Original idea extraction from written text data

Abstract

Original idea extraction from written data is provided by capturing expression as written text data, obtaining a knowledge graph representing concepts and relationships between the concepts, automatically topic modeling the written text data to ascertain thought units and identify respective concepts of the thought unit, mapping a thought unit to the knowledge graph, determining that the thought unit is an original idea, and based on determining that the thought unit is an original idea, storing a representation of the original idea to an idea repository and invoking processing of at least one computer.

What is claimed is: 
     
         1 . A computer-implemented method comprising:
 electronically capturing expression of one or more individuals as written text data using one or more electronic devices;   obtaining a knowledge graph data structure for a knowledge dataset, the knowledge graph comprising representations of concepts and relationships between the concepts as identified from the knowledge dataset;   automatically topic modeling the written text data to ascertain a plurality of thought units expressed in the written text data, and identifying, for each thought unit, a respective set of concepts of the thought unit;   mapping a thought unit of the plurality of thought units to the knowledge graph by correlating the concepts of the thought unit to a correlated set of concepts represented in the knowledge graph;   determining that the thought unit is an original idea, the determining being based on a graph distance in the knowledge graph between at least some of the correlated concepts represented in the knowledge graph, and being based further on a cardinality of the set of concepts of the thought unit exceeding a threshold; and   based on determining that the thought unit is an original idea, storing a representation of the original idea to an idea repository and invoking processing of at least one computer.   
     
     
         2 . The method of  claim 1 , wherein the capturing expression as written text data comprises transforming a voice stream of a user to a textual representation of the voice stream. 
     
     
         3 . The method of  claim 1 , wherein the capturing expression as written text data comprises transforming at least one selected from the group consisting of: (i) drawings and (ii) user gestures, to a textual representation. 
     
     
         4 . The method of  claim 1 , wherein the concepts of the thought unit include concepts explicitly expressed in the written text data as the thought unit and one or more concepts identified from a context in which the thought unit was expressed. 
     
     
         5 . The method of  claim 1 , wherein the thought unit is characterized by an identification of an individual expressing the thought unit, the identified concepts of the thought unit, at least one sentiment score of the thought unit, and an indication of any other individuals receiving a communication in which the thought unit was expressed by the individual. 
     
     
         6 . The method of  claim 1 , further comprising assigning relevance scores to the concepts of the thought unit, wherein the determining that the thought unit is an original idea is further based on the relevance scores assigned to the concepts. 
     
     
         7 . The method of  claim 1 , wherein the obtaining the knowledge graph further comprises assigning weights to the concepts represented in the knowledge graph, and wherein the determining that the thought unit is an original idea is further based on the weights assigned to the correlated concepts represented in the knowledge graph. 
     
     
         8 . The method of  claim 7 , wherein the weight assigned to a concept represented in the knowledge graph is based on at least one selected from the group consisting of: (i) area of innovation to which the concept pertains and (ii) a frequency or trend in coverage of the concept in news media. 
     
     
         9 . The method of  claim 1 , wherein the invoking processing of at least one computer invokes provision of a graphical user interface that indicates the representation of the original idea to an individual, of the one or more individuals, who expressed the thought unit, to notify the individual that the thought unit is an original idea. 
     
     
         10 . The method of  claim 1 , further comprising:
 comparing the thought unit to other thought units determined to be original ideas and having representations thereof stored in the idea repository; and   identifying another thought unit, of the other thought units, for which the thought unit and the another thought unit share a common pair of concepts represented in the knowledge graph, wherein the one or more individuals comprise a first individual who expressed the thought unit and a second individual who expressed the another thought unit.   
     
     
         11 . The method of  claim 10 , wherein based on determining that the expression of the thought unit by the first individual and expression of the another thought unit by the second individual were not made in a common conversation between the first individual and second individual, the invoking processing of the at least one computer comprises providing a first electronic communication to a first computer of the first individual and providing a second electronic communication to a second computer of the second individual, the first and second electronic communications to network together the first and second individuals. 
     
     
         12 . The method of  claim 11 , further comprising:
 ascertaining a first sentiment score of the thought unit and a second sentiment score of the another thought unit; and   determining whether to network together the first and second individuals based on the first and second sentiment scores.   
     
