International Business Machines Corporation

Palo Alto Research Center Inc.

Nec Corporation

Sap Se

Robert John Moore

Pawan Raghunath Chowdhary

Sunhwan Lee

Shun Jiang

Guangjie Ren

Eric Kevin Butler

Hovey R Strong, Jr

Thomas D Griffin

Anca Andreea Chandra

Jeanette L Blomberg

Divyesh Jadav

Heiko Hary Ludwig

Nathalie Baracaldo Angel

Chung-hao Tan

Raphael I Arar

Lei Huang

Margaret Helen Szymanski

Taiga Nakamura

Rafah A Hosn

Eric Young Liu

James Douglass Thornton

Nicolas B Ducheneaut

Trudy L Hewitt

Robert Huntington Grant

Daniel Gureasko Bobrow

Diana Kathryn Smetters

W Keith Edwards

Chris Kau

Eric Stephen Nickell

Michal Shmueli-Scheuer

Susanne M Glissmann-Hochstein

Mitchell Mason

Saurabh Mishra

Amir J Safavi

Kenneth A Winburn

Eric Hc Liu

Jeffrey Thomas Kreulen

Hovey Raymond Strong

Allison Gyle Woodruff

Fatma Ozcan

Paul Masami Aoki

Peifeng Yin

Dorian B Miller

Abdul Hussain Quamar

Sungeun An

Koji Kawashima

Techniques for personalizing an AI automated conversational system are provided. In one aspect, a method for personalizing an automated conversational system includes: making predictions of a familiarity of a user with concepts needed to understand a standard output utterance based on the familiarity of an aggregate of users and a background knowledge model of the concepts and related concepts, wherein the standard output utterance assumes that the concepts are known; and giving, by the automated conversational system, an output utterance that is tailored to the user given the predictions. For instance, the automated conversational system can give the standard output utterance to the user when it is predicted that the user is familiar with the concepts, or a nonstandard output utterance when it is it is predicted that the user is unfamiliar with at least one of the concepts.

Personalizing automated conversational system based on predicted level of knowledge

A computer-implemented method for generating an ontology-driven conversational interface includes generating an ontology from a description of a domain schema of a Data Analysis (DA) model, in which the DA model is a defined in terms of quantifiable, qualifying or categorical entities and their relationships as described by the domain schema. Conversational artifacts of a conversation space including a conversational pattern framework are generated by extracting DA-related intents, entities, and a dialog from the generated ontology for the conversational interface. A dialog logic table maps DA-related patterns to intents, extracted quantifiable, qualifying or categorical attributes to entities, and the dialog to user-prompts for one or more parameters in an identified DA pattern. The conversation space is integrated with at least one of an external data source or an analytics platform that stores and processes data.

Ontology-driven conversational interface for data analysis

A computer-implemented method of voice-to-text tagging for transcription of a human voice signal by one of an automatic speech recognition system, or a natural conversation, includes generating a speech-to-text verbal transcript of the verbal vocalizations of an audio signal at a verbal timestamp of the audio signal. A voice-to-text non-verbal transcript of the one or more non-verbal vocalizations of the audio signal is generated at a non-verbal timestamp of the audio signal. The non-verbal transcript and the verbal transcript are combined to generate an enhanced transcript.

System for voice-to-text tagging for rich transcription of human speech

A computer-implemented method according to one embodiment includes determining a starting folder within a file system, computing, for each child folder of the starting folder, a similarity metric indicating a level of similarity to a file, selecting two child folders of the starting folder having greatest similarity metrics, comparing a difference between the greatest similarity metrics of the two child folders to a predetermined threshold, and conditionally selecting the starting folder as a recommended folder to which the file is saved, based on the comparing.

Suggesting a destination folder for a file to be saved

According to one embodiment, a computer-implemented method for dynamically modifying placeholder text in a conversational interface includes: processing a conversation log reflecting a conversation between a human user and an automated agent; determining, based at least in part on the processing: one or more capabilities of the automated agent; and/or a trajectory of the conversation; and dynamically modifying placeholder text in the conversational interface based at least in part on: the one or more capabilities of the automated agent; the trajectory of the conversation; or both the one or more capabilities of the automated agent and the trajectory of the conversation. Other embodiments in the form of systems and computer program products are also disclosed.

Dynamic modification of placeholder text in conversational interfaces

One embodiment provides a method for predicting a next action in a conversation system that includes obtaining, by a processor, information from conversation logs and a conversation design. The processor further creates a dialog graph based on the conversation design. Weights and attributes for edges in the dialog graph are determined based on the information from the conversation logs and adding user input and external context information to an edge attributes set. An unrecognized user input is analyzed and a next action is predicted based on dialog nodes in the dialog graph and historical paths. A guiding conversation response is generated based on the predicted next action.

