International Business Machines Corporation

Accenture Global Solutions Limited

Nuance Communications, Inc.

Krishna Kummamuru

Amit P Bohra

Abhishek Shivkumar

Donna Karen Byron

Alexander Pikovsky

Anand B Bhagwat

Timothy P Winkler

Swapnasarit Sahu

Guruprasad Dasappa

Chung-Sheng Li

Biplav Srivastava

Vijay Krishnarao Naik

Raghuram Krishnapuram

Vijay A Kumar

Lakshminarayanan Krishnamurthy

Prasad Manikarao Deshpande

John Arthur Pershing, Jr

Anuradha Bhamidipaty

Benjamin L Johnson

Pradeep Varma

Deepak S Padmanabhan

Anshu Narendra Jain

William Francis Jerome

Ajay Raina

Chetan Narasimha Yadati

Sameh Afif Fakhouri

Anurag Tripathi

Bibudh Lahiri

Sonam Gupta

Rinki Arya

Arjun Atreya V

Manoj N Kumar

Nitendra Rajput

Srikanth Govindaraj Tamilselvam

Vibha Singhal Sinha

Jorjeta Gueorguieva Jetcheva

Shourya Roy

L Venkata Subramaniam

Peter Richard Badovinatz

Karthik Visweswariah

Pradeep Kumar Dubey

Madhura Shivaram

Guanglei Xiong

Rema Ananthanarayanan

Debdoot Mukherjee

Guruduth Somasekhara Banavar

Natwar Modani

Ramendra K Sahoo

Parul Alok Mittal

Chinnappa Guggilla

Colin Connors

Swati Tata

Leugim A Bustelo

Naveen G Balani

Deepak Kumar

Alok Aggarwal

Shailabh Nagar

Pankaj Kankar

Raghavendra Uppinakuduru Udupa

Vipul Bansal

Shruti Chhabra

Vinay Narayana

Virendra K Varshneya

Peter B Badovinatz

Sven Ruytinx

Alexander Frederick John Piers Hall

Tanuj Chawla

Thomas Mammen Tharakan

Kiran Cskumar

Cyrille Witjas

Vivek Chenna

Deepak S Padmanaban

Deepak Dalwani

Vijii Enara Chenthamarakshan

Venkata Ramakrishnap

Mudita Shah

Sreerama K Murthy

Christopher Banschbach

Satuloori Sridhar

Rema Ananthanaratanan

Thomas Michael Fahey

Atrayee Roychowdhury

Parul A Mittal

The present disclosure relates to automated chatbot generation for different domains from available human-to-human chat logs. The systems and methods may be configured to cluster user utterances as well as agent utterances from the human chat logs. A data miner mines intents and entities from the user utterance clustering and mines actions from agent utterances. The intents, entities and actions mined are used to generate a set of stories or flows which are further used by a machine learning engine to train the chatbot. The stories or flows are also generated automatically by mapping the intents with the actions.

Automated generation of chatbot

A system and method for upgrading an executable chatbot is disclosed. The system may include a processor including a fallout utterance analyzer, a response identifier, a deviation identifier, a flow generator and enhancer. The fallout utterance analyzer may receive chats logs comprising a plurality of utterances and corresponding bot responses. The fallout utterance analyzer may classify the plurality of utterances into multiple buckets pertaining to at least one of an out-of-scope intent, a newly identified intent, and a new variation of an existing intent. The response identifier may generate auto-generated responses corresponding to new intents for upgrading the executable chatbot. The deviation identifier may overlay corresponding intent in the chat logs with the prestored flow dialog network to designate an extent of deviation with respect to flow prediction performance by the executable chatbot. The flow generator and enhancer may generate an auto-generated conversational dialog flow for upgrading the executable chatbot.

Automated learning based executable chatbot

An Artificial Intelligence (AI)-based innovation data processing system receives at least one query word related to a category. Information material including textual and non-textual data is retrieved from a plurality of data sources using the at least one query word. The information material is tokenized and parsed using a dependency parser for entity recognition, building entity relationships and for generating knowledge graphs. The output of the dependency parser is accessed by a trained classifier for obtaining respective confidence levels for each of the sentences in the textual data. The confidence levels are compared to a predetermined threshold confidence level for determining if the sentences include references to innovations. In addition, trends in the innovations are determined and responses to user queries are generated based on one or more of knowledge graphs and the trends.

Artificial intelligence (AI) based innovation data processing system

A machine learning (ML) based automated search system receives an entity information document including a plurality of entities and identifies new entities that are similar to the plurality of entities which are not included in the entity information document via automated searches. Entity intelligence reports are generated for the plurality of entities which are further used to extract search terms. The search terms are used for executing automatic searches for documents with relevant portions. The documents are further analyzed to identify other, new entities which are not included in the entity information document. Entity intelligence reports including information regarding the new entities are also generated. Significant attributes are determined for the entities. The significant attributes are further employed in ranking the new entities so that top ranked new entities are identified. Alerts can be generated based on the information regarding the new entities.

