公开(公告)号：US20220351056A1

公开(公告)日：2022-11-03

申请号：US17246543

申请日：2021-04-30

Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATION

Inventor： Maira G. de Bayser ,  Geeth Ranmal de Mel ,  Mathias B. Steiner ,  Mohab Elkaref ,  Ronaldo Giro ,  Bruce Gordon Elmegreen ,  Christopher R. Gibson ,  David Boaz ,  David S. Braines ,  Dean Clarke ,  Dmitry Zubarev ,  Flaviu Cipcigan ,  Kristin Schmidt ,  Lori French ,  Stacey Gifford

IPC: G06N5/04 ,  G06N5/02 ,  G06F16/332 ,  G06F16/35 ,  G06K9/62 ,  G06N20/00

Abstract: A computer implemented method generating query results is provided. The method includes generating by a computer processor, a training model through artificial intelligence. The training model may be based on annotated data. A knowledge base for a subject matter may be generated based on the training model. The knowledge base may be based on content from document sources related to the subject matter. A natural language query input from a user may be received. An intent and requirements for satisfying the intent may be inferred by the computer processor. The knowledge base may be referenced to extract information related to the intent and requirements, from documents in the knowledge base. Relationships between the extracted information and the requirements may be correlated from the documents in the knowledge base. In addition, query results may be displayed to the user. The query results are based on the correlated relationships.

公开(公告)号：US12299594B2

公开(公告)日：2025-05-13

申请号：US17246543

申请日：2021-04-30

Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATION

Inventor： Maira G. de Bayser ,  Geeth Ranmal de Mel ,  Mathias B. Steiner ,  Mohab Elkaref ,  Ronaldo Giro ,  Bruce Gordon Elmegreen ,  Christopher R. Gibson ,  David Boaz ,  David S. Braines ,  Dean Clarke ,  Dmitry Zubarev ,  Flaviu Cipcigan ,  Kristin Schmidt ,  Lori French ,  Stacey Gifford

IPC: G06N5/04 ,  G06F16/3329 ,  G06F16/35 ,  G06F18/214 ,  G06N5/022 ,  G06N20/00

Abstract: A computer implemented method for generating query results includes generating by a computer processor, a training model through artificial intelligence. The training model is based on annotated data. A knowledge base for a subject matter is generated based on the training model. The knowledge base is based on content from document sources related to the subject matter. A natural language query input is received. An intent and requirements for satisfying the intent is inferred by the computer processor. The knowledge base is referenced to extract information related to the intent and requirements, from documents in the knowledge base. Relationships between the extracted information and the requirements are correlated from the documents in the knowledge base. Query results are displayed to the user. The query results are based on the correlated relationships.