A recipe generating cooking teaching terminal and method of intelligent voice interaction

By employing a hybrid intent understanding architecture and multi-sensor monitoring, the problems of limited interaction and insufficient recognition accuracy in cooking aids have been solved, enabling efficient and continuous voice interaction and dynamic step control in the kitchen environment, thus improving the cooking experience and safety.

CN122369462APending Publication Date: 2026-07-10GUANGDONG TIANYI FUTURE TECHNOLOGY CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
GUANGDONG TIANYI FUTURE TECHNOLOGY CO LTD
Filing Date
2026-05-11
Publication Date
2026-07-10

AI Technical Summary

Technical Problem

Existing cooking aids have limited interaction methods, cannot achieve continuous voice control throughout the entire process, and lack sufficient voice wake-up and recognition accuracy in the high-noise environment of the kitchen, making it difficult to handle complex natural language retrieval and high-frequency commands.

Method used

It adopts a hybrid intent understanding architecture, combining local speech recognition and cloud services to realize recipe retrieval, step-by-step teaching and dynamic step control, supports offline high-frequency command response and online complex query, integrates multiple sensors to monitor cooking status, and provides full-process voice interactive teaching.

Benefits of technology

It enables efficient and continuous voice interaction in the kitchen environment, supports dynamic step adjustments and safety reminders, improves cooking smoothness and safety, and balances real-time response and recognition accuracy.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN122369462A_ABST
    Figure CN122369462A_ABST
Patent Text Reader

Abstract

This invention discloses an intelligent voice-interactive recipe generation cooking teaching terminal and method. The terminal includes: a voice acquisition module for acquiring the user's voice signal; an intent understanding module for recognizing the user's intent expressed by the voice signal, including recipe retrieval intent and step control intent; a recipe acquisition module for retrieving a target recipe in response to the recipe retrieval intent, the target recipe containing multiple cooking steps arranged in sequence; a step control module for dynamically adjusting the output state of the current cooking step in response to the step control intent; and a voice output module for converting the step text into voice broadcast. The technical highlight of this invention is that by constructing a closed-loop voice interaction system from recipe retrieval to step-by-step instruction, users do not need to consult paper recipes or operate touchscreen devices during the cooking process, achieving a fully immersive cooking experience from recipe retrieval to step-by-step voice instruction and then to dynamically adjusting the cooking steps.
Need to check novelty before this filing date? Find Prior Art