Activity Area Estimation Using Location Data Filtering

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing activity area estimation methods for target users in social networking services (SNSs) often inaccurately estimate activity areas due to the inclusion of irrelevant position information in posted content.

Innovation Solution

An activity area estimation apparatus that generates first location information from posted content, decides on its usefulness using related user information, and estimates the activity area based on the useful location information.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Quantity of substance

If position information from posted information is used to estimate activity area, then the quantity of location data increases, but the estimation accuracy deteriorates due to inclusion of irrelevant positions

Engineering Contradiction:

Improvequantity of location informationVSAvoidactivity area estimation accuracy

Core Design Contradiction:

Quantity of substanceVSMeasurement precision

Solution Approach 1:

The patent segments the posted information into multiple components: first position information (user's actual location), second position information (related user's location), and third position information (location mentioned in text). This segmentation allows selective processing and filtering of different position types to improve estimation accuracy while managing the quantity of location data.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The patent extracts and filters out irrelevant position information from the posted content. By identifying and removing the second position information (related user's location) and third position information (mentioned locations) that are not reflective of the target user's actual activity area, the system retains only the first position information that accurately represents user activity, thereby resolving the contradiction between data quantity and accuracy.

Inventive Principle:

Principle #2Taking out (Extraction)

2Loss of information

If all position information in posted content is utilized, then data completeness improves, but estimation reliability deteriorates due to irrelevant location data

Engineering Contradiction:

Improvecompleteness of location dataVSAvoidactivity area estimation reliability

Core Design Contradiction:

Loss of informationVSReliability

Solution Approach 1:

The patent performs preliminary classification and filtering of position information before estimation. By预先 identifying and categorizing different types of position information (first, second, and third position information) and removing irrelevant ones, the system ensures that only reliable location data is used for activity area estimation, thus maintaining both completeness and reliability.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The patent introduces an intermediary filtering mechanism that processes the raw posted information. This intermediary layer identifies and separates relevant first position information from irrelevant second and third position information, acting as a mediator between the complete posted data and the final estimation process, thereby preserving reliability while maintaining data completeness.

Inventive Principle:

Principle #24Intermediary (Mediator)

3Quantity of substance

If position information from related users is included, then the amount of available data increases, but the precision of target user activity area estimation decreases

Engineering Contradiction:

Improveamount of position dataVSAvoidtarget user activity area precision

Core Design Contradiction:

Quantity of substanceVSMeasurement precision

Solution Approach 1:

The patent specifically extracts and removes the second position information (related user's location) from the dataset used for estimation. By taking out this irrelevant data that does not reflect the target user's actual activity area, the system maintains data completeness for other relevant information while eliminating the precision-degrading effect of related user positions.

Inventive Principle:

Principle #2Taking out (Extraction)

Solution Approach 2:

The patent segments the position information into distinct categories, separating the first position information (target user's location) from the second position information (related user's location). This segmentation enables selective use of only the relevant first position data for estimation, preventing the dilution of precision that would occur if all position data were mixed together.

Inventive Principle:

Principle #1Segmentation

Data Source

PatentUS20250166089A1Activity area estimation apparatus, activity area estimation method, and non-transitory computer readable medium

Publication Date: 2025.05.22 NEC CORP

AI summary

In order to improve accuracy of estimating an activity area of a target user, an activity area estimation apparatus includes: a first generation unit that generates, based on first posted information of a target user, first location information; a usefulness decision unit that decides, by using related user information relating to a related user being a user related to the target user, whether the first location information is useful in order to estimate an activity area of the target user in a real space; and an activity area estimation unit that estimates, by using the first location information decided as being useful, the activity area of the target user.