Mobile Terminal Intelligent Agent Voice Image Context Integration
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current mobile terminals lack the capability to provide intelligent agent (IA) services effectively using a combination of voice and image inputs, limiting their functionality and user interaction.
Innovation Solution
A mobile terminal equipped with a display unit, camera, microphone, angle sensor, location sensor, and communication unit, which activates an intelligent agent upon a preset voice signal and uses context information from images and voice inputs to provide IA services, including tag information and visual or voice output.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If IA service is provided using only voice signal, then the system complexity is low, but the functionality and user interaction capability are limited
Solution Approach 1:
The patent combines multiple input modalities (voice signal, image signal, screen shot signal) into a unified IA service processing system. The controller integrates these different signal types to provide comprehensive IA services, thereby enhancing functionality while managing system complexity through unified processing architecture
Solution Approach 2:
The intelligent agent is designed to handle multiple types of inputs (voice, image, screen shots) and provide diverse IA services including tag information extraction, visual output, and voice output. This multi-functional design allows the same system to adapt to different input types and service requirements
2Reliability
If camera is activated continuously to capture images for IA service, then the image input quality is high, but the energy consumption increases
Solution Approach 1:
The camera is activated periodically based on specific conditions (preset input signal detection) rather than continuously. The controller determines camera activation timing based on the need for image input in IA service, thereby maintaining image quality when needed while reducing energy consumption during non-activation periods
Solution Approach 2:
The system automatically determines when camera activation is necessary based on the IA service requirements and input signal conditions. The controller autonomously manages camera activation without continuous user intervention, optimizing the balance between image quality and energy consumption
Data Source
AI summary
Disclosed are a mobile terminal for providing an intelligent agent (IA) service and controlling method thereof. The mobile terminal includes a display unit, a camera, a sensing unit comprising a microphone configured to sense a surrounding voice of the mobile terminal, an angle sensor configured sense an angle of the mobile terminal, and a location sensor configured to sense a location of the mobile terminal, a communication unit configured to transmit/receive data with a server configured to store a context information of a user, and a controller, if a trigger signal including a preset voice signal is sensed through the microphone, activating an intelligent agent (IA), the controller, if a preset input signal is sensed in a state that the IA is activated, activating the camera.