Systems for creating and/or maintaining databases and a system for facilitating online advertising with improved privacy

Abstract

A system for creating and/or maintaining a database is disclosed. In one example, the system includes one or more processors; a classification module configured to determine primary weights for primary data streams, each primary weight referring to a correlation between one of the primary data streams and one segment category of several predefined segment categories; a recognition module configured to identify explicit concepts and implicit concepts in the primary data streams, and to determine first secondary weights characterizing embeddings of the identified concepts; an expansion module configured to determine for the identified concepts respective related concepts; and a storage module configured to save the identified concepts.

1 . A system for creating and/or maintaining a first database, the system comprising:
 one or more processors;   a classification module that is, when executed by at least one of the one or more processors, configured to determine primary weights for primary data streams, each primary weight referring to a correlation between one of the primary data streams and one segment category of several predefined segment categories;   a recognition module that is, when executed by at least one of the one or more processors, configured to identify explicit concepts and implicit concepts in the primary data streams, and to determine first secondary weights characterizing embeddings of the identified concepts in the respective main segment category with highest primary weight using a concept database storing weights for concepts within the predefined segment categories;   an expansion module that is, when executed by at least one of the one or more processors, configured to determine for the identified concepts respective related concepts and second secondary weights of the related concepts characterizing embeddings of the related concepts in at least one of the predefined segment categories; and   a storage module that is, when executed by at least one of the one or more processors, configured to save the identified concepts, the first secondary weights, the related concepts, and the second secondary weights in the first database.   
     
     
         2 . The system of  claim 1 , further comprising
 an analysis module that is, when executed by at least one of the one or more processors, configured to identify in the primary data streams a rating comprising at least one of a sentiment, and an emotion,   
       wherein the storage module is configured to save the identified rating in the first database. 
     
     
         3 . The system of  claim 1 , wherein the recognition module comprises at least one of:
 a linguistic analysis module that is, when executed by at least one of the one or more processors, configured to determine for the primary data streams a respective normalized set of keywords; and   a concept enrichment module that is, when executed by at least one of the one or more processors, configured to identify the explicit concepts, the implicit concepts, and the first and second secondary weights using the concept database.   
     
     
         4 . The system of  claim 1 , wherein the system is configured to host the first database and/or wherein the storage module is configured to save the identified concepts, the first secondary weights, the related concepts, the second secondary weights, and/or the identified rating in a semantic knowledge graph structure of the first database. 
     
     
         5 . The system of  claim 1 , wherein the classification module comprises a trained CNN. 
     
     
         6 . A system for maintaining a second database, the system comprising:
 one or more processors;   a classification module that is, when executed by at least one of the one or more processors, configured to determine primary weights for primary data streams, each primary weight referring to a correlation between one of the primary data streams and one segment category of several predefined segment categories;   a learning module that is, when executed by at least one of the one or more processors, configured to determine for known concepts comprising a respective term found in the primary data streams embedding terms for the respective term and weights characterizing the embeddings of the embedding terms in the respective segment categories; and   a storage module configured to update the known concepts stored in the second database in accordance with the embedding terms and the weights.   
     
     
         7 . The system of  claim 6 , wherein the learning module comprises a deep learning module which is based on a neural network. 
     
     
         8 . The system of  claim 6 , wherein the concept learning module implements a word embedding algorithm for determining the weights characterizing the embeddings of the embedding terms. 
     
     
         9 . The system of  claim 6 , wherein the concept learning module comprises at least one of:
 an embedding module that is, when executed by at least one of the one or more processors, configured to determine the weights characterizing the embeddings of the embedding terms; and   a linguistic analysis module that is, when executed by at least one of the one or more processors, configured to normalize the names of concepts and/or terms to a respective base form.   
     
     
         10 . A system for facilitating online advertising with improved privacy in a network, the system comprising:
 one or more processors;   a matching module that is, when executed by at least one of the one or more processors, configured to use weighted semantic target metadata for a target content provided in the network and weighted semantic campaign metadata for an advertising campaign to be presented in the network and referring to a respective product and/or a service to determine a matching parameter between the target content and the advertising campaign; and   a management module that is, when executed by at least one of the one or more processors, configured to use the matching parameter to decide if the advertising campaign is to be provided to the target content.   
     
     
         11 . The system of  claim 10 , wherein the weighted semantic target metadata for the target content comprise weights for the concepts of the target content, and wherein the weighted semantic campaign metadata comprise weights for the concepts of the advertising campaign, and, wherein the matching module is, when executed by the at least one of the one or more processors, configured to determine the matching parameter as a function of the weights for the concepts of the target content and the weights for the concepts of the advertising campaign. 
     
     
         12 . The system of  claim 11 , wherein the function depends on the products of the weights of common concepts of the target content and the advertising campaign. 
     
     
         13 . The system of  claim 10 , wherein the system comprises a campaign database storing semantic metadata for advertising campaigns, and wherein the matching module has, when executed by the at least one of the one or more processors, access to the campaign database. 
     
     
         14 . The system of  claim 10 , wherein the matching module has, when executed by the at least one of the one or more processors, access to a campaign analyzing system which is configured to determine semantic metadata for advertising campaigns and/or to store the semantic metadata in a campaign database. 
     
     
         15 . The system of  claim 14 , wherein the campaign analyzing system comprises:
 one or more processors;   a semantic analysis module that is, when executed by the at least one of the one or more processors, configured to determine primary weighted semantic metadata for the advertising campaigns using a database storing weights for concepts within predefined segment categories; and   a semantic expansion module, that is, when executed by the at least one of the one or more processors, configured to determine secondary weighted semantic metadata for the advertising campaigns using a database storing first concepts, first weights for the first concepts in predefined segment categories, second concepts that are related to the first concepts, and second weights for the second concepts in predefined segment categories, and optionally identified ratings of the advertising campaigns.   
     
     
         16 . The system of  claim 15 , wherein at least one of the semantic analysis module and the semantic expansion module, is, when executed by the at least one of the one or more processors, configured to use additional content retrieved from the network for determining the respective weighted semantic metadata. 
     
     
         17 . The system of  claim 10 , wherein the system comprises at least one of a target database storing semantic metadata for target content, the matching module having, when executed by the at least one of the one or more processors, access to the target database, and a target analyzing system. 
     
     
         18 . The system of  claim 17 , wherein the target analyzing system comprises at least one of:
 one or more processors;   a semantic analysis module that is, when executed by the at least one of the one or more processors, configured to determine primary weighted semantic metadata for target content using a concept database storing weights for concepts within predefined segment categories;   a semantic expansion module, that is, when executed by the at least one of the one or more processors, configured to determine secondary weighted semantic metadata for the target content using a database storing first concepts, first weights for the first concepts in predefined segment categories, and optionally identified ratings of the target content; and   a storage module configured to store the respective weighted semantic metadata and optionally the identified ratings of the target content in a target database.   
     
     
         19 . The system of  claim 10 , wherein the system comprises at least one server which is connectable to the network and, in a connected state, configured to initiate sending via the network an advertising campaign to a client comprising a display displaying the target content, the advertising campaign comprising a matching parameter above a predefined threshold. 
     
     
         20 . The system of  claim 19 , wherein the system is configured to initiate sending the advertising campaign at least substantially based on the matching parameter, at least substantially based on the matching parameter, and identified ratings of the target content and/or the advertising campaign, and/or wherein the system is configured to initiate sending the advertising campaign without taking into account tracking data of registered users of the client.