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

Answer To Question Module (MMC-AQM):

Receives Text Object Text of query
Meaning Meaning of query Text
Intention Intention of query Text
Produces Text Object of AIM’s answer

2     Reference Model

Figure 1 specifies the Reference Module of the Answer To Question Module (MMC-AQM) AIM.

Figure 1 – The Answer To Question Module (MMC-AQM) AIM

3    Input/Output Data

Table 1 specifies the Input and Output Data of the Answer To Question Module (MMC-AQM) AIM.

Table 1 – I/O Data of the Answer To Question Module (MMC-AQM) AIM

Input data Description
TextObject Input Text Object, e.g., from Natural Language Understanding
Meaning Meaning of Text
Intention Intention in Text
Output data Description
TextObject Text Object of Answer to Question

4     SubAIMs

No SubAIMs.

5     JSON Metadata

https://schemas.mpai.community/MMC/V2.3/AIMs/AnswerToQuestionModule.json

6     Profiles

No Profiles.

7     Reference Software

8     Conformance Testing

Table 2 provides the Conformance Testing Method for MMC-AQM AIM.

If a schema contains references to other schemas, conformance of data for the primary schema implies that any data referencing a secondary schema shall also validate against the relevant schema, if present and conform with the Qualifier, if present.

Table 2 – Conformance Testing Method for MMC-AQM AIM

Input Text Object Shall validate against Text Object schema.
Also, Text Data shall conform with Text Qualifier.
Meaning Shall validate against the Meaning schema.
Intention Shall validate against the Intention schema.
Output Text Object Shall validate against the Text Object schema.
Also, Text Data shall conform with the Text Qualifier, e.g., the Language Format shall be that of input  Language.

Table 3 provides an example of MMC-AQM AIM conformance testing.

Table 3 – An example MMC-AQM AIM conformance testing

Input Data Data Type Input Conformance Testing Data
Text Object Unicode All input Text files to be drawn from Question Text Files.
Meaning JSON All input Meaning files to be drawn from Meaning JSON Files for Questions.
Intention JSON All input Intention files to be drawn from Intention JSON Files.
Output Data Data Type Output Conformance Testing Criteria
Text Object Unicode All Text files produced shall conform with Text.

9     Performance Assessment

Go To MPAI-MMC AI Modules