01μ΄λ‘Abstract
π ν΅μ¬ μμ½π One-Paragraph Summary
λ³Έ λ°λͺ
μ 19μ±λ QEEGλ‘λΆν° μΈ‘μ λ 6κ° μ£Όμ λ°μ΄μ€λ§μ»€ β Theta/Beta Ratio (TBR), Frontal Alpha Asymmetry (FAA), Posterior Alpha Power (PAP), High Beta Power (HBP), Coherence Index (COH), Peak Alpha Frequency (PAF) β λ₯Ό μ
λ ₯μΌλ‘ νμ¬, κ²°μ νΈλ¦¬ + λ£° κΈ°λ° λ§€ν ν¨μλ₯Ό ν΅ν΄ μΈκ³΅μ§λ₯ λν μμ€ν
μ 8κ° μλ΅ λ§€κ°λ³μ β λ§ μλ(WPS), μ μμ κ°λ(EI), μΈμ§ λΆν(CL), ν΄μ§ κΈΈμ΄(PD), κ²©λ € λΉλ(EF), λ©νμΈμ§ μ λ(MP), μ§μ μ±(DR), λ°λ»ν¨(WT) β λ₯Ό μ°μΆνκ³ , μ°μΆλ λ§€κ°λ³μλ₯Ό LLM μμ€ν
ν둬ννΈμ μ£Όμ
νμ¬ μ¬μ©μμ νμ¬ μ κ²½μ리νμ μν(κ³Όκ°μ±Β·μ κ°μ±Β·μ°μΈ ν¨ν΄ λ±)μ λ§μΆ°μ§ μλ΅μ μμ±νλ μ»΄ν¨ν° ꡬν λ°©λ² λ° μμ€ν
μ κ΄ν κ²μ΄λ€.
The present invention relates to a computer-implemented method and system that takes as input six (6) primary biomarkers measured from 19-channel QEEG β Theta/Beta Ratio (TBR), Frontal Alpha Asymmetry (FAA), Posterior Alpha Power (PAP), High Beta Power (HBP), Coherence Index (COH), and Peak Alpha Frequency (PAF) β and computes, via a decision-tree-plus-rule-based mapping function, eight (8) response parameters of an AI conversational system β words-per-second (WPS), emotional intensity (EI), cognitive load (CL), pause duration (PD), encouragement frequency (EF), metacognitive prompts (MP), directness ratio (DR), and warmth (WT); the resulting parameters are injected into an LLM system prompt so that responses are calibrated to the user's current neurophysiological state (hyperarousal, hypoarousal, depression patterns, and the like).
03λ°°κ²½ κΈ°μ Background
3.1 QEEG λ°μ΄μ€λ§μ»€μ μμμ μλ―Έ3.1 Clinical Significance of QEEG Biomarkers
μ λ λν(QEEG)λ 19κ° νμ€ μ κ·Ή(κ΅μ 10-20 μμ€ν
)μμ 5λΆκ° μμ μν(Eyes Closed/Eyes Open)μμ μΈ‘μ λ EEGλ₯Ό μ μ λͺ¨μ§λ¨ λ°μ΄ν°λ² μ΄μ€(Neuroguide, HBI)μ λΉκ΅νμ¬ Z-μ μλ₯Ό μ°μΆνλ€. μμμ μΌλ‘ μ λ’°μ± μλ 6κ° ν΅μ¬ λ°μ΄μ€λ§μ»€λ λ€μκ³Ό κ°λ€:
Quantitative EEG (QEEG) measures EEG over a five-minute resting period (eyes closed/eyes open) at nineteen standard electrodes (International 10-20 system) and computes Z-scores against normative databases (Neuroguide, HBI). The six clinically reliable core biomarkers are as follows:
| λ°μ΄μ€λ§μ»€Biomarker |
μ μDefinition |
μμ μκ·ΈλClinical Signal |
μ°Έκ³ λ¬ΈνReference |
TBR Theta/Beta Ratio | μ λμ½ μΈνν(4-8Hz) Γ· λ² νν(13-30Hz) λΉμ¨Frontal theta (4β8Hz) Γ· beta (13β30Hz) ratio | β ADHD, λΆμ£Όμ, μ κ°μ±β in ADHD, inattention, hypoarousal | Arns et al. 2013 |
