Granted Patent B2

US 12,602,546 · App. 18/081,410 · Granted Apr 14, 2026

Inventors: Mridu Baldevraj Narang (Redmond, WA); Xuenan Guo (Bellevue, WA); Shubham Tripathi (Redmond, WA); Guihong Cao (Bellevue, WA); Zicheng Huang (Bothell, WA); Xiaodong Fan (Bellevue, WA)

Assignee: Microsoft Technology Licensing, LLC

G06F40/279G06F40/12G06N3/08

Abstract

Claims (67)

1 . A method, comprising:

receiving a uniform resource locator (URL) of a webpage presented on a browser;

determining that a selection threshold is satisfied for the webpage based on a webpage title of the webpage and content of the webpage, wherein satisfying the selection threshold results in providing a summarization of content from the webpage;

identifying, using a machine learning model, webpage key points that summarize content from the webpage, wherein the webpage key points are obtained from the webpage;

analyzing a summary length of the webpage key points and the summarized content from the webpage;

causing the webpage key points to be presented adjacent to the webpage in a side pane of the browser in near real time of receiving the URL of the webpage in response to determining the summary length and the summarized content provides a value that is above a presentation threshold, wherein the presentation threshold controls whether the webpage key points are sent for presentation on the browser; and

causing a browser notification to be presented indicating that the webpage key points are unavailable in response to determining that the summary length and the summarized content provides a value that is below the presentation threshold.

2 . The method of claim 1 , further comprising:

obtaining webpage sentences for the webpage;

mapping the webpage sentences to a distributed representation;

providing contextual interactions to the webpage sentences; and

predicting an importance of sentence spans of the webpage sentences.

3 . The method of claim 2 , wherein identifying the webpage key points further comprises:

selecting sentence spans based on a ranking of the sentence spans; and

identifying the selected sentence spans as the webpage key points.

4 . The method of claim 2 , wherein mapping the webpage sentences to the distributed representation further comprises:

generating sentence embeddings for the webpage sentences that are independent of a context of the webpage.

5 . The method of claim 4 , wherein providing the contextual interactions to the webpage sentences further comprises:

fusing context information to the sentence embeddings; and

generating title-aware sentence embeddings for the webpage.

6 . The method of claim 5 , wherein predicting the importance of the sentence spans of the webpage sentences further comprises:

generating proposed sentence spans using the title-aware sentence embeddings, wherein the proposed sentence spans provide a summary of content of the webpage.

7 . The method of claim 6 , wherein ranking the sentence spans of the webpage sentences further comprises:

ranking the proposed sentence spans in descending order based on a confidence score of a summary provided by the proposed sentence spans; and

removing overlapping proposed sentence spans.

8 . The method of claim 1 , further comprising:

selecting terms in the webpage key points; and

sending the terms and the webpage key points to be presented in the side pane of the browser, wherein a highlight is applied to the terms that visually distinguishes the terms in the webpage key points.

9 . The method of claim 1 , further comprising:

comparing the webpage key points to the presentation threshold; and

sending, in response to the webpage key points being equal to the presentation threshold or exceeding the presentation threshold, the webpage key points for presentation in the side pane of the browser.

10 . The method of claim 9 , wherein the presentation threshold identifies a confidence level in a summary provided by the webpage key points of the webpage.

11 . The method of claim 9 , wherein the selection threshold controls whether the webpage key points are provided for the webpage.

12 . A device, comprising:

a memory to store data and instructions; and

a processor operable to communicate with the memory, wherein the processor is operable to:

receive a uniform resource locator (URL) of a webpage presented on a browser;

determine that selection threshold is satisfied for the webpage based on a webpage title of the webpage and content of the webpage, wherein satisfying the selection threshold results in providing a summarization of content from the webpage;

analyze a summary length of the webpage key points and the summarized content from the webpage;

identify webpage key points that summarize content from the webpage in response to the selection threshold being satisfied for the webpage, wherein the webpage key points are obtained from the webpage;

cause the webpage key points to be presented in a side pane of a browser nearby the webpage in near real time of receiving the URL of the webpage in response to determining the summary length and the summarized content provides a value that is above a presentation threshold, wherein the presentation threshold controls whether the webpage key points are sent for presentation on the browser; and

cause a browser notification to be presented indicating that the webpage key points are unavailable in response to determining that the summary length and the summarized content provides a value that is below the presentation threshold.

13 . The device of claim 12 , wherein the processor is further operable to use a plurality of machine learning models to identify the webpage key points.

14 . The device of claim 12 , wherein the processor is further operable to identify webpage key points for the webpage by:

obtaining, from a datastore, sentence embeddings for the webpage and context information for the sentence embeddings;

generating title-aware sentence embeddings for the webpage using the sentence embeddings and the context information;

generating proposed sentence spans using the title-aware sentence embeddings, wherein the proposed sentence spans provide a summary of content of the webpage;

selecting sentence spans based on a ranking of the proposed sentence spans; and

identifying the selected sentence spans as the webpage key points.

15 . The device of claim 12 , wherein the processor is further operable to:

select terms in the webpage key points; and

send the terms and the webpage key points for presentation in the side pane of the browser, wherein a highlight is applied to the terms that visually distinguishes the terms in the webpage key points.

16 . The device of claim 12 , wherein the processor is further operable to:

compare the webpage key points to the presentation threshold; and

send, in response to the webpage key points being equal to the presentation threshold or exceeding the presentation threshold, the webpage key points for presentation in the side pane of the browser.

17 . A device, comprising:

a memory to store data and instructions; and

a processor operable to communicate with the memory, wherein the processor is operable to:

present, on a browser, a webpage and a side pane with an icon adjacent to the webpage;

send, by the browser, in response to a selection of the icon, a uniform resource locator (URL) of the webpage to a summary model with a request for webpage key points;

receive, from the summary model based on the URL of the webpage and the webpage satisfying a selection threshold, the webpage key points for the webpage, wherein the webpage key points are obtained from content of the webpage and summarize the content of the webpage;

present, in the side pane of the browser, the webpage key points in near real time in response to a selection of the icon in response to a determination by the summary model that the summary length and the summarized content provides a value that is above a presentation threshold, wherein the presentation threshold controls whether the webpage key points are sent for presentation on the browser; and

present a browser notification indicating that the webpage key points are unavailable in response to the summary model determining that the summary length and the summarized content provides a value that is below the presentation threshold.

18 . The device of claim 17 , wherein the processor is further operable to:

provide a highlight of terms in the webpage key points that visually distinguishes the terms.

19 . The device of claim 17 , wherein the summary model is a plurality of machine learning models that analyze webpage sentences of the webpage and a webpage title to determine the webpage key points.

20 . The device of claim 17 , wherein the webpage key points are sentences or phrases obtained from different portions of the webpage.

Assignments (1)

Continuity (1)

References Cited (59)