Granted Patent B2

US 12,547,823 · App. 17/485,056 · Granted Feb 10, 2026

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

Assignee: Google LLC

G06F40/18G06F16/24522G06N5/02

Abstract

Claims (41)

1 . A method comprising:

generating, by a processing device and based on one or more natural language queries and one or more contextual items defined within a document, at least a portion of the document having a tabular structure comprising a plurality of cells arranged in a plurality of columns and a plurality of rows, wherein a natural language query of the one or more natural language queries is associated with at least one column of the plurality of columns, wherein a contextual item of the one or more contextual items comprises at least one row header of at least one row of the plurality of rows, wherein generating at least the portion of the document based on the one or more natural language queries and the one or more contextual items comprises defining a set of update controls for automatically updating content in at least one cell of the plurality of cells using at least one external data source comprising a knowledge graph, and wherein defining the set of update controls comprises determining a recommended update frequency, corresponding to an amount of time between updates of the content in the at least one cell, based on an analysis of at least one frequency of change of data within the at least one external data source;

detecting, by the processing device and based on the set of update controls, an event triggering an automated update of the content in the at least one cell; and

responsive to detecting the event:

obtaining, by the processing device, data from the at least one external data source comprising the knowledge graph in accordance with the set of update controls and based on a respective natural language query of the one or more natural language queries and a respective contextual item comprising respective at least one row header of the at least one cell; and

causing, by the processing device, the content in the at least one cell to be updated based on the data from the at least one external data source comprising the knowledge graph.

2 . The method of claim 1 , wherein the recommended update frequency is a default update frequency.

3 . The method of claim 1 , further comprising:

receiving, by the processing device via a user interface, user input specifying a user-defined update frequency for the at least one cell, wherein the user input causes the user interface to be modified to present the user-defined update frequency in association with the at least one cell; and

modifying, by the processing device, the set of update controls to include the user-defined update frequency for the at least one cell.

4 . The method of claim 1 , wherein obtaining the data from the at least one external data source further comprises:

determining that the amount of time has elapsed from a most recent update to the content maintained in the at least one cell; and

in response to determining that the amount of time has elapsed from the most recent update, retrieving the data from the at least one external data source.

5 . The method of claim 1 , wherein obtaining the data from the at least one external data source further comprises receiving the data from a subscriber associated with a portion of the at least one external data source.

6 . A system comprising:

a memory device; and

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

generating, based on one or more natural language queries and one or more contextual items defined within a document, at least a portion of the document having a tabular structure comprising a plurality of cells arranged in a plurality of columns and a plurality of rows, wherein a natural language query of the one or more natural language queries is associated with at least one column of the plurality of columns, wherein a contextual item of the one or more contextual items comprises at least one row header of at least one row of the plurality of rows, wherein generating at least the portion of the document based on the one or more natural language queries and the one or more contextual items comprises defining a set of update controls for automatically updating content in at least one cell of the plurality of cells using at least one external data source comprising a knowledge graph, and wherein defining the set of update controls comprises determining a recommended update frequency, corresponding to an amount of time between updates of the content in the at least one cell, based on an analysis of at least one frequency of change of data within the at least one external data source;

detecting, based on the set of update controls, an event triggering an automated update of the content in the at least one cell; and

responsive to detecting the event:

obtaining data from the at least one external data source comprising the knowledge graph in accordance with the set of update controls and based on a respective natural language query of the one or more natural language queries and a respective contextual item comprising respective at least one row header of the at least one cell; and

causing the content in the at least one cell to be updated based on the data from the at least one external data source comprising the knowledge graph.

7 . The system of claim 6 , wherein the recommended update frequency is a default update frequency.

8 . The system of claim 6 , wherein the operations further comprise:

receiving, via a user interface, user input specifying a user-defined update frequency for the at least one cell, wherein the user input causes the user interface to be modified to present the user-defined update frequency in association with the at least one cell; and

modifying the set of update controls stored in a data store to include the user-defined update frequency for the at least one cell.

9 . The system of claim 6 , wherein obtaining the data from the at least one external data source further comprises:

determining that the amount of time has elapsed from a most recent update to the content maintained in the at least one cell; and

in response to determining that the amount of time has elapsed from the most recent update, retrieving the data from the at least one external data source.

10 . The system of claim 6 , wherein obtaining the data from the at least one external data source further comprises receiving the data from a subscriber attached to a portion of the at least one external data source.

11 . A non-transitory computer readable storage medium comprising instructions for a server that, when executed by a processing device, cause the processing device to perform operations comprising:

generating, based on one or more natural language queries and one or more contextual items defined within a document, at least a portion of the document having a tabular structure comprising a plurality of cells arranged in a plurality of columns and a plurality of rows, wherein a natural language query of the one or more natural language queries is associated with at least one column of the plurality of columns, wherein a contextual item of the one or more contextual items comprises at least one row header of at least one row of the plurality of rows, wherein generating at least the portion of the document based on the one or more natural language queries and the one or more contextual items comprises defining a set of update controls for automatically updating content in at least one cell of the plurality of cells using at least one external data source comprising a knowledge graph, and wherein defining the set of update controls comprises determining a recommended update frequency, corresponding to an amount of time between updates of the content in the at least one cell, based on an analysis of at least one frequency of change of data within the at least one external data source;

detecting, based on the set of update controls, an event triggering an automated update of the content in the at least one cell; and

responsive to detecting the event:

obtaining data from the at least one external data source comprising the knowledge graph in accordance with the set of update controls and based on a respective natural language query of the one or more natural language queries and a respective contextual item comprising respective at least one row header of the at least one cell; and

causing the content in the at least one cell to be updated based on the data from the at least one external data source comprising the knowledge graph.

12 . The non-transitory computer readable storage medium of claim 11 , wherein the recommended update frequency is a default update frequency.

13 . The non-transitory computer readable storage medium of claim 11 , wherein the operations further comprise:

receiving, via a user interface, user input specifying a user-defined update frequency for the at least one cell, wherein the user input causes the user interface to be modified to present the user-defined update frequency in association with the at least one cell; and

modifying the set of update controls stored in a data store to include the user-defined update frequency for the at least one cell.

14 . The non-transitory computer readable storage medium of claim 11 , wherein obtaining the data from the at least one external data source further comprises receiving the data from a subscriber attached to a portion of the at least one external data source.

Assignments (1)

Continuity (1)

References Cited (88)