Identifying members of a small & medium business segment

Abstract

A system, apparatus, computer-program product and method are provided for identifying members of a particular user segment. One particular user segment of interest includes members who work for employers having a number of employees within a predetermined range. Members of an online service provide data purporting to identify their employers and/or other personal or professional attributes. The data entries are normalized by standardizing terms, removing superfluous or unneeded terms, and/or performing other processing. The members are then clustered according to their normalized employer names, and members within clusters that have sizes within the range are added to the user segment. Invalid employer names (e.g., fictitious companies, non-existent entities) may be filtered out. Within a cluster, a professional social networking site (or other site) may be analyzed to determine if the clustered members have developed relationships; if not, the cluster may be cancelled.

What is claimed is: 
     
         1 . A computer system-implemented method for identifying users associated with employers having a number of employees within a predetermined range, the method comprising:
 receiving, from multiple users, employer information intended to identify the users' employers;   normalizing the employer information, using a computer processor, to yield normalized employer names, wherein said normalizing is context-sensitive so as not to remove a distinguishing feature of the normalized employer names;   using the computer processor to cluster the multiple users to produce a set of clusters based on the normalized employer names, wherein each cluster is associated with a different normalized employer name; and   for each cluster containing a number of users within the predetermined range, categorizing users within the cluster as members of a segment of users associated with employers having a number of employees within the predetermined range.   
     
     
         2 . The method of  claim 1 , further comprising:
 analyzing relationships between users in a single cluster to determine if they are likely to be employed by the same employer.   
     
     
         3 . The method of  claim 2 , wherein analyzing the relationships comprises determining whether the users have formed relationships in a social network. 
     
     
         4 . The method of  claim 2 , wherein analyzing the relationships comprises determining whether the users have exchanged content. 
     
     
         5 . The method of  claim 1 , further comprising:
 for each of one or more clusters, determining whether the cluster's associated normalized employer name is invalid.   
     
     
         6 . The method of  claim 5 , wherein determining whether the cluster's associated normalized employer name is invalid comprises comparing the associated normalized employer name to a list of known invalid names. 
     
     
         7 . The method of  claim 5 , wherein determining whether the cluster's associated normalized employer name is invalid comprises analyzing a social networking site to determine if users within the cluster have formed social relationships. 
     
     
         8 . The method of  claim 1 , wherein normalizing the employer information comprises standardizing one or more terms of an employer name. 
     
     
         9 . The method of  claim 8 , wherein said normalizing the employer information further comprises removing one or more superfluous terms. 
     
     
         10 . The method of  claim 1 , wherein the predetermined range is between 1 and approximately 200. 
     
     
         11 . The method of  claim 1 , further comprising:
 analyzing, using the computer processor, social network relationships between users in a single cluster associated with a single employer name, to determine whether they are likely to be employed by the same employer; and   determining whether at least a predetermined threshold number of users in the same cluster have formed at least one social relationship, in a social network, with another user in that cluster.   
     
     
         12 . An apparatus for identifying users associated with employers having a number of employees within a predetermined range, the apparatus comprising:
 one or more processors; and   memory configured to store instructions that, when executed by the one or more processors, cause the apparatus to:
 receive from multiple users employer information intended to identify the users' employers; 
 normalize the employer information to yield normalized employer names, wherein said normalizing is context-sensitive so as not to remove a distinguishing feature of the normalized employer names; 
 cluster the multiple users to produce a set of clusters based on the normalized employer names, wherein each cluster is associated with a different normalized employer name; and 
 for each cluster containing a number of users within the predetermined range, categorize users within the cluster as members of a segment of users associated with employers having a number of employees within the predetermined range. 
   
     
     
         13 . The apparatus of  claim 12 , wherein the memory is further configured to store instructions that, when executed by the one or more processors, cause the apparatus to:
 analyze relationships between users in a single cluster to determine if they are likely to be employed by the same employer.   
     
     
         14 . The apparatus of  claim 13 , wherein analyzing the relationships comprises determining whether the users have formed relationships in a social network. 
     
     
         15 . The apparatus of  claim 12 , wherein the memory is further configured to store instructions that, when executed by the one or more processors, cause the apparatus to:
 for each of one or more clusters, determine whether the cluster's associated normalized employer name is invalid.   
     
     
         16 . The apparatus of  claim 15 , wherein determining whether a cluster's associated normalized employer name is invalid comprises comparing the associated normalized employer name to a list of known invalid names. 
     
     
         17 . The apparatus of  claim 15 , wherein determining whether a cluster's associated normalized employer name is invalid comprises analyzing a social networking site to determine if users within the cluster have formed social relationships. 
     
     
         18 . The apparatus of  claim 12 , wherein normalizing the employer information comprises:
 standardizing one or more terms of an employer name; and   removing one or more superfluous terms.   
     
     
         19 . The apparatus of  claim 12 , wherein the predetermined range is between 1 and approximately 200. 
     
     
         20 . The apparatus of  claim 12 , wherein the memory is further configured to store instructions that, when executed by the one or more processors, cause the apparatus to:
 analyze, using the computer processor, social network relationships between users in a single cluster associated with a single employer name, to determine whether they are likely to be employed by the same employer; and   determine whether at least a predetermined threshold number of users in the same cluster have formed at least one social relationship, in a social network, with another user in that cluster.