FAA Frontal Alpha Asymmetry | F4 μν - F3 μν (Z)F4 alpha β F3 alpha (Z) | L>R (negative): μ°μΈ ν¨ν΄L>R (negative): depression pattern | Henriques & Davidson 1991 |
PAP Posterior Alpha Power | O1, O2, P3, P4 μνν νκ· Mean alpha at O1, O2, P3, P4 | β μΈμ, λ§μ± μ€νΈλ μ€β in trauma, chronic stress | Teicher et al. 2016 |
HBP High Beta Power | μ λμ½ 20-30Hz νμ±Frontal 20β30Hz activity | β λΆμ, κ³Όκ°μ±β in anxiety, hyperarousal | Knyazev 2007 |
COH Coherence Index | μ λ-λμ κ° μν μΌκ΄μ±Frontoparietal alpha coherence | ββ μΈμ§ ν΅ν© κ²°μβ/β cognitive integration deficits | Thatcher 2012 |
PAF Peak Alpha Frequency | μνλ μ£Όνμ νΌν¬ (Hz)Frequency at alpha peak (Hz) | β μΈμ§ μ ν, λ
Έν, TBIβ cognitive decline, aging, TBI | Klimesch 1999 |
3.2 LLM μ±λ΄μ μ κ²½ μν 무κ΄μ± λ¬Έμ 3.2 The Neural-State Decoupling Problem in LLM Chatbots
νμ¬μ λͺ¨λ μμ© LLM μ±λ΄(GPT-4, Claude, Gemini, κ·Έλ¦¬κ³ Woebot, Wysa, Replikaλ₯Ό ν¬ν¨νλ μ μ κ±΄κ° μ±λ΄)μ μ¬μ©μμ μ κ²½μ리νμ μνμ μμ ν λΆλ¦¬λμ΄ μλνλ€. μ¦, μ¬μ©μκ° κ³Όκ°μ±(HBPβ) μνμ΄λ μ κ°μ±(TBRβ) μνμ΄λ λμΌν μλ΅μ λ°λλ€. μ΄λ λ€μμ μμμ λΆμ ν©μ μΌκΈ°νλ€:
Currently deployed commercial LLM chatbots (GPT-4, Claude, Gemini, and mental health chatbots including Woebot, Wysa, Replika) operate entirely decoupled from the user's neurophysiological state. That is, a user receives identical responses whether they are in a hyperaroused state (HBPβ) or a hypoaroused state (TBRβ). This produces the following clinical mismatches:
- κ³Όκ°μ± μ¬μ©μμκ² λΉ λ₯Έ λ§ μλ, μκ·Ήμ μ΄ν β λΆμ μ
νFast speech pacing and stimulating vocabulary directed at a hyperaroused user β exacerbated anxiety
- μ κ°μ±/μ°μΈ μ¬μ©μμκ² λλ¦° λ§, λ¨μ‘°λ‘μ΄ κ²©λ € β 무λ ₯κ° μ
νSlow speech and monotonous encouragement directed at a hypoaroused/depressed user β worsened helplessness
- μΈμ§ λΆν νκ³ λ¬΄μ β νμ΅Β·μκ°μ±μ°° μ°¨λ¨Ignored cognitive-load thresholds β blocked learning and self-reflection
- FAA μ°μΈ μκ·Έλ 무μ β λΆμ μ λ°λ³΅ κ°νIgnored FAA depression signals β reinforced negative rumination
3.3 BCN+QEEG μμκ°μ λ
μ μ ν΅μ°°3.3 BCN-Plus-QEEG Clinical Expertise
Board Certified in Neurofeedback (BCN) μ격μ κ°μ§ μμκ°λ νμμ QEEGλ₯Ό λ³΄κ³ μμ λ©΄λ΄ μ μμ μ λ§ μλ, μ μμ κ°λ, ν΄μ§ κΈΈμ΄λ₯Ό μ§κ΄μ μΌλ‘ μ‘°μ νλ κ²μ μ§μ
μ μ λ¬Έμ±μΌλ‘ νλ€. λ³Έ λ°λͺ
μ μ΄ μμμ μ§κ΄μ μκ³ λ¦¬μ¦ννμ¬ AI μ±λ΄μ μ΄μνλ€. μ΄ λ§€νμ BCN μμκ°λ§μ΄ λ§λ€ μ μλ λ
μ μ μ§μ μμ°μ΄λ€.
