International Business Machines Corporation

Sony Corporation

Lenovo (singapore) Pte. Ltd.

Airbnb, Inc.

Claudio Santos Pinhanez

Ana Paula Appel

Gopal Sarma Pingali

Paulo Rodrigo Cavalin

Heloisa Caroline De Souza Pereira Candello

Rogerio Abreu De Paula

Alan Braz

Anthony Tom Levas

Marisa Affonso Vasconcelos

Maira Athanazio De Cerqueira Gatti

Silvia C S Bianchi

Julio Nogima

Mark Edward Podlaseck

Maira Gatti De Bayser

Luis Gregorio Moyano

Andre Gama Leal

Frederik Carl Moesgaard Kjeldsen

Victor Boa Juliani

Marcela Megumi Terakado

Chandrasekhar Narayanaswami

Mu Qiao

Mandayam Thondanur Raghunath

Vagner Figueredo De Santana

Frederik C Kjeldsen

Sergio Borger

Sinem Guven

Yuya Jeremy Ong

Frederik C M Kjeldsen

Nicholas Linck

Mauro Carlos Pichiliani

Melina De Vasconcelos Alberio Guerra

Marcelo Carpinette Grave

Carlos R Mendes

Franck Nielsen

Kim Binsted

Joao P Forny De Melo

Frederik Carl Moesgaard K{umlaut Over (j)}eldsen

Heloisa C S P Candello

Renato L F Cunha

Piyawadee Sukavitiya

Victor Henrique Alves Ribeiro

Gabriel Louzada Malfatti

A system may include a memory and a processor in communication with the memory. The processor may be configured to perform operations that include analyzing interactions by a user within a network and generating a user profile for the user. The operations by the processor may further include identifying an attempt by the user to share a post via the network and prompting the user with a personalized alert to evaluate the post, wherein the personalized alert is generated based on the interactions, the user profile, and the properties of the post.

Personalized alert generation based on information dissemination

A method of automatically creating new intents and assigning examples to those new intents in a dialog system includes generating at least one predicted intent from an intent concept graph by combining two or more nodes of the intent concept graph. A graph embedding is generated of the at least one predicted intent. A sentence embedding is generated from examples from a call log. The graph embedding of the at least one predicted intent is then matched with the examples from the sentence embedding and the at least one predicted intent, with the examples, is connected into a dialog system.

Concept prediction to create new intents and assign examples automatically in dialog systems

A computer system includes a processor configured to execute a conversational agent generator function. The conversational agent generator function is configured to receive a plurality of model input queries. Each model input query includes an intent and a corresponding answer to the intent. A database stores a corpus including sets of textual responses indicative of a common meaning. Each textual response in a given set of textual responses indicates a common meaning constructed in a different style indicative of a corresponding tone of communication. The processor is further configured to execute a rephrasing function configured determine the answer of one of the plurality of model input queries, and convert the answer of one of the plurality of model input queries into a plurality of different rephrased answers from the corpus stored in the database. The processor further outputs the plurality of different rephrased answers to the conversational agent generator function.

Adapting conversational agent communications to different stylistic models

A method of providing examples to a computerized conversation agent includes associating one or more triplets of two concepts and a relationship therebetween with an intent related to a query. The triplet is embedded in a knowledge graph and the concepts in the knowledge graph are mapped to the intent. A call log is scanned for examples of the intent based on the concepts in the knowledge graph and the examples are mapped to the intent.

Management of concepts and intents in conversational systems

Embodiments provide for dialog based speech recognition by clustering a plurality of nodes comprising a dialog tree into at least a first cluster and a second cluster; creating a first dataset of natural language sentences for the first cluster and a second dataset of natural language sentences for the second cluster; generating a first specialized language model (LM) associated with the first cluster based on the first dataset; and generating a second specialized LM associated with the second cluster based on the second dataset, wherein the first specialized LM is different from the second specialized LM.

Dialog based speech recognition

A user expertise classifying method, system, and computer program product, include analyzing an input by a user based on at least one of vocabulary, orthography, and grammar of the user input, processing user background data obtained from a database, and calculating an expertise score of the user based on the analyzed user input and the processed background data.

System, method and computer product for classifying user expertise

A conversational agent capability assessment method, system, and computer program product, includes assessing a performance, a personality and a cognitive trait of a conversational agent based on natural written language by a second conversational agent by combining an analysis of a plurality of metrics that each compare a metric from the conversational agent with a metric from the second conversational agent and producing a report detailing the performance, the personality, and the cognitive trait of the conversational agent.

System, method and computer program product for assessing the capabilities of a conversation agent via black box testing

A method for indexing a user interface test recording includes capturing, during a session, a recording of a plurality of interactions with the user interface, capturing, during the session, an event stream including a plurality of user interface events, synchronizing, in time, the plurality of interactions and the plurality of user interface events, identifying a point of interest in the event stream, wherein the point of interest is correlated to a time in the recording by the synchronization, and annotating the recording at a time correlated to when the point of interest occurred.

Indexing and annotating a usability test recording

Identifying life events within social network feeds. The method may include receiving social media data. The method may include identifying life event data within the social media data. The method may include determining a life event probability score associated with a life event class for the life event data using metadata. The method may include assigning a first life event class to each item of life event data based on the life event probability score. The method may include creating conversations by grouping the life event data. The method may include extracting metadata. The method may include determining a conversation probability score for each conversation based on the metadata and the life event probability score associated with each item of life event data. The method may include assigning a second life event class based on the conversation probability score. The method may include displaying the conversations based on user preferences.

Identification of life events within social media conversations

The present disclosure relates generally to the field of segmenting social media users (such as users of a social media network) by means of life event detection (such as based upon social media messages and/or postings) and entity matching. In various embodiments, systems, methods and computer program products are provided.

Segmenting social media users by means of life event detection and entity matching

A conversational agent capability assessment method, system, and computer program product, includes obtaining data to create at least one scenario for testing a conversational agent, performing a set of tests using a scenario of the at least one scenario created to assess a capability of the conversational agent, and comparing a result of the capability from the set of tests with an expected result of the scenario.

Backup and restore of digital data may utilize online social network parameters of a user to determine a number of parts into which to divide digital data and distribute the parts. A list of friends from the social network friends may be selected, e.g., based on a relationship to the user in the social network, to store the parts. The parts may be stored in a friend's device memory, each of the parts stored with a different friend. The digital data may be reconstructed by obtaining a threshold number of parts from the friends.

Storage and recovery of digital data based on social network

A method for surveilling a monitored environment includes classifying an individual detected in the monitored environment according to a role fulfilled by the individual within the monitored environment, generating a trajectory that illustrates movements and locations of the individual within the monitored environment, and detecting when the trajectory indicates an event that is inconsistent with an expected pattern for the role.

Role-based tracking and surveillance

Growing community of inventors

Sao Paulo, Brazil

Claudio Santos Pinhanez