Machine learning (ML) based expansion of a data set

Examples of cognitive procurement and proactive continuous sourcing are defined. In an example, the system receives a procurement request. The system implements an artificial intelligence component to sort the supplier data into a plurality of domains. The system modifies a domain from the plurality of data domains based on new supplier data being received. The system generates user procurement behavior data based on the procurement interaction and a domain from the plurality of data domains. The system establishes a user procurement behavior model corresponding to a guideline associated with the procurement interaction. The system determines whether the user procurement behavior model should be updated based on modification in the plurality of data domains and updates the same. The system notifies the user regarding change in the user procurement behavior model due to change in a domain of the received supplier data selected by the user.

Cognitive procurement

A method for generating an appendix from document content is provided. Included is analyzing a structure of a document to identify at least one logical element in a content of a page of the document; identifying at least one relation within the identified at least one logical element to determine an appendix topic; determining a degree of relevance of the at least one relation identifying the appendix topic; extracting an appendix content from at least one source document, based on determining a relevance of the source document to the appendix topic; and formatting the appendix based on the extracted appendix content.

Analyzing document content and generating an appendix

An information request processor analyzes an information request and automatically selects search queries and information sources that are responsive to the information request. Prior reports and portions of browsing history that were generated during the creation of the prior reports are selected based at least on a primary entity included in the information request. The entities extracted from the prior reports using trained Information Extraction (IE) models are mapped to the search terms extracted from the portions of the browsing history in order to identify the successful search queries that provided the information for the prior reports. A report responsive to the information request can be generated either automatically or by receiving user input that validates and rephrases the successful search queries.

Document processing based on proxy logs

An AI-based data processing system analyzes a received information request to generate an interactive visualization including data responsive to the information request. The information request is processed to obtain the primary entity and one or more informational items related to the primary entity. Auxiliary entities and informational items related to the primary entity are identified and searches are executed on a knowledge base and the internet. The results from the searches are analyzed to obtain knowledge nuggets which are included into a selected one of a visualization template to generate the interactive visualization. If it is determined via user interactions with the interactive visualization that an informational gap exists between the information request and the data in the interactive visualization, the interactive visualization can be updated to address the informational gap.

Artificial intelligence based-document processing

An approach is provided for an information handling system to present knowledge-based information. In the approach, a semantic analysis is performed on the document with the analysis resulting in various sets of semantic content. Each of the sets of semantic content corresponds to an area in the document. The areas of the document are visually highlighted using visual indicators that show the availability of the sets of semantic content to a user via a user interface. In response to a user selection, such as a selection using the user interface or a user specified configuration setting, a selected set of semantic content is displayed to the user using the interface.

Active knowledge guidance based on deep document analysis

A mechanism is provided in a data processing system for determining comprehensiveness of a question paper given a syllabus of topics. An answer and evidence generator of a question answering system executing on the data processing system finds one or more answers based on the syllabus of topics for each question in the question paper. The answer and evidence generator identifies evidence for the one or more answers in the syllabus for each question in the question paper. A concept identifier of the question answering system identifies a set of concepts in the syllabus corresponding to the evidence for each question in the question paper to form a plurality of sets of concepts. The mechanism determines a value for a comprehensiveness metric for the question paper with respect to the syllabus of topics based on the plurality of sets of concepts.

Determining comprehensiveness of question paper given syllabus

A mechanism is provided in a data processing system for automatically generating question and answer pairs for training a question answering system for a given domain. The mechanism identifies a set of patterns of components in passages within a corpus of documents for the given domain. The mechanism identifies a set of rules that correspond to the set of patterns for generating question and answer pairs from the passages within the corpus of documents. The mechanism applies the set of rules to the passages to generate the question and answer pairs.

Automatically generating test/training questions and answers through pattern based analysis and natural language processing techniques on the given corpus for quick domain adaptation

A computer-implemented method includes receiving a question set. The question set is for a question answer system. The method receives a plurality of domain cluster topics. The plurality of domain cluster topics are for the question set. The method organizes the question set based on the plurality of domain cluster topics to yield a plurality of question set topics. The method receives a document corpus. The document corpus is for the question answer system. The method organizes the document corpus based on the plurality of domain cluster topics to yield a plurality of document corpus topics. The method maps the plurality of question set topics to the plurality of document corpus topics. The method determines whether any of the plurality of question set topics are unmatched. The method is responsive to any of the plurality of question set topics being unmatched. The method requests enrichment for the document corpus.

Requesting enrichment for document corpora

Mechanisms for identifying hidden meaning in a portion of natural language content are provided. A primary portion of natural language content is received and a secondary portion of natural language content is identified that references the natural language content. The secondary portion of natural language content is analyzed to identify indications of meaning directed to elements of the primary portion of natural language content. A probabilistic model is generated based on the secondary portion of natural language content modeling a probability of hidden meaning in the primary portion of natural language content. A hidden meaning statement data structure is generated for the primary portion of natural language content based on the probabilistic model.

Extracting veiled meaning in natural language content

Growing community of inventors

Bengaluru, India

Krishna Kummamuru