Clinicians who hold Board Certified in Neurofeedback (BCN) credentials professionally and intuitively adjust their speech pacing, emotional intensity, and pause length during clinical interviews based on a patient's QEEG. The present invention algorithmizes this clinical intuition and transplants it into an AI chatbot. The resulting mapping is a proprietary knowledge asset that only BCN clinicians can construct.
06μμΈ μ€λͺ
Detailed Description
6.1 QEEG λ°μ΄μ€λ§μ»€ μΈ‘μ νλ‘ν μ½6.1 QEEG Biomarker Measurement Protocol
νμ€νλ μΈ‘μ μ μ°¨:Standardized measurement procedure:
- 19μ±λ (Fp1, Fp2, F3, F4, F7, F8, Fz, T3, T4, C3, C4, Cz, T5, T6, P3, P4, Pz, O1, O2)19 channels (Fp1, Fp2, F3, F4, F7, F8, Fz, T3, T4, C3, C4, Cz, T5, T6, P3, P4, Pz, O1, O2)
- μνλ§ 256 Hz, μνΌλμ€ < 5 kΞ©256 Hz sampling rate; impedance < 5 kΞ©
- Eyes Closed (EC) 5λΆ + Eyes Open (EO) 5λΆ + μΈμ§ κ³Όμ 5λΆ5 minutes Eyes Closed (EC) + 5 minutes Eyes Open (EO) + 5 minutes cognitive task
- Neuroguide λλ HBI μ μ λ°μ΄ν°λ² μ΄μ€ λλΉ Z-μ μ μ°μΆZ-scoring against the Neuroguide or HBI normative database
6.2 μ κ²½ μν λΆλ₯ (5 ν΄λμ€)6.2 Neural State Classification (5 Classes)
κ²°μ κ·μΉDecision Rules
IF HBP > +1.5 SD AND PAP < -1 SD β State = HYPERAROUSAL
ELIF TBR > +1.5 SD β State = HYPOAROUSAL
ELIF FAA < -1 SD AND PAP < -0.5 SD β State = DEPRESSIVE
ELIF HBP > +1 SD AND COH(F-P) < -1 SD β State = ANXIOUS
ELSE β State = BALANCED
6.3 8κ° μλ΅ λ§€κ°λ³μ μ μ6.3 Definition of the Eight Response Parameters
| # |
λ§€κ°λ³μParameter |
λ¨μUnit |
λ²μRange |
μ€λͺ
Description |
| P1 | WPS Words Per Second | w/s | 1.5β4.5 | λ§ μλ (μμ±Β·ν
μ€νΈ λͺ¨λ)speech pacing (voice + text) |
| P2 | EI Emotional Intensity | 0β10 | 0β10 | μ μμ λ¨μ΄ λΉλ + κ°λemotional word frequency Γ intensity |
| P3 | CL Cognitive Load | 0β10 | 0β10 | κ°λ
λ°λ + μΆμλconcept density Γ abstraction level |
| P4 | PD Pause Duration | ms | 200β2500 | λ¬Έμ₯ κ° ν΄μ§ μκ°inter-utterance pause time |
| P5 | EF Encouragement Frequency | per 5 turns | 0β4 | κ²©λ €Β·κΈμ νν λΉλfrequency of encouragement and affirmation |
