Information network with linked information nodes

Abstract

A machine-implemented method of relating information nodes in an information network, comprising the steps of: processing a plurality of data objects according to a predefined dictionary containing a plurality of information units and a plurality of correlation-indicating elements to defect in the plurality of data objects the presence of a correlation between respective information units; establishing an information network with a plurality of information nodes and links between the information nodes, said information nodes being related to said information units and said links being related to said detected correlations; and analyzing a link connectivity state of said information network to find a path across information nodes that represent an inference or a set of inferences being input by a query searched by a user.

1 . A method of relating multiple concepts in an information network, comprising:
 receiving, by a processor, a plurality of data objects from a storage device, wherein the plurality of data objects comprise one or more documents;   determining, by the processor for each of the plurality of data objects, one or more concepts associated with the data object, wherein a predefined dictionary contains the one or more concepts;   identifying, by the processor, one or more links between the one or more concepts, wherein the one or more links correspond to one or more correlation-indicating elements, wherein the correlation-indicating elements include one or more verbs having respective weights;   establishing, by the processor, the information network with the one or more concepts and the one or more links between the concepts;   generating, by the processor, a plurality of traversed paths comprising a plurality of one or more links between two concepts;   determining, by the processor, a plurality of link connectivity states as a plurality of functions of the plurality of traversed paths;   identifying, by the processor, one or more inferences by analyzing the link connectivity states of the information network to find a plurality of paths across a plurality of the concepts; and   in response to a user query, presenting at least a portion of the information network to a user.   
     
     
         2 . The method of  claim 1 , further comprising: collecting, by the processor, the plurality of data objects from distributed input sources; and
 storing the plurality of data objects in the data store.   
     
     
         3 . The method of  claim 1 , wherein the identifying one or more inferences is based on a semantic analysis of the plurality of data objects. 
     
     
         4 . The method of  claim 1 , wherein the weights of the correlation-indicating elements include identifying a co-occurrence of data objects. 
     
     
         5 . The method of  claim 1 , further comprising determining, by the processor, a weight of a traversed path across two or more links of the plurality of concepts of the information network, by statistical and mathematical analysis of correlation-indicating elements in the plurality of data objects of the traversed path. 
     
     
         6 . The method of  claim 1 , further comprising: ranking, by the processor, the traversed paths in the information network based on link weights and a stochastic analysis. 
     
     
         7 . The method of  claim 1 , wherein the concepts are objects retrieved from a query inputted by the user. 
     
     
         8 . The method of  claim 1 , wherein the predefined dictionary is user defined. 
     
     
         9 . The method of  claim 1 , wherein analyzing the link connectivity state of the information network is based on exploring indirect paths identified from one or more of the plurality of data objects or topology information. 
     
     
         10 . The method of  claim 1 , wherein the concepts define an object term related to: an industrial, a financial, a business, a social, a political, an economic, a scientific, a research, an analysis, a medical, a biochemical, a biomolecular, a chemical, a technical, or a pharmaceutical term. 
     
     
         11 . The method of  claim 10 , wherein the object term defines an object, a node, or a concept that is related to one or more areas of the following applications: constituent objects, a drug, an active ingredient, an active agent, a medical compound, a chemical compound, a pharmaceutical compound, a therapy, a cure, a cause, an effect, a disease, a symptom, a disease symptom, a diet, a nutrition, a lifestyle feature, a habit, a pathogenesis, a disease cause, a disease pathogenesis, an item associated with a disease, an item associated with a pathogenesis of a disease, an economic measure, a statistical similarity, a call detail record (CDR), the status of a subscriber or a line, interactions between or across multiple lines, statistical correlations or any concepts identifying statistical behavior, a sentiment, or its dynamics for a social application. 
     
     
         12 . A system comprising:
 a storage device for storing executable code and for storing a plurality of data objects;   a communication device configured to exchange the data objects via a network; and   a processor configured to receive the data objects over the network, and further configured to execute the code stored in the storage device;   the processor being further configured to:   receive the plurality of data objects over the network from the communication device;   compare a first predefined dictionary to the data objects to identify a plurality of information units;   compare a second predefined dictionary to the data objects to identify a plurality of correlation-indicating elements associated with the information units;   establish an information network with a plurality of information nodes and a plurality of links between the information nodes, the information nodes being related to the information units and the links being related to the plurality of correlation-indicating elements; and   utilize, in response to a query from a user, a probabilistic crawler to analyze a link connectivity state of the information network to find a path across the information nodes.   
     
     
         13 . The system of  claim 12 , wherein the processor is configured to collect the plurality of data objects from distributed input sources. 
     
     
         14 . The system of  claim 12 , wherein the processor is configured to process the plurality of data objects based on a semantic analysis. 
     
     
         15 . The system of  claim 12 , wherein the processor is configured to determine a strength of one of the links across at least two of the plurality of information nodes of the information network by statistical and mathematical analysis of relations specified in the plurality of data objects. 
     
     
         16 . The system of  claim 12 , wherein the processor is configured to rank paths in the information network according to measures of relevance based on link weights and a stochastic analysis. 
     
     
         17 . The system of  claim 12 , wherein the information nodes are objects retrieved by a query searched by the user. 
     
     
         18 . The system of  claim 12 , wherein the path across the information nodes involves at least two of the plurality of data objects. 
     
     
         19 . One or more computer-readable media storing non-transitory instructions executable by one or more processors, wherein the instructions program the one or more processors to:
 receive a plurality of data objects containing concepts and a plurality of correlation-indicating elements;   identify, for each of the plurality of data objects, a plurality of concepts contained in the data object, wherein a first dictionary identifies the plurality of concepts;   identify, for each of the plurality of data objects, a plurality of correlation-indicating elements contained in the data object, wherein a second dictionary identifies the plurality of correlation-indicating elements;   generate correlations between the plurality of identified concepts based, at least in part, on the identified correlation-indicating elements;   generate a knowledge map that correlates the plurality of identified concepts together; and   display the knowledge map to a user in response to a query from the user.   
     
     
         20 . The computer-readable media according to  claim 19  further comprising instructions to generate weighted correlations between the plurality of identified concepts based, at least in part, on heuristics, including whether the concepts appear in the same document, whether the concepts appear in the same sentence, and whether the concepts are syntactically closer inside the same sentence.