Capital One Services, LLC

Electronics and Telecommunications Research Institute

The City University of New York

Rui Zhang

Erik Thomas Mueller

Victor Alvarez Miranda

Kunlaya Soiaporn

Minh Le

Alexandra Coman

Arturo Hernandez Zeledon

Vinay Igure

Scott Karp

Oluwatobi Olabiyi

Pamela Katali

Tanushree Luke

Kwan-Yuet Ho

Zachary Kulis

Parag Jain

Liwei Dai

Andrew Oestreicher

Tate Travaglini

Sara Mikulic

Varun Singh

Sudheendra Kumar Kaanugovi

Jimmy Sambuo

Cheol Sig Pyo

Eun Ju Lee

Jong Suk Chae

Tae Rim Park

Bong Soo Kim

Myung Jong Lee

Jae Hong Ruy

Angelina Huynh

Alexa Choi

Rachel Johnston

Shweta Jadhav

Jay Goodman Tamboli

William Miller

Jonathan Gross

Dustin Summers

Jihoon Jay Song

Chihyen Yang

Methods and systems are described herein for generating dynamic conversational responses. Conversational responses include communications between a user and a system that may maintain a conversational tone, cadence, or speech pattern similar to a human during an interactive exchange between the user and the system. The interactive exchange may include the system responding to one or more user actions (which may include user inactions), and/or predicting responses prior to receiving a user action.

Systems and methods for generating dynamic conversational responses using deep conditional learning

Methods and systems are described for generating dynamic interface options using machine learning models. The dynamic interface options may be generated in real time and reflect the likely goals and/or intents of a user. The machine learning model may provide these features by interpreting multi-modal feature inputs. For example, the machine learning model may include a first machine learning model, wherein the first machine learning model comprises a convolutional neural network, and a second machine learning model, wherein the second machine learning model performs a Weight of Evidence (WOE) analysis.

Systems and methods for generating dynamic interface options using machine learning models

The disclosed technology involves autonomously identifying goals and sub-goals from a user utterance and generating responses to the user based on the goals and sub-goals.

Systems and methods for generating automated natural language responses based on identified goals and sub-goals from an utterance

Methods and systems are described for generating dynamic conversational responses sensitive to different emotional contexts using machine learning models. The dynamic conversational responses may be generated in real time and reflect the likely emotional context by detecting socially close entities and events in user input.

Modifying dynamic conversational responses based on detecting references to socially close people

Methods and systems for dynamically updating machine learning models that provide conversational responses through the use of a configuration file that defines modifications and changes to the machine learning model are disclosed. For example, the configuration file may be used to define an expected behavior and required attributes for instituting modifications and changes (e.g., via a mutation algorithm) to the machine learning model.

Systems and methods for dynamically updating machine learning models that provide conversational responses

Described are methods and systems are for generating dynamic conversational queries. For example, as opposed to being a simply reactive system, the methods and systems herein provide means for actively determining a user's intent and generating a dynamic query based on the determined user intent. Moreover, these methods and systems generate these queries in a conversational environment.

Systems and methods for generating dynamic conversational queries in user interfaces using state machine libraries

Systems and methods for generating dynamic conversational responses using ensemble prediction based on a plurality of machine learning models

Systems and methods for identifying irregularities during an automated user interaction are disclosed. The system may receive a communication and extract a perceived irregularity from the communication. The system may generate a first explanatory hypothesis associated with the perceived irregularity having an associated confidence measurement. The system may selectively retrieve user information based on the generated hypothesis and generate an investigational strategy associated with the hypothesis. In response to the investigational strategy, the system may receive a user communication, and the system may update the confidence measurement based on the user communication. When the confidence measurement exceeds the predetermined confidence threshold the system may validate the perceived irregularity as a true irregularity and provide a computer-generated dialogue response indicative of a proposed resolution of the irregularity. When no existing hypothesis has a confidence measurement exceeding the threshold, the system may generate a novel hypothesis to be validated.

