Search

CN-122004626-A - Temperature regulation and control method, device and equipment for intelligent mattress and storage medium

CN122004626ACN 122004626 ACN122004626 ACN 122004626ACN-122004626-A

Abstract

The application discloses a temperature regulation and control method, a device, equipment and a storage medium of an intelligent mattress, which acquire model information of the intelligent mattress to determine standard reflection duration of temperature regulation and control of the intelligent mattress, and synchronously acquiring sensor parameters, system environment parameters (including the current working temperature) and individual sign information of the target object when the intelligent mattress is used. Next, first feature data characterizing the current state of the user is extracted based on the multi-source information. The first characteristic data is input to a human thermal comfort prediction model so as to predict a thermal sensation of a user after a standard reflection period. According to the prediction result, the working temperature of the intelligent mattress can be regulated and controlled in advance, and the passive response is changed into active intervention, so that the thermal sensation of a user is stabilized in a comfortable range, sleep interruption caused by temperature fluctuation is effectively avoided, and the sleep experience of the user is improved. The intelligent mattress can be widely applied to the technical field of intelligent mattresses.

Inventors

  • WANG BINGKUN

Assignees

  • 慕思健康睡眠股份有限公司

Dates

Publication Date
20260512
Application Date
20260116

Claims (10)

  1. 1. A method for temperature regulation of an intelligent mattress, the method comprising: obtaining model information of the intelligent mattress, and determining standard reflection duration of temperature regulation and control of the intelligent mattress according to the model information; Acquiring sensor parameters and system environment parameters of a target object when the target object uses the intelligent mattress, and acquiring individual sign information corresponding to the target object, wherein the system environment parameters comprise the current working temperature of the intelligent mattress; Extracting and obtaining first characteristic data corresponding to the target object at present according to the sensor parameters, the system environment parameters and the individual sign information; According to the first characteristic data and the standard reflection duration, predicting a first thermal sensation prediction result corresponding to the target object after the standard reflection duration by using a human thermal comfort prediction model; And regulating and controlling the working temperature of the intelligent mattress according to the first heat sensation prediction result.
  2. 2. The method for controlling temperature of an intelligent mattress according to claim 1, wherein the step of acquiring the sensor parameters of the target object when the intelligent mattress is in use comprises: And acquiring physiological signals of the target object through a sensor arranged in the intelligent mattress, wherein the physiological signals comprise at least one of heart rate signals, respiratory signals or body movement signals.
  3. 3. The method for controlling temperature of an intelligent mattress according to claim 2, wherein the extracting, according to the sensor parameter, the system environment parameter and the individual sign information, the first feature data of the target object corresponding to the current time includes: Preprocessing the physiological signal and segmenting a sliding window to obtain segmented signals under a plurality of time windows; extracting the characteristics of each segmented signal to obtain second characteristic data; and performing feature stitching on the second feature data, the system environment parameters and the individual feature information to obtain the first feature data.
  4. 4. The temperature regulation method of an intelligent mattress according to claim 1, wherein the human thermal comfort prediction model is obtained by: Acquiring an initial predictive model pre-trained on a large-scale training dataset; Acquiring a plurality of groups of historical characteristic data extracted by the target object when the intelligent mattress is used in a previous period, and feeding back the thermal sensation experience of the target object; determining personalized labels corresponding to each group of historical characteristic data according to the thermal sensation experience feedback, wherein the personalized labels are used for representing real thermal sensation of the target object after the time point corresponding to the historical characteristic data passes through the standard reflection duration; And performing fine tuning training on the initial prediction model according to each group of the historical characteristic data and the personalized tag to obtain the human thermal comfort prediction model.
  5. 5. The method of claim 4, wherein the obtaining an initial predictive model pre-trained on a large-scale training dataset comprises: Acquiring a plurality of groups of sample feature data extracted by a plurality of sample objects when the intelligent mattress is used and training labels of the sample objects, wherein the training labels are used for representing real heat sensation of the sample objects after the sample feature data correspond to time points and the standard reflection time length; predicting a second thermal sensation prediction result corresponding to the sample object after the time point corresponding to the sample characteristic data passes through the standard reflection duration according to the sample characteristic data and the standard reflection duration through an initial prediction model; determining a training loss value according to the second thermal sensation prediction result and the training label; and carrying out parameter updating on the initial prediction model according to the loss value to obtain a trained initial prediction model.
  6. 6. The method of claim 4, wherein obtaining the thermal sensory experience feedback of the target object comprises: Acquiring a regulating instruction of the target object to the intelligent mattress after the time point corresponding to the historical characteristic data passes through the standard reflection duration; And determining the thermal sensation experience feedback of the target object according to the regulation and control instruction.
  7. 7. The method of any one of claims 1-6, wherein said controlling said operating temperature of said intelligent mattress based on said first thermal sensation prediction result comprises: if the first thermal sensation prediction result is characterized as cold, increasing the working temperature of the intelligent mattress; or if the first thermal sensation prediction result is characterized as neutral, maintaining the operating temperature of the intelligent mattress; or if the first thermal sensation prediction result is characterized as hot, reducing the operating temperature of the intelligent mattress.
  8. 8. A temperature regulation apparatus for an intelligent mattress, the apparatus comprising: The intelligent mattress temperature control system comprises an acquisition unit, a control unit and a control unit, wherein the acquisition unit is used for acquiring model information of the intelligent mattress and determining standard reflection duration of temperature control of the intelligent mattress according to the model information; the intelligent mattress comprises an acquisition unit, a control unit and a control unit, wherein the acquisition unit is used for acquiring sensor parameters and system environment parameters of a target object when the intelligent mattress is used, and acquiring individual sign information corresponding to the target object, wherein the system environment parameters comprise the current working temperature of the intelligent mattress; The extraction unit is used for extracting and obtaining first characteristic data corresponding to the target object at present according to the sensor parameters, the system environment parameters and the individual sign information; The prediction unit is used for predicting a first thermal sensation prediction result corresponding to the target object after the standard reflection duration through a human thermal comfort prediction model according to the first characteristic data and the standard reflection duration; and the execution unit is used for regulating and controlling the working temperature of the intelligent mattress according to the first thermal sensation prediction result.
  9. 9. An electronic device, comprising: At least one processor; at least one memory for storing at least one program; When the at least one program is executed by the at least one processor, the at least one processor is caused to implement a method of temperature regulation of an intelligent mattress as claimed in any one of claims 1 to 7.
  10. 10. A computer readable storage medium, in which a processor executable program is stored, characterized in that the processor executable program is for implementing a temperature regulation method of an intelligent mattress according to any one of claims 1-7 when being executed by a processor.

