Synheart Core Architecture - Synheart Documentation

System Overview

Synheart Core SDK is a modular, on-device human state intelligence system that collects multi-modal signals, fuses them into a unified state representation (HSV - Human State Vector), and provides optional interpretation modules for focus and emotion.

┌────────────────────────────────────────────────────────┐
│                 Synheart Core SDK                      │
├────────────────────────────────────────────────────────┤
│                                                        │
│  ┌──────────┐  ┌──────────┐  ┌────────────────┐     │
│  │   Wear   │  │  Phone   │  │    Behavior    │     │
│  │  Module  │  │  Module  │  │     Module     │     │
│  └─────┬────┘  └─────┬────┘  └────────┬───────┘     │
│        │             │                 │              │
│        └─────────────┼─────────────────┘              │
│                      ▼                                │
│              ┌───────────────┐                        │
│              │  HSI Runtime  │                        │
│              │  (On-device)  │                        │
│              └───────┬───────┘                        │
│                      │                                │
│        ┌─────────────┼─────────────┐                 │
│        │             │              │                 │
│   ┌────▼────┐  ┌────▼────┐  ┌──────▼──────┐         │
│   │  Focus  │  │ Emotion │  │   Cloud     │         │
│   │ Module  │  │ Module  │  │ Connector   │         │
│   └─────────┘  └─────────┘  └─────────────┘         │
│                                                        │
└────────────────────────────────────────────────────────┘

Module System

Signal Collection Modules

1. Wear Module

Collects biosignals from wearable devices. Data Sources:

Heart rate (HR)
Heart rate variability (HRV)
Sleep stages
Motion/activity
Skin temperature (if available)

Output:

Derived signals only (no raw biosignals)
30s, 5m, 1h, 24h aggregations
Quality metrics and confidence scores

Platform Support:

iOS: HealthKit
Android: Health Connect
Multi-device: Apple Watch, Fitbit, WHOOP, Garmin, Samsung

// Example: Wear module output
{
  "hr_mean": 72,
  "hr_std": 8,
  "hrv_rmssd": 45,
  "hrv_sdnn": 62,
  "quality_score": 0.95,
  "window": "30s"
}

2. Phone Module

Collects device-level signals. Data Sources:

Motion (accelerometer, gyroscope)
Screen state (on/off, brightness)
App context (coarse categories)
Location context (stay/move, no coordinates)

Privacy:

No fine-grained location
No app names (only categories: social, productivity, etc.)
No notification content

// Example: Phone module output
{
  "motion_state": "stationary",
  "screen_on": true,
  "screen_brightness": 0.8,
  "app_category": "productivity",
  "context": "work"
}

3. Behavior Module

Captures interaction patterns. Data Sources:

Tap frequency and pressure
Scroll speed and direction
Typing cadence
App switching frequency
Screen unlock patterns

Privacy:

No content (what you type/read)
Only patterns (how you interact)

// Example: Behavior module output
{
  "tap_frequency": 12.5,
  "scroll_velocity_mean": 0.4,
  "typing_cadence": 3.2,
  "app_switches_per_min": 2.1,
  "interaction_stability": 0.82
}

HSI Runtime

The HSI Runtime fuses signals from all modules into a unified state representation (HSV - Human State Vector). Core Functions:

Multimodal Fusion: Combines biosignals, phone sensors, and behavior
State Axes: Calculates affect and engagement indices
Time Windows: Maintains state across 30s, 5m, 1h, 24h windows
State Embedding: Generates 64D vector representation

Output:

{
  "affect": {
    "arousal_index": 0.72,      // 0.0-1.0
    "valence_index": 0.15,      // -1.0 to 1.0
    "intensity": 0.68           // 0.0-1.0
  },
  "engagement": {
    "engagement_stability": 0.81,
    "cognitive_load": 0.65,
    "attention_level": 0.73
  },
  "state_embedding": [0.12, 0.34, ...], // 64D vector
  "window": {
    "duration": "30s",
    "start": "2025-01-15T10:30:00Z",
    "end": "2025-01-15T10:30:30Z"
  },
  "timestamp": "2025-01-15T10:30:30Z"
}

Update Frequency:

30s window: Updated every 30 seconds
5m window: Updated every minute
1h window: Updated every 5 minutes
24h window: Updated every 15 minutes

Performance:

Latency: ≤ 100ms
CPU: < 2%
Memory: < 15MB
Battery: < 0.5%/hr

Interpretation Modules

1. Focus Module

Estimates cognitive focus and concentration. Inputs:

HSI state embedding
Engagement indices
Behavioral patterns

Outputs:

