# US 2010/0169299 A1 · Method and system for information extraction and modeling

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2010/0169299 A1
- Document ID: US20100169299A1
- Status: Published application
- Kind: A1
- Application number: 11/434,847
- Filed: 2006-05-17
- Published: 2010-07-01
- Earliest claimed: 2006-05-17
- Assignees: Mitretek Systems, Inc.
- Inventors: Victor J. Pollara
- Web page: https://patentgrep.com/patent/US20100169299A1

## CPC

- G06F 40/247: Thesauruses; Synonyms
- G06F 16/353: into predefined classes
- G06F 40/284: Lexical analysis, e.g. tokenisation or collocates
- Y10S 707/99931: Database or file accessing
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- Y10S: TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS

## Abstract

Systems and methods for modeling information from a set of documents are disclosed. A tool allows a user to extract and model concepts of interest and relations among the concepts from a set of documents. The tool automatically configures a database of the model so that the model and extracted concepts from the documents may be customized, modified, and shared.

## Claims

### Claim 1

A method for visually modeling information sought from a set of documents implemented using a computer having a processor and a display, comprising:
analyzing a set of documents using the processor;
storing a plurality of concepts from the set of documents in a database;
creating a visual model comprising visual elements corresponding to the plurality of concepts;
presenting the visual model to a user on the display;
enabling the user to add a visual element to the visual model, the visual element corresponding to a new concept;
enabling the user to add a relation between visual elements in the visual model;
generating extractors, each extractor corresponding to one of the visual elements or one of the relations between the visual elements in the visual model; and
based on a user selection of one of the visual elements or the relations, extracting information related to the concept corresponding to the selected visual element or the selected relation from the set of documents using the corresponding extractor.

### Claim 2 (depends on 1)

The method of claim 1, wherein the extractors are defined by the user.

### Claim 3 (depends on 1)

The method of claim 1, wherein the extractors are assigned automatically.

### Claim 4 (depends on 1)

The method of claim 1, wherein analyzing the set of documents further comprises:
searching the set of documents to identify grammatical parts of speech and lexica.

### Claim 5 (depends on 1)

The method of claim 1, wherein the visual elements include:
a synonym for the associated concept.

### Claim 6 (depends on 1)

The method of claim 1, wherein storing a plurality of concepts from the set of documents in a database further comprises:
creating a data structure of the plurality of concepts in the database; and
updating the data structure to indicate which documents in the set of documents include at least one of the plurality of concepts.

### Claim 7 (depends on 1)

The method of claim 1, wherein the extracted information comprises a part of a document from the set of documents marked to show the concepts.

### Claim 8 (depends on 1)

The method of claim 1, wherein the extracted information comprises a subset of the set of documents.

### Claim 9 (depends on 1)

The method of claim 1, wherein the extracted information comprises a list of documents containing at least one of the plurality of concepts.

### Claim 10 (depends on 1)

The method of claim 1, further comprising:
displaying the visual model using an entity-relationship diagram, wherein the visual elements are depicted as entities, and the relations between the visual elements are depicted as relations between the entities.

### Claim 11 (depends on 1)

The method of claim 1, further comprising:
receiving a color specified by the user for each of the visual elements; and
adding the specified colors to the visual elements.

### Claim 12

(canceled)

### Claim 13

A method for visually modeling information sought from a set of documents implemented using a computer having a processor and a display, comprising:
analyzing a set of documents using the processor;
storing a plurality of concepts from the set of documents in a database;
creating a visual model comprising visual elements corresponding to the plurality of concepts;
presenting the visual model to a user on the display;
enabling the user to add a visual element to the visual model, the visual element corresponding to a new concept;
enabling the user to add a relation between visual elements in the visual model;
generating extractors, each extractor corresponding to one of the visual elements or the relations between the visual elements in the visual model;
based on a user selection of one of the visual elements or the relations, extracting information related to the concept corresponding to the selected visual element or the selected relation from the set of documents using the corresponding extractor; and
customizing the visual model based on user input in response to the extracted information.

### Claim 14 (depends on 13)

The method of claim 13, wherein the extractors are defined by the user.

