EP1472624A2 - Systeme d analyse predictive de flux temporels d inform ations - Google Patents
Systeme d analyse predictive de flux temporels d inform ationsInfo
- Publication number
- EP1472624A2 EP1472624A2 EP03718824A EP03718824A EP1472624A2 EP 1472624 A2 EP1472624 A2 EP 1472624A2 EP 03718824 A EP03718824 A EP 03718824A EP 03718824 A EP03718824 A EP 03718824A EP 1472624 A2 EP1472624 A2 EP 1472624A2
- Authority
- EP
- European Patent Office
- Prior art keywords
- values
- predictive analysis
- flow
- digital information
- vector
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Ceased
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/06—Asset management; Financial planning or analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
Definitions
- the present invention relates to a system for predictive analysis of temporal flows of digital information with which text information is associated.
- the invention relates to a predictive analysis system comprising means for automatically predicting values of a temporal flow of digital information from past values of this flow.
- Many predictive analysis systems of this type are known. These are generally based on the analysis of the past values of a temporal flow of digital information to predict the future values of this flow.
- financial textual information provided with past values also has a significant influence on the future values of the time flow of digital information.
- conventional predictive analytics systems cannot be completely reliable.
- the invention aims to remedy this drawback by providing a predictive analysis system improving the prediction of temporal information flows.
- the subject of the invention is therefore a predictive analysis system of the aforementioned type, characterized in that it includes means for analyzing textual information for the supply, to the prediction means, of a vector of weighted concepts associated with past values of the time flow of digital information.
- a system according to the invention also takes into account textual information associated with the temporal flow of digital information to be analyzed, in order to make a prediction. The predicted results will be all the better.
- the prediction means are also means for predicting future values of a weighted concept vector from past values of the time stream of digital information and past values of the weighted concept vector;
- the system comprises means for generating future textual information from the future values of the predicted weighted concept vector
- the prediction means comprise a network of neurons receiving as input the past values of the flow of digital information and of the weighted concept vector, and supplying as output the future values of the temporal flow of digital information and of the weighted concept vector.
- the central unit 10 further comprises means 14 for semantic analysis of textual information and means 16 for generating a conceptual summary. These analysis means 14 and generation 16 are connected to the neural network 12, respectively at the input and at the output thereof.
- the semantic analysis means 14 are conventional. They include, for example, the semantic analyzer developed by the company Convera. These semantic analysis means 14 are adapted to receive textual information as input 18 and to output a vector 20 modeling the textual information 18 in a multidimensional space of predefined concepts. The coordinates of this vector of concepts 20 precisely describe the essence of the concepts contained in the textual information 18.
- the concept vector 20 is supplied at the input of the neural network 12 with past values 22 of a temporal flow of digital information.
- the neural network 12 is configured in such a way that it outputs, on the one hand, predicted values 24 of the temporal flow of digital information and, on the other hand, a predicted concept vector 26.
- the configuration of the neural network 12 is obtained in a conventional manner by a series of learnings.
- the predicted concept vector 26 is provided at the input of the means 16 for generating a conceptual summary, to provide at the output thereof predicted textual information 28.
- the means for generating the conceptual summary are adapted to provide intelligible text to starting from the concepts of the space of predetermined concepts, weighted by the predicted concept vector 26. It clearly appears that the system described previously makes it possible to improve the prediction of temporal flows of digital information by also taking into account associated textual information to past values of this stream.
- Another advantage of this system is that it also makes it possible to provide predicted textual information, based on past textual information and past values of the temporal flow of digital information associated with past textual information. This system can in particular be applied to the processing of temporal flows of financial information.
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Finance (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- Technology Law (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Human Resources & Organizations (AREA)
- Operations Research (AREA)
- Entrepreneurship & Innovation (AREA)
- Game Theory and Decision Science (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Testing And Monitoring For Control Systems (AREA)
- Arrangements For Transmission Of Measured Signals (AREA)
Abstract
Description
Claims
Applications Claiming Priority (3)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
FR0201417 | 2002-02-06 | ||
FR0201417A FR2835632B1 (fr) | 2002-02-06 | 2002-02-06 | Systeme d'analyse predictive de flux temporels d'informations |
PCT/FR2003/000326 WO2003067463A2 (fr) | 2002-02-06 | 2003-02-03 | Systeme d'analyse predictive de flux temporels d'informations |
Publications (1)
Publication Number | Publication Date |
---|---|
EP1472624A2 true EP1472624A2 (fr) | 2004-11-03 |
