Bank of America Corporation

Barclays Capital Inc.

Lehman Brothers Inc.

Hari Gopalkrishnan

Ramakrishna R Yannam

Emad Noorizadeh

Sushil Golani

Isaac Persing

Bridget Elizabeth O'Connor

Dana Patrice Morrow Branch

Priyank R Shah

Castigliana Cimpian

Benjamin Wu

Sandeep Kumar Chauhan

Jagadish Reddy

Rafman Azeez

Sabet A Elias

Ford Mackinnon Stewart

Methods for building and training a network of chatbots are provided. Methods may perform data analysis on a first chatbot in the network. The first chatbot may include a first domain of intents. The data analysis may identify and rank the intents in the first domain. The first domain may represent answers to a first domain of user queries. Methods may select a predetermined number of highest-ranking intents from the first domain based on the data analysis. Methods may input the selected intents into a second chatbot in the network. The second chatbot may include a second domain of intents. The second domain may represent answers to a second domain of user queries. Methods may input a hook into the second chatbot. The hook may include a trigger word and may correspond to the first domain. When the hook is triggered, the second chatbot may invoke the first chatbot.

Building and training a network of chatbots

Apparatus and methods for leveraging machine learning and artificial intelligence to generate a response to an utterance expressed by a user during an interaction between an interactive response system and the user is provided. The methods may include a natural language processor processing the utterance to output an utterance intent. The methods may also include a signal extractor processing the utterance, the utterance intent and previous utterance data to output utterance signals. The methods may additionally include an utterance sentiment classifier using a hierarchy of rules to extract, from a database, a label, the extracting being based on the utterance signals. The methods may further include a sequential neural network classifier using a trained algorithm to process the label and a sequence of historical labels to output a sentiment score. The methods may further include, based on the utterance intent, the label and the score, to output a response.

Methods and apparatus for leveraging machine learning for generating responses in an interactive response system

Aspects of the disclosure relate to receiving a stateless application programming interface ('API') request. The API request may store an utterance, previous utterance data and a sequence of labels, each label in the sequence of labels being associated with a previous utterance expressed by a user during an interaction. The previous utterance data may, in certain embodiments, be limited to a pre-determined number of utterances occurring prior to the utterance. Embodiments process the utterance, using a natural language processor in electronic communication with the first processor, to output an utterance intent, a semantic meaning of the utterance and an utterance parameter. The utterance parameter may include words in the utterance and be associated with the intent. The natural language processor may append the utterance intent, the semantic meaning of the utterance and the utterance parameter to the API request. A signal extractor processor may append the plurality of utterance signals to the API request.

Methods and apparatus for leveraging an application programming interface ('API') request for storing a list of sentiment values in real time interactive response systems

Apparatus and methods for leveraging machine learning and artificial intelligence to assess a sentiment of an utterance expressed by a user during an interaction between an interactive response system and the user is provided. The methods may include a natural language processor processing the utterance to output an utterance intent. The methods may also include a signal extractor processing the utterance, the utterance intent and previous utterance data to output utterance signals. The methods may additionally include an utterance sentiment classifier using a hierarchy of rules to extract, from a database, a label, the extracting being based on the utterance signals. The methods may further include a sequential neural network classifier using a trained algorithm to process the label and a sequence of historical labels to output a sentiment score.

Multi-tier rule and AI processing for high-speed conversation scoring and selecting of optimal responses

Multi-tier rule and AI processing for high-speed conversation scoring

A network of chatbots is provided. The network may include a user-facing router for receiving queries and a plurality of chatbots. Each chatbot included in the plurality of chatbots may identify a single logical grouping of a domain, identify a limited number of intents from each other chatbot included in the plurality of chatbots and communicate with each other chatbot included in the plurality of chatbots. When the router receives a query, the router may receive the query with an associated domain. The router may select a chatbot based on the received domain. The router may direct the query to the selected chatbot. The selected chatbot may determine that the domain associated with the query is incorrect. The selected chatbot may identify a second chatbot based on a hook included in the query and identified within the selected chatbot. The selected chatbot may transfer the query to the second chatbot.

Executing a network of chatbots using a combination approach

Systems, computer program products, and methods are described herein for information transfer between communication channels. The present invention is configured to electronically receive, via a first communication channel associated with an entity, information associated with a transfer of resources from a user at a first time; initiate one or more machine learning algorithms at on the information associated with the transfer of resources at the first time; generate, using the one or more machine learning algorithms, a summary of the information associated with the transfer of resources; electronically receive an indication that the user wishes to transfer to a second communication channel; and initiate a communication channel transfer protocol to transmit the summary of the information associated with the transfer of resources to the second communication channel.

System for information transfer between communication channels

A system includes a client device and a server including a communication module configured to be accessed by the client device through which a user of the client device connects to another user via one of a plurality of communication services connected to the server, wherein one of the plurality of communication services is telephony.

Industry-specific communication framework

A secure remote access system includes client software installed on a portable computer that establishes a remote session with a counterpart server software installed on a server in a DMZ of the company's internal network through a secure tunnel. The DMZ server is connected to a router behind an enterprise second level firewall. The router routes the session to the appropriate desktop computer if the desktop is permitted remote access. A bandwidth limiter may be provided to balance the load through the router.

System and method for secure remote desktop access

A method and system for monitoring and managing applications and services. A repository comprising information identifying a plurality of assets and one or more relationships among the assets is maintained. One or more assets used to support an application are identified, along with one or more applications that are included in a service. Event and performance data are collected by a plurality of tools that perform monitoring and/or managing of the identified assets, the application, and/or the service. The gathered event and performance data is aggregated. The user is provided with a portal to access the aggregated event and performance data. Through this portal, the user can determine an impact of an event or a performance issue on the application or service based on the aggregated event or performance data and the relationships among the assets.

Monitoring and management of assets, applications, and services using aggregated event and performance data thereof

An organization asset database (ADb) is described that contains a complete, up-to-date, secure, and easily accessible inventory of the organization's assets. Each asset is mapped onto a structure that represents the organizational hierarchy of the organization, which provides for multiple levels of accountability for each asset. Each asset has one or more roles in relation to other assets in the ADb and has one or more entitlements in relation to other assets in the ADb. The relationship between assets ensures that the ADb is complete and up-to-date and allows for easy filtering and retrieval of the information contained in the ADb.

Growing community of inventors

Plainsboro, NJ, United States of America

Hari Gopalkrishnan