← Back to Patent Explorer
EP0933712A2 Expired / Lapsed EP ⏱️ 0.0 years remaining

Method and system for generating document summaries with navigation information

Assignee: Xerox Corp
•
Filing: 1999-01-14
•
Granted: —
•
Expires: 2019-01-14
📄 Original PDF 🌐 Google Patents 🔄 Sync Now

Abstract

Abstract A method and a system for generating a document summary. The method and the system extract text along with corresponding position information from a document, provide the extracted text to a document summarizer (62) and generates a summary with indicators that indicate the corresponding locations in the document from which the summary portions were extracted.

Inventors

  • 👤 Julian M. Kupiec

Bibliographic Details

Application Number —
Jurisdiction EP
Data Source google_patents
Last Synchronized 2026-10-24 11:04
CPC Classifications
G; G06; G06F; G06F16/00; G06F16/30; G06F16/34; G06F16/345; G06F40/00; G06F40/20; G06F40/258

Claims Analysis

Total Claims: 10
Claim 1
Independent Claim 64 words
A method for summarizing a document, the method comprising: extracting text from the document along with corresponding location information; identifying portions of the extracted text that reflect the content of the document; generating a presentation file that includes the identified portions and a first set of indicators that indicate the locations of the corresponding extracted text in the document; and presenting the presentation file.
Claim 2
Dependent Claim 12 words
The method of claim 1, where the location information comprises structural information.
Claim 3
Dependent Claim 15 words
The method of claim 1 or claim 2, where the location information comprises layout information.
Claim 4
Independent Claim 35 words
The method of any of claims 1 to 3, further comprising the step of identifying the document as being of a predetermined type, wherein the steps of extracting and identifying correspond to the predetermined type.
Claim 5
Independent Claim 87 words
The method of any of claims 1 to 4, further comprising: generating a second set of indicators that correspond to the first set of indicators; and placing the second set of indicators in the layout of the document adjacent to the corresponding extracted text, wherein the first set of indicators comprise presenting each corresponding portion of summary in a presentation attribute that corresponds to the second set of indicators that comprise the presentation of the corresponding extracted text of the document in the same corresponding presentation attribute.
Claim 6
Dependent Claim 87 words
An automatic document summarizer comprising: a processor that comprises: a text extractor that extracts text from a document along with corresponding extracted text location information; a document summarizer that identifies portions of the extracted text that reflect the content of the document; and a presentation file formatter that formats the layout of a presentation file that includes the identified portions and a first set of indicators that indicate the locations of the corresponding extracted text in the document; and a presentation system that presents the presentation file.
Claim 7
Dependent Claim 12 words
The summarizer of claim 6, where the location information comprises structural information.
Claim 8
Dependent Claim 15 words
The summarizer of claim 6 or claim 7, where the location information comprises layout information.
Claim 9
Dependent Claim 59 words
The summarizer of any of claims 6 to 8, wherein the processor further comprises a document type identifier that identifies the document as being of a predetermined type, wherein the text extractor extracts the text using a method corresponding to the identified predetermined type and the document summarizer identifies portions using a method corresponding to the identified predetermined type.
Claim 10
Dependent Claim 90 words
The summarizer of any of claims 6 to 9, where the presentation file formatter generates a second set of indicators that correspond to the first set of indicators and places the second set of indicators in the layout of the document adjacent to the corresponding extracted text, wherein the first set of indicators comprise presenting each corresponding portion of summary in a presentation attribute that corresponds to the second set of indicators that comprise the presentation of the corresponding extracted text of the document in the same corresponding presentation attribute.

References Cited (Backward Citations)

No citation records indexed.

USPTO Annuity & Maintenance Windows

Maintenance schedule is calculated for granted US utility patents.

Assigned Categories & Tags

No categories assigned to this patent yet.

Assign Category Tag