US 2018/0018334 A1Published application

Continuous evaluation and adjustment of search engine results

AssigneeBioz, Inc.

InventorsKarin Lachmi, Daniel Levitt, Ehud Pardo, Danny Grunspan

Life of this patent

Estimating the term…

Loading patent…

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.

Claims27

Dependent claims

A method performed by one or more computers for extracting metrics from research journals to develop objective rankings for scientific tools in a web search engine, the method comprising:

a.) receiving in a database, a corpus of research journals, the research journals including descriptions of scientific experiments and the scientific tools used therein, wherein scientific tools -include equipment, consumables, and resources used in generating the research for said research journals;
b.) recording, into the database, scientific tools included in the corpus of research journals, each scientific tool including a source;
c.) assigning, by a processor implemented evaluation module, value factors to each research journal, the value factors including:
i.) an impact factor as determined by third party rankings for a publication each research journal belongs to;
ii.) a recency factor as determined by how recently each research journal was published;
iii.) a citations factor as determined by the number of times other research journals cite a given research journal;
iv.) a citations timeline factor as determined by how recently a majority of citations for the given research journal have occurred;
and
v.) an overall factor as determined by combining all other value factors i., ii., iii., and iv.;
d.) assigning, by the processor implemented evaluation module, score factors to the scientific tools, the score factors including:
i.) efficacy factor as determined by a number of times a given scientific tool with a particular source is cited as compared to the given scientific tool is cited having other sources;
ii.) tendency factor as determined by a number of times the given science tool is referenced across the group of research journals as compared to a number of references similar science tools have;
iii.) protocol relevance as determined by a frequency the given science tool is referenced in the group of research journals as being used in an experiment with data;
iv.) timeline as determined by an aggregation of time data for trends for the given science tool;
and
v.) experiment involvement as determined by a ratio of efficacy factor to protocol relevance;
e.) receiving a search query, at the web search engine, for a type of science too;
f.) generating a rank score for the given science tool with respect to the other science tools using a combination of the score factors, wherein data used to assign the score factors is weighted by the value factors of the group of research journalsi
g.) returning search results, by the web search engine, including a plurality of science tools, each of the plurality of science tools conforming to the type of science tool in the search query;
and
h.) displaying the given science tool within the search results ordered based on the rank score of the first science tool as compared to other rank scores of other science tools included in the search results.

18 more elements

A method to develop an objective, numeric rank in a web search engine for a given science tool by extracting metrics from source data, the method comprising:

receiving a search query, at the web search engine, for a type of science tool, the web search engine including a corpus of source data from which to draw search results, the corpus of source data including a plurality of items;
returning search results, by the web search engine, including a plurality of science tools, each of the plurality of science tools conforming to the type of science tool in the search query;
computing a score rank for a first science tool of the plurality of science tools based on objective characteristics of textual references of the first science tool across the corpus of source data, the objective characteristics of the textual references including a numbering and a positioning within text of the corpus of source data, wherein some references to the first science tool contribute unevenly to the score rank based on a weighting of a source document for each reference;
displaying the first science tool within the search results ordered based on the score rank of the first science tool as compared to other score ranks of other science tools included in the search results.

1 more element

A method to generate a web search engine rank for science tools by extracting metrics from published source data to develop objective search rank values for scientific tools, the method comprising:

receiving, by a web search engine, a search query for a particular class of science tool, the web search engine including a corpus of published source data from which to draw search results, wherein the search results include science tools from the particular class of science tool;
identifying search results, by the web search engine, including a plurality of science tools of the particular class of science tool from the corpus of published source data, the source data comprised of items including any of research journals, research grants and grant proposals, scientific dissertations, or patent documents;
assigning, by the web search engine, a weight to each item within the corpus of published source data based at least on time related factors, independently assigned peer rankings, and citation frequency factors;
computing, by the web search engine, a search rank for each of the plurality of science tools amongst the particular class of science tool, the search rank based on content of textual direct references to each of the plurality of science tools within the items of the corpus of published source data, the content of the direct textual references including a numbering and a positioning within text of the corpus of source data, wherein an influence on the search rank of a given direct reference is determined by the weight of the item within the corpus of published source data the given direct reference originates from.

1 more element

A system to develop a search engine rank for science tools by extracting metrics from published source data to develop objective rating values for scientific tools, the system comprising:

a processor:
a memory including instructed that when executed cause the processor to:
a resource database including a corpus of published source data, the source data comprised of items including any of research journals, research grants and grant proposals, scientific dissertations, or patent documents;
a search engine user interface configured to receive a search query for a particular class of science tool;
and
a processor for executing computer-readable instructions that, when executed:
identify search results including a plurality of science tools of the particular class of science tool from the corpus of published source data, the source data comprised of items including any of research journals, research grants and grant proposals, scientific dissertations, or patent documents;
assign a weight to each item within the corpus of published source data based at least on time related factors, independently assigned peer rankings, and citation frequency factors;
compute a search rank for each of the plurality of science tools amongst the particular class of science tool, the search rank based on content of direct textual references to each of the plurality of science tools within the items of the corpus of published source data, the content of the direct textual references including a numbering and a positioning within text of the corpus of source data, wherein an influence on the search rank of a given direct reference is determined by the weight of the item within the corpus of published source data the given direct reference originates from.

6 more elements

Dependencies are inferred from the claim text.

Facts

Application: 15/605,771Filed 25 May 2017
Priority: 18 Jul 2016
Published: 18 Jan 2018
Term ends: Not estimatedThe source records don’t support an estimate.

Classification14 codes

G06F 16/24578
With adaptation to user needs: using ranking
G06F 16/248
Querying: presentation of query results
G06F 16/252
Integrating or interfacing systems involving database management systems: between a Database Management System and a front-end application
G06F 16/313
Indexing; Data structures therefor; Storage structures: selection or weighting of terms for indexing

Family

Application62/363,779Us provisional application · filed 18 Jul 2016
Application15/235,777Continuation · filed 12 Aug 2016
Application15/605,771Continuation
US 10,956,427 B2Related patent
US 2018/0018333 A1Published application
US 2018/0018334 A1This patent

From the US filing history. Foreign family members aren’t listed.