Dynamic Digital Signage Content Adaptation via Face and Position Detection

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing digital signage systems do not effectively provide content that is tailored to the changing state and position of a target, such as variations in gender, age, and group dynamics, which limits their effectiveness in engaging and informing the target audience.

Innovation Solution

An information processing apparatus and method that includes an image pickup unit, display unit, position detection unit, face detection unit, attribute determination unit, group determination unit, content determination unit, and display processing unit, which together analyze the target's attributes and position to dynamically adjust the content and display style in real-time, ensuring the content is relevant and engaging based on the target's state and proximity to the display.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If content is provided based on target attribute information alone, then content suitability for the target is improved, but timing appropriateness deteriorates

Engineering Contradiction:
Improvecontent suitabilityVSAvoidtiming appropriateness
Core Design Contradiction:
Adaptability or versatilityVSLoss of time

Solution Approach 1:

The system dynamically adjusts content provision based on real-time detection of target state (face detection results, position information) rather than using static attribute information alone. The content determination is continuously updated as the target's state changes, ensuring both suitability and timing appropriateness.

Inventive Principle:
Principle #15Dynamics

Solution Approach 2:

The system uses feedback from the image pickup device and position detection device to continuously monitor target state and adjust content provision accordingly. This closed-loop feedback mechanism ensures content is provided at appropriate times based on current target conditions rather than relying solely on pre-obtained attribute information.

Inventive Principle:
Principle #23Feedback

2Loss of time

If the system monitors target state continuously, then timing appropriateness of content provision is improved, but system complexity increases

Engineering Contradiction:
Improvetiming appropriatenessVSAvoidsystem complexity
Core Design Contradiction:
Loss of timeVSDevice complexity

Solution Approach 1:

The image pickup device serves multiple functions: capturing images for face detection, determining target state, and tracking position information. This multi-functionality reduces the need for separate dedicated sensors and decreases overall system complexity while enabling continuous monitoring.

Inventive Principle:
Principle #6Universality (Multi-functionality)

Solution Approach 2:

The system combines face detection results and position information processing into a unified content determination mechanism. By merging these detection functions and their processing workflows, the system achieves continuous state monitoring without proportionally increasing complexity.

Inventive Principle:
Principle #5Merging (Combining)

3Adaptability or versatility

If multiple detection and analysis functions are added, then content personalization is improved, but processing time increases

Engineering Contradiction:
Improvecontent personalizationVSAvoidprocessing time
Core Design Contradiction:
Adaptability or versatilityVSLoss of time

Solution Approach 1:

The system performs preliminary face detection and attribute extraction in advance, storing results for rapid content determination. By pre-processing and caching detection results, the system reduces real-time processing requirements while maintaining high content personalization.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The content determination process is segmented into distinct stages: face detection, attribute extraction, position determination, and content selection. This segmentation allows parallel processing of different detection functions and optimizes the overall processing pipeline efficiency.

Inventive Principle:
Principle #1Segmentation

Data Source

PatentUS8659649B2Information processing apparatus and information processing method
Publication Date: 2014.02.25 SONY GROUP CORP
  • US8659649B2 patent drawing
  • US8659649B2 patent drawing
  • US8659649B2 patent drawing

AI summary

There is provided an information processing apparatus including an image pickup part; a display part; a position detecting part for detecting a position of a target relative to the display part; a face detecting part for detecting a face from a taken image; an attribute obtaining part for obtaining attribute information of the target; a group determining part for determining a group to which the target belongs, at least based on the attribute information of the detected target; a content determining part for determining a content to be provided to the target based on at least one of group information of the target and the attribute information of the target; and a display processing part for displaying content information of the content to be provided to the target, on the display part in a display style in accordance with the position of the target.