Image-Based Map POI Selection for Accurate Queries

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing map information processing technologies lack convenience and accuracy in user interaction and query results, particularly when using images for point of interest (POI) queries.

Innovation Solution

A method and apparatus that utilize object recognition in images to select target POIs from electronic maps, incorporating scene environment information and map service associations, with user attribute filtering for enhanced accuracy and convenience.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of operation

If traditional text-based POI query methods are used, then the system is simple to operate, but the user interaction convenience and query accuracy are insufficient

Engineering Contradiction:
Improveuser interaction convenienceVSAvoidsystem complexity
Core Design Contradiction:
Ease of operationVSDevice complexity

Solution Approach 1:

The patent replaces traditional text-based query input (mechanical keyboard typing) with image-based visual interaction. Users capture images of POIs using their device camera, and the system automatically processes these images to identify and retrieve relevant POI information, eliminating the need for manual text entry and significantly improving interaction convenience.

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The patent introduces an image processing intermediary layer between the user and the POI database. The system captures images, processes them through object recognition and scene analysis algorithms, extracts relevant POI features, and then queries the database based on these extracted features. This intermediary processing layer enables natural image-based interaction while maintaining system manageability.

Inventive Principle:
Principle #24Intermediary (Mediator)

2Ease of operation

If image-based POI queries are implemented, then user interaction convenience is improved, but the processing complexity and computational requirements increase

Engineering Contradiction:
Improvequery convenienceVSAvoidprocessing complexity
Core Design Contradiction:
Ease of operationVSDevice complexity

Solution Approach 1:

The patent segments the image processing task into distinct modular components: image acquisition, object recognition, scene environment analysis, POI feature extraction, and database querying. Each module handles a specific aspect of the processing pipeline, making the overall complex system more manageable and maintainable while enabling comprehensive image analysis for accurate POI retrieval.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent performs preliminary processing of images by pre-extracting POI-related features and scene context information before querying the database. The system analyzes images in advance to identify key POI characteristics, stores these extracted features, and then uses them for efficient database matching, reducing the computational burden during actual query operations.

Inventive Principle:
Principle #10Preliminary action

3Measurement precision

If only basic object recognition is used, then the processing speed is fast, but the POI selection accuracy is insufficient

Engineering Contradiction:
ImprovePOI selection accuracyVSAvoidprocessing time
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The patent applies different processing depths to different regions and elements within the image based on their relevance to POI identification. The system performs detailed analysis on key POI-related objects and scene elements while using faster, lighter processing for background or less relevant areas, thereby improving overall accuracy without proportionally increasing processing time for the entire image.

Inventive Principle:
Principle #3Local quality

Data Source

PatentEP4174439B1Method and apparatus for processing map information, device, and storage medium
Publication Date: 2025.10.15 BEIJING BAIDU NETCOM SCI & TECH CO LTD
  • EP4174439B1 patent drawingFigure 1~2
  • EP4174439B1 patent drawingFigure 3A
  • EP4174439B1 patent drawingFigure 3B

AI summary

Provided are a method and apparatus for processing map information, a device, and a storage medium which relate to the field of computer technology and, in particular, to the fields of intelligent transportation and computer vision technology. The specific implementation includes that an object in an image for query is recognized to obtain an object recognition result and that a target point of interest matching the image for query is selected from at least one candidate point of interest of an electronic map according to the object recognition result. The convenience and accuracy of processing map information can be improved.