# US 2026/0064762 A1 · Image retrieval method, electronic device and non-transitory computer-readable storage medium

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

- Number: US 2026/0064762 A1
- Document ID: US20260064762A1
- Status: Published application
- Kind: A1
- Application number: 19/316,515
- Filed: 2025-09-02
- Published: 2026-03-05
- Earliest claimed: 2024-09-02
- Assignees: Beijing Zitiao Network Technology Co., Ltd.
- Applicants: Beijing Zitiao Network Technology Co., Ltd.
- Inventors: Gonglei SHI; Yutao CHENG; Maoke YANG; Zhao ZHANG
- Web page: https://patentgrep.com/patent/US20260064762A1

## CPC

- G06F 16/532: Query formulation, e.g. graphical querying
- G06F 16/583: using metadata automatically derived from the content
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)

## Abstract

The present disclosure relates to an image retrieval method, an electronic device, and non-transitory computer-readable storage medium. The method includes: obtaining retrieval reference information, where the retrieval reference information includes first semantic information and first pixel information; based on the first semantic information, retrieving from a preset semantic information library and obtaining multiple candidate semantic information that match the first semantic information; based on candidate sample images to which the multiple candidate semantic information respectively belong, retrieving from a preset pixel information library and obtaining candidate pixel information corresponding to each of the multiple candidate sample images; according to a similarity between the candidate pixel information corresponding to each of the multiple candidate sample images and the first pixel information, selecting a target sample image from the multiple candidate sample images, and taking the target sample image as a retrieval result image corresponding to the retrieval reference information.

## Claims

### Claim 1

An image retrieval method, comprising:
obtaining retrieval reference information, wherein the retrieval reference information comprises first semantic information and first pixel information;
based on the first semantic information, retrieving from a preset semantic information library and obtaining multiple candidate semantic information that match the first semantic information, wherein the semantic information library contains semantic information of multiple sample images;
based on multiple candidate sample images to which the multiple candidate semantic information respectively belong, retrieving from a preset pixel information library and obtaining candidate pixel information corresponding to each of the multiple candidate sample images, wherein the pixel information library contains pixel information of the multiple sample images; and
according to a similarity between the candidate pixel information corresponding to each of the multiple candidate sample images and the first pixel information, selecting a target sample image from the multiple candidate sample images, and taking the target sample image as a retrieval result image corresponding to the retrieval reference information.

### Claim 2 (depends on 1)

The image retrieval method of claim 1, wherein the obtaining the retrieval reference information, comprises:
obtaining a first reference image;
performing semantic feature extraction on the first reference image and obtaining the first semantic information; and performing pixel feature extraction on the first reference image and obtaining the first pixel information.

### Claim 3 (depends on 2)

The image retrieval method of claim 2, wherein the obtaining the first reference image, comprises:
obtaining a target reference image; and
obtaining an image corresponding to a material contained in the target reference image, and taking the image corresponding to the material as the first reference image.

### Claim 4 (depends on 3)

The image retrieval method of claim 3, wherein multiple materials are contained in the target reference image, and the image retrieval method further comprises:
based on position information and layer information of the multiple materials in the target reference image, performing combination processing on retrieval result images corresponding to the multiple materials and obtaining a matching image corresponding to the target reference image.

### Claim 5 (depends on 2)

The image retrieval method of claim 2, wherein the performing the semantic feature extraction on the first reference image and obtaining the first semantic information, comprises:
performing the semantic feature extraction on the first reference image and obtaining a first semantic feature; and
taking the first semantic feature as the first semantic information.

### Claim 6 (depends on 2)

The image retrieval method of claim 2, wherein the performing the semantic feature extraction on the first reference image and obtaining the first semantic information, comprises:
performing the semantic feature extraction on the first reference image and obtaining a first semantic feature; and
obtaining a quantization feature corresponding to the first semantic feature based on a preset quantization semantic codebook, and obtaining the first semantic information based on the quantization feature corresponding to the first semantic feature.

### Claim 7 (depends on 2)

The image retrieval method of claim 2, wherein the performing the pixel feature extraction on the first reference image and obtaining the first pixel information, comprises:
performing the pixel feature extraction on the first reference image and obtaining a first pixel feature; and
taking the first pixel feature as the first pixel information.

### Claim 8 (depends on 2)

The image retrieval method of claim 2, wherein the performing the pixel feature extraction on the first reference image and obtaining the first pixel information, comprises:
performing the pixel feature extraction on the first reference image and obtaining a first pixel feature; and
obtaining a quantization feature corresponding to the first pixel feature based on a preset quantization pixel codebook, and obtaining the first pixel information based on the quantization feature corresponding to the first pixel feature.

### Claim 9 (depends on 1)

The image retrieval method of claim 1, wherein the obtaining the retrieval reference information, comprises:
obtaining retrieval prompt information; and
based on the retrieval prompt information, generating the first semantic information and the first pixel information by using a preset generation model.

