Intelligent generation of customized questionnaires

1. A method for implementing intelligent generation of questions by a processor, comprising:

receiving, by a dialog system, data representative of a user profile, a domain knowledge, and historical questions associated with historical questionnaires for each of a plurality of users;

training, using one or more deep learning operations executed by machine learning logic, the dialog system to automatically and adaptively generate one or more customized questions or questionnaires using the data, wherein the training includes initially grouping each of the plurality of users into clusters according to characteristics identified in the data;

subsequent to initially grouping each of the plurality of users into the clusters, generating the one or more customized questions or questionnaires according to an analysis of the data, and to which of the clusters each of the plurality of users currently belongs, by the one or more deep learning operations in conjunction with one or more current responses to one or more current queries iteratively provided to a selected user by the dialog system subsequent to initially generating the one or more customized questions or questionnaires, wherein, the one or more customized questions or questionnaires are initially generated using only textual content of the data, and any spoken interaction comprising spoken utterances between the dialog system and the user subsequent to the initial generation and with respect to the one or more current queries is to resolve uncertainties in the data when generating further questions of the one or more customized questions or questionnaires for the user; and

responsive to the one or more current responses from the selected user yielding an inconclusive result that currently updates a placement of the selected user into conflicting clusters, dynamically updating the one or more customized questions or questionnaires in real time by automatically generating intermediate questions during the one or more current queries to resolve the inconclusive result and determine which of the clusters the selected user currently belongs prior to continuing with generating the one or more customized questions or questionnaires.

2. The method of claim 1 , further including determining a selected order for delivering the one or more customized questions or questionnaires using a dialog system.

3. The method of claim 2 , further including dynamically adjusting the selected order of the one or more customized questions or questionnaires according to a response provided to a previous query.

4. The method of claim 1 , further including collecting feedback information relating to the one or more customized questions or questionnaires.

5. The method of claim 1 , further including determining a degree of relevance of the one or more customized questions or questionnaires according to contextual information and collected feedback data.

6. The method of claim 1 , further including initializing a machine learning mechanism to apply one or more machine learning models or rules to generate the one or more customized questions or questionnaires for the selected user, taking into account previously collected feedback, modify the one or more customized questions or questionnaires, learning customized questions pertaining to the similar profiles of the alternative users, analyze the one or more current responses to the one or more current queries, or perform a combination thereof.

7. A system for implementing intelligent generation of questions, comprising:

one or more computers with executable instructions that when executed cause the system to:

receive, by a dialog system, data representative of a user profile, a domain knowledge, and historical questions associated with historical questionnaires for each of a plurality of users;

train, using one or more deep learning operations executed by machine learning logic, the dialog system to automatically and adaptively generate one or more customized questions or questionnaires using the data, wherein the training includes initially grouping each of the plurality of users into clusters according to characteristics identified in the data;

subsequent to initially grouping each of the plurality of users into the clusters, generate the one or more customized questions or questionnaires according to an analysis of the data, and to which of the clusters each of the plurality of users currently belongs, by the one or more deep learning operations in conjunction with one or more current responses to one or more current queries iteratively provided to a selected user by the dialog system subsequent to initially generating the one or more customized questions or questionnaires, wherein, the one or more customized questions or questionnaires are initially generated using only textual content of the data, and any spoken interaction comprising spoken utterances between the dialog system and the user subsequent to the initial generation and with respect to the one or more current queries is to resolve uncertainties in the data when generating further questions of the one or more customized questions or questionnaires for the user; and

responsive to the one or more current responses from the selected user yielding an inconclusive result that currently updates a placement of the selected user into conflicting clusters, dynamically update the one or more customized questions or questionnaires in real time by automatically generating intermediate questions during the one or more current queries to resolve the inconclusive result and determine which of the clusters the selected user currently belongs prior to continuing with generating the one or more customized questions or questionnaires.

8. The system of claim 7 , wherein the executable instructions further determine a selected order for delivering the one or more customized questions or questionnaires using a dialog system.

9. The system of claim 8 , wherein the executable instructions further dynamically adjust the selected order of the one or more customized questions or questionnaires according to a response provided to a previous query.

10. The system of claim 7 , wherein the executable instructions further collect feedback information relating to the one or more customized questions or questionnaires.

11. The system of claim 7 , wherein the executable instructions further determine a degree of relevance of the one or more customized questions or questionnaires according to contextual information and collected feedback data.

12. The system of claim 7 , wherein the executable instructions further initialize a machine learning mechanism to apply one or more machine learning models or rules to generate the one or more customized questions or questionnaires for the selected user, taking into account previously collected feedback, modify the one or more customized questions or questionnaires, learning customized questions pertaining to the similar profiles of the alternative users, analyze the one or more current responses to the one or more current queries, or perform a combination thereof.

13. A computer program product for implementing intelligent generation of questions by a processor, the computer program product comprising a non-transitory computer-readable storage medium having computer-readable program code portions stored therein, the computer-readable program code portions comprising:

an executable portion that receives, by a dialog system, data representative of a user profile, a domain knowledge, and historical questions associated with historical questionnaires for each of a plurality of users;

an executable portion that trains, using one or more deep learning operations executed by machine learning logic, the dialog system to automatically and adaptively generate one or more customized questions or questionnaires using the data, wherein the training includes initially grouping each of the plurality of users into clusters according to characteristics identified in the data;

an executable portion that, subsequent to initially grouping each of the plurality of users into the clusters, generating the one or more customized questions or questionnaires according to an analysis of the data, and to which of the clusters each of the plurality of users currently belongs, by the one or more deep learning operations in conjunction with one or more current responses to one or more current queries iteratively provided to a selected user by the dialog system subsequent to initially generating the one or more customized questions or questionnaires, wherein, the one or more customized questions or questionnaires are initially generated using only textual content of the data, and any spoken interaction comprising spoken utterances between the dialog system and the user subsequent to the initial generation and with respect to the one or more current queries is to resolve uncertainties in the data when generating further questions of the one or more customized questions or questionnaires for the user; and

an executable portion that, responsive to the one or more current responses from the selected user yielding an inconclusive result that currently updates a placement of the selected user into conflicting clusters, dynamically updating the one or more customized questions or questionnaires in real time by automatically generating intermediate questions during the one or more current queries to resolve the inconclusive result and determine which of the clusters the selected user currently belongs prior to continuing with the one or more customized questions or questionnaires.

14. The computer program product of claim 13 , further including an executable portion that:

determines a selected order for delivering the one or more customized questions or questionnaires using a dialog system; and

dynamically adjusts the selected order of the one or more customized questions or questionnaires according to a response provided to a previous query.

15. The computer program product of claim 13 , further including an executable portion that collects feedback information relating to the one or more customized questions or questionnaires.

16. The computer program product of claim 13 , further including an executable portion that determines a degree of relevance of the one or more customized questions or questionnaires according to contextual information and collected feedback data.

17. The computer program product of claim 13 , further including an executable portion that initializes a machine learning mechanism to apply one or more machine learning models or rules to generate the one or more customized questions or questionnaires for the selected user, taking into account previously collected feedback, modify the one or more customized questions or questionnaires, learning customized questions pertaining to the similar profiles of the alternative users, analyze the one or more current responses to the one or more current queries, or perform a combination thereof.