SG11201805746YA - Self-service classification system - Google Patents

Abstract

INTERNATIONAL APPLICATION PUBLISHED UNDER THE PATENT COOPERATION TREATY (PCT) (19) World Intellectual Property Organization International Bureau (43) International Publication Date 12 October 2017 (12.10.2017) WIPO I PCT (10) International Publication Number WO 2017/176749 Al (51) International Patent Classification: G06F 3/0482 (2013.01) GO6K 9/62 (2006.01) G06F 17/28 (2006.01) G1OL 15/18 (2013.01) (21) International Application Number: PCT/US2017/025937 (22) International Filing Date: 4 April 2017 (04.04.2017) (25) Filing Language: English (26) Publication Language: English (30) Priority Data: 62/318,412 5 April 2016 (05.04.2016) US 62/376,039 17 August 2016 (17.08.2016) US (71) Applicant: THOMSON REUTERS GLOBAL RE- SOURCES UNLIMITED COMPANY [IE/CH]; Neuhof- strasse 1, 6340 Baar (CH). (72) Inventor; and (71) Applicant (for US only): HERTZ, Shai [IL/US]; 2 Chauncy, Apartment 4, Cambridge, MA 02138 (US). (72) Inventors: ZAROSIM, Hila; Moshe Sharet 22, Bat Yam (IL). HAZAI, Oren; Zeiltin 13, Tel Aviv (IL). ROM, Ofri; Harey Yehuda 59, Ganey Tikva (IL). AZIKRI, Ehud; Keren Kayemet 7/5, Herzliya (IL). WEINTRAUB, Lior; Einsfein 15, Petach Tikva (IL). LINDMAN, Yael; Haerez 5/06, Shoham (IL). WEINREB, Enav; Hanesiim 45/9, Petach Tikva (IL). KHALAMAN, Savva; Jabotinsky 50/807, Givat Shmuel (IL). BEN-SHLOMO, Yossi; Lasal 22, Tel Aviv (IL). LEVINSON, Dmitry; Wormaiza 7/10, Tel Aviv (IL). SHARABI, Evyatar; HaBustan 10, Kfar Hess (IL). GOLDSHLAGER, Alexandra, Rabinovich; Dizingof 81, Tel Aviv (IL). (74) Agent: CHAN-PARSONS, Katy; Thomason Reuters c/o Intellectual Property, 3 Times Square, New York, NY 10036 (US). (81) Designated States (unless otherwise indicated, for every kind of national protection available): AE, AG, AL, AM, AO, AT, AU, AZ, BA, BB, BG, BH, BN, BR, BW, BY, BZ, CA, CH, CL, CN, CO, CR, CU, CZ, DE, DJ, DK, DM, DO, DZ, EC, EE, EG, ES, FI, GB, GD, GE, GH, GM, GT, HN, HR, HU, ID, IL, IN, IR, IS, JP, KE, KG, KH, KN, KP, KR, KW, KZ, LA, LC, LK, LR, LS, LU, LY, MA, MD, ME, MG, MK, MN, MW, MX, MY, MZ, NA, NG, NI, NO, NZ, OM, PA, PE, PG, PH, PL, PT, QA, RO, RS, RU, RW, SA, SC, SD, SE, SG, SK, SL, SM, ST, SV, SY, TH, TJ, TM, TN, TR, TT, TZ, UA, UG, US, UZ, VC, VN, ZA, ZM, ZW. (84) Designated States (unless otherwise indicated, for every kind of regional protection available): ARIPO (BW, GH, GM, KE, LR, LS, MW, MZ, NA, RW, SD, SL, ST, SZ, TZ, UG, ZM, ZW), Eurasian (AM, AZ, BY, KG, KZ, RU, TJ, TM), European (AL, AT, BE, BG, CH, CY, CZ, DE, DK, EE, ES, FI, FR, GB, GR, HR, HU, IE, IS, IT, LT, LU, [Continued on next page] (54) Title: SELF-SERVICE CLASSIFICATION SYSTEM 100 CLASSIFICATION SERVER RAN UM ACCESS MEMORY 114 PROCESSOR 112 INPUT/ OUTPUT tie L 111111111111110111011111111111010111110111010111100111011111110111111111110111111 Production Server 180 production dataset 182 L test datesel 184 NON-VOLATILE MEMORY ,20 Waillerig - Filtering ! Med - erffig Training - Trilling Module Module Module Module Module 122 124 ! 128 128 130 esting Publication Module Module 132 134 W O 20 1717 / 67 49 Al DATA STORE 140 User Date Store 142 Customized Classincation Model Data Store 148 Filtered User Data Store 144 Taxonomy Date Store 150 Preliminary Model Data Store 148 NETWORK 160 Access Device 170 user interface 174 FIG. 1 (57) : Systems, technologies and techniques for generating a customized classification model are disclosed. The system and technologies, such as THOMSON REUTERS SELF-SERVICE CLASSIFICATIONTM, employ part machine learning and part an user interactive approach to generate a customized classification model. The system combines a novel approach for text classifica- tion using a smaller initial set of data to initiate training, with a unique workflow and user interaction for customization. WO 2017/176749 Al MIDEDIMOHNIIMME3010MINEDIEEMEHOIMI LV, MC, MK, MT, NL, NO, PL, PT, RO, RS, SE, SI, SK, Published: SM, TR), OAPI (BF, BJ, CF, CG, CI, CM, GA, GN, GQ, GW, KM, ML, MR, NE, SN, TD, TG). with international search report (Art. 21(3))