Search

CN-121993009-A - Window closing control method, intelligent window and intelligent home system

CN121993009ACN 121993009 ACN121993009 ACN 121993009ACN-121993009-A

Abstract

The application discloses a window closing control method, an intelligent window and an intelligent home system, and relates to the technical field of intelligent home, wherein the method is applied to the intelligent window, the intelligent window comprises a window body and a pickup sensor arranged on the window body, and the method comprises the steps of acquiring sound signals acquired by the pickup sensor; and judging whether rainfall occurs based on the sound signals, and closing the window if the judgment result is that the rainfall occurs. The intelligent window automatic closing method and the intelligent window automatic closing device improve accuracy and timeliness of the intelligent window during automatic window closing.

Inventors

  • ZHOU JIANFENG

Assignees

  • 歌尔智能科技有限公司

Dates

Publication Date
20260508
Application Date
20260204

Claims (10)

  1. 1. The window closing control method is characterized by being applied to an intelligent window, wherein the intelligent window comprises a window body and a pickup sensor arranged on the window body, and the window closing control method comprises the following steps of: Acquiring sound signals acquired by the pickup sensor; judging whether rainfall occurs or not based on the sound signal; And if the rainfall occurs, closing the window.
  2. 2. The window closing control method according to claim 1, wherein the step of determining whether rainfall occurs based on the sound signal includes: Extracting sound features from the sound signal, wherein the sound features include at least one of pulse density features, energy variation features, and spectral features; matching the sound characteristics with a preset raindrop knocking characteristic model to obtain a matching result; if the matching result is that the matching is successful, determining that rainfall occurs; And if the matching result is that the matching fails, determining that rainfall does not occur.
  3. 3. The window closing control method according to claim 2, wherein the sound features include the pulse density features, the spectrum features and the energy variation features, and the step of matching the sound features with a preset raindrop striking feature model to obtain a matching result includes: Performing a first match based on the pulse density characteristics, a second match based on the spectral characteristics, and a third match based on the energy variation characteristics, respectively; if the first matching, the second matching and the third matching are successful, determining that the matching result is successful in matching with a preset raindrop knocking feature model; If any one of the first matching, the second matching and the third matching fails, determining that the matching result fails to match with a preset raindrop knocking feature model; The first matching is to judge whether the pulse density of the sound signal is in a preset first threshold range; The second matching is to judge whether the energy duty ratio of a preset intermediate frequency band is larger than a preset second threshold value in the frequency spectrum of the sound signal and/or whether a characteristic formant related to raindrop knocking is detected; The third matching is whether the rising time of the energy envelope of the sound signal is smaller than a preset first time threshold value and/or whether the decay time of the energy envelope is larger than a preset second time threshold value.
  4. 4. A window closing control method according to claim 3, wherein the steps of performing a first match based on the pulse density characteristic, a second match based on the spectral characteristic, and a third match based on the energy variation characteristic, respectively, include Performing a first match based on the pulse density characteristics; if the first matching is successful, performing a second matching based on the spectral features; And if the second matching is successful, performing a third matching based on the energy variation characteristic.
  5. 5. The window closing control method according to claim 3, wherein before the step of determining that the matching result is successful with the preset raindrop striking feature model, the method further comprises: respectively obtaining matching degree scores of the first matching, the second matching and the third matching; Weighting calculation is carried out on the matching degree score based on a preset weight coefficient, so that comprehensive matching degree is obtained; If the comprehensive matching degree is greater than or equal to a preset comprehensive threshold value, executing the step of determining that the matching result fails to match with a preset raindrop knocking feature model; If the comprehensive matching degree is smaller than a preset comprehensive threshold, determining that the matching result is failed to match with a preset raindrop knocking feature model.
  6. 6. The window closing control method according to claim 1, wherein after the step of determining whether or not rainfall occurs based on the sound signal, the method further comprises: If the judgment result shows that rainfall does not occur, the sound signal is used as background environmental noise; Constructing or updating a background noise feature model based on the background environmental noise, wherein the background noise feature model is a model for representing environmental background noise statistical features; and carrying out noise reduction processing on the sound signals acquired next time based on the background noise characteristic model, and executing the step of judging whether rainfall occurs or not based on the sound signals based on the noise reduced sound signals.
  7. 7. The window closing control method according to claim 6, wherein the step of constructing or updating a background noise feature model based on the background environmental noise comprises: extracting noise features from the background ambient noise, the noise features comprising noise spectral magnitudes and/or noise energy levels; and constructing or updating a background noise characteristic model based on the extracted noise characteristics.
  8. 8. The window closing control method according to any one of claims 1 to 7, wherein the step of closing the window includes: Searching a target signal matched with the sound signal in a preset user habit database; Acquiring window closing control parameters corresponding to the target signals in the preset user habit database, wherein the window closing control parameters comprise window closing speed and/or window closing angle; and closing the window according to the window closing control parameters.
  9. 9. A smart window, characterized in that it comprises a window body, a pickup sensor provided in the window body, and a control unit, the pickup sensor being connected to the control unit, the control unit being adapted to perform the steps of the window closing control method according to any one of claims 1 to 8.
  10. 10. An intelligent home system, characterized in that the intelligent home system comprises an intelligent window and a center console, the intelligent window comprises a window body and a pickup sensor arranged on the window body, and the center console is used for executing the steps of the window closing control method according to any one of claims 1 to 8.