### Claim 10 (depends on 9)

The image retrieval method of claim 9, wherein based on the retrieval prompt information, generating the first semantic information and the first pixel information by using the preset generation model, comprises:
based on the retrieval prompt information, generating a first semantic feature flag sequence and a first pixel feature flag sequence by using a preset generation model;
obtaining a quantization feature corresponding to the first semantic feature flag sequence based on a preset quantization semantic codebook, and taking the quantization feature corresponding to the first semantic feature flag sequence as the first semantic information; and
obtaining a quantization feature corresponding to the first pixel feature flag sequence based on a preset quantization pixel codebook, and taking the quantization feature corresponding to the first pixel feature flag sequence as the first pixel information.

### Claim 11 (depends on 1)

The image retrieval method of claim 1, wherein the retrieving from the preset semantic information library and obtaining the multiple candidate semantic information that match the first semantic information, comprises:
arranging similarities between the first semantic information and semantic information in the preset semantic information library in order of magnitude, and selecting top N pieces of semantic information with a highest similarity as the multiple candidate semantic information that match the first semantic information, wherein N is a preset positive integer greater than one.

### Claim 12 (depends on 1)

The image retrieval method of claim 1, wherein the retrieving from the preset semantic information library and obtaining the multiple candidate semantic information that match the first semantic information, comprises:
taking semantic information in the preset semantic information library whose similarity to the first semantic information is higher than a preset threshold, as the multiple candidate semantic information that match the first semantic information.

### Claim 13

An electronic device, comprising:
a storage apparatus, wherein a computer program is stored on the storage apparatus; and
a processing apparatus, configured to execute the computer program on the storage apparatus to implement an image retrieval method,
wherein the image retrieval method comprises:
obtaining retrieval reference information, wherein the retrieval reference information comprises first semantic information and first pixel information;
based on the first semantic information, retrieving from a preset semantic information library and obtaining multiple candidate semantic information that match the first semantic information, wherein the semantic information library contains semantic information of multiple sample images;
based on multiple candidate sample images to which the multiple candidate semantic information respectively belong, retrieving from a preset pixel information library and obtaining candidate pixel information corresponding to each of the multiple candidate sample images, wherein the pixel information library contains pixel information of the multiple sample images; and
according to a similarity between the candidate pixel information corresponding to each of the multiple candidate sample images and the first pixel information, selecting a target sample image from the multiple candidate sample images, and taking the target sample image as a retrieval result image corresponding to the retrieval reference information.

### Claim 14 (depends on 13)

The electronic device of claim 13, wherein the obtaining the retrieval reference information, comprises:
obtaining a first reference image;
performing semantic feature extraction on the first reference image and obtaining the first semantic information; and performing pixel feature extraction on the first reference image and obtaining the first pixel information.

### Claim 15 (depends on 14)

The electronic device of claim 14, wherein the obtaining the first reference image, comprises:
obtaining a target reference image; and
obtaining an image corresponding to a material contained in the target reference image, and taking the image corresponding to the material as the first reference image.

### Claim 16 (depends on 15)

The electronic device of claim 15, wherein multiple materials are contained in the target reference image, the method further comprising:
based on position information and layer information of the multiple materials in the target reference image, performing combination processing on the retrieval result images corresponding to the multiple materials and obtaining a matching image corresponding to the target reference image.

### Claim 17 (depends on 14)

The electronic device according to claim 14, wherein the performing the semantic feature extraction on the first reference image and obtaining the first semantic information, comprises:
performing the semantic feature extraction on the first reference image and obtaining a first semantic feature; and
taking the first semantic feature as the first semantic information.

### Claim 18 (depends on 14)

The electronic device according to claim 14, wherein the performing the pixel feature extraction on the first reference image and obtaining the first pixel information, comprises:
performing the pixel feature extraction on the first reference image and obtaining a first pixel feature; and
taking the first pixel feature as the first pixel information.

### Claim 19 (depends on 13)

The electronic device of claim 13, wherein the obtaining the retrieval reference information, comprises:
obtaining retrieval prompt information; and
based on the retrieval prompt information, generating the first semantic information and the first pixel information by using a preset generation model.

### Claim 20

A non-transitory computer-readable storage medium, wherein the storage medium stores a computer program, the computer program is configured to execute an image retrieval method, and
the image retrieval method comprises:
obtaining retrieval reference information, wherein the retrieval reference information comprises first semantic information and first pixel information;
based on the first semantic information, retrieving from a preset semantic information library and obtaining multiple candidate semantic information that match the first semantic information, wherein the semantic information library contains semantic information of multiple sample images;
based on multiple candidate sample images to which the multiple candidate semantic information respectively belong, retrieving from a preset pixel information library and obtaining candidate pixel information corresponding to each of the multiple candidate sample images, wherein the pixel information library contains pixel information of the multiple sample images; and
according to a similarity between the candidate pixel information corresponding to each of the multiple candidate sample images and the first pixel information, selecting a target sample image from the multiple candidate sample images, and taking the target sample image as a retrieval result image corresponding to the retrieval reference information.
