System and process for concept tagging and content retrieval
Inventors
Charlot, Regis J P • Naeymi-Rad, Frank • OGANESOVA, Alina E. • YOUNG, JR., Andre L. • NAEYMI-RAD, Andrei • BODAL, Aziz M. • HAINES, David O. • Maldonado, Jose A. • Kobashi, Masayo • SCHAEFER, Stephanie J.
Assignees
Interested in licensing this patent?
MTEC can help explore whether this patent might be available for licensing for your application.
Abstract
A system and process for tagging electronic documents or other electronic content with concepts mentioned, contained, or otherwise described in that content. Once tagged, the content may be searchable, indexable, and retrievable in order to provide that content to an end user or another recipient. The system may be configured to handle a considerable number of asset files and a large number of users, workflows, and access applications simultaneously. The system may auto-tag the content and also may include a user interface for confirming and updating those tags and for manually creating new or additional tags. Content may include documents such as medical documents relating to procedures, diagnoses, medications or other domains. Alternatively, the content may include information about various care providers, in order to allow a user to locate a physician meeting one or more desired criteria.
Core Innovation
The invention provides a computer-implemented process for content and workflow management that populates a database concept table with a plurality of concepts and a unique concept identifier, where each concept resides hierarchically under a domain and is unique within a given domain. The process also populates a database description table with a plurality of descriptions, where each description has one or more description terms and a unique description identifier. Each description is an alternative way to express an associated concept, and the descriptions have a many-to-one relationship with each concept such that each description matches to only one respective concept.
The process generates a plurality of description-concept pairings by relating each description to a respective concept. Using the description terms, the process identifies portions of digital content that satisfactorily match one or more stored descriptions in the database description table. For each identified portion, the process creates a tag that directly maps the portion of the content to a respective matching description, where the tag includes the unique description identifier relating to the satisfactory description match, an identifier of the content being tagged, and a reference to a location of the identified portion within the content.
For retrieval and display, the process receives a search query and finds one or more satisfactory description search matches by comparing the search query against each tag. The comparing step uses the description-concept pairings to identify satisfactory description matches including other descriptions sharing the same concept as the search query, and thereby extends to one or more satisfactory content matches. The process further supports identifying a closest description match to the query, matching content linked with the same concept as the closest description match, and displaying selected content with visual indicators indicating where the related descriptions or related concept descriptions are tagged.
Claims Coverage
The provided independent claims are clm-00001, clm-00010, and clm-00018. They cover four inventive features centered on storing concepts and alternative descriptions with unique identifiers, using description-to-concept relationships to match digital content via description terms, applying description-linked tags with content location references, and performing query-time matching that extends from a directly matched description or closest description to other descriptions sharing the same concept, with user interface display using visual indicators.
Hierarchical concepts and many-to-one description mapping
Populating a database concept table with a plurality of concepts comprising one or more concept terms and a unique concept identifier, where each concept resides hierarchically under a domain and is unique within a given domain; and populating a database description table with a plurality of descriptions comprising one or more description terms and a unique description identifier; wherein each description is an alternative way to express an associated concept, and the descriptions have a many-to-one relationship with each concept such that each description matches to only one respective concept.
Description-concept pairings and content portion tagging with location
Generating a plurality of description-concept pairings by relating each description to a respective concept; using the description terms to identify portions of digital content that satisfactorily match one or more of the descriptions stored in the database description table; and creating a tag for each portion of the content identified from the satisfactory description match, the tag directly mapping the portion to a respective one of the matching descriptions, the tag including the unique description identifier relating to the satisfactory description match, an identifier of the content being tagged, and a reference to a location of the identified portion within the content.
Query matching via description tags and concept-based extension
Receiving a search query; and finding one or more satisfactory description search matches by comparing the search query against each tag, the comparing step using the description-concept pairings to identify satisfactory description matches including other descriptions sharing the same concept as the search query, and, by extension, one or more satisfactory content matches.
Closest description match with concept-linked content retrieval and visual tag indicators
Populating a database concept table with a plurality of concepts comprising one or more concept terms and a unique concept identifier; and populating a database description table with a plurality of descriptions comprising one or more description terms and a unique description identifier; where a description is an alternative way to express an associated concept; generating a plurality of description-concept pairings by relating each description to a respective concept; using the description terms to identify portions of digital content that satisfactorily match to one or more of the descriptions; applying a plurality of description tags to the content in a plurality of locations within the content, each description tag directly mapping the content at a respective location to the matching one or more descriptions; creating a link between the content and concepts related to the content where the related concepts are related to the plurality of description tags; receiving a query; matching one or more items of content to the query including identifying items of content including a closest description match to the query and, via the description-concept pairings, content linked with the same concept as the closest description match; and displaying the selected content with visual indicators of the applied description tags that match the query as a result of being a closest description match or that match descriptions related to the closest description match as a result of being related to the same concept as the closest description match.
Across clm-00001, clm-00010, and clm-00018, the claims cover a workflow for concept-based content tagging and query-time retrieval that stores hierarchical concepts and alternative descriptions with unique identifiers, establishes description-concept pairings, applies location-referenced tags that embed the unique description identifier, and uses the description-concept relationships to retrieve and display content by extending from a matched or closest description to other descriptions sharing the same concept, with visual indicators on a user interface.
Stated Advantages
Provides a way to identify portions of digital content that satisfactorily match stored descriptions using description terms.
Enables query matching that includes other descriptions sharing the same concept as the query and, by extension, satisfactory content matches.
Supports displaying selected content with visual indicators indicating where related descriptions and related concept descriptions are tagged.
Documented Applications
Medical records and provider profiles are managed for concept-based auto-tagging and manual curation, including a physician search engine for ranking and retrieving physician profiles.
A user interface displays highlighted tag locations and ranked results for content and physician search results using inclusive/exclusive physician tags.
Interested in licensing this patent?