Historical Map Annotation via Data Normalization and Ranking

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Modern mapping systems primarily provide current information, lacking historical data which can lead to inaccurate representations of changed locations, and struggle to efficiently integrate and analyze diverse historical sources for accurate historical mapping.

Innovation Solution

A computer-implemented method that retrieves, normalizes, and ranks historical data from various repositories, generating a confidence score to provide accurate historical annotations on maps, using learning models to piece together fragmented data and present reliable historical information to users.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If historical data from multiple diverse repositories is integrated to improve historical mapping accuracy, then the reliability of historical mappings is improved, but the device complexity and data processing complexity increase

Engineering Contradiction:

Improvehistorical mapping accuracyVSAvoiddata integration complexity

Core Design Contradiction:

ReliabilityVSDevice complexity

Solution Approach 1:

The system segments historical data processing by dividing it into discrete references from multiple repositories, each reference being independently retrieved, normalized, and ranked. This allows complex multi-source data integration to be broken down into manageable individual data units that can be processed systematically

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The patent introduces intermediate processing steps including normalization to common coordinate systems and ranking mechanisms that act as mediators between diverse historical data sources and the final mapping output. These intermediaries standardize and prioritize data before integration, reducing the complexity of directly combining heterogeneous sources

Inventive Principle:

Principle #24Intermediary (Mediator)

2Measurement precision

If learning models are used to piece together fragmented historical data, then the measurement precision of historical location data is improved, but the loss of time for data processing increases

Engineering Contradiction:

Improvehistorical location accuracyVSAvoiddata processing time

Core Design Contradiction:

Measurement precisionVSLoss of time

Solution Approach 1:

The system performs preliminary actions by pre-retrieving and pre-normalizing historical references before they are needed for specific mapping queries. Historical data is proactively collected and standardized in advance, so when mapping requirements arise, the processing time is reduced as the heavy normalization work has already been completed

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The patent transforms fragmented historical data into structured, normalized coordinates through parameter changes. By converting diverse historical references into a common coordinate system format with standardized parameters, the system enables efficient processing and comparison without repeatedly performing complex transformations during query execution

Inventive Principle:

Principle #35Parameter changes

3Ease of operation

If historical data is normalized to common coordinate systems from diverse sources, then the homogeneity of data integration is improved, but the manufacturing precision of location accuracy may be reduced due to coordinate transformation errors

Engineering Contradiction:

Improvedata integration easeVSAvoidlocation accuracy

Core Design Contradiction:

Ease of operationVSManufacturing precision

Solution Approach 1:

The patent replaces manual or mechanical coordinate transformation methods with automated learning models that piece together fragmented historical data. These intelligent systems substitute traditional coordinate conversion mechanisms, providing more accurate transformations that account for historical coordinate system variations and improvements

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

4Quantity of substance

If multiple references are retrieved and ranked from various data repositories, then the quantity of historical data available is improved, but the difficulty of detecting and measuring accurate historical information increases

Engineering Contradiction:

Improvehistorical data volumeVSAvoidhistorical information verification

Core Design Contradiction:

Quantity of substanceVSDifficulty of detecting and measuring

Solution Approach 1:

The system implements feedback mechanisms through ranking algorithms that evaluate and prioritize retrieved references based on their reliability and relevance. The ranking process provides feedback on data quality, allowing the system to identify and select the most accurate historical information from multiple sources while filtering out less reliable data

Inventive Principle:

Principle #23Feedback

Data Source

PatentUS11593411B2Historical augmentation of electronic maps

Publication Date: 2023.02.28 INTERNATIONAL BUSINESS MACHINE CORPORATION

AI summary

Disclosed is a computer implemented method to annotate electronic maps with historical data, the method comprising: receiving a first query from a user, wherein the first query includes a request for historical data of a mapped area. The method also comprises retrieving a plurality of references, wherein each reference includes a location reference, and each reference is related to the mapped area. The method further comprises normalizing each location reference to a common coordinate system. The method also comprises ranking each of the plurality of references. The method further comprises generating a first result, wherein the first result is responsive to the first query, and the first result is based on the ranking. The method further comprises determining a confidence score for the first result, and returning the first result to the user.