International Business Machines Corporation

Sandipto Neogi

Mandar Mutalikdesai

Ashish Rao

Yash Veer Singh

Sheetal Srivastava

Anagha M

Kartikeya Vats

Sudarsan Lakshminarayanan

Pranjal Srivastava

Shivangi Tak

Simardeep Singh Arneja

Shivam Ratnakar

Yash Vardhan Singh

Arnika Kumar

Ojasvi Bhalerao

A method and related system determine a localness measure that represents accessibility of a node connectiveness within a signed network. The method comprises, with a computer processor, receiving focus node (FN) information related to an FN of a graph representing the signed network, receiving neighbor node (NN) information related to a plurality of NNs in the signed network, and determining the localness measure based on the NN information and the FN information. The method and system also determine a harmony measure that represents importance of a node connectiveness within a signed network. The method comprises, with a computer processor, receiving source node (SN) information related to an SN of a graph representing the signed network, receiving destination node (DN) information related to a DN in the signed network, and determining the harmony measure based on the SN information and the DN information.

Global and local measures of centrality for signed and unsigned networks

An approach is provided in which the approach applies, by a first node, a first axiom to a set of data points to generate a set of first outputs. The approach applies, by a second node, a second axiom to the set of data points to generate a set of second outputs. The first node and the second node are part of a computer network that includes multiple nodes. The approach computes a first nuance based on a set of disagreements between the set of first outputs and the set of second outputs, and adjusts a reliability of the first node in the computer network based on the first nuance.

Preserving data integrity in cognitive multi-agent systems

An approach for enhancing user communication with a chatbot is provided. In an embodiment, a communication from a user using a chatbot application is received. One or more intents related to the user communication are identified, with each intent having a respective confidence score. Further, any number of attributes related to the user communication are extracted. If multiple viable intents are found (e.g., intents having a confidence score exceeding a predefined threshold), then relationships between the extracted attributes are derived to establish a context. Based on the context, a disambiguation question is generated to clarify an actual intent of the user.

Enhanced conversational bots processing

Growing community of inventors

Bengaluru, India

Sandipto Neogi