### Claim 15 (depends on 13)

The method of claim 13, wherein the extractors are assigned automatically.

### Claim 16 (depends on 13)

The method of claim 13, further comprising:
extracting updated information from the set of documents according to the customized model.

### Claim 17 (depends on 13)

The method of claim 13, wherein customizing comprises:
identifying the visual elements related to the set of documents based on a lexica module;
receiving a selection of the visual elements from the user; and
updating the visual model according to the selection.

### Claim 18 (depends on 13)

The method of claim 13, wherein customizing comprises:
associating a unique identifier selected from the group consisting of a color, a font, and a shape with one of the elements of the visual display.

### Claim 19

A method for visually modeling information sought from a set of documents implemented using a processor and a display, comprising:
analyzing a set of documents using the processor;
storing a plurality of concepts from the set of documents in a database;
creating a visual model comprising visual elements corresponding to the plurality of concepts;
presenting the visual model to a user on the display;
enabling the user to add a visual element to the visual model, the visual element corresponding to a new concept;
enabling the user to add a relation between visual elements in the visual model;
generating extractors, each extractor corresponding to one of the visual elements or the relations between the visual elements in the visual model;
based on a user selection of one of the visual elements or the relations, extracting information related to the concept corresponding to the selected visual element or the selected relation from the set of documents using the corresponding extractor;
customizing the visual model based on user input in response to the extracted information; and
exporting the customized model.

### Claim 20 (depends on 19)

The method of claim 19, further comprising:
exporting the set of documents together with the customized model.

### Claim 21 (depends on 19)

The method of claim 19, further comprising:
exporting the set of documents together with the customized model using formats that facilitate at least one of sale, exchange, and reuse of the customized model with matching sets of documents.

### Claim 22

A method for visually creating a model of information contained in a set of documents, comprising:
analyzing a set of documents using the processor;
storing a plurality of concepts from the set of documents in a database;
creating a visual model comprising visual elements corresponding to the plurality of concepts;
presenting the visual model to a user on the display;
enabling the user to add a visual element to the visual model, the visual element corresponding to a new concept;
enabling the user to add a relation between visual elements in the visual model;
generating extractors, each extractor corresponding to one of the visual elements or the relations between the visual elements in the visual model;
based on a user selection of one of the visual elements or the relations, extracting information related to the concept corresponding to the selected visual element or the selected relation from the set of documents using the corresponding extractor; and
presenting the extracted information to the user.

### Claim 23 (depends on 22)

The method of claim 22, further comprising:
receiving a color specified by the user for each of the visual elements; and
displaying the extracted information including the specified colors for each of the visual elements.

### Claim 24 (depends on 22)

The method of claim 22, further comprising:
customizing the visual model based on user input in response to the extracted information; and
extracting information from the set of documents according to the customized model.

### Claim 25 (depends on 22)

The method of claim 22, wherein the extracted information comprises a part of a document from the set of documents marked to show the concepts.

### Claim 26 (depends on 22)

The method of claim 22, wherein the extracted information comprises a subset of the set of documents.

### Claim 27 (depends on 22)

The method of claim 22, wherein the extracted information comprises a list of documents containing at least one of the plurality of concepts.

### Claim 28

A system for visually modeling information sought from a set of documents, comprising:
a processor;
an analyzing component configured in the processor to analyze a set of documents;
a database configured to store a plurality of concepts from the set of documents;
a visual model component configured in the processor to create a visual model comprising visual elements corresponding to the plurality of concepts;
a display configured to present the visual model to a user;
a graphical user interface configured to enable a user to add a visual element to the visual model, the visual element corresponding to a new concept;
the graphical user interface further configured to enable the user to add a relation between the visual elements;
a generation component configured in the processor to generate extractors, each extractor corresponding to one of the visual elements or the relations between the visual elements in the visual model; and
an extraction component configured in the processor to extract information, based on a user selection of one of the visual elements or the relations, extracting information related to the concept corresponding to the selected visual element or the selected relation from the set of documents using the corresponding extractor.

