Creating new documents based on global intent and local context

Patent metadata

Field	Value
Publication number	US-2016124968-A1
Application number	US-201614993499-A
Country	US
Kind code	A1
Filing date	Jan 12, 2016
Priority date	Jan 14, 2014
Publication date	May 5, 2016
Grant date	—

Abstract

An approach is provided for creating a new document. Keywords specifying a subject matter of the new document are received. Metadata of documents is determined to match keyword(s) included in the received keywords and the documents are retrieved. Based on a section being created in the new document, a ranked list of the retrieved documents is generated. A selection of a document included in the ranked list is received. The selected document is added to the new document. The keywords are refined based on the added document. Based on the subject matter and the refined keywords, the new document is completed by repeating the steps of determining the metadata, retrieving the documents, generating the ranked list, receiving the selection, and adding the selected document.

First claim

1 . A method of creating a new document, the method comprising the steps of:
a computer receiving keywords specifying a subject matter of the new document; the computer determining metadata of documents or metadata of parts of the documents matches one or more keywords included in the received keywords; the computer retrieving the documents or the parts of the documents whose metadata matches the one or more keywords; based on a section or subsection being created in the new document, the computer generating a ranked list of the retrieved documents or parts of the documents; the computer receiving a selection of a document or a part of a document included in the ranked list; the computer adding content to the new document, the added content being the document or the part of the document whose selection was received; the computer refining the keywords based in part on the added content; and based in part on the subject matter and the refined keywords, the computer completing the new document by repeating the steps of determining the metadata, retrieving the documents, generating the ranked list, receiving the selection, and adding the content.

2 . The method of claim 1 , further comprising the steps of:
the computer system receiving an outline of sections and subsections in the new document; and the computer receiving an association between the outline and the received keywords, wherein the step of completing the new document is based in part on the outline and the association between the outline and the received keywords.

3 . The method of claim 2 , wherein the step of completing the new document is further based on a global intent provided by the outline and based on a local context provided by the step of refining the keywords.

4 . The method of claim 1 , further comprising the step of:
the computer expanding the keywords to include (1) other keywords derived from the received keywords based on natural language processing techniques including stemming and synonyms, and (2) other keywords that are related to the received keywords based on one or more business glossaries, wherein the step of determining the metadata of the documents or the metadata of parts of the documents matches the at least one keyword includes determining the metadata of documents or the metadata of parts of the documents matches at least one of the expanded keywords.

5 . The method of claim 1 , further comprising the steps of:
subsequent to the step of adding the content to the new document, the computer receiving from a user a modification of the added content; and the computer automatically determining one or more keywords based on the modification of the added content, without the user identifying the one or more keywords, wherein the step of refining the keywords includes adding the one or more keywords to the received keywords based on the received modification of the added content.

6 . The method of claim 1 , further comprising the step of:
subsequent to the step of adding the content to the new document, the computer receiving from a user a modification of the added content and receiving from the user an identification of one or more keywords specifying the modification of the added content, wherein the step of refining the keywords includes adding the one or more keywords to the received keywords based in part on the received modification of the added content.

7 . The method of claim 1 , further comprising the step of:
the computer receiving from a user a selection indicating an aggressive retrieval or a conservative retrieval for the step of retrieving the documents or parts of the documents, wherein the step of determining the metadata of documents or the metadata of parts of the documents matches the one or more keywords includes determining the metadata of the documents or the metadata of parts of the documents matches any keyword included in the received keywords, if the selection indicates the aggressive retrieval, wherein the step of retrieving the documents or the parts of the documents is based on the metadata of the documents or the metadata of parts of the documents matching any keyword included in the received keywords, if the selection indicates the aggressive retrieval, wherein the step of determining the metadata of documents or the metadata of parts of the documents matches the one or more keywords includes determining the metadata of the documents or the metadata of parts of the documents matches all of the received keywords, if the selection indicates the conservative retrieval, and wherein the step of retrieving the documents or the parts of the documents is based on the metadata of the documents or the metadata of parts of the documents matching all of the received keywords, if the selection indicates the conservative retrieval.

8 . The method of claim 1 , further comprising the step of:
providing at least one support service for at least one of creating, integrating, hosting, maintaining, and deploying computer-readable program code in the computer, the program code being executed by a processor to implement the steps of receiving the keywords, determining the metadata, retrieving, generating, receiving the selection, adding, refining, and repeating.

9 . A computer system comprising:
a central processing unit (CPU); a memory coupled to the CPU; and a computer-readable, tangible storage device coupled to the CPU, the storage device containing instructions that are executed by the CPU via the memory to implement a method of creating a new document, the method comprising the steps of:
the computer system receiving keywords specifying a subject matter of the new document;
the computer system determining metadata of documents or metadata of parts of the documents matches one or more keywords included in the received keywords;
the computer system retrieving the documents or the parts of the documents whose metadata matches the one or more keywords;
based on a section or subsection being created in the new document, the computer system generating a ranked list of the retrieved documents or parts of the documents;
the computer system receiving a selection of a document or a part of a document included in the ranked list;
the computer system adding content to the new document, the added content being the document or the part of the document whose selection was received;
the computer system refining the keywords based in part on the added content; and
based in part on the subject matter and the refined keywords, the computer system completing the new document by repeating the steps of determining the metadata,
retrieving the documents, generating the ranked list, receiving the selection, and adding the content.

10 . The computer system of claim 9 , wherein the method further comprises the steps of:
the computer system receiving an outline of sections and subsections in the new document; and the computer system receiving an association between the outline and the received keywords, wherein the step of completing the new document is based in part on the outline and the association between the outline and the received keywords.

11 . The computer system of claim 10 , wherein the step of completing the new document is further based on a global intent provided by the outline and based on a local context provided by the step of refining the keywords.

12 . The computer system of claim 9 , wherein the method further comprises the step of:
the computer system expanding the keywords to include (1) other keywords derived from the received keywords based on natural language processing techniques including stemming and synonyms, and (2) oth

Assignees

• IBM

Inventors

• Joshi Sachindra
• Mehta Sameep
• Mohania Mukesh K
• Negi Sumit

Classifications

• G06F16/3344

  using natural language analysis · CPC title

• G06F3/0482

  Interaction with lists of selectable items, e.g. menus · CPC title

• G06F16/24578 Primary

  using ranking · CPC title

• G06F40/166

  Editing, e.g. inserting or deleting · CPC title

• G06F16/3325 Primary

  Reformulation based on results of preceding query · CPC title