A method for creating a graph database implemented knowledge mesh is disclosed. The method includes receiving, by a computer system, data from a plurality of different streams and identifying, by the computer system executing at least one machine learning model, a plurality of triples included in th
A method for creating a graph database implemented knowledge mesh is disclosed. The method includes receiving, by a computer system, data from a plurality of different streams and identifying, by the computer system executing at least one machine learning model, a plurality of triples included in the data. The method also comprises filtering, by the computer system, the plurality of triples to identify a relevant subset of triples by applying an ontological filter, applying, by the computer system, a disambiguation routine to the relevant subset of triples to correlate entities included in the relevant subset to other entities in a graph database and determine a degree of confidence with each correlation, and creating, by the computer system, a knowledge mesh using the graph database. The knowledge mesh comprises the relevant subset of triples, each correlation identified by application of the disambiguation routine, and the degree of confidence with each correlation.
대표청구항▼
1. A method for creating a graph database implemented knowledge mesh, comprising: receiving, by a computer system, data of a plurality of different content types from a plurality of different streams, wherein the plurality of different streams comprises one or more of a text stream, an audio stream,
1. A method for creating a graph database implemented knowledge mesh, comprising: receiving, by a computer system, data of a plurality of different content types from a plurality of different streams, wherein the plurality of different streams comprises one or more of a text stream, an audio stream, a video stream, an image stream, or a custom stream, and wherein the data is enhanced by the inclusion of added attributes;after the data is enhanced by the inclusion of added attributes, identifying, by the computer system executing at least one machine learning (ML) model, a plurality of triples included in the data;filtering, by the computer system, the plurality of triples to identify a relevant subset of triples by applying a customer defined ontological filter to the plurality of triples, wherein the customer defined ontological filter refines the plurality of triples with customer defined parameters to identify the relevant subset of triples;applying, by the computer system, a disambiguation routine to the relevant subset of triples to correlate entities included in the relevant subset of triples to other entities in a graph database and to determine a degree of confidence that correlated entities are the same entity; andcreating, by the computer system, a knowledge mesh using the graph database, wherein the knowledge mesh comprises knowledge mesh data including the relevant subset of triples, each correlation identified by application of the disambiguation routine, and the degree of confidence with each correlated entity. 2. The method of claim 1, wherein the ML model comprises at least one of a noun-verb-noun extraction or a subject-predicate-object ML extraction. 3. The method of claim 1, wherein at least some of the triples are expressly identified from the data and at least some of the triples are impliedly identified from the data and the attributes added to the data. 4. The method of claim 1, wherein the attributes added to a corresponding data comprise characteristics of the corresponding data, and wherein the characteristics comprise one or more of a source of the corresponding data, an identity of a person in the corresponding data, a location in the corresponding data, a time in the corresponding data, or a topic associated with the corresponding data. 5. The method of claim 1, wherein the customer defined ontological filter defines that any triples comprising a person be included in the relevant subset of triples. 6. The method of claim 1, wherein the disambiguation routine uses one or more of the attributes added to the data. 7. The method of claim 1, wherein the disambiguation routine is applied to the relevant subset of triples in flight, at storage of a relevant triple, or responsive to receipt of a query. 8. The method of claim 1, wherein the knowledge mesh data comprises a plurality of dimensions, and wherein at least some of the plurality of dimensions correspond to a different stream of data, a different data source, or a different type of source material. 9. The method of claim 8, wherein the knowledge mesh data comprises intra-dimensional relationships between entities represented in a single dimension and interdimensional relationships between entities represented in different dimensions. 10. The method of claim 1, further comprising creating and storing a recipe for each entity represented in the knowledge mesh data, wherein the recipe for each entity comprises a link to a corresponding source data and corresponding disambiguation instructions used to determine any relationships and degrees of confidence associated with the entity. 11. A system for creating a graph database implemented knowledge mesh, comprising: a graph database; anda computer system comprising: a non-transitory memory; anda processor, wherein the computer system is configured to: receive data of a plurality of different content types from a plurality of different streams, wherein the plurality of different streams comprises one or more of a text stream, an audio stream, a video stream, an image stream, or a custom stream, and wherein the data is enhanced by the inclusion of added attributes,after the data is enhanced by the inclusion of added attributes, identify, by executing at least one machine learning (ML) model, a plurality of triples included in the data,filter the plurality of triples to identify a relevant subset of triples by applying a customer defined ontological filter to the plurality of triples, wherein the customer defined ontological filter refines the plurality of triples with customer defined parameters to identify the relevant subset of triples,apply a disambiguation routine to the relevant subset of triples to correlate entities included in the relevant subset of triples to other entities in the graph database and determine a degree of confidence that correlated entities are the same entity, andcreate a knowledge mesh using the graph database, wherein the knowledge mesh comprises knowledge mesh data including the relevant subset of triples, each correlation identified by application of the disambiguation routine, and the degree of confidence with each correlated entity. 12. The system of claim 11, wherein the computer system executes the at least one ML model in parallel to identify the plurality of triples. 13. The system of claim 12, wherein the ML model comprises at least one of a noun-verb-noun extraction or a subject-predicate-object ML extraction. 14. The system of claim 11, wherein the computer system if further configured to create and store a recipe for each entity represented in the knowledge mesh data, wherein the recipe for each entity comprises a link to a corresponding source data and corresponding disambiguation instructions used to determine any relationships and degrees of confidence associated with the entity. 15. The system of claim 11, wherein the attributes added to a corresponding data comprise characteristics of the corresponding data, and wherein the characteristics comprise one or more of a source of the corresponding data, an identity of a person in the corresponding data, a location in the corresponding data, a time in the corresponding data, or a topic associated with the corresponding data. 16. The system of claim 15, wherein at least some of the triples are expressly identified from the data and at least some of the triples are impliedly identified from the data and the attributes added to the data. 17. The system of claim 16, wherein the disambiguation routine uses one or more of the attributes added to the data. 18. The system of claim 11, wherein the knowledge mesh data comprises a plurality of dimensions, and wherein at least some of the plurality of dimensions correspond to a different stream of data, a different data source, or a different type of source material. 19. The system of claim 11, wherein the knowledge mesh data comprises intra-dimensional relationships between entities represented in a single dimension and interdimensional relationships between entities represented in different dimensions. 20. The system of claim 11, wherein the customer defined ontological filter defines that any triples comprising a person be included in the relevant subset of triples.
※ AI-Helper는 부적절한 답변을 할 수 있습니다.