Vehicle AI Service Intent Recognition via Multi-Source Data Fusion

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Conventional vehicle AI services struggle to accurately recognize user intentions due to unclear or ambiguous voice inputs, leading to incorrect service provisioning.

Innovation Solution

A method involving an AI service providing device that analyzes voice analysis data, real-time trend data, user history data, and situation data to identify user intentions by matching scores of skill and command candidates, using a processor to determine the final skill and command that align with the user's intent.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If conventional voice analysis is used to recognize user intention, then the system is simple and fast, but the recognition accuracy is low due to ambiguous voice inputs

Engineering Contradiction:
Improvevoice recognition accuracyVSAvoidsystem complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent combines multiple data sources (voice analysis data, real-time trend data, user history data, and situation data) into a unified analysis framework. The processor integrates these diverse data types to comprehensively determine user intention, resolving ambiguities that single data sources cannot address alone.

Inventive Principle:
Principle #5Merging (Combining)

Solution Approach 2:

The patent adds temporal and contextual dimensions to voice analysis by incorporating real-time trend data (temporal dimension) and situation data (contextual dimension). This multi-dimensional approach enables more accurate intention recognition by analyzing user requests from multiple perspectives simultaneously.

Inventive Principle:
Principle #17Another dimension (Dimensionality change)

2Measurement precision

If multiple data types are analyzed to improve intention recognition, then accuracy improves, but processing time and computational load increase

Engineering Contradiction:
Improveintention recognition accuracyVSAvoidprocessing time
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The system performs preliminary analysis by pre-processing and organizing multiple data types before final intention determination. Voice analysis data, real-time trend data, user history data, and situation data are prepared in advance, allowing the processor to efficiently integrate them when needed without excessive processing delays.

Inventive Principle:
Principle #10Preliminary action

3Reliability

If only voice analysis data is used, then the system is fast and simple, but service provisioning errors occur due to ambiguous or incorrect voice inputs

Engineering Contradiction:
Improveservice provisioning accuracyVSAvoiddata processing complexity
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The system uses user history data as feedback to improve intention recognition. By analyzing past user requests and behaviors, the system learns from previous interactions and uses this feedback to disambiguate current voice inputs, reducing service provisioning errors while maintaining reasonable system complexity.

Inventive Principle:
Principle #23Feedback

Data Source

PatentUS10741178B2Method for providing vehicle AI service and device using the same
Publication Date: 2020.08.11 OBIGO
  • US10741178B2 patent drawing
  • US10741178B2 patent drawing
  • US10741178B2 patent drawing

AI summary

A method for providing a vehicle AI service is provided. The method includes steps of: an AI service providing device (a) supporting an AI server to extract from a voice of a user (i) at least one of skill candidates including service categories and (ii) at least one of command candidates, to create voice analysis data, and receiving it from the AI server; and (b) (I) analyzing at least one of (i) the voice analysis data, (ii) second data created by analyzing voices of other users within a certain time, (iii) third data created by analyzing voices of the user within a particular time, and (iv) fourth data having information on context of the user, and (II) recognizing an intention included in the voice and determining a final skill and a final command matching the intention; wherein each of the data includes the skill candidates and the command candidates.