Information Processor Arrangement

Abstract

Irregular links and relationships in a data set may relate to fraudulent actions or identify deception or risk assessment or knowledge generation but may be identified by simple superficially unlinked actions. Thus, for example a claimant may claim through an address using one telephone number but contact the insurer for that claim using a different telephone number. By 10 pooling all the information received, including all. telephone numbers, unusual or irregular or fraudulent leads can be identified by establishing telephone numbers or other gateway cluster nodes for each dataset such that supposedly unrelated claims can be matched and therefore be more closely scrutinised. The information processor arrangement may create a cascade of clusters for an as presented data set which can be configured through cluster nodes to allow better identification of suspect activity or for better analysis profiling.

1 - 46 . (canceled) 
     
     
         47 . A method of structuring a dataset the method comprising the steps of:
 (a) collecting a dataset in the form of information entities interlinked by reference links to each other; and the context in which each information entity is taken relative to the reference link or reference links,   (b) defining unexpected links to be identified by the method by reference to at least one information entity and a relevance model that defines expected reference links as direct links and indirect links between the information entities whereby unexpected links are all other reference links between the information entities,   (c) defining a plurality of gateway cluster nodes for the dataset, each cluster node being one of the information entities whereby each information entity is considered to determine its reference links with other Information entities, until each information entity is resolved through a link path to the gateway cluster node as a member of a cluster referenced by the gateway cluster node, each member comprising the link path in other form of a string or network of reference links to the gateway cluster node, and   (d) selection of a cluster by reference to the relevance model as including an unexpected link and determining whether the number population in the selected cluster respectively meet preset specific search criteria or repeating step (c) specifically upon the cluster with cluster nodes defined by information entities other than the gateway cluster node used to define the selected cluster until the preset specific search criteria are achieved.   
     
     
         48 . A method as claimed in  claim 47  wherein a minimum and/or maximum number of gateway cluster nodes are defined in order to provide adequate structuring of the dataset to determine presence of the unexpected links between information entities. 
     
     
         49 . A method as claimed in  claim 47  wherein a minimum and/or maximum number of links between information entities is prescribed for resolution as a member of a cluster referenced by the gateway cluster node. 
     
     
         50 . A method as claimed in  claim 49  wherein links will be defined relative to a hierarchy relative to the gateway node. 
     
     
         51 . A method as claimed in  claim 50  wherein hierarchy may allow links between information entities to be lateral that is to say if information entities of the same type e.g. name or telephone number or upward or downward that is to say telephone number may be downward and then an upward link would be back to the same information entity type as that of the gateway cluster node that is to say name. 
     
     
         52 . A method as claimed in  claim 47  wherein some gateway cluster nodes may be given a ranking or priority to other gateway cluster nodes. 
     
     
         53 . A method as claimed in  claim 47  wherein information entities and attributes will comprise many different types and classes of information depending upon the field of operation but examples would be address and/or name of individuals and/or telephone numbers and/or documentation reference numbers or types or any information linked to or providing reference to an activity or service or goods such as for example a motor vehicle registration number. 
     
     
         54 . A method as claimed in  claim 47  wherein the dataset may be continuously updated and steps (c) and (d) performed in order to provide clusters. 
     
     
         55 . A method as claimed in  claim 47  wherein steps (c) and (d) are performed upon the whole updated database. 
     
     
         56 . A method as claimed in  claim 47  wherein steps (c) and (d) are performed upon predetermined selected clusters updated as part of the dataset. 
     
     
         57 . A method as claimed in  claim 47  wherein at least one sub-cluster is provided in order to achieve the predetermined specific search criteria. 
     
     
         58 . A method as claimed in  claim 47  wherein the predetermined specific search criteria is member population number value in a cluster or sub-cluster or sub-sub-cluster as appropriate. 
     
     
         59 . A method as claimed in  claim 47  wherein clusters are analysed to alter the means for collection of a dataset in terms of the information entities required. 
     
     
         60 . A method as claimed in  claim 47  wherein the dataset comprises mandatory information entities and voluntary information entities. 
     
     
         61 . A method as claimed in  claim 47  wherein the dataset may incorporate information entities achieved by interrogation of available sources rather than passive presentation of such information entities by individuals. 
     
     
         62 . A method as claimed in  claim 47  the clusters are analysed to identify expected links for elimination or illumination of members in the cluster and therefore reduce remainder cluster member populations for determination of the preset specific search criteria. 
     
     
         63 . A method as claimed in  claim 47  wherein clusters are grouped for mutual confirmation of unexpected links by similarity of gateway cluster node and subsequent cluster node linkage similarity or reciprocity of linkage route. 
     
     
         64 . A method as claimed in  claim 47  wherein the gateway cluster links are specifically determined for identification of the unexpected links prior to performance of the method. 
     
     
         65 . A method as claimed in  claim 64  wherein the gateway cluster links can be rearranged and changed over time as new knowledge is discovered. 
     
