A bedding control method, device, electronic device, and storage medium

Abstract

The present invention discloses a bedding control method, device, electronic device and storage medium. Among them, the method includes: when it is determined that the target bedding enters the use state, monitoring the air pressure change state in the target bedding; determining the target air pressure value of the target bedding according to a preset neural network model under the air pressure change state; and adjusting the target bedding according to the target air pressure value. The embodiments of the present invention realize precise control of the air pressure of the bedding, enable the bedding to precisely adapt to the user's body state, can improve the intelligence level of the bedding, and enhance the user's sleep quality.

Description

Technical Field

[0001] The present invention relates to the field of computer application technologies, and in particular, to a bedding control method, device, electronic device, and storage medium. Background Art

[0002] With the development of intelligence, the intelligence level of bedding such as beds, mattresses, and pillows has gradually increased. In order to improve the sleep quality of users, the intelligence of bedding needs to meet the needs of users, so that the bedding can truly improve the user's sleep. How to achieve intelligent control of bedding through the sleep information of users and enhance the user experience has become the research focus in the current industry. Currently, common intelligent bedding is equipped with pressure sensors to collect the pressure of the user's head on the bedding during sleep and control the bedding based on this pressure to meet the user's usage needs. Taking an intelligent pillow as an example, some solutions have been proposed to extend a pressure sensor outward on the side of the pillow facing the human shoulder, and some other solutions require setting sensors and their circuit accessories inside the pillow. However, these methods often destroy the original comfortable state of the bedding, resulting in the intelligence of the bedding actually reducing the user's sleep quality. Therefore, there is an urgent need for a bedding control method that can accurately adjust the bedding based on the user's sleep state without changing the structural state of the bedding, thereby enhancing the user experience. Summary of the Invention

[0003] The present invention provides a bedding control method, device, electronic device, and storage medium to achieve precise control of the air pressure of the bedding, enabling the bedding to accurately adapt to the user's body state, improving the intelligence level of the bedding, and enhancing the user's sleep quality.

[0004] According to one aspect of the present invention, there is provided a bedding control method, which includes:

[0005] When it is determined that the target bedding enters the usage state, monitoring the air pressure change state inside the target bedding;

[0006] Determining the target air pressure value of the target bedding according to a preset neural network model under the air pressure change state;

[0007] Adjusting the target bedding according to the target air pressure value.

[0008] According to another aspect of the present invention, there is provided a bedding control device, which includes:

[0009] A state detection module, configured to monitor the air pressure change state inside the target bedding when it is determined that the target bedding enters the usage state;

[0010] An air pressure determination module, configured to determine the target air pressure value of the target bedding according to a preset neural network model under the air pressure change state;

[0011] An adjustment control module for adjusting the target bedding according to the target air pressure value.

[0012] According to another aspect of the present invention, there is provided an electronic device, which includes:

[0013] At least one processor; and

[0014] A memory communicatively connected to the at least one processor; wherein,

[0015] The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the bedding control method according to any embodiment of the present invention.

[0016] According to another aspect of the present invention, there is provided a computer-readable storage medium storing computer instructions for causing a processor to implement the bedding control method according to any embodiment of the present invention when executed.

[0017] The technical solution of the embodiment of the present invention obtains the air pressure change state in the target bedding when the target bedding enters the working state, determines the target air pressure value of the target bedding according to the air pressure change state and a preset neural network model, and adjusts the target bedding according to the target air pressure value, so that the state of the target bedding adapts to the user's body parameters, which can enhance the intelligence level of the bedding and thus improve the user's sleep quality.

