Xerox Corporation

Conduent Business Services, LLC

Tong Sun

Wei Hua Peng

Saurabh Singh Kataria

Michael David Shepherd

Hua Liu

Shriram V Revankar

Arun Bakthavachalu

Sumit Bhatia

Veerasundaravel Thirugnanasundaram

Ming Zhong

John Oliver Walker

Philip Crane Rose

Alan Thomas Coté

Alan T Cote

Dhanwant Singh Kang

Lei Li

Narasimha Raju Gottumukkala

Palghat Srinivas Ramesh

Jing Zhou

David R Vandervort

Margaret Helen Szymanski

Arvind Agarwal

Francisco Marino Valeriano

Jonas Karlsson

Sabrina Pui-Wah Matsunaga

Amos Y Kuo

Julien Jean Lucien Bourdaillet

Changjun Wu

Raju N Gottumukkala

Xue Gu

Jingxuan Li

Akiko Okazaki

Joshua Mateo

Edward Werner

Robert Hendricks

Fenglong Ma

Alexandra Woodbury

Gregory Cameron

Radha Chitta

A long-term memory network method and system for text comprehension. A recurrent neural network can be provided, which includes an external memory module and a long-short term memory unit, wherein said recurrent neural network encodes raw text information into vector representations, forms memories, finds relevant sentences to answer questions, and generates multi-word answers to said questions utilizing the long short term memory unit.

Long-term memory networks for knowledge extraction from text and publications

The disclosed embodiments illustrate methods and systems for searching for a first user. The one or more inputs pertaining to one or more first attributes of the first user are received. Further, the one or more first attributes of the first user are ranked based on at least a presence of the one or more first attributes among one or more second attributes pertaining to one or more second users. Thereafter, one or more search strings comprising at least one attribute selected from the ranked one or more first attributes are generated, wherein the one or more search strings are utilizable to search for the first user. Finally, a list of third users is obtained from one or more search engines in response to the one or more search strings.

Methods and systems for searching for users

A method, non-transitory computer readable medium, and apparatus for recommending a topic-cohesive and interactive implicit community are disclosed. For example, the method receives a request for customer care, selects an implicit community identified from a plurality of individual users of a social media website based upon a relevance score related to a topic of the request for customer care and recommends the implicit community in response to the request for customer care.

Method and apparatus for recommending topic-cohesive and interactive implicit communities in social customer relationship management

A method and a system are provided for correlation detection in multiple spatio-temporal datasets for event sensing in a geographical area. The method includes extracting datasets, comprising information about one or more events, from one or more data sources. The method further includes identifying a primary data source and secondary data sources from the one or more data sources. The method further includes extracting primary features from the datasets associated with the primary data source and secondary features from the datasets associated with the secondary data sources. The primary features are categorized into one or more categories. The method further includes training classifiers based on the primary features and/or the one or more categories. The method further includes detecting a correlation among the information associated with the one or more events based on a category transfer distribution from the primary data source to the secondary data sources.

Method and system for correlation detection in multiple spatio-temporal datasets for event sensing

A method and a system for generating a search query to extract one or more relevant messages from a plurality of messages shared over a computer network. The method includes extracting a plurality of keywords and information pertaining to a plurality of customers from the plurality of messages. Further, the method identifies a set of influential customers from the plurality of customers based on a first score and a second score. The method further includes extracting a set of influential keywords from a first set of messages based on a first number of occurrences of the plurality of keywords in the plurality of messages within a pre-defined time interval. The method further includes generating the search query that includes at least the set of influential customers and the set of influential keywords.

Method and system for generating a search query

A first embodiment of the disclosure relates to a method for responding to a message posted in a social media stream. The method includes monitoring a social media site for at least one message including select subject matter. In response to identifying a message, the method includes collecting a series of exchanges that form a conversational thread including the message. The method includes determining at least one content attribute of the message. The method includes classifying the message using at least one key attribute. The method includes searching a database for a reference message using a combination of the at least one content and key attributes. The method includes determining a previous outcome of a reference thread including the reference message. The method includes using the previous outcome for determining a course of action.

System and method for auto-suggesting responses based on social conversational contents in customer care services

The technical solution under the present disclosure automatically analyzes conversations between users by receiving a training dataset having a text sequence including sentences of a conversation between the users; extracting feature(s) from the training dataset based on features; providing equation(s) for a plurality of tasks, the equation(s) being a mathematical function for calculating value of a parameter for each of the tasks based on the extracted feature; determining value of the parameter for tasks by processing the equation(s); assigning label(s) to each of the sentences based on the determined value of the parameter, a first label being selected from a plurality of first labels, and a second label being selected from a number of second labels; and storing and maintaining with the database a pre-defined value of the parameter, first labels, conversations, second labels, a test dataset, equation(s), and pre-defined features.

