International Business Machines Corporation

Conduent Business Services, LLC

Invensys Systems, Inc.

Arvind Agarwal

Saurabh Singh Kataria

Sameep Mehta

Ajay Gupta

Harshit Kumar

Vitobha Munigala

Ankush Gupta

Balaji Viswanathan

Rajmohan Chandrahasan

Thomas Andrew Troy

Mitesh H Vasa

Shanmukha Chaitany Guttula

Sanjay M Shah

Kuntal Dey

Nitin Kumar Gupta

Seema Nagar

Palghat Srinivas Ramesh

Arun Kumar

Srikanth Govindaraj Tamilselvam

Soma Shekar Naganna

Malolan Chetlur

Abhishek Seth

Tong Sun

Mudit Mehrotra

Venkata Nagaraju Pavuluri

Shashank Mujumdar

Vinayak Sastri

Balaji Ganesan

Ritwik Chaudhuri

Sumit Bhatia

Meenal Kapoor

Veerasundaravel Thirugnanasundaram

Devbrat Sharma

Avirup Saha

Muhammed Abdul Majeed Ameen

Sandipan Sarkar

Riddhiman Dasgupta

Ion Ho

Nicholas Gomez Phan

Subhendu Dey

Naresh Olladapu

Kirushikesh Db

Cailing Dong

Embodiments of the present invention provide an approach for exploring interesting data patterns in structured tables through recommending aggregate questions in a conversational data exploration. Specially, interesting features and operators are selected that are used to frame aggregate questions based on user intent and the data. The aggregate questions are ranked based on user persona and interestingness of the questions. The approach dynamically adapts and improves the recommendation of interesting and relevant aggregate questions for the user based on user feedback iteratively.

Recommending aggregate questions in a conversational data exploration

An apparatus is disclosed which includes at least one processing device comprising a processor coupled to a memory. The at least one processing device, when executing program code, is configured to: extract one or more entities identified in a plurality of data artifacts based at least in part on one or more datasets, extract one or more entities identified in a plurality of code artifacts based at least in part on the one or more datasets, extract one or more entities identified in a plurality of user interface artifacts based at least in part on the one or more datasets, generate a set of dependency graphs each based at least in part on one or more relationships among the respective extracted one or more entities, and perform one or more of a lexical analysis and a semantic analysis on the set of dependency graphs to identify a data domain of the one or more datasets.

Automatic data domain identification

Records can be matched by a graph neural network model performing entity resolution on the records, and representing each record as a respective node in a graph. Record matching explanations can be generated, each record matching explanation indicating a first set of attributes, and a first set of corresponding values, used for the matching at least two of the records. Nodes can be clustered into a plurality of clusters by aggregating the record matching explanations and, based on the record matching explanations, determining which of the records have high importance values, in the first set of values, that match. At least one cluster explanation can be generated, the cluster explanation indicating a second set of attributes, and a second set of values corresponding to the second set of attributes, used for the clustering the nodes. The record matching explanation and the cluster explanation can be output.

Entity explanation in data management

A method, system, and computer program product for managing communication privacy in a conversation system are provided. The method detects an utterance on a public channel by a user of a computing device. A privacy nature of the utterance is determined. Based on the privacy nature, a classification confidence is determined for the utterance. The method generates a privacy question to be presented to the user based on the privacy nature and the classification confidence. In response to a confirmation response, a privacy channel is established. The method switches from the public channel to the privacy channel.

Managing communication privacy in encroaching environments

A computer-implemented method gathers a set of previously filed applications, performs intent identification on the set, clusters applications in the set based on identified common intents, receives input from user and identifying intent of the input, matches the input to a cluster based on a common intent, and generates a new application based on the input using filed applications in a cluster having a common intent between the cluster and the input.

Automatical process application generation

Techniques for automatically determining different data types found in databases are disclosed. In one example, a computer implemented method comprises receiving a portion of identifying information for one or more components of a database, and generating one or more descriptions for the one or more components based at least in part on the portion of the identifying information for the one or more components. The one or more descriptions are inputted to one or more machine learning models, and, using the one or more machine learning models, one or more data types associated with the one or more components are predicted. The prediction is based at least in part on the one or more descriptions.

Automated classification of data types for databases

One embodiment provides a method, including: obtaining at least two documents, wherein one of the at least two documents comprises a revision different than another of the at least two documents; identifying, within each of the at least two documents, portions corresponding to groups of text containing a conceptual unit; assigning at least a subset of the identified portions to a category type corresponding to a topic of a given portion, wherein the assigning comprises (i) generating a semantic tag for the identified portions in the subset and (ii) tagging the identified portions in the subset with the semantic tag; and determining changes between the at least two documents, wherein the determining comprises (iii) aligning given portions across the at least two documents based upon a relationship between the given portions across the at least two documents, (iv) identifying semantic differences between the aligned portions, and (v) identifying any remaining unaligned portions.

