International Business Machines Corporation

Ke Ke Cai

Zhong Su

Li Ni Zhang

Shi Wan Zhao

Hong Lei Guo

Chang Hua Sun

Sheng Hua Bao

Shuo Zhang

Feng Jin

Xian Wu

Changhua Sun

Jing Ding

Zhi Li Guo

Dong Xu Duan

Shiwan Zhao

Yong Qin

Jian Min Jiang

Yue Chen

Bing Jiang Sun

Honglei Guo

Hamid Reza Motahari Nezhad

Shuang Ys Yu

En Liang Xu

Guo Yu Tang

Xiao Lu Zhang

Techniques are provided for training, by a system operatively coupled to a processor, an attention weighted recurrent neural network encoder-decoder (AWRNNED) using an iterative process based on one or more paragraphs of agent sentences from respective transcripts of one or more conversations between one or more agents and one or more customers, and based on one or more customer response sentences from the respective transcripts, and generating, by the system, one or more groups respectively comprising one or more agent sentences and one or more customer response sentences selected based on attention weights of the AWRNNED.

Facilitating automatic detection of relationships between sentences in conversations

A computer-implemented method is provided for allocating a set of shared dockless bikes. The method includes providing a notification to a user of an availability prediction of a shared dockless bike, from among the set of shared dockless bikes, based on a trajectory of the shared dockless bike with respect to a current location of the user, and adding the user to a request queue associated with the current location of the user, responsive to the user agreeing to wait a specified time period for access to the shared dockless bike. The method further includes maintaining an available bikes queue for newly available shared dockless bikes, from among the shared dockless bikes, responsive to the newly available ones of the shared dockless bikes becoming available. The method also includes notifying users of the newly available shared dockless bikes in a priority order determined from the request queue.

Dynamic booking system for shared dockless bikes using trajectory position

A virtual change database system that supports iterative and parallel database application development is disclosed. The system stores a common set of base physical data and a plurality of sets of virtual changes. Each set of virtual changes is associated with a database object. A database application may access a database object in the database by using the virtual version of the object to extract the object's data content from the common base physical data. The database system present a first query response to (i) a first application based on the set of base physical data and (ii) a first set of virtual changes for a particular database object, while also presenting a second query response to a second application based on the set of base physical data and a second, different set of virtual changes for the particular database object.

Managing database object schema virtual changes

A data processing system identifies a first topic for a first table, identifies a second topic for a second table, collects at least one first table attribute comprising at least one row name for the first table, and collects at least one second table attribute comprising at least one row name for the second table. The at least one semantic vector for the first table is compared with the at least one semantic vector for the second table to identify as related at least one row of the first table and at least one row of the second table. The at least one row of the first table and the at least one row of the second table are provided to a communication device with an identification as related.

Comparing tables with semantic vectors

A method, a device and a computer program for conformity determination of cross-regional affairs. The method comprises obtaining characteristics from a description of an affair at least crossing a local region and a non-local region. The method further comprises generating a multi-level constraint based on the characteristics from a knowledge base, and the knowledge base includes regulations for cross-regional affairs, and the multi-level constraint includes a local constraint associated with the local region and a non-local constraint associated with the local region and the non-local region. Moreover, the method also comprises determining conformity of the affair to the multi-level constraint. The method can determine the conformity of the cross-regional affairs automatically, thereby reducing the consumption of human resources and the inconformity risk in the cross-regional affairs.

Conformity determination of cross-regional affairs

This disclosure provides a computer-implemented method. The method may include extracting one or more features based on a first utterance from a first interlocutor in a dialog and a second utterance from a second interlocutor in the dialog. The method may further include inferring one or more personality traits of the first interlocutor based on the one or more extracted features from the dialog.

Context-based linguistic analytics in dialogues

Embodiments of the invention provide a computer-implemented method, computing system and computer program product for analyzing a message in a social network. The method comprises identifying an entity from the message; detecting historical popularity of the entity in a social network; identifying a topic from the message; detecting historical popularity of the topic in the social network; and generating an entity-topic correlation factor for the entity and the topic based on the historical popularity of the entity and the historical popularity of the topic. Results obtained with embodiments of the invention may be provided to popularity prediction tools for improving popularity prediction of messages in social networks.

Analyzing messages in social networks

Embodiments include methods, and mobile computing devices, and computer program products for creating personalized photo albums on mobile computing devices based on social media data. Aspects include: accessing, via mobile computing device, various photos taken by a user of mobile computing device, retrieving, from one or more social media streams, various media photos posted by user of the mobile computing device, extracting image features from the photos and the media photos, and text features from the media photos, generating photo clusters based on the image features of the photos, and media photo clusters based on the image features of the media photos, respectively, matching the photo clusters and the media photo clusters, tagging the photo clusters and the media photo clusters matched based on the text features extracted from the media photos, and generating a personalized photo album based on the photo clusters tagged and the media photo clusters tagged.

Methods and systems of personalized photo albums based on social media data

In response to receiving a question, a corpus of textual data having content related to the question is obtained. At least one segment is extracted from the corpus of textual data. At least one question-answer pair is generated from at least one segment. Each question-answer pair comprises a candidate question and an answer corresponding to the candidate question.

Question-answer pair generation

Embodiments of the present disclosure relate to non-sequential document comparison. A first plurality of segments in a first document and a second plurality of segments in a second document are obtained. In response to a first segment from the first plurality of segments being associated with a second segment from the second plurality of segments, a third segment from the first plurality of segments is associated with a fourth segment from the second plurality of segments.

Non-sequential comparison of documents

A method for enriching contents of a website includes obtaining a corpus from the current website and other websites, and extracting object features from the corpus, wherein the corpus comprises specifications of the object and user reviews about the object; according to the corpus, constructing multi-dimensional vectors for the extracted features; for a specified feature, making similarity comparison of its multi-dimensional vector and multi-dimensional vectors of other extracted features; determining features with similarities higher than a predetermined threshold as the same features, and reinforcing the current website with features different from that of the object on the current website and their corresponding attributes.

Growing community of inventors

Beijing, China

Ke Ke Cai