# US 2026/0087071 A1 · Image Query Analysis

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2026/0087071 A1
- Document ID: US20260087071A1
- Status: Published application
- Kind: A1
- Application number: 19/198,782
- Filed: 2025-05-05
- Published: 2026-03-26
- Earliest claimed: 2020-08-10
- Assignees: Google Inc.
- Applicants: Google LLC
- Inventors: Gokhan H. Bakir; Marcin Bortnik; Malte Nuhn; Kavin Karthik Ilangovan
- Web page: https://patentgrep.com/patent/US20260087071A1

## CPC

- G06F 16/583: using metadata automatically derived from the content
- G06F 16/5866: {using information manually generated, e.g. tags, keywords, comments, manually generated location and time information}
- G06F 16/90332: {Natural language query formulation or dialogue systems}
- G06F 16/9038: Presentation of query results
- G06F 18/24: Classification techniques
- G06T 7/97: {Determining parameters from multiple pictures (depth or shape recovery from multiple images G06T7/55; stereo camera calibration G06T7/85)}
- G10L 13/08: Text analysis or generation of parameters for speech synthesis out of text, e.g. grapheme to phoneme translation, prosody generation or stress or intonation determination
- G10L 15/22: Procedures used during a speech recognition process, e.g. man-machine dialogue
- G10L 2015/221: {Announcement of recognition results}
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G10L: SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING

## Abstract

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for analyzing images for generating query responses. One of the methods includes determining, using a textual query, an image category for images responsive to the textual query, and an output type that identifies a type of requested content; selecting, using data that associates a plurality of images with a corresponding category, a subset of the images that each belong to the image category, each image in the plurality of images belonging to one of the two or more categories; analyzing, using the textual query, data for the images in the subset of the images to determine images responsive to the textual query; determining a response to the textual query using the images responsive to the textual query; and providing, using the output type, the response to the textual query for presentation.

## Claims

### Claim at position 1

-20. (canceled)

### Claim 21

A computer-implemented method for image query processing, the method comprising:
obtaining, by a computing system comprising one or more computing devices, a user query, wherein the user query comprises one or more words;
determining, by the computing system and based on the user query, an image category associated with the user query;
determining, by the computing system, a subset of images that each belong to the image category;
processing, by the computing system, the user query and the subset of images to determine one or more images responsive to the user query;
determining, by the computing system, a response to the user query based on the one or more images responsive to the user query; and
providing, by the computing system, the response to the user query for presentation.

### Claim 22 (depends on 21)

The method of claim 21, further comprising:
determining, by the computing system, an output type that identifies a type of requested content based on the user query.

### Claim 23 (depends on 22)

The method of claim 22, wherein determining the response to the user query using the images responsive to the user query comprises:
selecting, for each image responsive to the user query using the output type, a portion of the image that depicts data responsive to the user query.

### Claim 24 (depends on 22)

The method of claim 22, wherein providing, by the computing system, the response to the user query for presentation comprises:
providing, using the output type, the response to the user query for presentation.

### Claim 25 (depends on 24)

The method of claim 24, wherein providing, using the output type, the response to the user query for presentation comprises:
generating instructions for an audible presentation of the response; and
providing the instructions to a speaker to cause the speaker to provide the audible presentation of the response.

### Claim 26 (depends on 21)

The method of claim 21, wherein providing, by the computing system, the response to the user query for presentation comprises:
generating instructions for presentation of a user interface that emphasizes, for each image responsive to the image query, a portion of the image that depicts the response to the user query; and
providing the instructions to a display to cause the display to present the user interface and at least one of the images responsive to the user query.

### Claim 27 (depends on 21)

The method of claim 21, further comprising:
determining, by the computing system, using the user query, one or more key phrases for the user query; and
wherein processing, by the computing system, the user query and the subset of images to determine one or more images responsive to the user query comprises analyzing, using the one or more key phrases, data for the images in the subset of the images to determine images responsive to the user query.

### Claim 28 (depends on 21)

The method of claim 21, wherein the image category is determined from two or more image categories defined for a plurality of images obtained by the one or more computing devices.

### Claim 29 (depends on 21)

The method of claim 21, wherein the user query is a spoken query received from a user by a microphone associated with the one or more computing devices.

### Claim 30 (depends on 29)

The method of claim 29, determining, by the computing system and based on the user query, the image category associated with the user query comprises determining, using a textual query derived from the spoken query, the image category is responsive to the textual query.

### Claim 31

A computing system for image query processing, 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 a user query, wherein the user query comprises one or more words;
determining, based on the user query, an image category associated with the user query;
determining a subset of images that each belong to the image category;
processing the user query and the subset of images to determine one or more images responsive to the user query;
determining a response to the user query based on the one or more images responsive to the user query; and
providing the response to the user query for presentation.

### Claim 32 (depends on 31)

The system of claim 31, wherein determining the subset of images that each belong to the image category comprises:
determining a plurality of images responsive to the user query; and
analyzing data for images in the image category to determine the subset of images responsive to the user query.

### Claim 33 (depends on 32)

The system of claim 32, wherein the operations further comprise:
selecting, for each image responsive to the user query, at least a portion of the image that depicts data responsive to the user query.

### Claim 34 (depends on 31)

The system of claim 31, wherein providing the response to the user query for presentation comprises:
generating instructions for a visual presentation of data responsive to the user query; and
causing a display associated with a computing device to provide the visual presentation of the data responsive to the user query.

### Claim 35 (depends on 31)

The system of claim 31, wherein providing the response to the user query for presentation comprises:
providing the response to the user query via at least one of a visual presentation or an audible presentation.

### Claim 36 (depends on 35)

The system of claim 35, wherein providing the response to the user query for presentation comprises:
providing instructions to a speaker to cause the speaker to provide the audible presentation of the response to the user query.

### Claim 37

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 a user query, wherein the user query comprises one or more words;
determining, based on the user query, an image category associated with the user query;
determining a subset of images that each belong to the image category;
processing the user query and the subset of images to determine one or more images responsive to the user query;
determining a response to the user query based on the one or more images responsive to the user query; and
providing the response to the user query for presentation.

### Claim 38 (depends on 37)

The one or more non-transitory computer-readable media of claim 37, wherein the operations further comprise:
determining an output type that identifies a type of content responsive to the user query, wherein the output type comprises at least one of an image, an annotated image, or a textual summary.

### Claim 39 (depends on 37)

The one or more non-transitory computer-readable media of claim 37, wherein the operations further comprise:
determining an output type that identifies a type of content responsive to the user query; and
wherein determining the subset of images comprises selecting the subset of the images using the output type and the image category.

### Claim 40 (depends on 37)

The one or more non-transitory computer-readable media of claim 37, wherein the presentation is an audible presentation, wherein the audible presentation of the response comprises a prompt indicating that a visual presentation associated with the response is available.
