Go to PGM-AUA V1.0 AI Modules

Function
Ref. Model
I/O Data
SubAIMs
JSON MData
Profiles
Ref. Software
Conformance
Performance

1. Function

The User State Creation (PGM‑USC) AIM aggregates the evidential outputs of the upstream Sub-AIMs — Multimodal Input Harmonisation, Linguistic‑Paralinguistic Analysis, Behavioural and Expressive Analysis, and Cross‑Modal Interpretation — into a single, consistent User State instance. It also assembles the multiplexed statuses and request signals produced by those Sub-AIMs into the corresponding composite output data types. Specifically, PGM‑USC:

  • Consumes structured evidence produced by upstream Sub-AIMs.
  • Produces a User State instance conforming to the User State data type.
  • Performs evidence‑based construction, as opposed to interpretation.
  • Applies normative constraints on the User State elements that may be populated.
  • Multiplexes the User CXT Status, User Domain Request, and User IH Request signals received from each Sub-AIM, composing the corresponding composite output, with one field per Sub-AIM.

2. Reference Model

Figure 1 depicts the Reference Model of the User State Creation (PGM‑USC) AIM.

Figure 1 – The User State Creation (PGM‑USC) AIM

3. Input/Output Data

Table 1 specifies the Input and Output Data of the User State Creation (PGM‑USC) AIM.

Table 1 – I/O Data of the User State Creation (PGM‑USC) AIM

Input Description
Harmonised Multimodal Context Audio, visual, textual, and paralinguistic evidence of the scene, placed on a common time base and attributed to the harmonised Entities, as produced by Multimodal Input Harmonisation.
Linguistic‑Paralinguistic Evidence Evidence carried by the content of the utterances of an Entity and by the manner of their delivery, as produced by Linguistic‑Paralinguistic Analysis.
Behavioural and Expressive Indicators Indicators carried by the conduct of an Entity and by the expression of its body, as produced by Behavioural and Expressive Analysis.
Cross‑Modal Interpretation Evidence Coherent cross‑modal interpretation of User behaviour and interaction context, as produced by Cross‑Modal Interpretation.
User CXT Status Multiplexed status signals from Multimodal Input Harmonisation, Linguistic‑Paralinguistic Analysis, Behavioural and Expressive Analysis, and Cross‑Modal Interpretation. Each Sub-AIM reports its processing outcome in a dedicated field.
User Domain Request Multiplexed domain knowledge requests from Multimodal Input Harmonisation, Linguistic‑Paralinguistic Analysis, Behavioural and Expressive Analysis, and Cross‑Modal Interpretation. The information provided by each Sub-AIMA is inserted in a dedicated field.
User Interaction History Request Multiplexed Interaction History requests from Multimodal Input Harmonisation, Linguistic‑Paralinguistic Analysis, Behavioural and Expressive Analysis, and Cross‑Modal Interpretation. The information provided by each Sub-AIMA is inserted in a dedicated field.
User CXT Directive Control directive specifying scope, depth, and policy constraints for User State Creation.
User Domain Response Domain‑specific knowledge supporting User State Creation.
User Interaction History Response Prior interaction‑history content supporting User State Creation.
Output Description
User State Structured representation of the cognitive, behavioural, expressive, and interaction state of the observed User, assembled from all evidence.
User CXT Status Composite status signal assembling the processing outcomes of all Sub-AIMs, with one field per Sub-AIM.
User Domain Request Composite domain knowledge request assembling the requests of all Sub-AIMs, with one field per Sub-AIM.
User Interaction History Request Composite Interaction History request assembling the requests of all Sub-AIMs, with one field per Sub-AIM.

4. SubAIMs

No SubAIMs.

5. JSON Metadata

https://schemas.mpai.community/PGM1/V1.0/AIMs/UserStateCreation.json

6. Profiles

No Profiles.

7. Reference Software

Not part of this specification.

8. Conformance Testing

Table 2 provides the Conformance Testing Method for the User State Creation (PGM‑USC) 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 the User State Creation (PGM‑USC) AIM

Receives Harmonised Multimodal Context Shall validate against Harmonised Multimodal Context schema.
Linguistic‑Paralinguistic Evidence Shall validate against Linguistic‑Paralinguistic Evidence schema.
Behavioural and Expressive Indicators Shall validate against Behavioural and Expressive Indicators schema.
Cross‑Modal Interpretation Evidence Shall validate against Cross‑Modal Interpretation Evidence schema.
User CXT Status Shall validate against User CXT Status schema. Each Sub-AIM field shall be present.
User Domain Request Shall validate against User Domain schema. Each Sub-AIM field shall be present.
User Interaction History Request Shall validate against Interaction History schema. Each Sub-AIM field shall be present.
User CXT Directive Shall validate against User CXT Directive schema.
User Domain Response Shall validate against User Domain schema.
User Interaction History Response Shall validate against Interaction History schema.
Produces User State Shall validate against User State schema.
User CXT Status Shall validate against User CXT Status schema. All Sub-AIM fields shall be populated.
User Domain Request Shall validate against User Domain schema. All Sub-AIM fields shall be populated.
User Interaction History Request Shall validate against Interaction History schema. All Sub-AIM fields shall be populated.

9. Performance Assessment

Not part of this specification.

Go to PGM-AUA V1.0 AI Modules