### Claim 29

A system for visually modeling information sought from a set of documents, comprising:
means for analyzing a set of documents;
means for storing a plurality of concepts from the set of documents;
means for creating a visual model comprising visual elements corresponding to the plurality of concepts;
means for presenting the visual model to a user;
means for enabling the user to add a visual element to the visual model, the visual element corresponding to a new concept;
means for enabling the user to add a relation between visual elements;
means for generating extractors, each extractor corresponding to one of the visual elements or the relations between the visual elements in the visual model; and
means for, based on a user selection of one of the visual elements or the relations, extracting information related to the concept corresponding to the selected visual element or the selected relation from the set of documents using the corresponding extractor.

### Claim 30

A computer-readable medium including instructions for performing a method for visually modeling information sought from a set of documents, the method comprising:
analyzing a set of documents;
storing a plurality of concepts from the set of documents in a database;
creating a visual model comprising visual elements corresponding to the plurality of concepts;
presenting the visual model to a user;
enabling the user to add a visual element to the visual model, the visual element corresponding to a new concept;
enabling the user to add a relation between visual elements in the visual model;
generating extractors, each extractor corresponding to one of the visual elements or the relations between the visual elements in the visual model; and
based on a user selection of one of the visual elements or or the relations, extracting information related to the concept corresponding to the selected visual element or the selected relation from the set of documents using the corresponding extractor.

### Claim 31

A method for visually modeling information sought from a set of documents implemented using a computer having a processor and a display, comprising:
analyzing a set of documents using the processor;
storing a plurality of concepts from the set of documents in a database;
creating a visual model comprising visual elements corresponding to the plurality of concepts;
presenting the visual model to a user on the display;
enabling the user to add a visual element to the visual model, the visual element corresponding to a new concept;
enabling the user to add a relation between visual elements in the visual model;
generating extractors, each extractor corresponding to one of the visual elements or the relations between the visual elements in the visual model;
receiving a series of user inputs to extract information from the set of documents using at least two visual elements in the visual model and the corresponding extractors;
receiving a new concept of interest to the user;
updating the visual model to include a visual element that represents the new concept; and
automatically assigning a new extractor to the visual element of the new concept based on the series of user inputs.

### Claim 32 (depends on 31)

The method of claim 31, wherein the new concept is created by the user after extracting information from the set of documents.

### Claim 33 (depends on 31)

The method of claim 31, further comprising:
assigning an extractor to an existing concept based on the series of user inputs.

### Claim 34 (depends on 31)

The method of claim 31, wherein the series of user inputs include a user selection of text to retrieve from the set of documents.

### Claim 35 (depends on 31)

The method of claim 31, further comprising:
automatically updating a database based on the new extractor.

### Claim 36

A method for processing information extracted from a model implemented using a computer having a processor and a display, comprising:
analyzing a set of documents using the processor;
storing a plurality of concepts from the set of documents in a database;
creating a visual model comprising visual elements corresponding to the plurality of concepts;
presenting the visual model to a user on the display;
enabling the user to add a visual element to the visual model, the visual element corresponding to a new concept;
enabling the user to add a relation between visual elements in the visual model;
generating extractors, each extractor corresponding to one of the visual elements or the relations between the visual elements in the visual model;
based on a user selection of one of the visual elements or the relations, extracting information related to the concept corresponding to the selected visual element or the selected relation from the set of documents using the first extractor; and
processing the extracted information to create post-extraction information.

### Claim 37 (depends on 36)

The method of claim 36, wherein processing the extracted information to create post-extraction information includes:
aggregating the extracted information into one of: a document, a graph, a table, a map, a spreadsheet, and a chart.

### Claim 38 (depends on 36)

The method of claim 36, wherein processing the extracted information to create post-extraction information includes:
receiving a user selection of categories for the extracted information.

### Claim 39 (depends on 36)

The method of claim 36, wherein processing the extracted information to create post-extraction information includes:
assigning a status to a document in the set of documents.

### Claim 40 (depends on 1)

The method of claim 1, further comprising:
displaying the model using one of: a document, a graph, a table, a map, a spreadsheet, and a chart.

### Claim 41 (depends on 1)

The method of claim 1, further comprising:
modifying a document in the set of documents.
