Continuous evaluation and adjustment of search engine results
Inventors
Lachmi, Karin • Levitt, Daniel • Pardo, Ehud • Grunspan, Dan
Assignees
Interested in licensing this patent?
MTEC can help explore whether this patent might be available for licensing for your application.
Publication Number
US-11768842-B2
Publication Date
2023-09-26
Expiration Date
Abstract
A search engine for objects in a corpus of document dynamically evaluates search rank of the objects through Natural Language Processing and machine learning. When a search query is received for a first object, the search engine identifies search results including a plurality of source values that are tied to the first object in the corpus of published documents. A search rank is computed for each identified search result based on content of direct textual references to each of the plurality of source values within the corpus of published documents, as well as a weight assigned to each published document. The identified search results are returned according to the computed search rank.
Core Innovation
The invention provides a system to develop a search engine rank for objects in a corpus of published documents. The corpus includes published documents that contain source values and objects tied to the source values based on semantic text analysis of the corpus, and the source values act as a source of the objects.
For a received search query specifying a first object, the system identifies search results that include a plurality of source values tied to the first object in the resource database. It then computes a search rank for each identified search result using the content of direct textual references to the plurality of source values within the corpus.
The computation also uses a weight assigned to each published document in which the direct textual references occur. The document weight is assigned based on one or more of time related factors, independently assigned peer rankings, or citation frequency factors, and the system returns the identified search results according to the computed search ranks.
Claims Coverage
The independent claims are clm-00001 and clm-00011. Across these independent claims, the core coverage includes semantic text analysis to tie objects to source values and a per-search-result ranking computed from direct textual reference content combined with a published-document weight, including one or more of time related factors, peer rankings, or citation frequency factors.
Semantic tying of objects to source values via semantic text analysis
Published documents in a corpus contain source values and objects tied to the source values based on semantic text analysis, where the source values are a source of the objects.
Ranking search results by direct textual references plus published-document weighting
For search results including a plurality of source values tied to a first object, compute a search rank based on the content of direct textual references to the plurality of source values within the corpus and a weight assigned to each published document in which the direct textual references occur.
Time-related, peer-ranking, and citation-frequency document weighting
Assign the weight for each published document based on one or more of time related factors, independently assigned peer rankings, or citation frequency factors.
The independent claims focus on associating a queried object with tied source values using semantic text analysis, then ranking source-value results by combining direct textual reference content with a published-document weight derived from time-related factors, peer rankings, and/or citation frequency factors.
Stated Advantages
Documented Applications
No documented applications found
Interested in licensing this patent?