     
         66 . A method as claimed in  claim 47  wherein gateway cluster links may be altered by the results of clusters relative to the preset specific search criteria in an alternative feedback adaptation process. 
     
     
         67 . An information arrangement structured to comprise
 (a) a relational database defining types of information entities and having reference links between each other,   (b) means to define reference links as a relevance model comprising expected reference links between the information entities whereby unexpected links are all other reference links between information entities, each unexpected link thereby identifiable, and   (c) means to define a plurality of gateway cluster nodes comprising one of the information entities and means to determine link paths from each information entity to each gateway cluster node and a network of link paths defining members of a respective cluster referenced by the gateway cluster node, means to select clusters by reference to the relevance model as including an unexpected link and means to determine whether each selected cluster meets pre-set specific search criteria and means, if the selective cluster does not meet the pre-set search criteria, to analyse that selected cluster by definition of further gateway cluster nodes comprising an information entity other than the information entity to define the selected cluster and use of the means to determine link paths to the further gateway cluster nodes to provide sub clusters for comparison with the relevant model to define unexpected links until a sub cluster meets the pre-set search criteria.   
     
     
         68 . An arrangement as claimed in  claim 67  wherein a minimum and/or maximum number of gateway cluster nodes are defined in order to provide adequate analysis of the dataset to determine presence of the unexpected links between information entities. 
     
     
         69 . An arrangement as claimed in  claim 67  wherein a minimum and/or maximum number of links between information entities is prescribed for resolution as a member of a cluster referenced by the gateway cluster node. 
     
     
         70 . An arrangement as claimed in  claim 67  wherein links will be defined relative to a hierarchy relative to the gateway node. 
     
     
         71 . An arrangement as claimed in  claim 70  wherein hierarchy may allow links between information entities to be lateral that is to say of information entities of the same type e.g. name or telephone number or upward or downward that is to say telephone number may be downward and then an upward link would be back to the same information entity type as that of the gateway cluster node that is to say name. 
     
     
         72 . An arrangement as claimed in  claim 67  wherein some gateway cluster nodes may be given a ranking or priority relative to other gateway cluster nodes. 
     
     
         73 . An arrangement as claimed in  claim 67  wherein information entities and attributes will comprise many different types and classes of information depending upon the field of operation but examples would be address and/or name of individuals and/or telephone numbers and/or documentation reference numbers or types or any information linked to or providing reference to an activity or service or goods such as for example a motor vehicle registration number. 
     
     
         74 . An arrangement as claimed in  claim 67  wherein the dataset may be continuously updated and steps (c) and (d) preformed in order to provide clusters. 
     
     
         75 . An arrangement as claimed in  claim 67  wherein steps (c) and (d) are performed upon the whole updated database. 
     
     
         76 . An arrangement as claimed in  claim 67  wherein steps (c) and (d) are performed upon predetermined selected clusters updated as part of the dataset. 
     
     
         77 . An arrangement as claimed in  claim 67  wherein at least one sub-cluster is provided in order to achieve the predetermined specific search criteria. 
     
     
         78 . An arrangement as claimed in  claim 67  wherein the predetermined specific search criteria is member population number value in a cluster or sub-cluster or sub-sub-cluster as appropriate. 
     
     
         79 . An arrangement as claimed in  claim 67  wherein clusters are analysed to alter the means for collection of a dataset in terms of the information entities required. 
     
     
         80 . An arrangement as claimed in  claim 79  wherein the dataset comprises mandatory information entities and voluntary information entities. 
     
     
         81 . An arrangement as claimed in  claim 79  wherein the dataset may increase information entities achieved by integration viable sources rather than passive presentation of such information entities by individuals. 
     
     
         82 . An arrangement as claimed in  claim 67  wherein the clusters are analysed to identify expected links for elimination or illumination of members in the cluster and therefore reduce remainder cluster member populations for determination of the preset specific search criteria. 
     
     
         83 . An arrangement as claimed in  claim 67  wherein clusters are grouped for mutual confirmation of unexpected links by similarity of gateway cluster node and subsequent cluster node linkage similarity or reciprocity of linkage route. 
     
     
         84 . An arrangement as claimed in  claim 67  wherein the gateway cluster links are specifically determined for identification of the unexpected links prior to performance of the method. 
     
     
         85 . An arrangement as claimed in  claim 67  wherein the gateway cluster links can be rearranged and changed over time as new knowledge is discovered. 
     
     
         86 . An arrangement as claimed in  claim 67  wherein gateway cluster links may be altered by the results of clusters relative to the preset specific search criteria in an iterative feedback adaptation process. 
     
     
         87 . A processor arranged to perform the method as claimed in  claim 47 . 
     
     
         88 . A memory storage device incorporating instructions to perform the method as claimed in  claim 47  when uploaded into a processor device for performance of the method. 
     
     
         89 . A memory storage device storing cluster or sub-clusters or sub-sub-clusters provided by a method as claimed in  claim 47 .