Method for searching related entities through entity co-occurrence

Abstract

A method for searching for related entities using entity co-occurrence is disclosed. Embodiments of the method may be employed in any search system that may include at least one search engine, at least one entity co-occurrence knowledge base, an entity extraction module, and at least an entity indexed corpus. The method may extract and disambiguate entities from search queries by using an entity co-occurrence knowledge base, find extracted entities in an entity indexed corpus and finally present search results as related entities of interest.

What is claimed is: 
     
         1 . A computer-implemented method comprising:
 in response to receiving a search query comprising one or more entities from an end user device, comparing, by the entity extraction computer, each respective entity with one or more co-occurrences of the respective entity in a co-occurrence database;   extracting, by the entity extraction computer, a subset of the one or more entities from the search query responsive to determining each respective entity of the subset that exceeds a confidence score of the co-occurrence database based on a degree of certainty of co-occurrence of the entity with one or more related entities in an electronic data corpus according to the co-occurrence database;   assigning, by the entity extraction computer, a confidence score to each of the extracted entities, wherein the confidence score is assigned based on a level of certainty that each of the extracted entities is extracted based on one or more feature attributes associated to each of the extracted entities;   assigning, by the entity extraction computer, an index identifier (index ID) to each of the extracted entities based at least on the confidence scores of each of the extracted entities, wherein the index ID for each of the extracted entities in saved in the electronic data corpus;   identifying, by a search server computer, index IDs of a subset of entities from the extracted entities based on relatedness of index IDs in which at least two of the extracted entities co-occur within the electronic data corpus; and   generating, by the search server computer, a search result list having data records corresponding to the identified index IDs.   
     
     
         2 . The computer-implemented method of  claim 1 , wherein the co-occurrence database comprises one or more entries for the one or more entities, and wherein each entry for the respective entity of the one or more entities contains a semantically-related entity that identifies the respective entity. 
     
     
         3 . The computer-implemented method of  claim 1 , wherein the co-occurrence is an instance of an entity of the one or more entities identified by the semantically-related entity in the corpus of documents in the co-occurrence database, and wherein the semantically-related entity corresponds to a model indicating distinct entities. 
     
     
         4 . The computer-implemented method of  claim 1  further comprising:
 sorting, by the search server computer, the search result list by relevance based on the confidence score; and 
 transmitting, by the search server computer, the sorted search result list to the end-user device. 
 
     
     
         5 . The computer-implemented method of  claim 1  further comprising:
 ranking, by the entity extraction computer, the extracted entities based on the confidence score. 
 
     
     
         6 . The computer-implemented method of  claim 1  further comprising:
 disambiguating, by the entity extraction computer, each of the entities of the extracted entities from one another based on relatedness of index IDs. 
 
     
     
         7 . The computer-implemented method of  claim 1 , wherein each of the one or more entities is selected from the group consisting of a person, an organization, a geographic location, a date, and a time. 
     
     
         8 . A system comprising:
 a co-occurrence database;   an entity extraction computer comprising one or more processors executing computer readable instructions for a plurality of computer modules, wherein the entity extraction computer is configured to:
 in response to receiving a search query comprising one or more entities from an end user device, compare each respective entity with one or more co-occurrences of the respective entity in a co-occurrence database; 
 extract a subset of the one or more entities from the search query responsive to determining each respective entity of the subset that exceeds a confidence score of the co-occurrence database based on a degree of certainty of co-occurrence of the entity with one or more related entities in an electronic data corpus according to the co-occurrence database; 
 assign a confidence score to each of the extracted entities, wherein the confidence score is assigned based on a level of certainty that each of the extracted entities is extracted based on one or more feature attributes associated to each of the extracted entities; and 
 assign an index identifier (index ID) to each of the extracted entities based at least on the confidence scores of each of the extracted entities, wherein the index ID for each of the extracted entities in saved in the electronic data corpus; and 
   a search server computer comprising one or more processors executing computer readable instructions for a plurality of computer modules, wherein the search server computer is configured to:
 identify index IDs of a subset of entities from the extracted entities based on relatedness of index IDs in which at least two of the extracted entities co-occur within the electronic data corpus; and 
 generate a search result list having data records corresponding to the identified index IDs. 
   
     
     
         9 . The system of  claim 8 , wherein the co-occurrence database comprises one or more entries for the one or more entities, and wherein each entry for the respective entity of the one or more entities contains a semantically-related entity that identifies the respective entity. 
     
     
         10 . The system of  claim 8 , wherein the co-occurrence is an instance of an entity of the one or more entities identified by the semantically-related entity in the corpus of documents in the co-occurrence database, and wherein the semantically-related entity corresponds to a model indicating distinct entities. 
     
     
         11 . The system of  claim 8 , wherein the entity extraction computer is further configured to:
 sort the search result list by relevance based on the confidence score and transmit the sorted search result list to the end-user device.   
     
     
         12 . The system of  claim 8 , wherein the entity extraction computer is further configured to rank the extracted entities based on the confidence score. 
     
     
         13 . The system of  claim 8 , wherein the entity extraction computer is further configured to disambiguate each of the entities of the extracted entities from one another based on relatedness of index IDs. 
     
     
         14 . The system of  claim 8 , wherein each of the one or more entities is selected from the group consisting of a person, an organization, a geographic location, a date, and a time. 
     
     
         15 . A non-transitory computer readable medium having stored thereon computer executable instructions comprising:
 in response to receiving a search query comprising one or more entities from an end user device, comparing, by the entity extraction computer, each respective entity with one or more co-occurrences of the respective entity in a co-occurrence database;   extracting, by the entity extraction computer, a subset of the one or more entities from the search query responsive to determining each respective entity of the subset that exceeds a confidence score of the co-occurrence database based on a degree of certainty of co-occurrence of the entity with one or more related entities in an electronic data corpus according to the co-occurrence database;   assigning, by the entity extraction computer, a confidence score to each of the extracted entities, wherein the confidence score is assigned based on a level of certainty that each of the extracted entities is extracted based on one or more feature attributes associated to each of the extracted entities;   assigning, by the entity extraction computer, an index identifier (index ID) to each of the extracted entities based at least on the confidence scores of each of the extracted entities, wherein the index ID for each of the extracted entities in saved in the electronic data corpus;   identifying, by a search server computer, index IDs of a subset of entities from the extracted entities based on relatedness of index IDs in which at least two of the extracted entities co-occur within the electronic data corpus; and   generating, by the search server computer, a search result list having data records corresponding to the identified index IDs.   
     
     
         16 . The computer readable medium of  claim 15 , wherein the co-occurrence database comprises one or more entries for the one or more entities, and wherein each entry for the respective entity of the one or more entities contains a semantically-related entity that identifies the respective entity. 
     
     
         17 . The computer readable medium of  claim 15 , wherein the co-occurrence is an instance of an entity of the one or more entities identified by the semantically-related entity in the corpus of documents in the co-occurrence database, and wherein the semantically-related entity corresponds to a model indicating distinct entities. 
     
     
         18 . The computer readable medium of  claim 15  further comprising:
 sorting, by the search server computer, the search result list by relevance based on the confidence score; and 
 transmitting, by the search server computer, the sorted search result list to the end-user device. 
 
     
     
         19 . The computer readable medium of  claim 15  further comprising:
 ranking, by the entity extraction computer, the extracted entities based on the confidence score. 
 
     
     
         20 . The computer readable medium of  claim 15  further comprising:
 disambiguating, by the entity extraction computer, each of the entities of the extracted entities from one another based on relatedness of index IDs.