Self-evolving knowledge graph

A computer system for updating a knowledge graph, the computer system comprising:

• one or more computer processors;
• one or more computer readable storage media;
• program instructions stored on the one or more computer readable storage media for execution by at least one of the one or more computer processors, the program instructions comprising instructions to:
• receive a model corresponding to a set of documents, wherein the model comprises a plurality of entities, a plurality of entity associations, and a plurality of confidence scores corresponding to the plurality of entity associations, wherein a confidence score for two entities of an entity association is calculated by dividing a number of documents of the set of the documents in which each of the two entities is present by a total number of documents of the set of documents;
• calculate a relevance value for each entity of the plurality of entities that are present in the set of documents and for each entity of the plurality of entities that are present in a new document;
• identify one or more entity associations that are supported by specific portions of the new document, wherein identifying the one or more entity associations that are supported by the new document comprises:
• calculating a plurality of cosine similarity values, wherein each cosine similarity value is calculated between a vector comprising the relevance values of the new document and a vector comprising the relevance values of a document of the set of documents, and
• determining that the plurality of cosine similarity values exceed a threshold value for a majority of the comparisons;
• and
• update the confidence scores for each of the identified one or more entity associations based on a level of support in the new document.

A computer program product for updating a knowledge graph, the computer program product comprising one or more computer readable storage media collectively having program instructions embodied therewith, the program instructions executable by a computer to cause the computer to:

• receive a model corresponding to a set of documents, wherein the model comprises a plurality of entities, a plurality of entity associations, and a plurality of confidence scores corresponding to the plurality of entity associations, wherein a confidence score for two entities of an entity association is calculated by dividing a number of documents of the set of the documents in which each of the two entities is present by a total number of documents of the set of documents;
• calculate a relevance value for each entity of the plurality of entities that are present in the set of documents and for each entity of the plurality of entities that are present in a new document;
• identify one or more entity associations that are supported by specific portions of the new document, wherein identifying the one or more entity associations that are supported by the new document comprises:
• calculating a plurality of cosine similarity values, wherein each cosine similarity value is calculated between a vector comprising the relevance values of the new document and a vector comprising the relevance values of a document of the set of documents, and
• determining that the plurality of cosine similarity values exceed a threshold value for a majority of the comparisons;
• and
• update the confidence scores for each of the identified one or more entity associations based on a level of support in the new document.