Description

Temperature regulation and control method, device and equipment for intelligent mattress and storage medium Technical Field The application relates to the technical field of intelligent mattresses, in particular to a temperature regulation and control method, a device, equipment and a storage medium of an intelligent mattress. Background With the popularization of smart home and healthy sleep concepts, users have increasingly increased thermal comfort requirements for sleep environments, and a continuous and stable personalized sleep temperature experience is expected. Based on the background, intelligent mattresses with temperature regulation function gradually enter the market. In the related art, the temperature control strategy of the intelligent mattress is simpler and more direct, and is mostly dependent on manual setting of a user, a preset program or feedback adjustment based on the instant body temperature and the ambient temperature. The method is difficult to effectively cope with the physiological state of the user which dynamically changes in the sleeping process, the regulation and control actions are often delayed from the actual thermal sensation change of the user, so that the user can respond passively after uncomfortable feeling occurs, the sleeping is easily interrupted frequently, and the overall comfortable experience is influenced. In view of the above, there is a need to solve the problems of the related art. Disclosure of Invention The present application aims to solve at least one of the technical problems existing in the related art to a certain extent. Therefore, an object of the embodiments of the present application is to provide a temperature regulation method, apparatus, device and storage medium for an intelligent mattress. In order to achieve the technical purpose, the technical scheme adopted by the embodiment of the application comprises the following steps: in one aspect, an embodiment of the present application provides a temperature regulation method for an intelligent mattress, where the method includes: obtaining model information of the intelligent mattress, and determining standard reflection duration of temperature regulation and control of the intelligent mattress according to the model information; Acquiring sensor parameters and system environment parameters of a target object when the target object uses the intelligent mattress, and acquiring individual sign information corresponding to the target object, wherein the system environment parameters comprise the current working temperature of the intelligent mattress; Extracting and obtaining first characteristic data corresponding to the target object at present according to the sensor parameters, the system environment parameters and the individual sign information; According to the first characteristic data and the standard reflection duration, predicting a first thermal sensation prediction result corresponding to the target object after the standard reflection duration by using a human thermal comfort prediction model; And regulating and controlling the working temperature of the intelligent mattress according to the first heat sensation prediction result. In addition, the temperature regulation method of the intelligent mattress according to the embodiment of the application can also have the following additional technical characteristics: further, in one embodiment of the present application, the collecting the sensor parameters of the target object when using the intelligent mattress includes: And acquiring physiological signals of the target object through a sensor arranged in the intelligent mattress, wherein the physiological signals comprise at least one of heart rate signals, respiratory signals or body movement signals. Further, in an embodiment of the present application, the extracting, according to the sensor parameter, the system environment parameter and the individual sign information, the first feature data of the target object corresponding to the current object includes: Preprocessing the physiological signal and segmenting a sliding window to obtain segmented signals under a plurality of time windows; extracting the characteristics of each segmented signal to obtain second characteristic data; and performing feature stitching on the second feature data, the system environment parameters and the individual feature information to obtain the first feature data. Further, in one embodiment of the present application, the human thermal comfort prediction model is obtained by: Acquiring an initial predictive model pre-trained on a large-scale training dataset; Acquiring a plurality of groups of historical characteristic data extracted by the target object when the intelligent mattress is used in a previous period, and feeding back the thermal sensation experience of the target object; determining personalized labels corresponding to each group of historical characteristic data according to the th