Method to allow for question and answer system to dynamically return different responses based on roles

A computer program product for adjusting answers to questions based on a user criteria by an information handling system capable of answering questions, the computer program product comprising a computer readable storage medium having program instructions embodied therewith, the program instructions executable by a processor to cause the processor to:

• manually tag documents for deep natural language processing (NLP);
• extract features from the manually-tagged documents;
• provide each of a plurality of documents with an access level based on extracted features;
• receive a question from a user having a user profile comprising a responsibility role of the user and a permission level of the user;
• derive a content access constraint criteria of the user from the responsibility role and the permission level;
• generate a plurality of candidate answers for the question;
• remove one or more candidate answers from the plurality of candidate answers, wherein the one or more candidate answers have an access level higher than the content access constraint criteria of the user, wherein the access level is provided by performing deep NLP and feature extraction on each text segment of each document, wherein the extracted features include particular entity types, relation types, predicates, and indicating words;
• apply natural language processing, deep analytic analysis, and evidence scoring to the plurality of documents having the access level no higher than the content access constraint criteria to select an answer to the question from the remaining candidate answers;
• and
• provide to the user a notification comprising the answer to the question.

A system for adjusting answers to questions based on a user criteria by an information handling system capable of answering questions, the system comprising:

• a memory comprising executable instructions;
• and
• a processor configured to execute the executable instructions to:
• manually tag documents for deep natural language processing (NLP);
• extract features from the manually-tagged documents;
• provide each of a plurality of documents with an access level based on extracted features;
• receive a question from a user having a user profile comprising a responsibility role of the user and a permission level of the user;
• derive a content access constraint criteria of the user from the responsibility role and the permission level;
• generate a plurality of candidate answers for the question;
• remove one or more candidate answers from the plurality of candidate answers,
• wherein the one or more candidate answers have an access level higher than the content access constraint criteria of the user, wherein the access level is provided by performing deep NLP and feature extraction on each text segment of each document, wherein the extracted features include particular entity types, relation types, predicates, and indicating words;
• apply natural language processing, deep analytic analysis, and evidence scoring to the plurality of documents having the access level no higher than the content access constraint criteria to select an answer to the question from the remaining candidate answers;
• and
• provide to the user a notification comprising the answer to the question.