Some content of this application is unavailable at the moment.
If this situation persist, please contact us atFeedback&Contact
1. (WO2002044991) METHOD AND SYSTEM FOR EMOTION PERCEPTION FROM TEXT
Latest bibliographic data on file with the International Bureau   

Pub. No.: WO/2002/044991 International Application No.: PCT/KR2001/002048
Publication Date: 06.06.2002 International Filing Date: 27.11.2001
Chapter 2 Demand Filed: 14.06.2002
IPC:
G06F 17/27 (2006.01)
G PHYSICS
06
COMPUTING; CALCULATING; COUNTING
F
ELECTRIC DIGITAL DATA PROCESSING
17
Digital computing or data processing equipment or methods, specially adapted for specific functions
20
Handling natural language data
27
Automatic analysis, e.g. parsing, orthograph correction
Applicants:
HAN, Ka-Ram [KR/KR]; KR
ZHANG, Byoung-Tak [KR/KR]; KR
MOON, Hyun-Ku [KR/KR]; KR
DIGITAL AGENT, INC. [KR/KR]; 10F, Sungdo Bldg., 587-23 Sinsa-dong, Kangnam-gu Seoul 135-892, KR (AllExceptUS)
Inventors:
HAN, Ka-Ram; KR
ZHANG, Byoung-Tak; KR
MOON, Hyun-Ku; KR
Agent:
KIM, Samsoo; 3rd floor, Dukwon Bldg., 637-19 Yoksam-dong, Kangnam-ku Seoul 135-909, KR
Priority Data:
2000/7206330.11.2000KR
Title (EN) METHOD AND SYSTEM FOR EMOTION PERCEPTION FROM TEXT
(FR) TECHNIQUE ET SYSTEME PERMETTANT DE PERCEVOIR DES EMOTIONS DANS UN TEXTE
Abstract:
(EN) A method for perceiving and visualizing emotion contained in a text is provided. A code representing an emotional status is allocated to each sample sentence. A priori probability of occurrence of sentences representing each emotional status is calculated . A code representing an emotional status is allocated to each word contained in the sentences. The probability of occurrence of the word in sentences representing the corresponding emotional status is calculated. Then, the probability of each emotional status of an object sentence is calculated by multiplying the a priori probability of status i with the probability of occurrence in status i of each word in the sentence, so that the emotional status yielding the highest probabilty is determined to represent the emotional status of the sentence. Expressions or punction marks capable as such of expressing emotions are processed separately in order to enhance the efficiency of the processing.
(FR) Cette invention concerne une technique permettant de percevoir et de visualiser une émotion contenue dans un texte. Après attribution d'un code représentant un état émotionnel à chaque phrase de l'échantillon, on calcule la probabilité d'apparition dans les phrase du mot représentant l'état émotionnel correspondant. On calcule ensuite la probabilité de chaque état émotionnel d'une phrase objet en multipliant la probabilité à priori du statut i avec la probabilité d'apparition dans l'état i de chaque mot de la phrase, ce qui permet de déterminer l'état émotionnel au taux de probabilité le plus élevé qui est représentatif de l'état émotionnel de la phrase. Pour améliorer l'efficacité du traitement, on traite séparément des expressions ou des signes de ponctuation pouvant exprimer des émotions.
front page image
Designated States: AE, AG, AL, AM, AT, AU, AZ, BA, BB, BG, BR, BY, BZ, CA, CH, CN, CO, CR, CU, CZ, DE, DK, DM, DZ, EC, EE, ES, FI, GB, GD, GE, GH, GM, HR, HU, ID, IL, IN, IS, JP, KE, KG, KP, KZ, LC, LK, LR, LS, LT, LU, LV, MA, MD, MG, MK, MN, MW, MX, MZ, NO, NZ, PH, PL, PT, RO, RU, SD, SE, SG, SI, SK, SL, TJ, TM, TR, TT, TZ, UA, UG, US, UZ, VN, YU, ZA, ZW
African Regional Intellectual Property Organization (ARIPO) (GH, GM, KE, LS, MW, MZ, SD, SL, SZ, TZ, UG, ZW)
Eurasian Patent Office (AM, AZ, BY, KG, KZ, MD, RU, TJ, TM)
European Patent Office (EPO) (AT, BE, CH, CY, DE, DK, ES, FI, FR, GB, GR, IE, IT, LU, MC, NL, PT, SE, TR)
African Intellectual Property Organization (BF, BJ, CF, CG, CI, CM, GA, GN, GQ, GW, ML, MR, NE, SN, TD, TG)
Publication Language: English (EN)
Filing Language: Korean (KO)