Multi-modal dialog agents representing a level of confidence in analysis
A multi-modal dialog apparatus includes a memory embodying computer executable instructions; and at least one processor, coupled to the memory, and operative by the computer executable instructions. More specifically, the processor is operative by the computer executable instructions to facilitate receiving a remark from a user; passing the remark to an intelligent system; receiving a response and a level of confidence from the intelligent system; portraying the response to the user via an equivocal persona in case the level of confidence is less than a pre-determined threshold value; and portraying the response to the user via an authoritative persona in case the level of confidence equals or exceeds the pre-determined threshold value.
1. A method comprising:
receiving a remark from a user via a multi-modal dialog agent, wherein the remark includes an image attachment;
passing the remark from the multi-modal dialog agent to an intelligent system;
in the intelligent system, generating a response to the remark based on image analysis of the image attachment and generating a level of confidence in the response;
receiving the response and the level of confidence from the intelligent system at the multi-modal dialog agent;
modifying the multi-modal dialog agent according to a persona selected from a set of personae in response to the level of confidence, wherein the set of personae includes an equivocal persona in case the level of confidence is less than a pre-determined threshold value and includes an authoritative persona in case the level of confidence equals or exceeds the pre-determined threshold value, wherein the authoritative persona has a first voice pattern and a first facial expression while the equivocal persona has a different second voice pattern and a different second facial expression, wherein the authoritative persona presents a single response option while the equivocal persona presents multiple response options;
portraying the response to the user via the multi-modal dialog agent; and
monitoring via the multi-modal dialog agent for user feedback on an accuracy of the response.
2. The method of claim 1 wherein the authoritative persona communicates using a fact-focused vocabulary.
3. The method of claim 1 wherein the authoritative persona communicates with a firm tone and a serious facial expression.
4. The method of claim 1 wherein the authoritative persona communicates with generally level pitch and descending pitch for emphasis of key words while maintaining eyebrows and mouth relaxed and generally horizontal.
5. The method of claim 1 wherein the authoritative persona communicates with formal grammar.
6. The method of claim 1 wherein the equivocal persona communicates using a question-focused vocabulary.
7. The method of claim 1 wherein the equivocal persona communicates with rapidly varying and generally rising pitch while squinting one eye and widening the other eye.
8. The method of claim 1 wherein the equivocal persona communicates with grammatical errors.
9. A multi-modal dialog agent apparatus comprising:
a memory embodying computer executable instructions; and
at least one processor, coupled to the memory, and operative by the computer executable instructions to facilitate:
receiving a remark from a user via a multi-modal dialog agent, wherein the remark includes an image attachment;
passing the remark from the multi-modal dialog agent to an intelligent system;
in the intelligent system, generating a response to the remark based on image analysis of the image attachment and generating a level of confidence in the response;
receiving the response and the level of confidence from the intelligent system at the multi-modal dialog agent;
modifying the multi-modal dialog agent according to a persona selected from a set of personae in response to the level of confidence, wherein the set of personae includes an equivocal persona in case the level of confidence is less than a pre-determined threshold value and includes an authoritative persona in case the level of confidence equals or exceeds the pre-determined threshold value, wherein the authoritative persona has a first voice pattern and a first facial expression while the equivocal persona has a different second voice pattern and a different second facial expression, wherein the authoritative persona presents a single response option while the equivocal persona presents multiple response options;
portraying the response to the user via the multi-modal dialog agent; and
monitoring via the multi-modal dialog agent for user feedback on an accuracy of the response.
10. The apparatus of claim 9 wherein the authoritative persona communicates using a fact-focused vocabulary.
11. The apparatus of claim 9 wherein the authoritative persona communicates with a firm tone.
12. The apparatus of claim 9 wherein the authoritative persona communicates with generally level pitch and descending pitch for emphasis of key words.
13. The apparatus of claim 9 wherein the authoritative persona communicates with formal grammar.
14. The apparatus of claim 9 wherein the equivocal persona communicates using a question-focused vocabulary.
15. The apparatus of claim 9 wherein the equivocal persona communicates with rapidly varying and generally rising pitch.
16. The apparatus of claim 9 wherein the equivocal persona communicates with grammatical errors.
17. A non-transitory computer readable medium embodying computer executable instructions which when executed by a computer cause the computer to facilitate:
receiving a remark from a user via a multi-modal dialog agent, wherein the remark includes an image attachment;
passing the remark from the multi-modal dialog agent to an intelligent system;
in the intelligent system, generating a response to the remark based on image analysis of the image attachment and generating a level of confidence in the response;
receiving the response and the level of confidence from the intelligent system at the multi-modal dialog agent;
modifying the multi-modal dialog agent according to a persona selected from a set of personae in response to the level of confidence, wherein the set of personae includes an equivocal persona in case the level of confidence is less than a pre-determined threshold value and includes an authoritative persona in case the level of confidence equals or exceeds the pre-determined threshold value, wherein the authoritative persona has a first voice pattern and a first facial expression while the equivocal persona has a different second voice pattern and a different second facial expression, wherein the authoritative persona presents a single response option while the equivocal persona presents multiple response options;
portraying the response to the user via the multi-modal dialog agent; and
monitoring via the multi-modal dialog agent for user feedback on an accuracy of the response.
18. The medium of claim 17 wherein the authoritative persona communicates with generally level pitch and descending pitch for emphasis of key words.
19. The medium of claim 17 wherein the equivocal persona communicates with grammatical errors.