Methods and systems for automatic analysis of conversations between customer care agents and customers

What is disclosed is a customer relationship management system to help customer care agents prioritize a response to an incoming message. Historical conversations between customers and agents are retrieved. Each conversation has associated features and an assigned priority. Features are categorized into a plurality of categories. A priority is assigned to each category based on the features and the cumulative priority of all conversations in each category. Thereafter, an incoming message is received from a customer's computing device. Features are extracted from the incoming message. A determination is then made as to which of the categories this incoming message belongs based on this message's features. A priority is then assigned to the incoming message based on a priority assigned to the category which the incoming message belongs. The priority is then displayed for a customer agent so the agent can prioritize his/her response to that customer's incoming message.

Methods and systems for assigning priority to incoming message from customer

The present disclosure provides a system that allows for the real-time and online monitoring of the exchanges between customers and a CRM team over social media. While crawling all messages exchanged over the social media by customers and CRM team, the system aggregates related messages exchanged between a given customer and the CRM team into a conversation. The system includes a linguistic framework for the analysis of conversations (based on the two linguistic theories of dialog acts and conversation analysis) to label the nature of the messages in a conversation or thread.

Conversation analysis of asynchronous decentralized media

A system and method for analyzing social media data by obtaining social media data from a social media platform, where the social media data includes documents from multiple users of the social media platform; classifying the documents using a sentiment classifier; tokenizing the documents into terms; associating a sentiment with each term; detecting a first event based on a number of occurrences of a first term in the documents; and providing information associated with the event to a user, where the information includes the first term and a sentiment associated with the first term.

Methods and systems for monitoring and analyzing social media data

A method, non-transitory computer readable medium, and apparatus for extracting text from a social media document are disclosed. For example, the method indexes a plurality of social media documents into a plurality of snippets, receives a query including one or more keywords and a purpose, identifies one or more of the plurality of snippets that include the one or more keywords in an index, ranks the one or more of the plurality of snippets in accordance with the purpose and provides the one or more plurality of snippets that are ranked in accordance with the purpose.

Method and apparatus for extracting portions of text from long social media documents

A method, non-transitory computer readable medium, and apparatus for large-scale web community detection using a graphical processing unit (GPU) are disclosed. For example, the method receives an input graph formatted into one or more first adjacency lists from a central processing unit (CPU), performs a first level shingling on the one or more first adjacency lists, sends the first level shingling to the CPU to generate an aggregate graph based upon the first level shingling, receives the aggregate graph formatted into one or more second adjacency lists from the CPU, performs a second level shingling on the one or more second adjacency lists and sends the second level shingling to the CPU to generate a dense sub-graph that identifies one or more web communities.

Method and apparatus for graphical processing unit (GPU) accelerated large-scale web community detection

Embodiments generally relate to systems and methods for detecting topics in social media data. More particularly, the systems and methods can extract a concept hierarchy from a set of data, wherein the concept hierarchy comprises a plurality of layers. Further, the systems and methods can train topic models based on the content in each of the layers. Still further, the systems and methods can select the most appropriate topic model for social media data by balancing the complexity of the model and the accuracy of the topic detection result. Moreover, the systems and methods can use the most appropriate topic model to detect topics in social media data.

Systems and methods for scalable topic detection in social media

Methods and a system are disclosed for a collaborate brainstorming interface that defines a collaboration session with a three dimensional holographic mind map. An intelligent agent guides a collaboration session that is structured by the interface. The intelligent agent detects key words, work flow steps and user interactions in the session to initiate searches that are filtered using artificial intelligence. The results are presented to developers interacting through the interface.

Smart collaborative brainstorming tool

A system and method for the dynamic allocation of resources based on fairness, throughput, and user behavior measurement. A resource allocation decision can be made based on an index value computed by a selection index function. A fairness coefficient and a throughput coefficient, which represent the significance of fairness and throughput can be computed utilizing a reinforcement learning algorithm. The degree of fairness and throughput coefficient can be varied while allocating resources. A user behavior coefficient with respect to a user can be computed to determine the degree of cooperativeness of the user with other users and the value of user behavior coefficient can be updated each time it interacts with the system.

Growing community of inventors

Penfield, NY, United States of America

Tong Sun