International Business Machines Corporation

Christina R Carlson

Andrew Ronald Freed

Roderick Charles Henderson

Corville O Allen

Lisa M Bradley

Lisa M W Bradley

Mechanisms are provided to implement an answer change notification system. The mechanisms receive a change operation to change a portion of a user profile data structure associated with a user and identify a first entry in a question and answer (QA) log data structure, corresponding to the user, having an indicator identifying a previous answer of the first entry as being dependent upon information in the user profile data structure. The mechanisms resubmit a question of the first entry to a question and answer (QA) system to generate a new answer to the question in response to identifying the entry. The mechanisms receive the new answer from the QA system and output, to a client device associated with the user, a notification identifying the new answer to the question in response to receiving the new answer.

Answer change notifications based on changes to user profile information

An approach is provided to correct documents ingested by a question answering (QA) system. A document previously ingested by the QA system is selected. A correction to the selected document is identified from one or more correction sources and the correction is applied to the selected document within the QA system. In one embodiment, the correction source is a non-ingested document, such as a published document or an issued correction. In another embodiment, the correction source is a post in a forum. In this embodiment, a statement in the ingested document is compared with a contradictory statement found in an ingested post of a threaded discussion. The statement and the contradictory statement are evaluated by the QA system. The statement in the ingested document is replaced with the contradictory statement in response to the evaluation revealing that the contradictory statement is correct and that the statement is incorrect.

Apply corrections to an ingested corpus

A data processing system generates a result of processing a natural language query. A determination is made as to whether the natural language query or the result has a temporal characteristic. In response, a reminder notification data structure is generated having an associated scheduled reminder notification time for outputting a reminder notification of the result generated for the natural language query. The reminder notification data structure is stored in a data storage device and, at a later time from a time that the reminder notification data structure was stored in the data storage device, in response to the later time being equal to or later than the scheduled reminder notification time, a reminder notification is output to a client device associated with a user. The reminder notification specifies the result generated for the natural language query.

Cognitive reminder notification mechanisms for answers to questions

An approach is provided to determine answer stability in a question answering (QA) system. In the approach, a question submitted to a question answering (QA) system is selected and data pertaining to a candidate answers generated by the QA system are analyzed. The analysis of the data results in a stability characteristic that pertains to the candidate answers. A confidence value associated with the candidate answers is adjusted based on the respective answer's stability characteristic. One or more of the candidate answers are provided to a requestor based on the adjusted confidence values.

Determining answer stability in a question answering system

A data processing system determines whether a natural language query or a result has a temporal characteristic. In response, at least one of user profile information or user activity history information for a user is analyzed to identify user characteristics indicative of a timeframe for scheduling a reminder notification of the result. A timeframe for scheduling the reminder notification is calculated based on results of analyzing the user profile information or user activity history information. A reminder notification is scheduled to be output at a scheduled reminder notification time based on the calculated timeframe. At a later time, in response to the later time being equal to or later than the scheduled reminder notification time, the reminder notification is output to a client device associated with the user, wherein the reminder notification specifies the result generated for the natural language query.

Cognitive reminder notification based on personal user profile and activity information

Mechanisms are provided, in a question and answer (QA) system, for monitoring changes in answers to previously submitted questions. A question is received for which an answer is to be generated. One answer for the question is generated and the question, answer, and a notification party are registered in a question registration data structure. Another answer to the question is generated, at a later time than when the previous answer was generated. A degree of a change in the two answers to the question is determined. An answer change notification is transmitted to the notification party based on the degree of the change in the two answers to the question. The notification party may be the source of the question or a registered party to which notifications are to be sent.

Changed answer notification in a question and answer system

Aspects include monitoring accesses to computer source code. A method includes detecting an access, by a user, to a source code repository. It is determined whether the access is consistent with a history of accesses by the user to the source code repository. Based on determining that the access is not consistent with the history of accesses by the user, the access is analyzed for a reason for the user to perform the access. The analyzing is based on information about the user and information about the access. A notification of the access is generated based on the analyzing resulting in an absence of a reason for the user to perform the access.

Growing community of inventors

Chanhassen, MN, United States of America

Christina R Carlson