Graph based prediction for next action in conversation flow

One embodiment provides a method that includes obtaining a default language corpus. A second language corpus is obtained based on a second language preference. A first transcription of an utterance is received using the default language corpus and natural language processing (NLP). At least one problem word in the first transcription is determined based on an associated grammatical relevance to neighboring words in the first transcription. Upon determining that a first probability score is below a first threshold, an acoustic lookup is performed for an audible match for the problem word in the first transcription based on an associated acoustical relevance. Upon determining that a second probability score is below a second threshold, it is determined whether a match for the problem word exists in the secondary language corpus. Upon determining that the match exists in the secondary language corpus, a second transcription for the utterance is provided.

Speech-to-text transcription with multiple languages

In one general aspect, a computer-implemented method includes identifying current choices with different verbosity levels for a current turn in a conversation; normalizing multi-dimensional verbosity vectors for each of the current choices to obtain a normalized value for each of the current choices; determining a state definition for the current turn in the conversation, utilizing the normalized values for each of the current choices; providing the state definition for the current turn in the conversation and the normalized values for each of the current choices to a trained reinforcement learning module; receiving, from the trained reinforcement learning module, a score associated with each of the current choices for the current turn in the conversation; and selecting one of the current choices to be entered for the current turn in the conversation, based on the score associated with each of the current choices for the current turn in the conversation.

Adjusting a verbosity of a conversation turn

One embodiment provides a method including receiving authoring conversational training data. A machine learning based conversational agent is trained with the conversational training data. The training includes: creating and storing example transcripts of user utterances, creating and storing example transcripts of agent utterances, sequencing utterance transcripts using the example transcripts of user utterances and the example transcripts of agent utterances, forming a corpus from the sequenced utterance transcripts, marking speech patterns that represent social actions from tagging the sequenced utterance transcripts, and forming a patterned corpus from the marked speech patterns.

Program dialog by example

One embodiment provides a method that includes generating, by a processor, a topic graph by converting information to topic nodes and edges in the topic graph. Bridges from a given topic node are provided to a neighbor node based on a weight assignment. The bridges are converted to an electronic form of communication. The processor orders suggested paths based on a determined distance from at least one other topic node to a topic goal node via an earliest topic node on each suggested path. The determined distance is found by a first search of the topic graph.

Topic bridging determination using topical graphs

Embodiments of the present invention provide a method comprising receiving a task set comprising multiple tasks, receiving operational information identifying one or more operating characteristics of multiple drones, and obtaining an initial heuristic ordering of the multiple tasks based on the operational information and the climate information. Each task has a corresponding task location. The method further comprises scheduling the multiple tasks to obtain a final ordering of the multiple tasks. The final ordering represents an order in which the multiple tasks are scheduled, and the final ordering may be different from the initial heuristic ordering.

Drone carrier

One embodiment provides a method comprising intercepting an incoming communication for a user, and determining whether to classify the incoming communication as a suspicious incoming communication based on content of the incoming communication and a learned classification model or learned signatures. The method further comprises monitoring one or more outgoing communications from the user, and invoking an action relating to scam prevention in response to determining an outgoing communication from the user is linked to a suspicious incoming communication.

Outgoing communication scam prevention

One embodiment provides a method comprising maintaining a multi-dimensional data structure partitioned into cells utilizing a tree data structure ('tree') comprising intervals for each dimension of a multi-dimensional space. To partition an interval for a node of the tree into multiple subintervals, multiple leaf nodes ('leaves') are generated, each leaf descending from the node. To merge multiple intervals for multiple nodes of the tree, a parent node (&#x201c;parent&#x201d;) and multiple leaves descending from the parent are generated, the parent and the leaves are time constrained, and the leaves are scheduled for a merger. When transient data in cells included in a list that corresponds to a leaf scheduled for merger expires, each cell in the list is converted into a cell for inclusion in a different list corresponding to a parent of the leaf, each leaf of the parent removed, and the parent turned into a leaf.

Drone management data structure

A method and system of automatically identifying topics of a conversation are provided. An electronic data package comprising a sequence of utterances between conversation entities is received by a computing device. Each utterance is classified to a corresponding social action. One or more utterances in the sequence are grouped into a segment based on a deep learning model. A similarity of topics between adjacent segments is determined. Upon determining that the similarity is above a predetermined threshold, the adjacent segments are grouped together. A transcript of the conversation including the grouping of the adjacent segments is stored in a memory.

Topic mining based on interactionally defined activity sequences

A computer-implemented method includes identifying a plurality of protected pieces from a conversation. The computer-implemented method further includes generating one or more confidence scores for each protected piece, wherein a confidence score is a degree of associativity between a protected piece and a type of sensitive information. The computer-implemented method further includes determining that the protected piece is associated with the type of sensitive information. The computer-implemented method further includes determining a type of protection action for each protected piece in the plurality of protected pieces. The computer-implemented method further includes performing the type of protection action for each protected piece in the plurality of protected pieces to form a modified conversation that is devoid of the sensitive information. A corresponding computer system and computer program product are also disclosed.

Selective enforcement of privacy and confidentiality for optimization of voice applications

Growing community of inventors

San Jose, CA, United States of America

Robert John Moore