[0018] It should be understood that the content described in this part is not intended to identify the key or important features of the embodiments of the present invention, nor is it used to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0020] Figure 1 is a flowchart of a bedding control method provided according to Embodiment 1 of the present invention;

[0021] Figure 2 is a flowchart of a bedding control method provided according to Embodiment 2 of the present invention;

[0022] Figure 3It is a flowchart of another bedding control method provided according to Embodiment 3 of the present invention;

[0023] Figure 4 It is a flowchart of another bedding control method provided according to Embodiment 4 of the present invention;

[0024] Figure 5 It is an example diagram of the air pressure change state of a pillow provided according to Embodiment 5 of the present invention;

[0025] Figure 6 It is an example diagram of digital filtering processing provided according to Embodiment 5 of the present invention;

[0026] Figure 7 It is an example diagram of off-pillow judgment provided according to Embodiment 5 of the present invention;

[0027] Figure 8 It is an example diagram of bedding control provided according to Embodiment 5 of the present invention;

[0028] Figure 9 It is a schematic structural diagram of a bedding control device provided according to Embodiment 6 of the present invention;

[0029] Figure 10 It is a schematic structural diagram of an electronic device for the bedding control method provided according to the embodiment of the present invention. Detailed implementation manners

[0030] In order to enable those skilled in the art to better understand the solution of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0031] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above drawings are used to distinguish similar objects, and do not necessarily need to describe a specific order or sequence. It should be understood that such data can be interchanged under appropriate circumstances so that the embodiments of the present invention described here can be implemented in an order different from those illustrated or described here. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device including a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but may include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0032] Embodiment 1

[0033] Figure 1 It is a flowchart of a bedding control method provided in Embodiment 1 of the present invention. This embodiment is applicable to the situation of adjusting the bedding according to the user's sleep state. This method can be executed by a bedding control device, which can be implemented in the form of hardware and / or software, and can be configured in the main control unit of the bedding. As Figure 1 shown, the method includes:

[0034] Step 110, when it is determined that the target bedding enters the use state, monitor the air pressure change state inside the target bedding.

[0035] Among them, the target bedding can be a sleep tool used by the user. The target bedding can include pillows, mattresses, beds, etc. The target bedding can include one or more airbags, and the airbag can provide sleep support for the user. The use state can be the state where the user is located on the target bedding and the target bedding provides sleep support for the user. Taking the target bedding as a pillow as an example, the use state can be the state where the user's head is on the pillow. The air pressure change state can be the change situation of the air pressure value of the airbag inside the target bedding. For example, the air pressure change state can be the change from low air pressure to high air pressure or the change from high air pressure to low air pressure, etc.

[0036] In the embodiment of the present invention, the use state of the target bedding can be monitored. After it is determined that the target bedding enters the use state, the air pressure inside the target bedding can be collected, and the air pressure change within a period of time can be used as the air pressure change state of the target bedding. It can be understood that the air pressure inside the target bedding can be the air pressure value at the air inlet end of the target bedding or the air pressure value inside the target bedding.

[0037] Step 120, determine the target air pressure value of the target bedding according to a preset neural network model under the air pressure change state.

[0038] Among them, the preset neural network model can be a neural network model trained according to the air pressure change state of the target bedding and the air pressure value that best matches the user. The preset neural network model can determine an air pressure value through the air pressure change state, and this air pressure value is the most suitable for the user's most comfortable state when using the target bedding to sleep. The target air pressure value can be the air pressure value used to adjust the target bedding, and the target air pressure value can provide the best sleep experience for the user. For example, when the target bedding is a pillow, the target air pressure value inside the pillow can be the air pressure value that provides the best pillow height and the softness and hardness of the pillow.

[0039] In an embodiment of the present invention, a pre-trained preset neural network model can be obtained. The preset neural network model can be trained by the user in the initialization state of the target bedding, the air pressure change state of the target bedding can be input into the preset neural network model, and the preset neural network model can predict the target air pressure value that meets the user's needs.

[0040] Step 130: Adjust the target bedding according to the target air pressure value.

[0041] In an embodiment of the present invention, the target bedding can be adjusted according to the target air pressure value so that the air pressure inside the target bedding meets the target air pressure value. For example, when the air pressure value inside the target bedding is higher than the target air pressure value, the target bedding can be controlled to be deflated until the air pressure value of the target bedding reaches the target air pressure value; or, when the air pressure value inside the target bedding is lower than the target air pressure value, the target bedding can be controlled to be inflated until the air pressure value of the target bedding reaches the target air pressure value.