Systems and methods using natural language processing to identify irregularities in a user utterance

Provided herein are systems and methods for using multi-modal regression to predict customer intent to contact a merchant. Multi-modal data including numerical data and unstructured data are extracted from customer interactions with the merchant. Features of the numerical data and the unstructured data are separately extracted and classified using techniques specific to the data types. The features for each type are then separately used to predict probabilities of customer intent. A neural network is used to combine the predictions into a single set of estimates of customer intent. This set of estimates of customer intents is used to estimate a probability that the customer will contact the merchant. The customer is then contacted based on the estimate.

Multi-modal regression to predict customer intent to contact a merchant

Methods and systems are described for generating dynamic conversational responses using two-tier machine learning models. The dynamic conversational responses may be generated in real time and reflect the likely goals and/or intents of a user. The two-tier machine learning model may include a first tier that determines an intent cluster based on a feature input, and a second tier that determines a specific intent from the cluster.

Systems and methods for a two-tier machine learning model for generating conversational responses

Provided herein are systems and methods for sanitizing logged data packets in a distributed system prior to storing them in a remote or third-party data server. Interactions with an application are monitored and values in a data packet are extracted from the interaction. The values are classified based on a classification configuration and respective labels of the values. The values are then sanitized based on the classification to prevent exposure of secure or private data. The sanitized data packets are then logged into the remote data server. The logged data can be used to help resolve events occurring in the application. The classification configuration can be iteratively updated and the interactions repeated to capture data that was previously sanitized to aid in resolution of events. The logged data can also be used in research or analysis, such as for identifying potential improvements to the application.

Secure and privacy aware monitoring with dynamic resiliency for distributed systems

Conversational agents (CAs) may analyze language input and generate and output a response to a user. For example, when receiving a user's support request, the CA may determine whether to conduct self-disclosure by including information about the CA's 'self' in a response to the user. For example, based on performing sentiment analysis of a support request user input, the CA may determine that the user is expressing negative emotions. Based on the user's expression of negative emotions, the CA may perform self-disclosure as part of generating a response to the user. A CA that is configured to engage in self-disclosure, for instance by including information about a CA's self in an output response, may increase users' acceptance of the CA, which may make a user more likely to trust and/or interact with a CA.

Self-disclosing artificial intelligence-based conversational agents

Systems and methods are provided herein for autonomously determining and resolving a customer's perceived discrepancy during a customer service interaction. The method can include receiving an incoming communication from a customer; extracting a perceived state and an expected state (possibly of a product or service) based on the incoming communication; determining a perceived discrepancy between the perceived and expected states of the customer; retrieving customer information; extracting a current state of the customer from the retrieved customer information, verifying, by a rule-based platform, the discrepancy; generating a response based on the discrepancy after comparing the perceived stated with the current state, where the response may include a confirmation or a correction related to the discrepancy and a personalized explanation describing the current state of the customer; and outputting, for presentation to the customer, the response.

Systems and methods for automated discrepancy determination, explanation, and resolution with personalization

Machine classifiers in accordance with embodiments of the invention capture long-term temporal dependencies in particular tasks, such as turn-based dialogues. Machine classifiers may be used to help users to perform tasks indicated by the user. When a user utterance is received, natural language processing techniques may be used to understand the user's intent. Templates may be determined based on the user's intent in the generation of responses to solicit information from the user. A variety of persona attributes may be determined for a user. The persona attributes may be determined based on the user's utterances and/or provided as metadata included with the user's utterances. A response persona may be used to generate responses to the user's utterances such that the generated responses match a tone appropriate to the task. A response persona may be used to generate templates to solicit additional information and/or generate responses appropriate to the task.

Multi-turn dialogue response generation with persona modeling

A system for providing software development performance predictions is disclosed. The system can include one or more processors and a memory in communication with the processors storing instructions that, when executed by the processors are configured to cause the system to perform method steps. The system can receive data associated with a plurality of completed projects and a request for a new software development project. The system can determine first metrics associated with each completed project and second metrics associated with the new software development project. The first and second metrics may be associated with one or more predictive variables. The system can define predictive model systems based on one or more predictive variables and identify completed projects including a first subgroup of first metrics that match the second metrics beyond a predetermined threshold. The system can determine a performance prediction based on the identified first subgroup of first metrics.

Systems and methods for providing software development performance predictions

Growing community of inventors

McLean, VA, United States of America

Rui Zhang