Establishing user specified interaction modes in a question answering dialogue

Patent metadata

Field	Value
Publication number	US-10088985-B2
Application number	US-201615052171-A
Country	US
Kind code	B2
Filing date	Feb 24, 2016
Priority date	Dec 10, 2014
Publication date	Oct 2, 2018
Grant date	Oct 2, 2018

Abstract

An approach is provided for automatically generating user-specific interaction modes for processing question and answers at the information handling system by receiving a question from a user, extracting user context parameters identifying a usage scenario for the user, identifying first input and output presentation modes for the user based on the extracted user context parameters, monitoring user interaction with the system in relation to the question, and adjusting the first input and output presentation modes based on the extracted user context parameters and detected user interaction with the system.

First claim

What is claimed is:

1. A method, in an information handling system comprising a processor and a memory, for generating user-specific interaction modes for processing question and answers at the information handling system, the method comprising:
extracting, by the system, a plurality of user context parameters identifying a usage scenario for the user, where the user context parameters are selected from a group consisting of a user ID, user group, user name, age, gender, date, time, location, input or output device type, mode, name, or IP address, and topic associated with a user submitted question;
identifying, by the system, a first input presentation mode and a first output presentation mode for the user based on the plurality of user context parameters extracted for the user, where the first input presentation mode comprises a default input presentation mode comprising specified question assistance settings to facilitate question submissions that are selected from a group consisting of a question clarification setting, question completion setting spell correction setting, and disambiguation assistance setting, and where the first output presentation mode comprises a first set of answer assistance settings to facilitate answer responses;
monitoring, by the system, user interaction with the system to detect dialog state information between the user and the system; and
adjusting, by the system, the first input and output presentation modes to become modified input and output presentation modes which are personalized over time based on the user interaction with the system.

2. The method of claim 1 , wherein extracting the plurality of user context parameters comprises identifying, by the system, the user's input device type, output device type, input modality, location, and one or more user attributes selected from a group consisting of age, experience, demography, and topic.

3. The method of claim 1 , wherein identifying the first input and output presentation modes comprises selecting the default input presentation mode comprising specified question assistance settings and selecting a default output presentation mode comprising specified answer granularity options.

4. The method of claim 3 , wherein the specified answer granularity options are selected from a group consisting of an enable exploration setting, a web link setting, a context setting, a precise response setting, a verbose response setting, an alternative response setting, a supporting evidence setting, an image setting, and an application launch setting.

5. The method of claim 3 , wherein adjusting the first input and output presentation modes comprises modifying one or more of the specified question assistance settings or specified answer granularity options.

6. The method of claim 1 , wherein monitoring user interaction with the system comprises monitoring user feedback and responses provided using the first input and output presentation modes to assess a dialog state indicating a user's desired presentation mode.

7. The method of claim 6 , wherein monitoring user feedback and responses comprises detecting natural language corrections by the user to responses provided by the system using the first input and output presentation modes, monitoring user click-through frequencies for responses provided by the system using the first input and output presentation modes, and detecting user activation of a user interface control included in the first input and output presentation modes.

8. A method, in an information handling system comprising a processor and a memory, for generating user-specific interaction modes for processing question and answers at the information handling system, the method comprising:
extracting, by the system, a plurality of user context parameters identifying a usage scenario for the user, where the user context parameters are selected from a group consisting of a user ID, user group, user name, age, gender, date, time, location, input or output device type, mode, name, or IP address, and topic associated with a user submitted question;
identifying, by the system, a first input presentation mode and a first output presentation mode for the user based on the plurality of user context parameters extracted for the user, where the first input presentation mode comprises a default input presentation mode comprising specified question assistance settings, and where the first output presentation mode comprises specified answer granularity options selected from a group consisting of an enable exploration setting, a web link setting, a context setting, a precise response setting, a verbose response setting, an alternative response setting, a supporting evidence setting, an image setting, and an application launch setting;
monitoring, by the system, user interaction with the system in relation to the question; and
adjusting, by the system, the first input and output presentation modes based on the user interaction with the system.

9. A method, in an information handling system comprising a processor and a memory, for generating user-specific interaction modes for processing question and answers at the information handling system, the method comprising:
extracting, by the system, a plurality of user context parameters identifying a usage scenario for the user, where the user context parameters are selected from a group consisting of a user ID, user group, user name, age, gender, date, time, location, input or output device type, mode, name, or IP address, and topic associated with a user submitted question;
identifying, by the system, a first input presentation mode and a first output presentation mode for the user based on the plurality of user context parameters extracted for the user;
monitoring, by the system, user interaction with the system in relation to the question by:
monitoring user feedback and responses provided using the first input and output presentation modes to assess a dialog state indicating a user's desired presentation mode, and
detecting natural language corrections by the user to responses provided by the system using the first input and output presentation modes, monitoring user click-through frequencies for responses provided by the system using the first input and output presentation modes, and detecting user activation of a user interface control included in the first input and output presentation modes; and

adjusting, by the system, the first input and output presentation modes based on the user interaction with the system.

Assignees

• IBM

Inventors

• Bufe John P
• Byron Donna K
• Swift Mary D
• Winkler Timothy P

Classifications

• G06F17/30905

  Physics · mapped topic

• G06F17/30867

  Physics · mapped topic

• G06F3/0484 Primary

  for the control of specific functions or operations, e.g. selecting or manipulating an object, an image or a displayed text element, setting a parameter value or selecting a range · CPC title

• H04L67/22

  Electricity · mapped topic

• H04L67/36

  Electricity · mapped topic