| P6 | MP Metacognitive Prompts | per 5 turns | 0β3 | "μ΄λ»κ² λκ»΄μ?" λ± μκ°μ±μ°° μ λprompts such as "how does that feel?" inviting self-reflection |
| P7 | DR Directness Ratio | 0β1 | 0β1 | μ§μ μ§μλ¬Έ / μ°ν νν λΉμ¨ratio of direct directives to circumlocution |
| P8 | WT Warmth | 0β10 | 0β10 | λ°λ»ν¨, κ³΅κ° μ΄ν λΉμ¨warmth and empathic-vocabulary ratio |
6.4 μνλ³ λ§€κ°λ³μ λ§€ν ν
μ΄λΈ6.4 State-Specific Parameter Mapping Table
| μ κ²½ μνNeural State |
WPS |
EI |
CL |
PD |
EF |
MP |
DR |
WT |
| Hyperarousal | 1.8 | 3 | 3 | 1500 | 2 | 0 | 0.3 | 9 |
| Hypoarousal | 3.5 | 7 | 4 | 500 | 3 | 2 | 0.7 | 7 |
| Depressive | 2.5 | 6 | 3 | 1200 | 4 | 1 | 0.4 | 10 |
| Anxious | 2.0 | 4 | 2 | 1800 | 3 | 0 | 0.4 | 9 |
| Balanced | 3.0 | 5 | 5 | 800 | 2 | 2 | 0.6 | 7 |
6.5 λ―ΈμΈ μ‘°μ (Fine-tuning by Severity)6.5 Severity-Based Fine-Tuning
μ¬κ°λ(Z-μ μ μ λκ°)μ λ°λΌ λ§€κ°λ³μμ κ°μ€μΉλ₯Ό μ μ©νλ€:Parameters are further weighted by severity (absolute Z-score):
P_final[i] = P_baseline[state, i] Γ (1 + Ξ± Β· |Z|/3)
where:
P_baseline = base value from state-mapping table
Z = relevant biomarker Z-score
Ξ± = sensitivity coefficient (0.05β0.20)
i = parameter index (1β8)
6.6 μμ€ν
ν둬ννΈ μλ μμ±6.6 Automatic System Prompt Generation
8κ° λ§€κ°λ³μκ° LLM μμ€ν
ν둬ννΈλ‘ λ³νλλ μ:Example conversion of the eight parameters into an LLM system prompt:
μμ (Hyperarousal μν)Example (Hyperarousal state)
You are speaking with a user currently in HYPERAROUSAL state
(measured via QEEG, HBP +2.1 SD, PAP -1.4 SD).
Apply the following response calibration:
- Speech pacing: 1.8 words/second (slow, deliberate)
- Emotional intensity: 3/10 (calm, low-stimulation)
- Cognitive load: 3/10 (simple, concrete)
- Pause duration: 1500ms between sentences
- Encouragement: 2 per 5 turns (gentle reassurance)
- Metacognitive prompts: 0 (avoid self-reflection demands now)
- Directness: 0.3 (use indirect, soft language)
- Warmth: 9/10 (high warmth, empathic words)
Goal: down-regulate cortical hyperarousal through paced, warm dialogue.
