Voice Function Execution System Word Order Analysis

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing voice recognition systems fail to accurately determine the intended function when multiple words or verbs are present in user utterances, leading to erroneous function execution, as seen in cases like 'Ashita No Tenki' where the scheduler is activated instead of weather forecasting.

Innovation Solution

A function-execution instruction system that determines the appropriate function to execute based on the order of input words, using word input means to arrange words in order and executed-function determination means to assign weights and associations, ensuring correct function execution even with multiple verbs or words.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Extent of automation

If verbs or words are extracted from voice recognition results to determine functions, then function execution is enabled, but erroneous determination occurs when multiple words indicate different functions

Engineering Contradiction:
Improvefunction execution capabilityVSAvoidfunction determination accuracy
Core Design Contradiction:
Extent of automationVSReliability

Solution Approach 1:

The system performs preliminary analysis by dividing the voice recognition result into multiple words and arranging them in order before determining the function. This preliminary structuring of information allows the system to consider the sequence and relationship between words, enabling more accurate function determination even when multiple verbs are present in the utterance.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The system changes the parameter of word arrangement by considering the order of words as a critical factor in function determination. By incorporating the sequential arrangement of words into the determination process, the system can distinguish between different intended functions even when the same words are present, resolving the ambiguity that causes erroneous determination.

Inventive Principle:
Principle #35Parameter changes

2Adaptability or versatility

If multiple verbs are present in user utterances, then more complex instructions can be recognized, but it becomes difficult to determine which function to activate

Engineering Contradiction:
Improveinstruction complexity handlingVSAvoidfunction selection clarity
Core Design Contradiction:
Adaptability or versatilityVSEase of operation

Solution Approach 1:

The system performs preliminary division of the voice recognition result into multiple words and establishes their arrangement order before function determination. This preliminary processing creates a structured foundation that enables the system to handle complex multi-verb instructions while maintaining clear function selection through systematic analysis of word sequences.

Inventive Principle:
Principle #10Preliminary action

Data Source

PatentUS9361063B2Function execution instruction system, function execution instruction method, and function execution instruction program
Publication Date: 2016.06.07 NTT DOCOMO INC
  • US9361063B2 patent drawing
  • US9361063B2 patent drawing
  • US9361063B2 patent drawing

AI summary

To appropriately execute a function based on a plurality of words, a function-execution instruction server of a function-execution instruction system includes: a function-execution instruction unit that issues an instruction of the execution of one or more tasks; a word input unit that inputs information containing a plurality of words that are arranged in order; and an executed-function determination unit that determines a task the execution of which is instructed on the basis of the order of words input.