Granted Patent B2

US 12,493,738 · App. 18/732,556 · Granted Dec 9, 2025

Inventors: Andrew J. Lavery (Austin, TX); Earl J. Wagner (Chicago, IL); Matthew Albright (Montclair, NJ)

Assignee: Google LLC

G06F40/18G06F16/9535G06N5/02

Abstract

Claims (71)

1 . A method comprising:

receiving, by a processing device from a client device associated with a user, a natural language query corresponding to a request to populate, for the user, a personalized document having a tabular structure;

determining, by the processing device, a set of attribute categories pertaining to the personalized document, the set of attribute categories comprising a first attribute category corresponding to one or more cells populated with one or more first attributes;

identifying, by the processing device, at least one external data source, the at least one external data source comprising at least one subjective data source related to the user, wherein the at least one external data source comprises a personalized knowledge graph corresponding to the user;

retrieving, by the processing device from the at least one external data source and using a semantic index representation associated with the personalized knowledge graph, a plurality of data items indicative of the set of attribute categories; and

populating, by the processing device, each cell of a plurality of cells of the personalized document with a respective data item of the plurality of data items.

2 . The method of claim 1 , wherein the at least one external data source further comprises an objective data source, and wherein retrieving the plurality of data items from the at least one external data source comprises:

retrieving, from the at least one subjective data source, one or more data items corresponding to the one or more first attributes, wherein the at least one subjective data source has content relevant to the user or a user group associated with the user; and

retrieving, from the objective data source, one or more data items corresponding to one or more second attributes corresponding to a second attribute category.

3 . The method of claim 1 , further comprising:

identifying, by the processing device, a change in user activity; and

generating, by the processing device, a new version of the personalized document, wherein the new version includes content reflecting the change in the user activity, the content being relevant to the user or a user group associated with the user.

4 . The method of claim 1 , further comprising:

retrieving, by the processing device, one or more additional data items from the at least one external data source; and

updating, by the processing device, the personalized document based on the one or more additional data items.

5 . The method of claim 4 , wherein retrieving the one or more additional data items further comprises:

receiving an additional natural language query; and

retrieving the one or more additional data items in response to receiving the additional natural language query.

6 . The method of claim 4 , wherein retrieving the one or more additional data items further comprises:

identifying a user interest in newly relevant data for the personalized document;

determining that the newly relevant data has been added to the at least one external data source; and

retrieving the newly relevant data from the at least one external data source.

7 . A system comprising:

a memory device; and

a processing device coupled to the memory device, the processing device to perform operations comprising:

receiving, from a client device associated with a user, a natural language query corresponding to a request to populate, for the user, a personalized document having a tabular structure;

determining a set of attribute categories pertaining to the personalized document, the set of attribute categories comprising a first attribute category corresponding to one or more cells populated with one or more first attributes;

identifying at least one external data source, the at least one external data source comprising at least one subjective data source related to the user, wherein the at least one external data source comprises a personalized knowledge graph corresponding to the user;

retrieving, from the at least one external data source and using a semantic index representation associated with the personalized knowledge graph, a plurality of data items indicative of the set of attribute categories; and

populating each cell of a plurality of cells of the personalized document with a respective data item of the plurality of data items.

8 . The system of claim 7 , wherein the at least one external data source further comprises an objective data source, and wherein retrieving the plurality of data items from the at least one external data source comprises:

retrieving, from the at least one subjective data source, one or more data items corresponding to the one or more first attributes, wherein the at least one subjective data source has content relevant to the user or a user group associated with the user; and

retrieving, from the objective data source, one or more data items corresponding to one or more second attributes corresponding to a second attribute category.

9 . The system of claim 7 , wherein the operations further comprise:

identifying a change in user activity; and

generating a new version of the personalized document, wherein the new version includes content reflecting the change in the user activity, the content being relevant to the user or a user group associated with the user.

10 . The system of claim 7 , wherein the operations further comprise:

retrieving one or more additional data items from the at least one external data source; and

updating the personalized document based on the one or more additional data items.

11 . The system of claim 10 , wherein retrieving the one or more additional data items further comprises:

receiving an additional natural language query; and

retrieving the one or more additional data items in response to receiving the additional natural language query.

12 . The system of claim 10 , wherein retrieving the one or more additional data items further comprises:

identifying a user interest in newly relevant data for the personalized document;

determining that the newly relevant data has been added to the at least one external data source; and

retrieving the newly relevant data from the at least one external data source.

13 . A system comprising:

a memory device; and

a processing device coupled to the memory device, the processing device to perform operations comprising:

receiving a plurality of natural language queries from a user;

determining that each natural language query of the plurality of natural language queries is associated with a similar topic;

sending a recommendation to the user to populate a personalized document having a tabular structure based on the plurality of natural language queries; and

in response to receiving an indication from the user to populate the personalized document, populating each cell of a plurality of cells of the document with a respective data item of a set of data items retrieved from at least one external data source comprising a subjective data source comprising a personalized knowledge graph corresponding to the user and a semantic index, wherein the set of data items corresponds to a set of attribute categories pertaining to the document, and wherein the set of attribute categories comprises a first attribute category corresponding to one or more cells populated with one or more first attributes.

14 . The system of claim 13 , wherein populating the document comprises converting the natural language query into a semantic index representation for accessing the at least one external data source using the semantic index.

15 . The system of claim 13 , wherein populating the personalized document comprises:

identifying the set of attribute categories pertaining to the personalized document; and

retrieving, from the at least one external data source, the set of data items.

16 . The system of claim 13 , wherein the at least one external data source further comprises an objective data source.

17 . The system of claim 16 , wherein retrieving the set of data items from the at least one external data source comprises:

retrieving, from the at least one subjective data source, one or more data items corresponding to the one or more first attributes, wherein the at least one subjective data source has content relevant to the user or a user group associated with the user; and

retrieving, from the objective data source, one or more data items corresponding to one or more second attributes corresponding to a second attribute category.

18 . The system of claim 13 , wherein the operations further comprise:

retrieving one or more additional data items from the at least one external data source; and

updating the personalized document based on the one or more additional data items.

19 . The system of claim 18 , wherein retrieving the one or more additional data items further comprises:

receiving an additional natural language query; and

retrieving the one or more additional data items in response to receiving the additional natural language query.

20 . The system of claim 18 , wherein retrieving the one or more additional data items further comprises:

identifying a user interest in newly relevant data for the personalized document;

determining that the newly relevant data has been added to the at least one external data source; and

retrieving the newly relevant data from the at least one external data source.

Assignments (1)

Continuity (2)

References Cited (80)