6.7 μ’
λ¨ λ³ν μΆμ 6.7 Longitudinal Change Tracking
μ κ²½νΌλλ°± νλ ¨μ΄ μ§νλλ©΄ QEEGκ° μ μνλμ΄ κ°λ©΄μ λ§€κ°λ³μκ° μλμΌλ‘ λ³ννλ€:As neurofeedback training proceeds, the QEEG normalizes and the parameters automatically shift accordingly:
Session 1 (HBP +2.1 SD, State: Hyperarousal) β WPS 1.8, CL 3, PD 1500
Session 5 (HBP +1.4 SD, State: Anxious) β WPS 2.0, CL 2, PD 1800
Session 10 (HBP +0.6 SD, State: Balanced) β WPS 3.0, CL 5, PD 800
08μ²κ΅¬νClaims
μ²κ΅¬ν 1 (λ
립ν)Claim 1 (Independent)
μ¬μ©μμ μ λ λν(QEEG) λ°μ΄ν°μ κΈ°λ°νμ¬ μΈκ³΅μ§λ₯ λν μμ€ν
μ μλ΅μ μ κ²½μ리νμ μνμ μ ν©μν€λ, μ»΄ν¨ν° ꡬν λ°©λ²μΌλ‘μ:
(a) 19μ±λ EEG λ°μ΄ν°λ‘λΆν° μ μ λͺ¨μ§λ¨ λ°μ΄ν°λ² μ΄μ€ λλΉ Z-μ μνλ 볡μμ QEEG λ°μ΄μ€λ§μ»€λ₯Ό μ°μΆνλ λ¨κ³λ‘μ, μκΈ° λ°μ΄μ€λ§μ»€λ Theta/Beta Ratio (TBR), Frontal Alpha Asymmetry (FAA), Posterior Alpha Power (PAP), High Beta Power (HBP), Coherence Index (COH) λ° Peak Alpha Frequency (PAF)λ₯Ό ν¬ν¨νλ λ¨κ³;
(b) μ°μΆλ λ°μ΄μ€λ§μ»€λ₯Ό κ²°μ κ·μΉμ μ μ©νμ¬, Hyperarousal, Hypoarousal, Depressive, Anxious λ° Balanced μ€ νλμ μ κ²½ μνλ₯Ό λΆλ₯νλ λ¨κ³;
(c) λΆλ₯λ μ κ²½ μνμ λμνλ μλ΅ λ§€κ°λ³μ λ§€ν ν
μ΄λΈλ‘λΆν° 8κ° μλ΅ λ§€κ°λ³μ β λ§ μλ(WPS), μ μμ κ°λ(EI), μΈμ§ λΆν(CL), ν΄μ§ κΈΈμ΄(PD), κ²©λ € λΉλ(EF), λ©νμΈμ§ μ λ(MP), μ§μ μ±(DR) λ° λ°λ»ν¨(WT) β μ κΈ°λ³Έκ°μ μΆμΆνλ λ¨κ³;
(d) μΆμΆλ λ§€κ°λ³μλ₯Ό μμ°μ΄ μμ€ν
ν둬ννΈλ‘ λ³ννμ¬ λν μΈμ΄ λͺ¨λΈμ μ£Όμ
νλ λ¨κ³; λ°
(e) μ£Όμ
λ λ§€κ°λ³μμ λ°λΌ μλ΅ ν
μ€νΈλ₯Ό μμ±νλ λ¨κ³;
λ₯Ό ν¬ν¨νλ λ°©λ².
A computer-implemented method for calibrating an artificial intelligence conversational system's response to a user's neurophysiological state based on quantitative electroencephalographic (QEEG) data, the method comprising:
(a) computing a plurality of QEEG biomarkers Z-scored against a normative population database from 19-channel EEG data, said biomarkers comprising Theta/Beta Ratio (TBR), Frontal Alpha Asymmetry (FAA), Posterior Alpha Power (PAP), High Beta Power (HBP), Coherence Index (COH), and Peak Alpha Frequency (PAF);
(b) applying the computed biomarkers to a decision rule to classify the user's neural state as one of Hyperarousal, Hypoarousal, Depressive, Anxious, or Balanced;
(c) extracting baseline values for eight response parameters β words-per-second (WPS), emotional intensity (EI), cognitive load (CL), pause duration (PD), encouragement frequency (EF), metacognitive prompts (MP), directness ratio (DR), and warmth (WT) β from a parameter mapping table corresponding to the classified neural state;
(d) converting the extracted parameters into a natural-language system prompt and injecting said prompt into a Large Language Model; and
(e) generating a response text in accordance with the injected parameters.
μ²κ΅¬ν 2 (μ’
μν)Claim 2 (Dependent)
μ²κ΅¬ν 1μ μμ΄μ, λ¨κ³ (c)μ μλ΅ λ§€κ°λ³μ μΆμΆ ν, κ΄λ ¨ λ°μ΄μ€λ§μ»€μ Z-μ μ μ λκ°μ κΈ°λ°ν κ°μ€μΉ (1 + Ξ± Β· |Z|/3)λ₯Ό μ μ©νμ¬ λ§€κ°λ³μμ μ΅μ’
κ°μ μ°μΆνλ, Ξ±λ 0.05 λ΄μ§ 0.20 λ²μμ λ―Όκ°λ κ³μμΈ κ²μ νΉμ§μΌλ‘ νλ λ°©λ².
