公开(公告)号：EP1072003A1

公开(公告)日：2001-01-31

申请号：EP99918135.7

申请日：1999-04-21

申请人： The Dialog Corporation plc

发明人： FERNANDES, Llewelyn, Ignazio ,  HAMMOND, Rachel

IPC分类号： G06F17/30

CPC分类号： G06F17/30705 ,  G06K9/62 ,  Y10S707/99931 ,  Y10S707/99932 ,  Y10S707/99933 ,  Y10S707/99934 ,  Y10S707/99935

摘要： Data files (205) are categorised in order to facilitate the searching for information. The analysis is performed in order to identify items which may be considered as having high value without actually being directly specified. Occurrences of unspecified candidate items are identified (207) in contexts for a preferred specified category. Occurrences of unspecified candidate items are identified (209) in non-preferred contexts. The preferred occurrences are processed (211) with the non-preferred occurrences for each candidate item in order to select candidate items as being high value items. In the preferred embodiment, data relating to companies is identified without specific company names being defined.

公开(公告)号：EP1073975A1

公开(公告)日：2001-02-07

申请号：EP99918128.2

申请日：1999-04-21

申请人： The Dialog Corporation plc

发明人： BAGSHAW, Marcus, Alexander

IPC分类号： G06F17/30

CPC分类号： G06F17/30705 ,  Y10S707/99933 ,  Y10S707/99936

摘要： Data files are associated with categories by processing said data files in combination with outline files. Large files (221) are divided into a plurality of file sections (223) each having a size substantially consistent with a preferred size. Each of the file sections is categorised (224) and the sets of associations are processed (225) to produce a set of category associations for the original undivided file (221).

公开(公告)号：EP0815517B1

公开(公告)日：1999-05-06

申请号：EP96907582.9

申请日：1996-03-19

申请人： The Dialog Corporation plc

发明人： DOWNS, Iain, Macauley ,  JAIN, Neetu

IPC分类号： G06F17/22 ,  G06F17/27 ,  G06F17/21

CPC分类号： G06F17/22 ,  G06F17/211 ,  G06F17/2205 ,  G06F17/2258 ,  G06F17/27 ,  Y10S707/99942

摘要： Structured graphical data is reorganised. The data, which may be defined in accordance with portable document format (PDF) includes graphical object definitions and references to said definitions. The data is reorganised so that the graphical object references are preceded by their respective object definitions.

公开(公告)号：EP1073974A1

公开(公告)日：2001-02-07

申请号：EP99918127.4

申请日：1999-04-21

申请人： The Dialog Corporation plc

发明人： HAMMOND, Rachel ,  FERNANDES, Llewelyn, Ignazio

IPC分类号： G06F17/30

CPC分类号： G06F17/30705

摘要： Asociation files (153, 154, 155) are generated that are suitable for determining whether a data file (151) belongs to a predetermined category (A, B). A plurality of included files (156) belonging to the category are stored in combination with a plurality of excluded files (157) not belonging to the category. Included files (156) are processed to identify candidate terms for an association file (155). The suitability of candidate terms is assessed with references to occurrences in the included files (156) in addition, the suitability is also assessed with reference to occurrences in the excluded files (157) so as to provide definition terms for an association file. Thus, if a term identified as a candidate also appears frequently in the excluded files (157) it is likely to be assessed as unsuitable for inclusion within the new association file.

公开(公告)号：EP1073976A1

公开(公告)日：2001-02-07

申请号：EP99918148.0

申请日：1999-04-22

申请人： The Dialog Corporation plc

发明人： HAMMOND, Rachel ,  FERNANDES, Llewelyn Ignazio

IPC分类号： G06F17/30

CPC分类号： G06F17/30707

摘要： Data files (251) are received by a central processing system (104) and these files analysed to determine whether they contain information which is relevant to user-specified characteristics. On detecting such a condition, an alert signal is supplied to the respective user (115). The incoming data files are analysed with respect to common data characteristics (252) to generate common category associations (253). The data files are then processed with respect to user-specific data characteristics (256). The user-specific data characteristics include examples of the common data characteristics (260) and the specific processing procedures make use of the previously defined common category associations.

公开(公告)号：EP0996927A1

公开(公告)日：2000-05-03

申请号：EP98934144.1

申请日：1998-06-16

申请人： The Dialog Corporation

发明人： ZHILYAEV, Maxim

IPC分类号： G06K9/62 ,  G06K9/68 ,  G06K9/70 ,  G06K9/74

CPC分类号： G06F17/30707 ,  G06K9/62

摘要： Documents are classified (20) into one or more clusters (C) corresponding to predefined classification categories by building a knowledge base (22) comprising matrices of vectors which indicate the significance of terms within a corpus (T) of text formed by the documents and classified (20) in the knowledge base (22) to each cluster (C). The significance of terms is determined assuming a standard normal probability distribution, and terms are determined to be significant to a cluster if their probability of occurence being due to chance is low. For each cluster, statistical signatures comprising sums of weighted products and intersections of cluster terms to corpus (T) terms are generated and used as discriminators for classifying documents. The knowledge base (22) is built using prefix and suffix lexical rules (38) which are context-sensitive and applied selectively to improve the accuracy and precision of classification.