Go To MPAI-MMC AI Modules

1     Function 2     Reference Model 3     Input/Output Data
4     SubAIMs 5     JSON Metadata 6     Profiles
7     Reference Software 8     Conformance Texting 9     Performance Assessment

1     Functions

Entity Dialogue Processing (MMC-EDP):

Receives Text Object
Object Instance ID
Input Personal Status
Text Descriptors
AV Scene Geometry
Speaker ID
Face ID
Summary
Handles One Text Object at a time from an Entity interacting with the Machine.
Recognises The identity of the Entity via Speech and/or Face.
Takes Past Text Objects into account and their spatial arrangement.
Produces Edited Summary based on input data
Machine Text
Machine Personal Status

2     Reference Model

Figure 1 depicts the Reference Model of the Entity Dialogue Processing (MMC-EDP) AIM.

Figure 1 – Entity Dialogue Processing (MMC-EDP) AIM Reference Model

3    Input/Output Data

Table 1 specifies the Input and Output Data of the Entity Dialogue Processing (MMC-EDP) AIM.

Table 1 – I/O Data of the Entity Dialogue Processing (MMC-EDP) AIM

Input Description
Summary The summary in the current state.
Text Object Text or Refined Text from the Entity the Machine is communicating with.
Meaning Descriptors of Text and/or Translated Text of the Entity the Machine is communicating with.
Personal Status Personal Status of the Entity the Machine is communicating with.
Instance ID ID of the Audio of Visual Object the Entity refers to.
Audio-Visual Scene Geometry The Geometry of the AV Scene.
Speaker ID The ID of the Speaker
Face ID The ID of the Face.
Output Description
Machine Text Text produced by the Machine in response to input.
Machine Personal Status The Personal Status the Machine intends to add to its Modalities.
Summary The result of refining the input Summary taking comments into consideration.

4     SubAIMs

No SubAIMs.

5     JSON Metadata

https://schemas.mpai.community/MMC/V2.2/AIMs/EntityDialogueProcessing.json

6     Profiles

Profiles of Entity Dialogue Processing are specified.

7     Reference Software

8     Conformance Testing

Input Data Data Type Input Conformance Testing Data
Meaning JSON All input JSON Emotion files to be drawn from Meaning JSON Files
Recognised Text Unicode All input Text files to be drawn from Text files.
Input Emotion JSON All input JSON Emotion files to be drawn from Emotion JSON Files
Output Data Data Type Output Conformance Testing Criteria
Machine Text Unicode All Text files produced shall conform with Text.
Machine Emotion JSON Emotion JSON Files shall validate against Emotion Schema

The two attributes emotion_Name and emotion_SetName must be present in the output JSON file of Emotion. The value of either of the two attributes may be null.

9     Performance Assessment

 

Go To MPAI-MMC AI Modules