     
         13 . A computer system comprising:
 a memory; and   a processor in communication with the memory, wherein the computer system is configured to perform a method comprising:
 electronically capturing expression of one or more individuals as written text data using one or more electronic devices; 
 obtaining a knowledge graph data structure for a knowledge dataset, the knowledge graph comprising representations of concepts and relationships between the concepts as identified from the knowledge dataset; 
 automatically topic modeling the written text data to ascertain a plurality of thought units expressed in the written text data, and identifying, for each thought unit, a respective set of concepts of the thought unit; 
 mapping a thought unit of the plurality of thought units to the knowledge graph by correlating the concepts of the thought unit to a correlated set of concepts represented in the knowledge graph; 
 determining that the thought unit is an original idea, the determining being based on a graph distance in the knowledge graph between at least some of the correlated concepts represented in the knowledge graph, and being based further on a cardinality of the set of concepts of the thought unit exceeding a threshold; and 
 based on determining that the thought unit is an original idea, storing a representation of the original idea to an idea repository and invoking processing of at least one computer. 
   
     
     
         14 . The computer system of  claim 13 , wherein the method further comprises assigning relevance scores to the concepts of the thought unit, wherein the determining that the thought unit is an original idea is further based on the relevance scores assigned to the concepts. 
     
     
         15 . The computer system of  claim 13 , wherein the obtaining the knowledge graph further comprises assigning weights to the concepts represented in the knowledge graph, and wherein the determining that the thought unit is an original idea is further based on the weights assigned to the correlated concepts represented in the knowledge graph, wherein the weight assigned to a concept represented in the knowledge graph is based on at least one selected from the group consisting of: (i) area of innovation to which the concept pertains and (ii) a frequency or trend in coverage of the concept in news media. 
     
     
         16 . The computer system of  claim 15 , wherein the method further comprises:
 comparing the thought unit to other thought units determined to be original ideas and having representations thereof stored in the idea repository; and   identifying another thought unit, of the other thought units, for which the thought unit and the another thought unit share a common pair of concepts represented in the knowledge graph, wherein the one or more individuals comprise a first individual who expressed the thought unit and a second individual who expressed the another thought unit, wherein based on determining that the expression of the thought unit by the first individual and expression of the another thought unit by the second individual were not made in a common conversation between the first individual and second individual, the invoking processing of the at least one computer comprises providing a first electronic communication to a first computer of the first individual and providing a second electronic communication to a second computer of the second individual, the first and second electronic communications to network together the first and second individuals.   
     
     
         17 . A computer program product comprising:
 a computer readable storage medium readable by at least one processor and storing instructions for execution by the at least one processor for performing a method comprising:
 electronically capturing expression of one or more individuals as written text data using one or more electronic devices; 
 obtaining a knowledge graph data structure for a knowledge dataset, the knowledge graph comprising representations of concepts and relationships between the concepts as identified from the knowledge dataset; 
 automatically topic modeling the written text data to ascertain a plurality of thought units expressed in the written text data, and identifying, for each thought unit, a respective set of concepts of the thought unit; 
 mapping a thought unit of the plurality of thought units to the knowledge graph by correlating the concepts of the thought unit to a correlated set of concepts represented in the knowledge graph; 
 determining that the thought unit is an original idea, the determining being based on a graph distance in the knowledge graph between at least some of the correlated concepts represented in the knowledge graph, and being based further on a cardinality of the set of concepts of the thought unit exceeding a threshold; and 
 based on determining that the thought unit is an original idea, storing a representation of the original idea to an idea repository and invoking processing of at least one computer. 
   
     
     
         18 . The computer program product of  claim 17 , wherein the method further comprises assigning relevance scores to the concepts of the thought unit, wherein the determining that the thought unit is an original idea is further based on the relevance scores assigned to the concepts. 
     
     
         19 . The computer program product of  claim 17 , wherein the obtaining the knowledge graph further comprises assigning weights to the concepts represented in the knowledge graph, and wherein the determining that the thought unit is an original idea is further based on the weights assigned to the correlated concepts represented in the knowledge graph, wherein the weight assigned to a concept represented in the knowledge graph is based on at least one selected from the group consisting of: (i) area of innovation to which the concept pertains and (ii) a frequency or trend in coverage of the concept in news media. 
     
     
         20 . The computer program product of  claim 17 , wherein the method further comprises:
 comparing the thought unit to other thought units determined to be original ideas and having representations thereof stored in the idea repository; and   identifying another thought unit, of the other thought units, for which the thought unit and the another thought unit share a common pair of concepts represented in the knowledge graph, wherein the one or more individuals comprise a first individual who expressed the thought unit and a second individual who expressed the another thought unit, wherein based on determining that the expression of the thought unit by the first individual and expression of the another thought unit by the second individual were not made in a common conversation between the first individual and second individual, the invoking processing of the at least one computer comprises providing a first electronic communication to a first computer of the first individual and providing a second electronic communication to a second computer of the second individual, the first and second electronic communications to network together the first and second individuals.