Systems and methods for targeted advertising

Abstract

Methods of generating recommendations may include obtaining social network data from one or more network resources. Word relationships may be created between selected words in the social network data to produce relationship data. Advertisement or other asset recommendations may be generated for a target user by analyzing browse information of the target user to identify one or more words. Other words in the relationship data may be identified that are related to the words in the target user's browse information. One or more advertisements may be identified having at least one keyword that corresponds to the other words. At least a portion of these advertisements may be selected from a data repository to provide to the target user.

1 . A system for generating targeted advertisement recommendations, the system comprising:
 a data aggregation module configured to obtain word data from social-network data of one or more network resources, the word data comprising a plurality of words in the social-network data;   a relationship mining module in communication with the data aggregation module, the relationship mining module configured to create word relationships between selected ones of the plurality of words in the word data to produce relationship data, each of the word relationships reflecting a degree of association between two or more of the selected words, wherein the degree of association is based at least in part on at least one of:
 a frequency of the selected words in the social network data, 
 a recency of a subset of the social-network data that comprises the two or more selected words, and 
 an authority factor of the subset of the social-network data; and 
   a recommender module in communication with the relationship module, the recommender module configured to:
 access browse information of a target user to identify one or more first words in the target user's browse information, 
 identify the one or more first words in the relationship data, 
 identify one or more second words in the relationship data that have one or more of said word relationships with the one or more first words, and 
 identify one or more advertisements having at least one keyword that corresponds to the one or more second words. 
   
     
     
         2 . The system of  claim 1 , wherein the relationship mining module is further configured to reassess the degree of association of the word relationships over time. 
     
     
         3 . The system of  claim 1 , wherein the browse information of the target user comprises a network resource currently accessed by the target user. 
     
     
         4 . The system of  claim 1 , wherein the browse information of the target user comprises a plurality of network resources accessed by the target user. 
     
     
         5 . The system of  claim 1 , wherein the recommender module is further configured to weight the one or more first words based at least in part on a frequency of which the one or more first words occur in the browse information of the target user. 
     
     
         6 . The system of  claim 1 , wherein a relationship mining module is further configured to create word relationships by creating one or more graphs of word relationships. 
     
     
         7 . The system of  claim 1 , further comprising a data repository for storing the word data. 
     
     
         8 . The system of  claim 1 , wherein the data aggregation module is further configured to obtain the word data from reference data of one or more network resources. 
     
     
         9 . The system of  claim 1 , wherein the data aggregation module is configured to obtain word data by using one or more natural language processing techniques to extract signal words from the social-network data. 
     
     
         10 . A computer-implemented method of generating targeted advertisement recommendations, the method comprising:
 obtaining word data from one or more network resources, the word data comprising words in content of the one or more network resources;   creating word relationships between selected words in the word data to produce relationship data, each word relationship indicating a degree of association between two or more of the selected words;   analyzing browse information of a target user to identify one or more first words in the target user's browse information;   identifying, based on the word relationships, second words in the relationship data that are related to the first words in the target user's browse information;   identifying one or more advertisements having at least one keyword that corresponds to the second words; and   selecting at least a portion of the one or more advertisements from a data repository to provide to the target user.   
     
     
         11 . The method of  claim 10 , further comprising inferring category relationships from the word relationships and inferring asset relationships from the category relationships. 
     
     
         12 . The method of  claim 11 , further comprising creating additional asset relationships by relating assets based at least in part on browse behavior relationships of a plurality of users. 
     
     
         13 . The method of  claim 12 , further comprising inferring additional word relationships from the additional asset relationships. 
     
     
         14 . The method of  claim 10 , wherein creating word relationships between two or more of selected words further comprises detecting the proximity of the selected words in a network resource. 
     
     
         15 . The method of  claim 10 , wherein creating word relationships between two or more of selected words further comprises analyzing behavioral relationships between different users of one or more network resources. 
     
     
         16 . The method of  claim 10 , wherein obtaining word data further comprises detecting signal words using one or more natural language processing techniques. 
     
     
         17 . The method of  claim 16 , wherein detecting signal words comprises generating graphs of words in the word data, the graphs comprising overlapping categories or related words of the words in the word data. 
     
     
         18 . A computer-implemented method of determining meanings of ambiguous words, the method comprising:
 obtaining word data from one or more network resources, the word data comprising words in content of the one or more network resources;   for a subset of the word data, determining parts of speech of selected words in the subset of the word data;   determining definitions of the selected words to determine forms of the selected words;   determining one or more categories or related words for each of the word forms;   for two selected word forms, connecting the two selected word forms in one or more graphs in response to determining that categories or related words of the two selected word forms overlap, wherein connecting the two selected word forms in the one or more graphs comprises creating weighted word relationships between the two selected word forms; and   determining that a selected graph having a highest total weight of word relationships compared to one or more other graphs indicates definitions of one or more of the selected words in the subset of the word data.   
     
     
         19 . The method of  claim 18 , further comprising:
 creating word relationships between selected words in the word data to produce relationship data, the relationships indicating a degree of association between the selected words; and   recommending one or more assets to a target user based at least in part on the relationship data.   
     
     
         20 . A system for dynamically generating targeted asset recommendations, the system comprising:
 means for obtaining word data from one or more network resources, the word data comprising words in content of the one or more network resources;   means for creating word relationships between selected words in the word data to produce relationship data, each word relationship indicating a degree of association between two or more of the selected words;   means for analyzing browse information of a target user to identify one or more first words in the target user's browse information;   means for identifying second words in the relationship data that are related to the first words in the target user's browse information;   means for identifying one or more assets that are related to the second words; and   means for selecting at least a portion of the one or more advertisements from a data repository to provide at least one recommendation for the target user.