International Business Machines Corporation

Emc IP Holding Company LLC

Marvellworld Trade Ltd.

Fudan University

Jing Ding

Li Ni Zhang

Zhong Su

Jian Wang

Jing Li

Shiwan Zhao

Keke Cai

Shi Wan Zhao

Ke Ke Cai

Chang Hua Sun

Ji Jiang Song

Xin Wang

Yourong Wang

Eric Wu

Fang Cai

Tingting Wu

Haitao Feng

Yingyan Zheng

Jianping Ma

Yujie Xie

Zhidong Mao

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

An erythropoiet-derived peptide having an amino acid sequence as shown in SEQ ID NO: 1. A, method for preparing the above-described erythropoietin-derived peptide. Also provided is the rrse of the above-described erythropoietin-derived peptide fo the preparation of medicament for reatin$ nerve cell damage. Also provided is the use of the above-described erythropoietin-derived peptide for the preparation of a medicament for treating hypoxic brain damage. Also provided is the use of the above-described erythropoietin-derived peptide for the preparation of a medicament for treating epilepsy. The novel EPO-derived peptide of the present invention has a small molecular weight and can penetrate the blood-brain barrier. Moreover, it is a small-molecule polypeptide derived from a functional protein in the human body, having an extremely small side effect to the human body compared with other developed and synthesized thugs, thereby it has a good clinical application prospect.

Erythropoietin-derived peptide, preparation method and use thereof

The subject disclosure relates to employing grouping and selection components to facilitate a grouping of failure data associated with oil and gas exploration equipment into one or more equipment failure type groups. In an example, a method comprises grouping, by a system operatively coupled to a processor, training data of a set of equipment failure data into one or more failure type groups based on one or more determined failure criteria, wherein the one or more failure type groups represent equipment failure classifications associated with energy exploration processes; and selecting, by the system, first ungrouped data from the set of equipment failure data based on a level of similarity between the first ungrouped data and the training data.

Facilitating classification of equipment failure data

A topic guidance method, system, and computer program product for suggesting, via a processor on a computer, a conversation topic for the agent to engage the customer based on a learned conversation topic model, the conversation model being a static model.

Dynamic topic guidance in the context of multi-round conversation

Examples are generally directed towards converting complex structure attributes into flattened data. A configuration capture component analyzes a set of objects associated with a set of complex structure attributes. A complex structure attribute is an attribute of an object that is an array attribute or a nested object attribute. The configuration capture component performs a hash type conversion to convert nested object attributes into flattened data. The configuration capture component performs an array type conversion to convert nested array attributes into flattened data. The flattened data is stored or imported in a set of flattened data files. An expansion component converts the flattened data files back into the complex structure attributes without losing or corrupting the complex structure data.

Converting complex structure objects into flattened data

A topic guidance method, system, and computer program product for creating a conversation model by learning a conversation pattern from a customer response to a conversation topic segment and suggesting a conversation topic for the agent to engage the customer in the conversation topic based on a customer response associated with the conversation model.

Example embodiments of the present disclosure provide methods, a computer system and a computer program product for multimedia information display in an elevator. According to an embodiment of the method, moving status information of an elevator is obtained. The moving status information comprises at least a source floor information indicating where a passenger enters the elevator and a target floor information indicating where the elevator is moving. The multimedia information to be displayed is determined based on the moving status information of the elevator and the determined multimedia information is displayed in the elevator.

Elevator multimedia information display

Aspects of the disclosure provide a method for use in a mobile communication device having at least a first communication system and a second communication system. The method includes conducting a network search with the first communication system to obtain network search information and providing the network search information to the second communication system in the mobile communication device to reduce a network search time of the second communication system.

Device and method for mobile communication

Growing community of inventors

Shanghai, China

Jing Ding