{
  "estimate": {
    "score": 0.85,           // 0.0-1.0
    "confidence": 0.92       // 0.0-1.0
  },
  "state": "focused",        // focused, distracted, neutral, deep_focus
  "trend": "increasing",     // increasing, decreasing, stable
  "timestamp": "2025-01-15T10:30:30Z"
}

States:

focused: Moderate to high sustained attention
deep_focus: Very high sustained attention
distracted: Low attention with high variability
neutral: Baseline state

2. Emotion Module

Estimates affective states from physiological and behavioral signals. Inputs:

HSI affect axes
Biosignals (HR, HRV)
Behavioral patterns

Outputs:

{
  "stress_index": 0.45,      // 0.0-1.0
  "energy_level": 0.72,      // 0.0-1.0
  "primary_emotion": "calm", // calm, stressed, excited, tired
  "valence": 0.2,           // -1.0 to 1.0
  "arousal": 0.65,          // 0.0-1.0
  "timestamp": "2025-01-15T10:30:30Z"
}

Emotion Categories:

calm: Low arousal, positive valence
stressed: High arousal, negative valence
excited: High arousal, positive valence
tired: Low arousal, negative valence

Cloud Connector

Securely uploads state snapshots (HSI 1.0 format) to the cloud (with user consent). Features:

Consent-gated uploads
Batch processing
WiFi-only option
Automatic retry
End-to-end encryption

Upload Payload:

{
  "user_id": "anon_user_123",
  "snapshots": [
    {
      "hsi": { /* HSV converted to HSI 1.0 format */ },
      "focus": { /* Focus estimate */ },
      "emotion": { /* Emotion state */ },
      "timestamp": "2025-01-15T10:30:30Z"
    }
  ],
  "metadata": {
    "sdk_version": "1.0.0",
    "platform": "ios",
    "capability_level": "core"
  }
}

Privacy:

No raw signals
No personally identifiable information
Only derived state snapshots (HSI 1.0 format)
User can revoke at any time

Manages permissions and data masking. Responsibilities:

Permission requests
Consent tracking
Data masking based on consent
Runtime enforcement

Consent Levels:

Module	Permission	Data Access
Wear	Health data	Derived biosignals
Phone	Motion & sensors	Coarse context only
Behavior	Accessibility (optional)	Interaction patterns only
Cloud	Network upload	HSI snapshots only

Example:

// Request consent
final granted = await Synheart.requestConsent(
  modules: [ConsentModule.wear, ConsentModule.cloud],
  reason: "We need access to provide personalized insights"
);

// Check current consent
final status = await Synheart.getConsentStatus();
// { wear: true, phone: true, behavior: false, cloud: true }

// Revoke consent
await Synheart.revokeConsent(ConsentModule.cloud);

Capability System

Different apps get different levels of access based on app signature and tenant ID.

Capability Levels

Level	Access	Who Gets It
Core	Basic HSV, derived signals	External developers
Extended	Full HSV embedding, higher frequency	Synheart apps (Syni Life, SWIP)
Research	Raw streams, full fusion vectors	Research apps (with authorization)

Capability Matrix

Module	Core	Extended	Research
Wear	Derived biosignals (30s windows)	Higher frequency (5s windows)	Raw HR/HRV streams
Phone	Motion, screen state	Advanced app context	Full context with app names
Behavior	Basic metrics (aggregated)	Extended metrics	Event-level streams
HSV Runtime	Basic state (affect, engagement)	Full 64D embedding	Full fusion vectors + intermediate states
Cloud	Ingest endpoint (HSI 1.0)	Extended endpoints	Research endpoints

Enforcement

Capability checks happen at:

SDK Initialization: Validates app signature and tenant ID
Module Enable: Checks capability for requested module
Data Access: Masks/filters data based on capability
Cloud Upload: Routes to appropriate endpoint

// Core capability (default)
Synheart.initialize(
  userId: userId,
  config: SynheartConfig(
    capabilityLevel: CapabilityLevel.core
  )
);

// Extended capability (Synheart apps only)
Synheart.initialize(
  userId: userId,
  config: SynheartConfig(
    capabilityLevel: CapabilityLevel.extended
  )
);

Data Flow

1. Signal Collection

Wearable Device → Wear Module → Derived Signals
Phone Sensors → Phone Module → Coarse Context
User Interactions → Behavior Module → Patterns

2. HSV Fusion

Derived Signals → HSI Runtime → HSV State Axes
Coarse Context → HSI Runtime → HSV State Embedding
Patterns → HSI Runtime → HSV Time Windows

3. Interpretation

HSV State → Focus Module → Focus Estimate
HSV State → Emotion Module → Emotion State