The method of Claim 1, further comprising, after extracting response parameters in step (c), applying a weighting factor (1 + Ξ± Β· |Z|/3) based on the absolute Z-score of a relevant biomarker to compute final parameter values, where Ξ± is a sensitivity coefficient in the range of 0.05 to 0.20.
μ²κ΅¬ν 3 (μ’
μν)Claim 3 (Dependent)
μ²κ΅¬ν 1μ μμ΄μ, λμΌ μ¬μ©μμ λν΄ μκ°μ μΌλ‘ λΆλ¦¬λ 볡μμ QEEG μΈ‘μ μΈμ
μ λν΄ λ¨κ³ (a) λ΄μ§ (e)λ₯Ό λ°λ³΅νκ³ , μΈμ
κ° λ°μ΄μ€λ§μ»€μ λ³ν μΆμ΄μ κΈ°λ°νμ¬ μλ΅ λ§€κ°λ³μμ λμ 보μ μ μννλ λ¨κ³λ₯Ό λ ν¬ν¨νλ λ°©λ².
The method of Claim 1, further comprising iterating steps (a) through (e) over a plurality of temporally separated QEEG measurement sessions for the same user, and performing dynamic recalibration of the response parameters based on inter-session biomarker trend changes.
μ²κ΅¬ν 4 (μ’
μν)Claim 4 (Dependent)
μ²κ΅¬ν 1μ μμ΄μ, λ¨κ³ (b)μ κ²°μ κ·μΉμ λ€μμ ν¬ν¨νλ κ²μ νΉμ§μΌλ‘ νλ λ°©λ²: HBPκ° +1.5 SD μ΄κ³Όμ΄κ³ PAPκ° -1 SD λ―Έλ§μΈ κ²½μ° Hyperarousalλ‘ λΆλ₯; TBRμ΄ +1.5 SD μ΄κ³ΌμΈ κ²½μ° Hypoarousalλ‘ λΆλ₯; FAAκ° -1 SD λ―Έλ§μ΄κ³ PAPκ° -0.5 SD λ―Έλ§μΈ κ²½μ° Depressiveλ‘ λΆλ₯; HBPκ° +1 SD μ΄κ³Όμ΄κ³ μ λ-λμ μΌκ΄μ±μ΄ -1 SD λ―Έλ§μΈ κ²½μ° Anxiousλ‘ λΆλ₯; κ·Έ μΈμ κ²½μ° Balancedλ‘ λΆλ₯.
The method of Claim 1, wherein the decision rule of step (b) comprises: classifying as Hyperarousal when HBP exceeds +1.5 SD and PAP is below β1 SD; classifying as Hypoarousal when TBR exceeds +1.5 SD; classifying as Depressive when FAA is below β1 SD and PAP is below β0.5 SD; classifying as Anxious when HBP exceeds +1 SD and frontoparietal coherence is below β1 SD; and classifying as Balanced otherwise.
μ²κ΅¬ν 5 (μ’
μν)Claim 5 (Dependent)
μ²κ΅¬ν 1μ μμ΄μ, QEEG μΈ‘μ μ μμ μν 5λΆ(λ κ°μ) + μμ μν 5λΆ(λ λΈ) + μΈμ§ κ³Όμ 5λΆμ νμ€ νλ‘ν μ½μ λ°λΌ μνλλ©°, 19μ±λμ κ΅μ 10-20 μμ€ν
μ λ°λ₯Έ Fp1, Fp2, F3, F4, F7, F8, Fz, T3, T4, C3, C4, Cz, T5, T6, P3, P4, Pz, O1 λ° O2λ₯Ό ν¬ν¨νλ κ²μ νΉμ§μΌλ‘ νλ λ°©λ².
