Back to results
US 11,687,984 B2Granted
Mining of distributed scientific data for enriched valuation
AssigneeScientist Solutions
InventorsMarcia Beth Allen, Joseph Ruston Bishop
Life of this patent
Estimating the term…
Abstract
Methods and systems are described that detail the rapid validation of scientific products and scientist consumer information derived from multiple science/research based sources, such as peer-reviewed scientific publications and online resources, for example, as well as any other available tasked forum or venue. The refined information will facilitate unique product evaluation opportunities via an accessible website/forum, trade shows, etc., and provide previously unknowable sales leads, market intelligence, and targeted advertising opportunities for product manufacturers.
Claims20
A computerized method for mining distributed scientific data for enriched product or contact valuation, comprising:
- obtaining distributed scientific data, presented in scientific publications, in scientific forums, peer-reviewed scientific publications and online resources and contact data from a plurality of independently segregated sources using an automatic searching tool, said distributed scientific data comprising data from subscription based resources and data from non-subscription based resources;
- using a computer to associate the obtained data relevant to at least one of the scientific data and contact data using an automatic association tool, and storing at least an aspect of the obtained data to provide a semantic association, using the data, as stored obtained data associations;
- applying a computerized semantic refinement algorithm to the associated data to obtain refined data, the applying of the computerized semantic refinement algorithm including mining relationships to search objects by linking data from scientific publications and other distributed scientific data from the subscription based resources and the non-subscription based resources as several possible resource examples, and using the resulting mined information to formulate relationships between the search objects and the linked data, thereby enhancing correlation and information transparency, the algorithm embodied directly in a software module resident in a storage medium, the storage medium is coupled to the processor such that the processor can read information from, and write information to, the storage medium;
- applying an algorithm function providing machine learning by performing assorted levels of information extraction, correlation, transformation, tagging and semantic analysis;
- using the computer to parse the refined data to an applicable scientific database and an applicable contact database and outputting information from the computer for storage in database store, wherein the databases contain concise information regarding at least one of a scientific data summary, product summary, product review, top citing publications for the product, web mentions, topic summary, related topics, other products in a family, related products, competing products, names of top experts using the product, current market share, market share trends, and Science 2.0 citations;
- and
- using a semantic enrichment process to generate new refinements of associations occurring from obtaining new knowledge by extracting or mining information from the stored obtained data associations.
4 more elements
A system for mining distributed scientific data for enriched product or contact valuation, comprising:
- computer hardware means for obtaining distributed scientific product data, presented in scientific publications, in scientific forums, peer-reviewed scientific publications and online resources and contact data from a plurality of independently segregated sources from scientific publications and the Internet using an automatic searching tool, said distributed scientific product data comprising data from subscription based resources and data from non-subscription based resources;
- computer hardware means for associating the obtained data relevant to at least one of the product and contact data using an automatic association tool, and storing at least an aspect of the obtained data to provide a semantic association, using the data, and storing the semantic associations as stored obtained data associations;
- means for applying a computerized semantic refinement algorithm to the associated data to obtain refined data, the applying of the computerized semantic refinement algorithm including mining relationships to search objects by linking data from scientific publications and other distributed scientific product data from the subscription based resources and the non-subscription based resources as several possible resource examples, and using the resulting mined information to formulate relationships between the search objects and the linked data, thereby enhancing correlation and information transparency, the algorithm embodied directly in a software module resident in a storage medium, the storage medium is coupled to the processor such that the processor can read information from, and write information to, the storage medium;
- an algorithm function providing machine learning by performing assorted levels of information extraction, correlation, transformation, tagging and semantic analysis;
- computer hardware means for automatically parsing the refined data to an applicable scientific product database and an applicable contact database for storage in database store, wherein the databases contain concise information regarding at least one of a product summary, product review, top citing publications for the product, web mentions, topic summary, related topics, other products in a family, related products, competing products, names of top experts using the product, current market share, market share trends, and Science 2.0 citations;
- and
- a semantic enrichment process for generating new refinements of associations occurring from obtaining new knowledge by extracting or mining information from the stored obtained data associations.
4 more elements
A non-transitory computer-readable medium comprising:
- programming code for obtaining distributed scientific product data, presented in scientific publications, in scientific forums, peer-reviewed scientific publications and online resources and contact data from a plurality of independently segregated sources using an automatic searching tool, said distributed scientific product data comprising data from subscription based resources and data from non-subscription based resources;
- programming code for associating the obtained data relevant to at least one of the product and contact data using an automatic association tool, and storing at least an aspect of the obtained data to provide a semantic association, using the data, and storing the semantic associations as stored obtained data associations;
- programming code for applying a computerized semantic refinement algorithm to the associated data to obtain refined data, the applying of the computerized semantic refinement algorithm including mining relationships to search objects by linking data from scientific publications and other distributed scientific product data from the subscription based resources and the non-subscription based resources as several possible resource examples, and using the resulting mined information to formulate relationships between the search objects and the linked data, thereby enhancing correlation and information transparency, the algorithm embodied directly in a software module resident in a storage medium, the storage medium is coupled to the processor such that the processor can read information from, and write information to, the storage medium;
- programming code for an algorithm function providing machine learning by performing assorted levels of information extraction, correlation, transformation, tagging and semantic analysis;
- and
- programming code for automatically parsing the refined data to an applicable scientific product database and an applicable contact database for storage in database store, wherein the databases contain concise information regarding at least one of a product summary, product review, top citing publications for the product, web mentions, topic summary, related topics, other products in a family, related products, competing products, names of top experts using the product, current market share, market share trends, and Science 2.0 citations;
- and
- programming code for using a semantic enrichment process to generate new refinements of associations occurring from obtaining new knowledge by extracting or mining information from the stored obtained data associations,
- wherein the concise information correlates at least one of product efficacy and product use with the obtained data for efficient valuation thereof.
6 more elements
Dependencies are inferred from the claim text.