Voice Skill Jumping Using Field Migration Maps Against Noisy Inputs

Solution Overview

Problem

Existing man-machine dialogue systems face inefficiencies due to incorrect field switching caused by ambiguous user inputs or noise, leading to disrupted interactions and incomplete task completion.

Innovation Solution

A field migration map is generated based on user historical dialogue data to predict and validate intended dialogue fields, shielding abnormal inputs and improving interaction efficiency by leveraging user interaction habits.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If the field jump switch is turned on to enable field switching, then user flexibility and adaptability are improved, but noise interference increases causing misidentification and erroneous field transitions

Engineering Contradiction:

Improvefield switching capabilityVSAvoidnoise interference

Core Design Contradiction:

Adaptability or versatilityVSObject-affected harmful factors

Solution Approach 1:

The system pre-learns user dialogue habits and field transition patterns before actual dialogue occurs, building a prediction model in advance. This preliminary action enables the system to anticipate user intentions and distinguish them from noise, resolving the contradiction between enabling field switching and preventing erroneous transitions caused by noise.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system continuously monitors actual user dialogue behavior and uses this feedback to refine the field transition prediction model. By incorporating real-world usage patterns into the prediction mechanism, the system improves its ability to distinguish intentional field switches from noise, maintaining adaptability while reducing misidentification.

Inventive Principle:

Principle #23Feedback

2Reliability

If the field jump switch is turned off to prevent noise-induced misidentification, then dialogue stability is improved, but user flexibility and field switching capability are reduced

Engineering Contradiction:

Improvedialogue stabilityVSAvoidfield switching capability

Core Design Contradiction:

ReliabilityVSAdaptability or versatility

Solution Approach 1:

The system pre-learns user dialogue habits and field transition patterns before actual dialogue occurs, building a prediction model in advance. This preliminary action enables the system to anticipate user intentions and distinguish them from noise, resolving the contradiction between enabling field switching and preventing erroneous transitions caused by noise.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system continuously monitors actual user dialogue behavior and uses this feedback to refine the field transition prediction model. By incorporating real-world usage patterns into the prediction mechanism, the system improves its ability to distinguish intentional field switches from noise, maintaining adaptability while reducing misidentification.

Inventive Principle:

Principle #23Feedback

3Device complexity

If rule-based task-based dialogue field scheduling is used to determine field order, then system complexity is reduced, but accuracy in identifying user intention deteriorates

Engineering Contradiction:

Improvescheduling strategy complexityVSAvoiduser intention identification accuracy

Core Design Contradiction:

Device complexityVSMeasurement precision

Solution Approach 1:

The system replaces the mechanical rule-based scheduling approach with a data-driven machine learning model. Instead of relying on predefined field priority rules, the system uses learned user behavior patterns to predict field transitions, significantly improving intention identification accuracy while maintaining reasonable system complexity through efficient model architecture.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The system transforms the static field priority parameters into dynamic prediction probabilities based on learned user behavior. By changing from fixed rule-based parameters to adaptive probability parameters, the system achieves higher accuracy in identifying user intentions while managing complexity through probabilistic modeling.

Inventive Principle:

Principle #35Parameter changes

Data Source

PatentEP4137931B1Voice skill jumping method for man-machine dialogue, electronic device, and storage medium

Publication Date: 2026.02.11 AISPEECH CO LTD

Figure 1~2
Figure 3~4
Figure 5

AI summary

Disclosed is a speech skill jumping method for man-machine dialogue applied to an electronic device, comprising constructing a field migration map in advance based on user's historical man-machine dialogue data, the field migration map being a directed map including a plurality of dialogue fields; receiving external speech; determining a dialogue field that the external speech hits; and judging whether the hit dialogue field belongs to one of the plurality of dialogue fields in the field migration map, and ignoring the external speech if not, or jumping to a speech skill corresponding to the hit dialogue field if yes. A field migration map is generated based on a user's historical man-machine dialogue data which reflects the user's interaction habits, and whether to perform a speech skill jump is judged based on the field migration map., obviously abnormal input content can be shielded, improving the task completion and interaction efficiency.