In-Vehicle Voice Search System with Geographical Condition Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing search systems require users to edit search conditions while viewing the screen, which can be inconvenient, especially when performing point-of-interest (POI) searches using voice input.
Innovation Solution
A search system comprising a database server, an in-vehicle terminal, and a relay server that uses voice recognition to convert voice inputs into keywords, storing geographical and non-geographical conditions, and determines whether the input is a geographical condition to search the POI database accordingly, allowing for searches without user intervention on screen editing.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If users manually edit search conditions on the screen, then search accuracy is improved, but ease of operation deteriorates
Solution Approach 1:
The system automatically determines whether voice input represents a geographical condition or non-geographical condition without requiring user intervention. The control unit autonomously analyzes the voice-converted string, queries the address database, and categorizes the input appropriately, allowing the system to serve itself in the search condition creation process.
Solution Approach 2:
The patent replaces the mechanical interaction of manually editing search conditions on screen with acoustic interaction through voice input. The voice input unit captures spoken commands, which are converted to text and automatically processed by the control unit to generate search conditions, substituting manual screen editing with voice-based automation.
2Ease of operation
If voice recognition is used to convert speech to keywords, then ease of operation is improved, but device complexity increases
Solution Approach 1:
The relay server is designed to perform multiple functions: voice recognition, text conversion, address database querying, geographical condition determination, and POI database searching. By consolidating these diverse functions into a single multi-functional system, the patent manages complexity through functional integration rather than requiring separate specialized components for each task.
Solution Approach 2:
The control unit acts as an intermediary that bridges voice input and database searching. It receives voice-converted strings, determines their nature (geographical or non-geographical), and appropriately queries the relevant databases. This intermediary layer simplifies the overall system architecture by providing a centralized intelligence point that coordinates between different components.
3Ease of operation
If the system automatically determines geographical conditions, then ease of operation is improved, but reliability may deteriorate due to automatic classification errors
Solution Approach 1:
The control unit queries the address database to verify whether the voice-converted string corresponds to a valid geographical location. This feedback mechanism allows the system to confirm or correct its automatic classification by checking against authoritative address data, thereby improving reliability while maintaining automated operation.
Data Source
AI summary
An in-vehicle terminal sends a speech input from a voice input unit as a voice signal to a relay server using a short-range wireless communication unit. The relay server converts the voice data received from the in-vehicle terminal into a string with a voice recognition unit, and makes an inquiry, via a communication unit, to an address database of a database server as to whether the string is a geographical condition. If the string converted by the voice recognition unit is a geographical condition based on the inquiry result of the communication unit, a POI data base is searched based on the geographical condition and a stored non-geographical condition, and the geographical condition is stored in a search history. If the string is a non-geographical condition, the POI database is searched based on the non-geographical condition and the geographical condition stored in the search history, and the non-geographical condition is stored in the search history.