System and process for concept tagging and content retrieval
Inventors
Charlot, Regis • Naeymi-Rad, Frank • Oganesova, Alina • Young, Andre • NAEYMI-RAD, Andrei • Bodal, Aziz • Haines, David • Maldonado, Jose • Kobashi, Masayo • SCHAEFER, Stephanie
Assignees
Interested in licensing this patent?
MTEC can help explore whether this patent might be available for licensing for your application.
Publication Number
US-9418150-B2
Publication Date
2016-08-16
Expiration Date
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 and system for tagging content with one or more descriptions that pertain to the content. A database is populated with a plurality of concepts, where each concept resides hierarchically under a domain and is unique within the given domain, and where each domain has its own hierarchical structure. At least one domain is a category selected from problem, procedure, diagnosis, medication, and allergy.
The system also populates a database with a plurality of descriptions, where each description is an alternative way to express an associated concept and is unique within a given domain. Descriptions have a many-to-one relationship with concepts, and each description has a presence factor indicative of the strength of the relationship between the description and its associated concept and of a physician's intent when the description is generally used by physicians.
Content is reviewed by identifying portions that match concepts by determining whether each content portion relates to one or more descriptions associated with the given concept. For satisfactory matches, description tags are created, including a reference to a location of the identified portion within the content, and the tags are stored in a format which can be searched by search tools.
In response to a query, the invention generates a rank for the content or for an electronic document using at least one of the description tags and a related concept, based at least on the presence factor for the descriptions of the description tags applied to the content or document. The content is then displayed in a list based on the rank, including a list of documents ordered by document rank, and the system supports automatic tagging and manual editing of electronic content using many-to-many relationships between electronic content items and content tags.
Claims Coverage
The independent claims are clm-00001, clm-00009, and clm-00015. They share five inventive features centered on hierarchical concepts, unique alternative descriptions, presence factor, content matching and tagging, and query-time ranking and display.
Hierarchical domains with unique concepts and unique alternative descriptions
Each concept resides hierarchically under a domain and is unique within the domain; each domain has its own hierarchical structure; at least one domain is selected from problem, procedure, diagnosis, medication, and allergy; each description is an alternative way to express an associated concept and is unique within a given domain; descriptions have a many-to-one relationship with concepts.
Presence factor reflecting relationship strength and physician intent
Each description has a presence factor indicative of the strength of the relationship between the description and its associated concept, and indicative of a physician's intent when the description is generally used by physicians.
Satisfactory-match content portion identification and location-based description tags
Content portions are reviewed to identify portions that match concepts by determining whether each content portion relates to one or more descriptions associated with a given concept; a description tag is created for each identified portion and includes a reference to a location within the content; the tags are stored in a format searchable by search tools.
Query-time ranking based on description tags and presence factor and ranked list display
In response to a query, a rank is generated for the content or document using at least one description tag and a related concept, and the ranking is based at least on the presence factor for the descriptions of the applied tags; the content or documents are displayed in a list based on rank.
Automatic tagging with many-to-many content tags and document ranking
Electronic content items are automatically tagged and may be manually edited; content tags have a many-to-many relationship with descriptions, electronic content items have a many-to-many relationship with content tags, rankings are generated in response to a query and based at least on the presence factor, and a database table stores information relating to the electronic content.
Across clm-00001, clm-00009, and clm-00015, the inventive concept centers on hierarchical, domain-specific concepts linked to unique alternative descriptions with a presence factor, identification of satisfactory matches in content or documents, creation of searchable location-based tags, and query-based ranking and display of results.
Stated Advantages
Not explicitly described in patent.
Documented Applications
Not explicitly described in patent.
Interested in licensing this patent?