[0042] In an embodiment of the present invention, the air pressure change state in the target bedding is obtained when the target bedding enters a working state, the target air pressure value of the target bedding is determined according to the air pressure change state and a preset neural network model, and the target bedding is adjusted according to the target air pressure value, so that the state of the target bedding adapts to the user's body parameters, which can enhance the intelligence of the bedding, thereby improving the user's sleep quality. At the same time, the bedding can be accurately adjusted based on the user's sleep state without changing the structural state of the bedding, thereby improving the user's usage experience.

[0043] Embodiment 2

[0044] Figure 2 is a flow chart of a bedding control method provided according to the second embodiment of the present invention. The embodiment of the present invention is a specific embodiment of the above invention, and describes in detail the monitoring process of the air pressure change state in the bedding. Figure 2 The bedding control method provided by the embodiment of the present invention specifically includes the following steps:

[0045] Step 210: Collect the real-time pressure value of the target bedding after power-on according to a preset time period.

[0046] Among them, the preset time period can be a collection period of the air pressure in the target bedding, and the air pressure value in the target bedding can be collected regularly according to the preset time period. The real-time pressure value can be the air pressure value collected in the target bedding according to the preset time period. The real-time pressure value can specifically be the air pressure value in one or more airbags in the target bedding.

[0047] In an embodiment of the present invention, after the target bedding is powered on, the air pressure value inside the target bedding can be collected at a preset time period as the real-time pressure value. Exemplarily, the output air pressure value of the air pump of the target bedding can be used as the real-time pressure value of the target bedding.

[0048] Step 220: When the waveform of the pressure curve formed by the real-time pressure values satisfies the preset characteristic conditions, it is determined that the target bedding enters the use state.

[0049] Among them, the pressure curve can be a curve formed by connecting the real-time pressure values in sequence according to time. The waveform can be the change shape of the pressure curve, and the waveform can reflect the user's sleeping state on the target bedding. The preset characteristic conditions can be the characteristic information for judging that the target bedding enters the use state, and the preset characteristic conditions can include specific change situations of the waveform.

[0050] Specifically, the collected real-time pressure values can be used to form a pressure curve according to time, and the pressure curve can be detected to determine whether the waveform of the pressure curve satisfies the specific waveform set in the preset characteristic conditions. If the waveform of the pressure curve satisfies the preset characteristic conditions, it can be determined that the target bedding enters the use state. If the waveform of the pressure curve does not satisfy the preset characteristic conditions, it can be determined that the target bedding has not entered the use state. Exemplarily, the real-time pressure values within 10 seconds of the target bedding can be used to form a pressure curve, and it can be determined whether there is a waveform of pressure change in the curve. If so, it is determined that the target bedding enters the use state, otherwise the target bedding has not entered the use state.

[0051] Step 230: Collect the airbag pressures of the head airbag and the neck airbag of the target bedding.

[0052] Among them, the head airbag and the neck airbag can be airbags in the target bedding that provide support for the user's head or the user's neck respectively. The shapes and numbers of the head airbag and the neck airbag in the target bedding are not limited herein. The airbag pressure can be the air pressure value inside the head airbag and the neck airbag in the target bedding, and the airbag pressure can be determined by the air pressure sensor of the target bedding.

[0053] In an embodiment of the present invention, the air pressure sensor of the target bedding can be monitored to collect the airbag pressures of the head airbag and the neck airbag inside the target bedding. It can be understood that there can be one or more air pumps in the target bedding, and each air pump can provide air pressure for the head airbag or the neck airbag separately, or the air pump can provide air pressure for the head airbag and the neck airbag together.

[0054] Step 240: Use the change curve of the airbag pressure over time as the air pressure change state.