The method of Claim 1, wherein the QEEG measurement is performed according to a standard protocol comprising five minutes of resting eyes-closed, five minutes of resting eyes-open, and five minutes of a cognitive task, and the 19 channels comprise Fp1, Fp2, F3, F4, F7, F8, Fz, T3, T4, C3, C4, Cz, T5, T6, P3, P4, Pz, O1, and O2 according to the International 10-20 System.
μ²κ΅¬ν 6 (μ’
μν)Claim 6 (Dependent)
μ²κ΅¬ν 1μ μμ΄μ, μ μ λͺ¨μ§λ¨ λ°μ΄ν°λ² μ΄μ€λ Neuroguide λλ Human Brain Index (HBI) μ κ·λ°μ΄ν°λ² μ΄μ€ μ€μμ μ νλλ κ²μ νΉμ§μΌλ‘ νλ λ°©λ².
The method of Claim 1, wherein the normative population database is selected from the Neuroguide or Human Brain Index (HBI) normative databases.
μ²κ΅¬ν 7 (λ
립ν β μμ€ν
)Claim 7 (Independent β System)
μ²κ΅¬ν 1 λ΄μ§ 6 μ€ μ΄λ ν νμ λ°©λ²μ μννκΈ° μν, μ μ΄λ νλμ νλ‘μΈμ, EEG λ°μ΄ν°λ₯Ό μμ νλ μ
λ ₯ μΈν°νμ΄μ€, λ° μκΈ° νλ‘μΈμμ μν΄ μ€νλλ λͺ
λ Ήμ΄λ₯Ό μ μ₯νλ λΉμΌμμ μ»΄ν¨ν° νλ
κ°λ₯ μ μ₯ 맀체λ₯Ό ν¬ν¨νλ μ κ²½ μν μ μν μΈκ³΅μ§λ₯ λν μμ€ν
.
A neural-state-adaptive artificial intelligence conversational system for performing the method of any one of Claims 1 through 6, the system comprising at least one processor, an input interface for receiving EEG data, and a non-transitory computer-readable storage medium storing instructions executable by the processor.
μ²κ΅¬ν 8 (λ
립ν β 맀체)Claim 8 (Independent β Medium)
μ»΄ν¨ν°μ μν΄ μ€νλ λ μ²κ΅¬ν 1 λ΄μ§ 6 μ€ μ΄λ ν νμ λ°©λ²μ μννλλ‘ νλ λͺ
λ Ήμ΄λ₯Ό μ μ₯νλ λΉμΌμμ μ»΄ν¨ν° νλ
κ°λ₯ μ μ₯ 맀체.
A non-transitory computer-readable storage medium storing instructions which, when executed by a computer, cause the computer to perform the method of any one of Claims 1 through 6.
11κ΄λ ¨ λ
Όλ¬ΈReferences
λ³Έ λ°λͺ
μ μ΄λ‘ μ Β·μμμ κ·Όκ±°κ° λλ ν΅μ¬ λ
Όλ¬Έ λ° μλ£. ν΄λ¦νλ©΄ μΈλΆ μΆμ²λ‘ μ΄λν©λλ€.
Key papers and resources providing the theoretical and clinical basis for this invention. Click links to access external sources.
A. QEEG ν΅μ¬ λ°μ΄μ€λ§μ»€A. Core QEEG Biomarkers
- A1Arns M, Conners CK, Kraemer HC. A decade of EEG Theta/Beta Ratio Research in ADHD: a meta-analysis. Journal of Attention Disorders, 2013; 17(5):374-383. DOI ↗
- A2Henriques JB, Davidson RJ. Left frontal hypoactivation in depression. Journal of Abnormal Psychology, 1991; 100(4):535-545. DOI ↗
- A3Knyazev GG. Motivation, emotion, and their inhibitory control mirrored in brain oscillations. Neuroscience & Biobehavioral Reviews, 2007; 31(3):377-395. DOI ↗
- A4Klimesch W. EEG alpha and theta oscillations reflect cognitive and memory performance. Brain Research Reviews, 1999; 29(2-3):169-195. DOI ↗
- A5Teicher MH, Samson JA, Anderson CM, Ohashi K. The effects of childhood maltreatment on brain structure, function and connectivity. Nature Reviews Neuroscience, 2016; 17(10):652-666. DOI ↗
- A6Thatcher RW. Coherence, Phase Differences, Phase Shift, and Phase Lock in EEG/ERP Analyses. Developmental Neuropsychology, 2012; 37(6):476-496. DOI ↗
B. μ λ λν (QEEG) μμ μμ©B. Quantitative EEG Clinical Applications
- B1Kropotov JD. Quantitative EEG, Event-Related Potentials and Neurotherapy. Academic Press, 2009. Book ↗
- B2Hammond DC. What is Neurofeedback: An Update. Journal of Neurotherapy, 2011; 15(4):305-336. DOI ↗
- B3Thatcher RW, Lubar JF. History of the scientific standards of QEEG normative databases. In: Budzynski TH et al. (Eds.), Introduction to Quantitative EEG and Neurofeedback, 2nd ed. Academic Press, 2009; 29-62.
