Abstract: Systems and methods for inclusive product design are disclosed. The system obtains likeness score for product attributes for product using survey before design phase of product, from user(s), and determines impact and relative contribution of each product attribute, for user, to inclusivity score, using multi-level machine learning models. The system segregates product attributes and inclusivity score at persona level, and determines feature importance score of each feature in product attributes for each user. System calculates risk score for each user indicating sensibility towards product designer choices, and provides what-if analysis capabilities to product designer for analyzing, based on risk score, risk of each user with sensibility towards product designer choices and receives multisensory review from user.

Abstract: A domain-specific question answering system receives an end-user's question, identifies relevant information from domain-specific documents, composes a natural-language based response including the relevant information to be provided to the end-user. A knowledge base includes a domain-specific ontology and is built from data structures configured to preserve the hierarchy of the informational elements within the domain-specific documents. The question received from the end-user is analyzed to extract the features and the key phrases which are used to identify the relevant data structures. A pre-trained model that is further trained on domain-specific data is used to identify the sentences that include information responsive to the question. A response to the end-user's question is composed from the sentences. The question answering system also enables validation of the answers provided to the users' questions.

Abstract: A domain-specific question answering system receives an end-user's question, identifies relevant information from domain-specific documents, composes a natural-language based response including the relevant information to be provided to the end-user. A knowledge base includes a domain-specific ontology and is built from data structures configured to preserve the hierarchy of the informational elements within the domain-specific documents. The question received from the end-user is analyzed to extract the features and the key phrases which are used to identify the relevant data structures. A pre-trained model that is further trained on domain-specific data is used to identify the sentences that include information responsive to the question. A response to the end-user's question is composed from the sentences. The question answering system also enables validation of the answers provided to the users' questions.