4. Output

HSV State → App Callbacks
Focus Estimate → App Callbacks
Emotion State → App Callbacks
HSV Snapshots → Cloud Connector (converts to HSI 1.0) → Synheart Platform

Thread Model

The SDK uses a multi-threaded architecture for performance:

Main Thread
│
├─ UI Updates (callbacks)
│
Worker Threads
│
├─ Signal Collection Thread
│  └─ Wear, Phone, Behavior modules
│
├─ HSI Processing Thread
│  └─ Fusion, state calculation
│
├─ Interpretation Thread
│  └─ Focus, Emotion modules
│
└─ Cloud Upload Thread
   └─ Batching, encryption, upload

Thread Safety:

All callbacks delivered on main thread
Internal state protected by locks
Async operations use platform-native concurrency (Coroutines, Combine, async/await)

Storage

Local Storage

HSV Cache:

Last 24 hours of HSV snapshots
Encrypted with AES-256
Auto-pruned to maintain size
Location: App-specific secure storage

Metadata:

Consent status
Capability level
Last sync timestamp
User preferences

Cloud Storage

Upload Policy:

Requires explicit consent
Only state snapshots - HSI 1.0 format (no raw data)
Encrypted in transit (TLS 1.3)
Encrypted at rest (AES-256)

Performance Characteristics

CPU Usage

Component	Typical	Peak
Signal Collection	0.5%	1%
HSI Processing	0.8%	1.5%
Interpretation	0.2%	0.5%
Total	1.5%	2%

Memory Usage

Component	Size
SDK Core	5 MB
HSV Cache	4 MB
Module State	3 MB
Total	12 MB

Battery Impact

Component	Impact
Signal Collection	0.1%/hr
HSI Processing	0.1%/hr
Cloud Upload	0.1%/hr
Total	0.3%/hr

Latency

Operation	Latency
HSV Update	80ms
Focus Estimate	50ms
Emotion State	60ms
Cloud Upload	60ms

Security

Data Protection

Encryption
- Local storage: AES-256
- Network: TLS 1.3
- Key storage: Platform keychain
Access Control
- Capability-based access
- App signature validation
- Tenant ID verification
Privacy
- No raw content
- No personal identifiers
- Consent-gated access

Threat Model

Protected Against:

Unauthorized data access
Man-in-the-middle attacks
Local storage compromise
Malicious apps accessing data

Not Protected Against:

Device compromise (jailbreak/root)
Physical device access
Platform-level vulnerabilities

Platform-Specific Notes

iOS

Uses HealthKit for biosignals
CoreMotion for motion sensors
Combine for reactive streams
Background delivery supported

Android

Uses Health Connect for biosignals
SensorManager for motion sensors
Kotlin Coroutines and Flow
WorkManager for background tasks

Flutter/Dart

Platform channels for native access
Streams for reactive updates
Async/await for operations
Cross-platform consistency

HSV Specification - State axes, indices, embeddings, and windows
Capability System - Access level details
Consent System - Permission model
Cloud Protocol - Upload protocol specification

Author: Israel Goytom

Get Started

HSI

Synheart Wear

Synheart Core

Synheart Emotion

Synheart Behavior

Synheart Focus

Synheart Flux

Synheart Sensor Agent

Guides

​System Overview

​Module System

​Signal Collection Modules

​1. Wear Module

​2. Phone Module

​3. Behavior Module

​HSI Runtime

​Interpretation Modules

​1. Focus Module

​2. Emotion Module

​Cloud Connector

​Consent Module

​Capability System

​Capability Levels

​Capability Matrix

​Enforcement

​Data Flow

​1. Signal Collection

​2. HSV Fusion

​3. Interpretation

​4. Output

​Thread Model

​Storage

​Local Storage

​Cloud Storage

​Performance Characteristics

​CPU Usage

​Memory Usage

​Battery Impact

​Latency

​Security

​Data Protection

​Threat Model

​Platform-Specific Notes

​iOS

​Android

​Flutter/Dart

​Related Documentation

System Overview

Module System

Signal Collection Modules

1. Wear Module

2. Phone Module

3. Behavior Module

HSI Runtime

Interpretation Modules

1. Focus Module

2. Emotion Module

Cloud Connector

Consent Module

Capability System

Capability Levels

Capability Matrix

Enforcement

Data Flow

1. Signal Collection

2. HSV Fusion

3. Interpretation

4. Output

Thread Model

Storage

Local Storage

Cloud Storage

Performance Characteristics

CPU Usage

Memory Usage

Battery Impact

Latency

Security

Data Protection

Threat Model

Platform-Specific Notes

iOS

Android

Flutter/Dart

Related Documentation