Inclusion of protocol conditions within search engine results
Inventors
Levitt, Daniel • Lachmi, Karin • Grunspan, Dan • Pardo, Ehud
Assignees
Interested in licensing this patent?
MTEC can help explore whether this patent might be available for licensing for your application.
Publication Number
US-11347937-B2
Publication Date
2022-05-31
Expiration Date
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.
Core Innovation
A natural language processor analyzes contextual data in a corpus of documents that are searchable by a search engine, where a first object is included in the corpus and the first object is a potential search result. The natural language processor identifies a first use of the first object through analysis of contextual data associated with references to the first object, and the first use is identified from the contextual data in the corpus of documents.
The natural language processor identifies a first protocol condition for the first use, where the first protocol condition includes a condition described in context associated with references to the first object in the corpus of documents as to how the first object was used for the first use. A search engine returns metadata for a search result including the first object, with metadata indicating a frequency of instances, in the corpus of documents, in which the first protocol condition occurs with reference to the first object during the first use.
The returned metadata indicates the frequency of instances of the first protocol condition compared to a number of all references of the first object in the corpus of documents or compared to a number of all references of the first use of the first object in the corpus of documents. The system can further generate ranked or tiered recommendations based on frequency tiers and can correlate protocol conditions with reported effectiveness or trends when measurable, while presenting search results with protocol-condition metadata and tiers.
Claims Coverage
The patent includes independent claims directed to a method, a system, and a non-transitory computer readable storage medium configured to generate metadata for a search result. Across these independent claims, the core inventive features focus on identifying a first use, identifying a first protocol condition described in context for how the object was used, and returning frequency metadata compared to baseline reference counts.
Generating metadata from a first use and protocol condition
A natural language processor identifies a first use of a first object included in a corpus of documents through analysis of contextual data associated with the first object, and identifies a first protocol condition for the first use including a condition described in context associated with references to the first object as to how the first object was used for the first use.
Returning frequency metadata compared to baseline reference counts
The search engine returns metadata for a search result including the first object, where the metadata indicates a frequency of instances in the corpus of documents in which the first protocol condition occurs with reference to the first object during the first use, as compared to a number of all references of the first object or as compared to a number of all references of the first use of the first object.
System with NLP for use and protocol condition identification plus search-result frequency metadata
A system includes a natural language processor that identifies a first use of a first object referenced in one or more documents in a corpus of documents and identifies a first protocol condition for the first use including a condition described in context associated with references to the first object; and a search engine communicatively coupled to the natural language processor that returns metadata for a search result including the first object with metadata indicating a frequency of instances where the first protocol condition occurs with reference to the first object during the first use compared to a number of all references of the first object or compared to a number of all references of the first use of the first object.
Non-transitory storage medium causing identification of use and protocol condition plus frequency metadata
A non-transitory computer readable storage medium stores executable computer program instructions that, when executed, cause a processor to identify a first use of a first object referenced in one or more documents in a corpus of documents, identify a first protocol condition for the first use including a condition described in context associated with references to the first object, and return metadata for a search result including the first object with metadata indicating a frequency of instances where the first protocol condition occurs with reference to the first object during the first use compared to a number of all references of the first object or compared to a number of all references of the first use of the first object.
Across the independent claims, the inventive coverage is directed to extracting a protocol condition described in context for a first use of an object and generating search-result metadata that quantifies how frequently that protocol condition occurs with the object during the first use, using frequency comparisons to baseline reference counts.
Stated Advantages
Provides metadata for a search result that indicates a frequency of protocol-condition instances associated with how an object was used during a first use, compared to baseline reference counts.
Documented Applications
Search results in a science-focused search engine that present protocol-condition metadata and frequency-based tiers for references to science tools/objects in a corpus of documents.
Generating metadata for a search result by identifying a first use of a first object in contextual text and extracting a protocol condition tied to that use from the corpus of documents.
Interested in licensing this patent?