclosed herein.

Enhanced communication system

Growing community of inventors

Beijing, China

Guang Ming Zhang