Description

Window closing control method, intelligent window and intelligent home system Technical Field The application relates to the technical field of intelligent home, in particular to a window closing control method, an intelligent window and an intelligent home system. Background With the rapid development of smart home technology, smart windows are becoming increasingly integrated into people's daily lives as an important component of home environment control. The intelligent window can automatically sense environmental changes and execute corresponding operations, so that a more convenient and comfortable living experience is provided for a user, and the intelligent window has potential application value in the aspect of coping with sudden weather changes. Conventional automatic window closing schemes are mostly dependent on environmental sensors or external weather information. For example, some systems detect raindrops directly through humidity sensors installed outside the window, or acquire real-time weather forecast data through networking, and issue window closing instructions when it is determined that rainfall is likely. However, the above-mentioned existing methods still have certain limitations. Specifically, the method relying on local humidity detection is susceptible to environmental interference (such as splash, fog, etc.) and may lead to erroneous judgment, and the method based on weather forecast information has the problems of information update delay and insufficient regional accuracy, so that immediate response to sudden local rainfall is impossible. Therefore, how to improve the accuracy and timeliness of smart windows during automatic window closing has become a technical problem to be solved. Disclosure of Invention The application mainly aims to provide a window closing control method, an intelligent window and an intelligent home system, and aims to solve the technical problem of how to improve the accuracy and timeliness of the intelligent window during automatic window closing. In order to achieve the above object, the present application provides a window closing control method, which is applied to an intelligent window, wherein the intelligent window comprises a window body and a pickup sensor arranged on the window body, and the window closing control method comprises the following steps: Acquiring sound signals acquired by the pickup sensor; judging whether rainfall occurs or not based on the sound signal; And if the rainfall occurs, closing the window. In one embodiment, the step of determining whether rainfall occurs based on the sound signal includes: Extracting sound features from the sound signal, wherein the sound features include at least one of pulse density features, energy variation features, and spectral features; matching the sound characteristics with a preset raindrop knocking characteristic model to obtain a matching result; if the matching result is that the matching is successful, determining that rainfall occurs; And if the matching result is that the matching fails, determining that rainfall does not occur. In an embodiment, the sound features include the pulse density feature, the frequency spectrum feature and the energy variation feature, and the step of matching the sound features with a preset raindrop knocking feature model to obtain a matching result includes: Performing a first match based on the pulse density characteristics, a second match based on the spectral characteristics, and a third match based on the energy variation characteristics, respectively; if the first matching, the second matching and the third matching are successful, determining that the matching result is successful in matching with a preset raindrop knocking feature model; If any one of the first matching, the second matching and the third matching fails, determining that the matching result fails to match with a preset raindrop knocking feature model; The first matching is to judge whether the pulse density of the sound signal is in a preset first threshold range; The second matching is to judge whether the energy duty ratio of a preset intermediate frequency band is larger than a preset second threshold value in the frequency spectrum of the sound signal and/or whether a characteristic formant related to raindrop knocking is detected; The third matching is whether the rising time of the energy envelope of the sound signal is smaller than a preset first time threshold value and/or whether the decay time of the energy envelope is larger than a preset second time threshold value. In one embodiment, the steps of performing a first match based on the pulse density characteristics, a second match based on the spectral characteristics, and a third match based on the energy variation characteristics, respectively, include Performing a first match based on the pulse density characteristics; if the first matching is successful, performing a second matching based on the spectral features;