Identification of changes between document versions

Methods, systems, and computer program products for contrasting document-embedded structured data and generating summaries thereof are provided herein. A computer-implemented method includes extracting two or more tables from two or more input documents, wherein each of the two or more input documents comprises structured data and unstructured data; normalizing the two or more extracted tables using one or more alignment techniques; determining at least one of (i) one or more differences and (ii) one or more similarities across the two or more extracted tables by performing a comparison of the two or more normalized tables; deriving one or more insights from the comparison by applying at least one analytical model to the at least one of the one or more determined differences and one or more determined similarities; and outputting at least a portion of the one or more insights to at least one user.

Contrasting document-embedded structured data and generating summaries thereof

One embodiment provides a method, including: obtaining a plurality of previously submitted application documents, wherein each of the previously submitted application documents comprises information provided by a user who initiated a given previously submitted application document; clustering the plurality of previously submitted application documents into clusters of application documents based upon topics of the previously submitted application documents; selecting a representative application document; identifying entities contained within a given representative application document, wherein each of the entities corresponds to information to be entered into a new application document created from the given representative application document; and engaging in a dialogue with a user to create the new application document utilizing a similar representative application document to request information from the user, wherein the similar representative application document comprises a representative application document of a cluster having a topic similar to a topic of the new application document.

Generation and population of new application document utilizing historical application documents

One embodiment provides a method, including: receiving, from a client, (i) a task of annotating information, (ii) a set of instructions for performing the task, and (iii) client annotations for a subset of the information within the task; assigning the subset to a plurality of annotators; obtaining (i) annotator annotations for the subset and (ii) a response time for providing the annotator annotation for each piece of information within the subset; identifying improvements to the set of instructions by (i) comparing the annotator annotations to the client annotations and (ii) identifying discrepancies made by the annotators in view of the response time; and generating a new set of instructions, wherein the generating comprises (i) identifying at least one feature of the information that distinguishes correctly annotated information from incorrectly annotated information and (ii) generating an instruction from the at least one feature.

Annotation task instruction generation

A form compliance manager configured to create a policy graph corresponding to an electronic image of an offline form and a corresponding instruction set. The form compliance manager further configured to generate an electronically fillable form corresponding to the offline form and including at least a first context cue for a first field in the electronically fillable form. The first context cue can be based on a subgraph of the policy graph associated with the first field, and the subgraph can include field completion information for the first field, field value information for the first field, and field format information for the first field. The electronically fillable form configured to present the first context cue in response to selection of the first field.

Automated electronic form generation with context cues

One embodiment provides a method, including: obtaining at least two documents, wherein one of the at least two documents comprises a different revision of another of the at least two documents; identifying a structure of each of the at least two documents by parsing each of the at least two documents to extract text from each of the at least two documents; aligning sections of the at least two documents, wherein the aligning comprises matching a section from one of the at least two documents and a corresponding section from another of the at least two documents; identifying at least one difference between the at least two documents; assigning a semantic label to the identified at least one difference; and providing a summary of the identified at least one difference by compressing the text surrounding the identified at least one difference using the assigned semantic label.

Document revision change summarization

Methods, systems, and computer program products for dynamically designing street-parking policies for events are provided herein. A computer-implemented method includes generating a parking map for each of one or more events that occurred within a specified geographic area; generating, for each of the parking maps, one or more traffic condition maps; generating, for each of the one or more events, based on (i) each parking map and (ii) its associated traffic condition map, an impact map for the corresponding event; adjusting, for a subsequent event within the specified geographic area, one or more street-parking policies based on the impact on parking suitability and street usability represented by the generated impact maps, and outputting the one or more adjusted street-parking policies.

Dynamically designing street-parking policies for events

Methods, systems, and computer program products for transferring context with delegation are provided herein. A computer-implemented method includes detecting an anticipated unavailability of a first individual for a given future event, based on inputs generated by the first individual and databases of stored calendar information pertaining to the first individual and the given future event; identifying tasks, related to the given future event, requiring a delegation as a result of the anticipated unavailability of the first individual, wherein identifying is based on data related to the given future event; determining additional individuals to whom the tasks can be delegated, based on qualifications of the additional individuals and one or more constraints; generating a summary of the delegation comprising a description of the tasks and information pertaining to the given future event; and outputting the summary to at least one of the additional individuals.

Transferring context with delegation authority

A system, method and non-transitory computer readable medium for labeling a plurality of messages from a customer-agent interaction on a social media service to identify an issue and a response are disclosed. For example, the system includes a conversation interface, a conversation database coupled to the conversation interface, a conversation analysis server coupled to the conversation database and a conversation knowledge repository coupled to the conversation analysis server. The conversation analysis server includes a preprocessing module, a dialogue act analysis module, an issue status analysis module and an issue/response identification module.

System and method for labeling messages from customer-agent interactions on social media to identify an issue and a response

Growing community of inventors

New Delhi, India

Arvind Agarwal