Continuous evaluation and adjustment of search engine results

Abstract

Taught is a search engine for science tools which dynamically evaluates search rank of said science tools through Natural Language Processing and machine learning. The search engine accepts into a corpus of public and private materials, which references individual science tools. Each item of the corpus is evaluated both as to how much that given item should be trusted, and what that item says about individual science tools. Each science tool is evaluated based on what the whole corpus of input data contains concerning those science tools, taking into account how valuable the source of the data is in order to render an overall score and search rank. The search engine generates a judgement of each individual science tool, which is dynamically updated as new information becomes available in the corpus of input data.

1 - 21 . (canceled) 
     
     
         22 . A method to develop a search engine rank for object-source pairs within a corpus of published documents, the method comprising:
 semantically identifying, by an evaluation module, objects and sources contained within the corpus of published documents, wherein each source is a name of an organization and each object is a noun that is not the name of an organization;   tying, by the evaluation module, each instance of a first object throughout the corpus of published documents to a source value based on textual semantics surrounding each instance of the first object within the corpus of published documents;   receiving, by a search engine, a search request for the first object; and   returning, by the search engine, a plurality of search results of the first object with different source values, wherein a search rank for the first object with a given source value is based on a number of times the given source value is tied to the first object.   
     
     
         23 . The method of  claim 22 , wherein the first object is a science tool and the given source value is an organization from which the science tool is purchasable. 
     
     
         24 . The method of  claim 22 , wherein the search rank for the first object with the given source value is further based on a location of the first object with the given source value within the corpus of published documents. 
     
     
         25 . The method of  claim 24 , wherein the search rank for the first object with the given source value is further based on:
 a publication date of particular documents within the corpus of published documents including instances of the first object with the given source value.   
     
     
         26 . The method of  claim 23 , wherein the search rank for the first object with the given source value is further based on:
 experiment involvement of the first object with the given source value in the corpus of published documents.   
     
     
         27 . The method of  claim 22 , further comprising:
 displaying the plurality of search results organized by the search rank.   
     
     
         28 . The method of  claim 27 , wherein said displaying the plurality of search results includes associated links for each of the plurality of search results, wherein the associated link for each of a respective search result of the plurality of search results directs users to a website of a respective source value. 
     
     
         29 . The method of  claim 28 , further comprising:
 updating the search rank for the first object with the given source value based on the frequency users click on the associated link of the given source value.   
     
     
         30 . The method of  claim 27 , further comprising:
 displaying, on the user display, a rating value for each of the search results, the rating value is a non-exclusive, numeric value with a positive correlation to search rank.   
     
     
         31 . The method of  claim 27 , further comprising:
 displaying, on the user display, a visual representations of how a given search result measures on a number of criteria used to determine search rank, the number of criteria including:   a time related factor;   an independently assigned peer ranking; and   a citation frequency factor.   
     
     
         32 . The method of  claim 27 , further comprising:
 wherein said displaying the plurality of search results includes associated links for each of the plurality of search results, wherein the associated link for each of a respective search result of the plurality of search results directs users to a published document including an instance of the first object with the given source value of the plurality of published documents.   
     
     
         33 . The method of  claim 23 , wherein said semantically identifying includes using a natural language processor to populate a number of properties for the first object, properties include any of:
 source;   conditions;   catalog number;   dilution;   location;   temperature; or   assay.   
     
     
         34 . A system to develop a search engine rank for object-source pairs within a corpus of published documents, the method comprising:
 a database including the corpus of published documents;   a processor-enabled evaluation module configured to semantically identify objects and sources contained within the corpus of published documents, wherein each source is a name of an organization and each object is a noun that is not the name of an organization, the evaluation module further configured to generate a plurality of object-source pairs by associating each instance of a first object throughout the corpus of published documents to a source based on textual semantics surrounding each instance of the first object within the corpus of published documents; and   a processor-enabled search engine configured to receive a search request for the first object and return a plurality of search results including the plurality of object-source pairs wherein the object of each of the object-source pair is the first object and the source of each of the object-source pairs varies, wherein a search rank for the first object with a given source is based on a number of times the given source is associated to the first object.   
     
     
         35 . The system of  claim 34 , wherein the first object is a science tool and the given source value is an organization from which the science tool is purchasable. 
     
     
         36 . The system of  claim 34 , wherein the search rank for the first object with the given source value is further based on a location of the first object with the given source value within the corpus of published documents. 
     
     
         37 . The system of  claim 36 , wherein the search rank for the first object with the given source value is further based on a publication date of particular documents within the corpus of published documents including instances of the first object with the given source value. 
     
     
         38 . The system of  claim 35 , wherein the search rank for the first object with the given source value is further based on:
 experiment involvement of the first object with the given source value in the corpus of published documents.   
     
     
         39 . The system of  claim 34 , further comprising:
 a user interface configured to display the plurality of search results organized by the search rank.   
     
     
         40 . The system of  claim 39 , wherein the user interface further displays associated links for each of the plurality of search results, wherein the associated link for each of a respective search result of the plurality of search results directs users to a website of a respective source value. 
     
     
         41 . The system of  claim 39 , wherein the user interface is further configured to communicate user clicks on associated links to the search engine and wherein the search engine is configured to update the search rank for the first object with the given source based on the frequency user clicks on the associated links of the given source. 
     
     
         42 . The system of  claim 27 , wherein the user interface further displays associated links for each of the plurality of search results, wherein the associated link for each of a respective search result of the plurality of search results directs users to a published document including an instance of the first object with the given source value of the plurality of published documents.