Family
ID=27619943
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
EP03718824A Ceased EP1472624A2 (fr) | 2002-02-06 | 2003-02-03 | Systeme d analyse predictive de flux temporels d inform ations |
Country Status (5)
Country | Link |
---|---|
US (1) | US7299214B2 (fr) |
EP (1) | EP1472624A2 (fr) |
AU (1) | AU2003222870A1 (fr) |
FR (1) | FR2835632B1 (fr) |
WO (1) | WO2003067463A2 (fr) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US10248719B2 (en) | 2015-08-24 | 2019-04-02 | Tata Consultancy Services Limited | System and method for analysing temporal text data |
Families Citing this family (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US7984001B2 (en) * | 2003-10-15 | 2011-07-19 | Alcatel-Lucent Usa Inc. | Neural network-based extension of global position timing |
US8584020B2 (en) * | 2007-12-28 | 2013-11-12 | Microsoft Corporation | User-defined application models |
Family Cites Families (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US5675710A (en) * | 1995-06-07 | 1997-10-07 | Lucent Technologies, Inc. | Method and apparatus for training a text classifier |
US6026397A (en) * | 1996-05-22 | 2000-02-15 | Electronic Data Systems Corporation | Data analysis system and method |
US6125105A (en) * | 1997-06-05 | 2000-09-26 | Nortel Networks Corporation | Method and apparatus for forecasting future values of a time series |
US6751606B1 (en) * | 1998-12-23 | 2004-06-15 | Microsoft Corporation | System for enhancing a query interface |
US6430539B1 (en) | 1999-05-06 | 2002-08-06 | Hnc Software | Predictive modeling of consumer financial behavior |
EP1107157A3 (fr) * | 1999-12-01 | 2001-11-28 | International Business Machines Corporation | Système et méthode pour la réalisation d'une analyse prévisionnelle |
US6868411B2 (en) * | 2001-08-13 | 2005-03-15 | Xerox Corporation | Fuzzy text categorizer |
-
2002
- 2002-02-06 FR FR0201417A patent/FR2835632B1/fr not_active Expired - Fee Related
-
2003
- 2003-02-03 US US10/503,744 patent/US7299214B2/en not_active Expired - Fee Related
- 2003-02-03 AU AU2003222870A patent/AU2003222870A1/en not_active Abandoned
- 2003-02-03 EP EP03718824A patent/EP1472624A2/fr not_active Ceased
- 2003-02-03 WO PCT/FR2003/000326 patent/WO2003067463A2/fr not_active Application Discontinuation
Non-Patent Citations (1)
Title |
---|
See references of WO03067463A2 * |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US10248719B2 (en) | 2015-08-24 | 2019-04-02 | Tata Consultancy Services Limited | System and method for analysing temporal text data |
Also Published As
Publication number | Publication date |
---|---|
US7299214B2 (en) | 2007-11-20 |
FR2835632B1 (fr) | 2004-04-30 |
FR2835632A1 (fr) | 2003-08-08 |
WO2003067463A3 (fr) | 2004-05-27 |
US20050119960A1 (en) | 2005-06-02 |
AU2003222870A1 (en) | 2003-09-02 |
WO2003067463A2 (fr) | 2003-08-14 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US10453447B2 (en) | Filtering data in an audio stream | |
US10902058B2 (en) | Cognitive content display device | |
US11688400B1 (en) | Systems and methods to utilize text representations of conversations | |
CN111984779B (zh) | 一种对话文本分析方法、装置、设备和可读介质 | |
US8311824B2 (en) | Methods and apparatus for language identification | |
US20140025376A1 (en) | Method and apparatus for real time sales optimization based on audio interactions analysis | |
KR20180107136A (ko) | 서치 엔진 선택 및 최적화를 위한 방법 및 시스템 | |
KR102080081B1 (ko) | 해외 건설 계약서 내의 독소 조항 및 누락 조항의 자동 검토 프로그램 | |
EP1364316A2 (fr) | Dispositif d'extraction d'informations d'un texte a base de connaissances | |
US9270811B1 (en) | Visual options for audio menu | |
WO2002017273A8 (fr) | Methode de formation pour personnel d'entretien devant assurer l'entretien d'un equipement donne | |
FR3105862A1 (fr) | PROCEDE ET système DE SELECTION D’UN MODELE D’apprentissage AU SEIN D’UNE PLURALITE DE MODELES D’apprentissage | |
Shim et al. | Phonetic analytics technology and big data: real-world cases | |
Klop et al. | Term rewriting systems | |
US11797842B2 (en) | Identifying friction points in customer data | |
EP1472624A2 (fr) | Systeme d analyse predictive de flux temporels d inform ations | |
Shah et al. | A review of natural language processing in contact centre automation | |
US20190115028A1 (en) | Methods and systems for optimizing engine selection | |
Youssfi Nouira et al. | Bitcoin Price Prediction Considering Sentiment Analysis on Twitter and Google News | |
US20210304139A1 (en) | Process flow diagram prediction utilizing a process flow diagram embedding | |
WO2005069166A1 (fr) | Systeme automatique de traitement des informations portees par des textes courts | |
Hanafi et al. | Machine-Assisted Error Discovery in Conversational AI Systems | |
Ribeiro et al. | Assessing user expertise in spoken dialog system interactions | |
FR2842930A1 (fr) | Systeme d'analyse d'un flux temporel d'informations pour l'extraction d'indices de satisfaction et procede correspondant | |
US20230177518A1 (en) | Enhanced issue detection and resolution in a call center |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PUAI | Public reference made under article 153(3) epc to a published international application that has entered the european phase |
Free format text: ORIGINAL CODE: 0009012 |
|
17P | Request for examination filed |
Effective date: 20040803 |
|
AK | Designated contracting states |
Kind code of ref document: A2 Designated state(s): AT BE BG CH CY CZ DE DK EE ES FI FR GB GR HU IE IT LI LU MC NL PT SE SI SK TR |
|
AX | Request for extension of the european patent |
Extension state: AL LT LV MK RO |
|
17Q | First examination report despatched |
Effective date: 20070608 |
|
RAP1 | Party data changed (applicant data changed or rights of an application transferred) |
Owner name: ORANGE |
|
REG | Reference to a national code |
Ref country code: DE Ref legal event code: R003 |
|
STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: THE APPLICATION HAS BEEN REFUSED |
|
18R | Application refused |
Effective date: 20140419 |