- B4Lubar JF. Discourse on the development of EEG diagnostics and biofeedback for attention-deficit/hyperactivity disorders. Biofeedback and Self-Regulation, 1991; 16(3):201-225.
C. μ κ²½μ리νμ κ°μ± μνC. Neurophysiological Arousal States
- C1Sterman MB. Sensorimotor EEG operant conditioning: experimental and clinical effects. The Pavlovian Journal of Biological Science, 1977; 12(2):63-92. DOI ↗
- C2Sterman MB, Egner T. Foundation and practice of neurofeedback for the treatment of epilepsy. Applied Psychophysiology and Biofeedback, 2006; 31(1):21-35. DOI ↗
- C3Pfurtscheller G, Lopes da Silva FH. Event-related EEG/MEG synchronization and desynchronization: basic principles. Clinical Neurophysiology, 1999; 110(11):1842-1857. DOI ↗
D. μ μ μ»΄ν¨ν
λ° μΈκ°-AI μνΈμμ©D. Affective Computing and Human-AI Interaction
- D1Picard RW. Affective Computing. MIT Press, 1997.
- D2Picard RW, Vyzas E, Healey J. Toward machine emotional intelligence: Analysis of affective physiological state. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2001; 23(10):1175-1191. DOI ↗
- D3Calvo RA, D'Mello SK. Affect detection: An interdisciplinary review of models, methods, and their applications. IEEE Transactions on Affective Computing, 2010; 1(1):18-37. DOI ↗
E. μμ±Β·λ§ μλμ μ μ μνE. Speech Rate and Affective State
- E1Mundt JC, Snyder PJ, Cannizzaro MS, et al. Voice acoustic measures of depression severity and treatment response. Journal of Neurolinguistics, 2007; 20(1):50-64. DOI ↗
- E2Cummins N, Scherer S, Krajewski J, et al. A review of depression and suicide risk assessment using speech analysis. Speech Communication, 2015; 71:10-49. DOI ↗
F. μμ λ©΄λ΄ κΈ°λ² λ° μΉλ£ λλ§ΉF. Clinical Interview and Therapeutic Alliance
- F1Bordin ES. The generalizability of the psychoanalytic concept of the working alliance. Psychotherapy: Theory, Research & Practice, 1979; 16(3):252-260. DOI ↗
- F2Horvath AO, Del Re AC, FlΓΌckiger C, Symonds D. Alliance in individual psychotherapy. Psychotherapy, 2011; 48(1):9-16. DOI ↗
- F3Wampold BE. How important are the common factors in psychotherapy? An update. World Psychiatry, 2015; 14(3):270-277. DOI ↗
G. Brain-Computer Interface λ° EEG-AI ν΅ν©G. Brain-Computer Interface and EEG-AI Integration
- G1Lotte F, Bougrain L, Cichocki A, et al. A review of classification algorithms for EEG-based brain-computer interfaces: a 10 year update. Journal of Neural Engineering, 2018; 15(3):031005. DOI ↗
- G2Roy Y, Banville H, Albuquerque I, et al. Deep learning-based electroencephalography analysis: a systematic review. Journal of Neural Engineering, 2019; 16(5):051001. DOI ↗