AI-BASED DISEASE DIAGNOSIS METHOD AND DEVICE USING VOICE DATA

• Main Author: SHIN, Grace Jung Eun
• Format: Patent
• Language: English; French; Korean
• Published: 02.11.2023
• Subjects: ACOUSTICS; DIAGNOSIS; HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATIONTECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING ORPROCESSING OF MEDICAL OR HEALTHCARE DATA; HUMAN NECESSITIES; HYGIENE; IDENTIFICATION; INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTEDFOR SPECIFIC APPLICATION FIELDS; MEDICAL OR VETERINARY SCIENCE; MUSICAL INSTRUMENTS; PHYSICS; SPEECH ANALYSIS OR SYNTHESIS; SPEECH OR AUDIO CODING OR DECODING; SPEECH OR VOICE PROCESSING; SPEECH RECOGNITION; SURGERY

The present invention relates to an AI-based disease diagnosis method using voice data, the method comprises the steps of: collecting first voice data; removing at least one of noise, unique characteristics of a voice, and disease characteristics of a voice from the first voice data to generate second voice data; and diagnosing at least one disease among dementia, depression, and hearing loss, on the basis of AI by using the second voice data. La présente invention se rapporte à un procédé de diagnostic de maladie basé sur une intelligence artificielle (IA) utilisant des données vocales, le procédé comprenant les étapes consistant : à collecter des premières données vocales ; à supprimer un bruit et/ou des caractéristiques uniques d'une voix et/ou des caractéristiques de maladie d'une voix à partir des premières données vocales pour générer des secondes données vocales ; et à diagnostiquer au moins une maladie parmi la démence, la dépression et la perte d'audition, sur la base d'une intelligence IA en utilisant les secondes données vocales. 본 발명은 음성 데이터를 이용한 AI 기반의 질병 진단 방법으로서, 제1 음성 데이터를 수집하는 단계, 상기 제1 음성 데이터에서 소음, 음성의 고유특성, 또는 음성의 질환특성 중 적어도 하나를 제거하여 제2 음성 데이터를 생성하는 단계, 및 상기 제2 음성 데이터를 이용하여 치매, 우울증, 또는 난청 중 적어도 하나의 질병을 AI에 기반하여 진단하는 단계를 포함한다.