Search

CN-121987166-A - Intelligent sleep environment adjusting system and method

CN121987166ACN 121987166 ACN121987166 ACN 121987166ACN-121987166-A

Abstract

The invention relates to the technical field of sleep regulation, and provides an intelligent sleep environment regulation system and method. The system comprises a main control module, a sleep sensing module, a sleep stage deducing module, a light effect strategy generating module and a light effect executing module, wherein the sleep sensing module senses vital sign signals, temperature distribution information and space contour information in a monitoring area in a non-contact mode, the sleep stage deducing module carries out fusion analysis on multi-source heterogeneous data acquired by the sleep sensing module and deduces a sleep stage of a user, the main control module generates different light control instructions based on different sleep stages, the light effect strategy generating module responds to the light control instructions and outputs light effect driving signals corresponding to the sleep stages, and the light effect executing module generates sleep adjustment light effects according to the light effect driving signals. The scheme eliminates wearing discomfort and sleep disturbance, and overcomes the defects of low accuracy, poor anti-disturbance and weak scene understanding of a single sensor.

Inventors

  • YANG LIN
  • GUO BIN

Assignees

  • 深圳好易达科技有限公司

Dates

Publication Date
20260508
Application Date
20260309

Claims (10)

  1. 1. The intelligent sleep environment regulating system is characterized by comprising a main control module, a sleep sensing module, a sleep stage deducing module, a light effect strategy generating module and a light effect executing module, wherein the sleep sensing module senses vital sign signals, temperature distribution information and space contour information in a monitoring area in a non-contact mode, and the vital sign signals comprise respiratory rate, heart rate and body movement signals of a user; The main control module generates different light control instructions based on different sleep stages, the light effect strategy generation module responds to the light control instructions and outputs light effect driving signals corresponding to the sleep stages, and the light effect execution module generates sleep adjustment light effects according to the light effect driving signals.
  2. 2. The intelligent sleep environment adjustment system according to claim 1, wherein the sleep perception module comprises a radar module for sensing vital sign signals in the monitored area and a thermal imaging module for sensing temperature distribution information and spatial profile information in the monitored area.
  3. 3. The intelligent sleep environment adjustment system according to claim 2, wherein the sleep perception module comprises a passive infrared sensor for sensing a human body movement signal in the monitoring area, the sleep stage inference module identifies a scene state based on the human body movement signal, the scene state comprises a distinction of a user in a bed, out of bed and a person in a pet, and the light effect strategy generation module combines the scene state and the recognition result of the sleep stage and outputs a corresponding light effect driving signal to adjust the brightness, the color, the irradiation range and the beam angle of the light effect execution module.
  4. 4. The intelligent sleep environment adjustment system as set forth in claim 1, further comprising a photoelectric module mounted to the light effect execution module, wherein the photoelectric module is electrically connected to the main control module, and the photoelectric module emits pulse light to a fingertip of a user along with the light effect execution module to obtain blood oxygen data of the user.
  5. 5. The intelligent sleep environment adjustment system according to claim 1, wherein the sleep stage inference module is integrated inside the main control module and shares a signal transmission channel with the main control module to realize real-time data interaction; or the sleep stage deducing module is arranged separately from the main control module, and the sleep stage deducing module is in communication connection with the main control module through a communication bus to realize the transmission of the multi-source heterogeneous data and the feedback of the sleep stage.
  6. 6. The intelligent sleep environment adjustment system according to claim 1, wherein the sleep stage inference module runs a pre-trained lightweight neural network model that performs the following functions: Performing time alignment and feature level fusion on the multi-source heterogeneous data to generate an environment interference resistant joint feature; classifying sleep stages of a user, the sleep stages including at least a awake state, a light sleep state, a deep sleep state, and a fast eye movement sleep stage; physiological abnormalities are detected, including mild respiratory disorders and apneas.
  7. 7. The intelligent sleep environment adjustment system according to claim 1, further comprising an audio module communicatively connected to the main control module, wherein the audio module comprises a digital audio decoding chip and a micro speaker, and the main control module controls the audio module to play audio content in coordination with the sleep adjustment light effect according to the sleep stage, wherein the audio content comprises sleep-aiding white noise and natural sound for guiding sleep, and fade-in music for mild wake-up.
  8. 8. The intelligent sleep environment adjustment system as set forth in claim 7, further comprising a touch sensing module communicatively coupled to said main control module, said touch sensing module employing a capacitive touch chip for receiving user local control input, said main control module responsive to user input for adjusting parameters of said sleep adjustment light effects and audio playback modes of said audio module in real time.
  9. 9. The intelligent sleep environment adjustment system according to any one of claims 1 to 8, wherein: The main control module integrates a wireless communication unit, and the wireless communication unit is used for encrypting and transmitting the desensitized sleep report and the identification result to the user terminal; And/or the system further comprises a shell, wherein the main control module, the sleep perception module, the sleep stage inference module, the light effect strategy generation module and the light effect execution module are integrated in the shell.
  10. 10. An intelligent sleep environment adjustment method applied to the intelligent sleep environment adjustment system according to any one of claims 1 to 9, characterized by comprising the steps of: S100, continuously acquiring multi-source heterogeneous data in a time-synchronous manner by a sleep perception module, and performing filtering, denoising, non-uniformity correction and anti-shake preprocessing on the original multi-source heterogeneous data by the main control module; s200, a sleep stage deducing module conducts feature extraction and depth fusion on the preprocessed multi-source heterogeneous data, and deduces the sleep stage of a user through a neural network model; S300, the main control module receives the sleep stage and generates a corresponding light control instruction by combining a user history preference model; S400, responding to the light control instruction by the light effect strategy generation module, and outputting a light effect driving signal matched with the current sleep stage; S500, encrypting and storing complete closed-loop data including original sensing data, an identification result, a light-operated instruction and a feedback state change by a system; And S600, returning to the step S100 to continue to monitor in real time, and performing local incremental learning on the neural network model by utilizing the closed-loop data recorded in the step S500 in an idle period to optimize the recognition accuracy and the suitability of a feedback strategy so as to form an intelligent closed loop.

