Proactive query and content suggestion with generative model generated question and answer

Patent metadata

Field	Value
Publication number	US-12488057-B2
Application number	US-202418785365-A
Country	US
Kind code	B2
Filing date	Jul 26, 2024
Priority date	Sep 20, 2023
Publication date	Dec 2, 2025
Grant date	Dec 2, 2025

Abstract

Systems and methods for proactive query and content suggestion can include obtaining web data, determining a change event occurred, and generating a query and content suggestion. Generating the query and content suggestion can include processing data descriptive of the change event with a generative model to generate one or more model-generated query suggestions. One or more web resources can be obtained then processed to generate a change event summary. The one or more query suggestions and the change event summary can then be provided for display.

First claim

What is claimed is:

1 . A computer-implemented method for proactive content suggestion newsfeed generation, the method comprising:
obtaining, by a computing system comprising one or more processors, web data, wherein the web data is descriptive of content provided by a corpus of web resources; processing, by the computing system, the web data to determine a plurality of change events occurred, wherein the plurality of change events comprise a plurality of updates associated with a plurality of topics; processing, by the computing system, data descriptive of the plurality of change events with a language model to generate a plurality of query suggestions, wherein the language model comprises a generative model, and wherein each query suggestion is associated with a respective change event of the plurality of change events; for each respective query suggestion of the plurality of query suggestions:
determining, by the computing system, one or more web resources associated with the respective query suggestion, wherein the one or more web resources are associated with one or more topics of the respective change event of the plurality of change events;
generating, by the computing system, one or more graphical cards based on the one or more web resources;
generating, by the computing system, a respective pair comprising the respective query suggestion and the one or more graphical cards; and
generating, by the computing system, a newsfeed interface based on a plurality of respective pairs, wherein the newsfeed interface comprises a user interface that provides the plurality of query suggestions adjacent to respective graphical cards associated with the plurality of change events.

2 . The method of claim 1 , further comprising:
providing, by the computing system, the newsfeed interface for display.

3 . The method of claim 1 , wherein the one or more graphical cards are one or more discover feed cards, and wherein the one or more graphical cards are descriptive of the one or more web resources.

4 . The method of claim 1 , wherein the one or more graphical cards comprise one or more model-generated summaries that were generated to be responsive to the respective query suggestion based on processing one or more web resources.

5 . The method of claim 1 , wherein the one or more graphical cards comprise one or more content items from the one or more web resources.

6 . The method of claim 1 , wherein each change event of the plurality of change events are determined based on:
determining an influx in articles associated with a respective topic.

7 . The method of claim 1 , wherein each change event of the plurality of change events are determined based on:
determining an influx in social media posts associated with a respective topic.

8 . The method of claim 1 , wherein processing, by the computing system, the web data to determine the plurality of change events occurred comprises:
determining a plurality of web page updates associated with one or more topics.

9 . The method of claim 1 , wherein processing, by the computing system, the web data to determine the plurality of change events occurred comprises:
determining a plurality of web page generation instances associated with one or more topics.

10 . The method of claim 1 , wherein the language model comprises a machine-learned generative model trained to generate natural language data tailored to emulate a vocabulary, tone, and style of a particular user.

11 . A computing system for proactive content suggestion newsfeed generation, the system comprising:
one or more processors; and one or more non-transitory computer-readable media that collectively store instructions that, when executed by the one or more processors, cause the computing system to perform operations, the operations comprising:
obtaining web data, wherein the web data is descriptive of content provided by a corpus of web resources;
processing the web data to determine a plurality of change events occurred, wherein the plurality of change events comprise a plurality of updates associated with a plurality of topics;
processing data descriptive of the plurality of change events with a language model to generate a plurality of query suggestions, wherein the language model comprises a generative model, and wherein each query suggestion is associated with a respective change event of the plurality of change events;
for each respective query suggestion of the plurality of query suggestions:
determining one or more web resources associated with the respective query suggestion, wherein the one or more web resources are associated with one or more topics of the respective change event of the plurality of change events;
generating one or more graphical cards based on the one or more web resources;
generating a respective pair comprising the respective query suggestion and the one or more graphical cards; and

generating a newsfeed interface based on a plurality of respective pairs, wherein the newsfeed interface comprises a user interface that provides the plurality of query suggestions adjacent to respective graphical cards associated with the plurality of change events.

12 . The system of claim 11 , wherein the generative model was trained to generate query suggestions that are formatted in natural language such that a user can easily understand the topic and direction of the plurality of query suggestions.

13 . The system of claim 11 , wherein the operations further comprise:
for each respective query suggestion of the plurality of query suggestions: processing the one or more web resources with the language model to generate a change event summary.

14 . The system of claim 13 , wherein the one or more graphical cards comprise the change event summary.

15 . The system of claim 13 , wherein the operations further comprise:
providing the change event summary for display with the respective pair.

16 . The system of claim 13 , wherein the change event summary is descriptive of a change associated with one or more topics of the plurality of topics as outlined by the one or more web resources.

17 . One or more non-transitory computer-readable media that collectively store instructions that, when executed by one or more computing devices, cause the one or more computing devices to perform operations, the operations comprising:
obtaining web data, wherein the web data is descriptive of content provided by a corpus of web resources; processing the web data to determine a plurality of change events occurred, wherein the plurality of change events comprise a plurality of updates associated with a plurality of topics; processing data descriptive of the plurality of change events with a language model to generate a plurality of query suggestions, wherein the language model comprises a generative model, and wherein each query suggestion is associated with a respective change event of the plurality of change events; for each respective query suggestion of the plurality of query suggestions:
determining one or more web resources associated with the respective query suggestion, wherein the one or more web resources are associated with one or more topics of the respective change event of the plurality of change events;
generating one or more graphical cards based on the one or more web resources;
generating a respective pair comprising the respective query suggestion and the one or more graphical cards; and
generating a newsfeed interface based on a plurality of respective pairs, wherein the newsfeed interface comp

Assignees

• Google Llc

Inventors

• Badr Ibrahim
• Guo Yunsong
• Mansuri Imran R

Classifications

• G06F40/20

  Natural language analysis (semantic analysis of natural language G06F40/30) · CPC title

• G06N3/0475

  Generative networks · CPC title

• G06F16/345

  Summarisation for human users · CPC title

• G06F16/957

  Browsing optimisation, e.g. caching or content distillation · CPC title

• G06F16/9538

  Presentation of query results · CPC title