Function
Ref. Model
I/O Data
SubAIMs
JSON MData
Profiles
Ref. Software
Conformance
Performance
1 Functions
The Personal Status Extraction (MMC‑PSE) AIM receives the four components of the Personal Status – Text, Speech, Face, and Gesture – or their descriptors and produces the Personal Status. The input selector informs the MMC‑PSE whether it should use as input Text, Speech, Face, and Gesture or their descriptors:
| Receives | Text Object or Text Descriptors | |
| Text Selector | Indicating whether Text or Text Descriptors should be used. | |
| Speech Object or Speech Descriptors | ||
| Speech Selector | Indicating whether Speech or Speech Descriptors should be used. | |
| Face or Face Descriptors | ||
| Face Selector | Indicating whether Face or Face Descriptors should be used. | |
| Body or Gesture Descriptors | ||
| Body Selector | Indicating whether Body or Gesture Descriptors should be used. | |
| Computes and then Interprets | depending on reception of | the Descriptors of a Modality (Text, Speech, or Face). |
| Text Descriptors | Alternatively, Interprets the received Descriptors and produces Personal Status of the Text Object (PS‑Text). | |
| Speech Descriptors | Alternatively, Interprets the received Descriptors and produces Personal Status of the Speech Object (PS‑Speech). | |
| Face Descriptors | Alternatively, Interprets the received Descriptors and produces Personal Status of the Face (PS‑Face). | |
| Gesture Descriptors | Alternatively, Interprets the received Gesture Descriptors of the Body. | |
| Multiplexes | The results of the interpretations. | |
| Produces | Entity’s Personal Status |
2 Reference Model
Figure 1 depicts the Reference Model of the Personal Status Extraction (MMC‑PSE) AIM.
Figure 1 – The Personal Status Extraction (MMC‑PSE) AIM
3 I/O Data
Table 1 specifies the Input and Output Data of the Personal Status Extraction (MMC‑PSE) AIM.
| Input Selector | An external signal | Media or Descriptors Selector. |
| Text Object | Keyboard or AIM | Text or Recognised Text. |
| Text Descriptors | An upstream AIM | Functionally equivalent to Text Description. |
| Speech Object | Microphone/upstream AIM | Speech of Entity. |
| Speech Descriptors | An upstream AIM | Functionally equivalent to Speech Description. |
| Face Visual Object | Visual Scene Description | The face of the Entity. |
| Face Descriptors | An upstream AIM | Functionally equivalent to Face Description. |
| Body Visual Object | Visual Scene Description | The body of the Entity. |
| Gesture Descriptors | An upstream AIM | Functionally equivalent to Body Description. |
| Personal Status | A downstream AIM | For further processing. |
4 SubAIMs
4.1 Reference Model
A Personal Status Extraction AIM instance can be implemented as a Composite AIM with different degrees of composition. The most extended composition is depicted by Figure 2.
Figure 2 – The Personal Status Extraction (MMC‑PSE) AIM with the highest level of composition
4.2 Operation
A combination of the four media enter the system as media or their descriptors. If media they are described and fed into the appropriate Interpretation AIMs. If they enter as descriptors they enter straight into the appropriate AIMs. Different media can enter as Media or Descriptors. The outputs of the Interpretation AIM are combined in the Personal Status outpu.
4.3 Functions of AI Modules
Table 2 specifies the Function of the AI Modules.
Table 2 – Functions of Health Back End AI Modules
| Sub-AI Module | Description |
| Health Federated Learning | Performs Federated Learning of Front Ends’ NN Model. |
| Entity Text Description | Provides Descriptors of the input Text. |
| Entity Speech Description | Provides Descriptors of the input Speech. |
| Entity Face Description | Provides Descriptors of the input Dace. |
| Entity Body Description | Provides Descriptors of the input Body. |
| PS‑Text Interpretation | Uses Input Text descriptors to extract the Personal Status of Input Text. |
| PS‑Speech Interpretation | Uses Input Speechdescriptors to extract the Personal Status of Input Speech. |
| PS‑Face Interpretation | Uses Input Face descriptors to extract the Personal Status of Input Face. |
| PS‑Gesture Interpretation | Uses Input Bodydescriptors to extract the Personal Status of Input Bosy. |
| Personal Status Multiplexing | Multiplexes Media Personal Statuses into Personal Status. |
4.4 I/O Data of AI Modules
Table 4 gives the AIMs and JSON Metadata of MMC‑PSE. AIM1 indicates the Composite AIM and AIM2 its SubAIMs.
| MMC‑PSE | Personal Status Extraction | X | |
| MMC‑ETD | Entity Text Description | X | |
| MMC‑ESD | Entity Speech Description | X | |
| PAF‑EFD | Entity Face Description | X | |
| PAF‑EBD | Entity Body Description | X | |
| MMC‑PTI | PS‑Text Interpretation | X | |
| MMC‑PSI | PS‑Speech Interpretation | X | |
| PAF‑PFI | PS‑Face Interpretation | X | |
| PAF‑PGI | PS‑Gesture Interpretation | X | |
| MMC‑PMX | Personal Status Multiplexing | X |
5 JSON Metadata
https://schemas.mpai.community/MMC/V2.5/AIMs/PersonalStatusExtraction.json
6 Profiles
The Profiles of the Personal Status Extraction (MMC‑PSE) AIM are specified.
7 Reference Software
Not part of this specification.
8 Conformance Testing
Table 3 provides the Conformance Testing Method for the MMC‑PSE AIM as a Basic AIM. Conformance Testing of the individual SubAIMs is given by the individual AIM specifications.
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.
| Text Object | Shall validate against Text Object schema. Text Data shall conform with Text Qualifier. | |
| Text Descriptors | Shall validate against Text Descriptors schema. | |
| Text Selector | Shall validate against Text Selector schema. | |
| Speech Object | Shall validate against Speech Object schema. Speech Data shall conform with Speech Qualifier. | |
| Speech Descriptors | Shall validate against Speech Descriptors schema. | |
| Speech Selector | Shall validate against Speech Selector schema. | |
| Face Visual Object | Shall validate against Visual Object schema. Visual Data shall conform with Visual Qualifier. | |
| Face Descriptors | Shall validate against Face Descriptors schema. | |
| Face Selector | Shall validate against Face Selector schema. | |
| Body Visual Object | Shall validate against Visual Object schema. Visual Data shall conform with Visual Qualifier. | |
| Gesture Descriptors | Shall validate against Gesture Descriptors schema. | |
| Body Selector | Shall validate against Body Selector schema. | |
| Entity Personal Status | Shall validate against Personal Status schema. |
9 Performance Assessment
Not part of this specification.