Description

Intelligent sleep environment adjusting system and method Technical Field The invention relates to the technical field of sleep regulation, in particular to an intelligent sleep environment regulation system and method. Background Sleep is an indispensable vital activity of people, good sleep is critical to the health of people, sleep problems such as sleep disturbance and sleep diseases affect the work and life of people and become inducement of many diseases, and therefore, the sleep quality of people is required to be monitored. Chinese patent CN110585551a discloses a lamplight wake-up control system based on sleep stage. The system comprises a basic data collector, a processor and a wake-up device. According to the basic data of the user, the sleep stage of the user is calculated, and the wake-up device is controlled to form differentiated and weak-to-strong light stimulus, wherein the light stimulus is continuously and gradually changed in the whole wake-up process. However, the basic data collector acquires basic data of the user through the portable wearable device, and the wearable monitoring brings discomfort to the user and affects sleep. Therefore, the existing sleep adjustment scheme has the technical problems of user discomfort and high misjudgment rate. Disclosure of Invention The invention aims to provide an intelligent sleep environment adjusting system and method, and aims to solve the technical problems of discomfort of a user and high misjudgment rate of the existing sleep adjusting scheme. In a first aspect, the application provides an intelligent sleep environment adjusting system, which comprises a main control module, a sleep sensing module, a sleep stage deducing module, a light effect strategy generating module and a light effect executing module, wherein the sleep sensing module senses vital sign signals, temperature distribution information and space contour information in a monitoring area in a non-contact mode, and the vital sign signals comprise respiratory rate, heart rate and body movement signals of a user; The main control module generates different light control instructions based on different sleep stages, the light effect strategy generation module responds to the light control instructions and outputs light effect driving signals corresponding to the sleep stages, and the light effect execution module generates sleep adjustment light effects according to the light effect driving signals. In a second aspect, the present application provides an intelligent sleep environment adjustment method, which is applied to any one of the above intelligent sleep environment adjustment systems, and includes the following steps: S100, continuously acquiring multi-source heterogeneous data in a time-synchronous manner by a sleep perception module, and performing filtering, denoising, non-uniformity correction and anti-shake preprocessing on the original multi-source heterogeneous data by the main control module; s200, a sleep stage deducing module conducts feature extraction and depth fusion on the preprocessed multi-source heterogeneous data, and deduces the sleep stage of a user through a neural network model; S300, the main control module receives the sleep stage and dynamically generates a light control instruction by combining a user history preference model; S400, responding to the light control instruction by the light effect strategy generation module, and outputting a light effect driving signal matched with the current sleep stage; S500, encrypting and storing complete closed-loop data including original sensing data, an identification result, a light-operated instruction and a feedback state change by a system; And S600, returning to the step S100 to continue to monitor in real time, and performing local incremental learning on the neural network model by utilizing the closed-loop data recorded in the step S500 in an idle period to optimize the recognition accuracy and the suitability of a feedback strategy so as to form an intelligent closed loop. The intelligent sleep environment adjusting system and method have the advantages that the sleep sensing module adopts the non-contact sensing vital sign signals, the temperature distribution information and the spatial profile information in the monitoring area to eliminate wearing discomfort and sleep interference and support long-term noninductive monitoring, the sleep stage deducing module enables multi-source heterogeneous data to be deeply fused to achieve accurate recognition of sleep stages, overcomes the defects of low accuracy, poor interference resistance and weak scene understanding of a single sensor, greatly reduces misjudgment rate and improves system robustness, and the sleep adjusting light effect is used for completing closed loop adjustment to achieve upgrading from passive monitoring to active sleep adjustment, so that interaction is more intelligent, and the technical problems of user discomfort and high misjud