# US 10,372,716 B2 · Automatic discovery and presentation of topic summaries related to a selection of text

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

- Number: US 10,372,716 B2
- Document ID: US10372716B2
- Status: Granted
- Kind: B2
- Application number: 14/622,072
- Filed: 2015-02-13
- Published: 2015-09-24
- Granted: 2019-08-06
- Earliest claimed: 2014-03-18
- Assignees: International Business Machines Corporation
- Applicants: International Business Machines Corporation
- Inventors: Patrick W. Fink; Philip E. Parker
- Web page: https://patentgrep.com/patent/US10372716B2

## CPC

- G06F 16/24578: {using ranking}
- G06F 40/295: Named entity recognition
- G06F 40/30: Semantic analysis
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)

## Abstract

Topic summaries related to a selection of text in an electronic document may be generated and presented. A topic summary application receives the user-selected text and identifies entities in the text using natural language processing. Using natural language processing, the summary application also identifies related entities and associated text phrases in a remaining portion of the electronic document. The remaining portion may be a portion of the document that precedes the user-selected text, so that a summary generated therefrom may be used to refresh the memory of the user while not revealing information that the user has not yet encountered. In addition, the summary application determines semantically important text phrases using text analytics and generates a summary, presented to the user in a pop-up window, of most frequently correlated related entities along with text phrases that are semantically important.

## Claims

### Claim 1

A computer implemented method for processing text, the method comprising:
receiving a selected portion of text in a document;
determining at least a first entity referenced in the selected portion;
evaluating a remaining portion of text excluding the selected portion in the document and one or more other documents accessible via links in the document to identify text content relating to and excluding the first entity in the document and the one or more other documents, wherein the identified text content comprises second entities within a distance of the first entity in the document and the one or more other documents;
generating, from the identified text content relating to and excluding the first entity, a summary of the first entity, wherein the summary of the first entity comprises a plurality of truncated phrases generated from the identified text content selected based, at least in part, on a history of previous selections of text; and
displaying the summary on a display screen by generating a popup window including the summary.

### Claim 2 (depends on 1)

The method of claim 1, wherein generating the summary of the first entity includes:
identifying entities related to the first entity and associated text phrases in the remaining portion of text in the document, and
ranking the associated text phrases in the remaining portion of text in the document based on semantic meaning, and
wherein the summary includes one or more of the related entities and associated text phrases chosen based on the ranking.

### Claim 3 (depends on 2)

The method of claim 2, wherein the related entities are identified through natural language processing.

### Claim 4 (depends on 3)

The method of claim 3, wherein the natural language processing removes filler and statistically common words in sentences which include the identified entity, and one or more remaining clauses in the sentences are identified as the related entities.

### Claim 5 (depends on 2)

The method of claim 2, wherein ranking the associated text phrases is performed using text analytics.

### Claim 6 (depends on 5)

The method of claim 5, wherein the ranking of the associated text phrases is based on number of times the associated text phrases or similar phrases appear in the document.

### Claim 7 (depends on 2)

The method of claim 2, wherein the one or more related entities included in the summary are frequently correlated entities determined based on number of times the one or more related entities occur in same sentences as the identified entity.

### Claim 8 (depends on 1)

The method of claim 1, wherein the remaining portion comprises text content of the document preceding the selected portion of text in the document.

### Claim 9 (depends on 1)

The method of claim 1, wherein the summary is displayed in a pop-up user interface.

### Claim 10 (depends on 1)

The method of claim 1, wherein the summary is generated based on a prior usage history of a user.