Location-based mode(s) for biasing provisioning of content when an automated assistant is responding to condensed natural language inputs

Patent metadata

Field	Value
Publication number	US-11568146-B2
Application number	US-201916605838-A
Country	US
Kind code	B2
Filing date	Sep 10, 2019
Priority date	Sep 10, 2019
Publication date	Jan 31, 2023
Grant date	Jan 31, 2023

Abstract

Implementations set forth herein relate to an automated assistant that operates according to a variety of different location-based biasing modes for rendering responsive content for a user and/or proactively suggesting content for the user. The user can provide condensed spoken utterances to the automated assistant, when the automated assistant is operating according to one or more location-based biasing modes, but nonetheless receive accurate responsive outputs from the automated assistant. A responsive output generated by biasing toward a subset of location characteristic data that has been prioritized over other subsets of location characteristic data. The biasing allows the automated assistant to compensate for any details that may be missing from a spoken utterance, but allows the user to provide shorter spoken utterances, thereby reducing an amount of language processing when processing inputs from the user.

First claim

What is claimed is:

1. A method implemented by one or more processors, the method comprising:
determining, based on data accessible via a portable computing device, that a user is within an area that includes a location of interest,
wherein the location of interest is associated with location characteristic data that is accessible via one or more applications of the portable computing device,
wherein the location characteristic data includes particular content characterizing features of the area and the location of interest, and
wherein the portable computing device is operable in a first location-based biasing mode and a second location-based biasing mode;

receiving, via an automated assistant of the portable computing device, a spoken utterance from the user,
wherein the spoken utterance includes natural language content corresponding to a request for the automated assistant to provide information about the location of interest;

when the portable computing device is operating in the first location-based biasing mode:
generating, in response to receiving the spoken utterance from the user, responsive data by biasing, according to a first degree of biasing, a data selection from the location characteristic data, wherein biasing according to the first degree of biasing includes refraining from modifying the request, and
rendering, via the automated assistant of the portable computing device, a responsive output that is based on the responsive data; and

when the portable computing device is operating in the second location-based biasing mode:
generating, in response to receiving the spoken utterance from the user, other responsive data by biasing, according to a second degree of biasing that corresponds to a greater degree of biasing than the first degree of biasing, another data selection from the location characteristic data, wherein biasing according to the second degree of biasing includes modifying the request by adding an alias having a defined relationship to the area, and
rendering, via the automated assistant of the portable computing device, another responsive output that is based on the other responsive data.

2. The method of claim 1 , wherein biasing the other data selection from the location characteristic data according to the second degree of biasing includes modifying the request by replacing a pronoun of the request with an alias having a defined relationship to the location of interest.

3. The method of claim 1 , wherein biasing the other data selection from the location characteristic data according to the second degree of biasing includes restricting the data selection to a particular subset of the location characteristic data.

4. The method of claim 3 , wherein biasing the data selection from the location characteristic data according to the first degree of biasing includes promoting a score assigned to the particular content, from the location characteristic data, that satisfies the request, and wherein generating the other responsive data is based on the scoring.

5. The method of claim 1 , wherein biasing the data selection from the location characteristic data according to the first degree of biasing includes promoting scores, to a first extent, for any of the particular content that satisfies the request.

6. The method of claim 5 , wherein biasing the other data selection from the location characteristic data according to the second degree of biasing includes promoting scores, to a second extent that is of greater magnitude than the first extent, for any of the particular content that matches the request.

7. The method of claim 1 , further comprising:
responsive to determining that the user is within the area that includes the location of interest:
causing the portable computing device to render a prompt that solicits whether the user desires the automated assistant to enter second location-based biasing mode; and
causing the computing device to operate according to the second location-based biasing mode responsive to receiving an affirmative user input responsive to the prompt.

8. The method of claim 1 ,
wherein biasing the data selection from the location characteristic data according to the first degree of biasing includes biasing speech to text processing toward a first set of terms that are related to the location of interest without biasing toward a second set of terms that are also related to the location of interest, and
wherein biasing the other data selection from the location characteristic data according to the second degree of biasing includes biasing speech to text processing toward the first set of terms and toward the second set of terms.

9. The method of claim 1 , further comprising:
determining, based on determining that the user is within the area that includes the location of interest, whether the area or the location of interest was identified in assistant data that was generated during an interaction between the automated assistant and the user prior to the user being located within the area that includes the location of interest,
wherein the computing device operates in the first location-based biasing mode when the area is identified in the assistant data, and the computing device operates in the second location-based biasing mode when the location of interest is identified in the assistant data.

10. A method implemented by one or more processors, the method comprising:
determining, based on data accessible via a portable computing device, that a user is geographically located within an area that includes a location of interest,
wherein the location of interest is characterized by location characteristic data that is accessible via one or more applications of the portable computing device;

receiving, via an automated assistant of the portable computing device, a spoken utterance from the user,
wherein the spoken utterance includes natural language content corresponding to a request for the automated assistant to provide information about the location of interest;

assigning a score for each subset of location characteristic data, of subsets of location characteristic data, according to an extent to which each subset of location characteristic data satisfies a request characterized by the spoken utterance, and
when a geographic location of the user satisfies a geographic criteria associated with the location of interest:
identifying a particular score assigned to a subset of the location characteristic data that characterizes the location of interest, and
causing the particular score assigned to the subset of the location characteristic data to be modified, at least based on the subset of location characteristic data characterizing the location of interest;

when the geographic location of the user does not satisfy the geographic criteria associated with the location of interest:
identifying another particular score assigned to another subset of the location characteristic data that characterizes the area, and
causing the other particular score assigned to the other subset of the location characteristic data to be modified, at least based on the other subset of location characteristic data characterizing the area; and

causing, in response to receiving the spoken utterance from the user, the automated assistant to render a responsive output via the portable computing device and based on a particular subset of the location characteristic data having an assigned score that is prioritized over other available subsets of the location characteristic data.

11. The method of claim 10 , further comprising:
when the geographic location of the user satisfies a geographic criteria associated with the location of interest:

Assignees

• Google Llc

Inventors

• Stovezky Sharon
• Adan Yariv
• Voroneanu Radu
• Behzadi Behshad
• Koerkamp Ragnar Groot
• Nowak-Przygodzki Marcin

Classifications

• G06F40/295 Primary

  Named entity recognition · CPC title

• G06F16/9537

  Spatial or temporal dependent retrieval, e.g. spatiotemporal queries · CPC title