[0055] In an embodiment of the present invention, the variation curve generated by sorting the collected airbag pressure according to time can be used as the air pressure variation state, and the variation of the airbag pressure of the target bedding can be used as the air pressure variation state.

[0056] Step 250: Determine the target air pressure value of the target bedding according to the preset neural network model under the air pressure variation state.

[0057] Step 260: Adjust the target bedding according to the target air pressure value.

[0058] In an embodiment of the present invention, the real-time pressure value after the target bedding is powered on is collected through a preset time period. When the waveform of the pressure curve formed by processing the real-time pressure value meets the preset characteristic conditions, it is determined that the target bedding enters the use state. The airbag pressures of the head airbag and the neck airbag of the target bedding are collected, and the variation curve of the airbag pressure with time is used as the air pressure variation state. The target air pressure value corresponding to this air pressure variation state is determined according to the preset neural network model, and the head airbag and the neck airbag of the target bedding are adjusted according to the target air pressure value, so as to accurately adjust the air pressure in the target bedding, enhance the adaptability between the target bedding and the user, improve the user's bedtime experience, and enhance the user's sleep quality.

[0059] Further, on the basis of the above-mentioned embodiment of the invention, the preset characteristic conditions include: there is a change rate of the real-time pressure value at the first moment greater than the first threshold, and after the first moment, the fluctuation range of the change rate of the real-time pressure value meets less than the second threshold.

[0060] In the implementation of the present invention, the change rate of the real-time pressure value at different moments can be determined, and the change rate can be compared with the preset first threshold respectively. Among them, the first threshold can be a change rate threshold, and the first threshold can be configured based on experiments or user experience. When the change rate of the real-time pressure is greater than the first threshold, it can be judged whether the real-time pressure value after the first moment is stable within a range, that is, the fluctuation range of the change rate of the real-time pressure value is less than the second threshold. In this case, it can be determined that the waveform of the real-time pressure value meets the condition for the target bedding to enter the use state. Taking the target bedding as a pillow as an example, after the user lies on the pillow, the pressure of the pillow will generate a waveform, which rapidly rises within a certain period of time and remains stable in the subsequent period of time. For this characteristic, the first threshold and the second threshold of the preset characteristic conditions of the pillow can be set as the average change rate of the rapid rise and the average pressure value maintained by the pressure value of the corresponding type of pillow. It can be understood that for different types of target bedding, the first threshold and the second threshold in the preset characteristic conditions set for it can be different.

[0061] Embodiment III

[0062] Figure 3It is a flowchart of another bedding control method provided by Embodiment 3 of the present invention. The embodiments of the present invention are specific implementations based on the above-mentioned invention embodiments, and the training process of the preset neural network model is described in detail. Refer to Figure 3 The method provided by the embodiments of the present invention specifically includes the following steps:

[0063] Step 310: Read the user historical state parameters corresponding to the target bedding.

[0064] Among them, the user historical state parameters may be the air pressure change state when the user used the target bedding in the past. It can be understood that the user historical state parameters may not be limited to the current target bedding, and may also include the user usage state parameters of the target bedding of the same type.

[0065] In the embodiments of the present invention, when it is necessary to train the preset neural network model, the user historical state parameters of the target bedding can be read. The user historical state parameters can be stored in the target bedding or the cloud server that manages the target bedding, and the corresponding user historical state parameters can be obtained through the identification information of the target bedding.

[0066] Step 320: Collect the airbag pressure in the target bedding when the target bedding enters the usage state.

[0067] In the embodiments of the present invention, the airbag pressure after the target bedding enters the usage state can be collected. The airbag pressure can be the internal air pressure of the airbag in the target bedding.

[0068] Step 330: Determine the user body state parameters according to the airbag shape parameters and airbag pressure of the target bedding.

[0069] Among them, the airbag shape parameters may be information reflecting the shape of the airbag in the target bedding. The airbag shape parameters may include information such as the shape and size of the airbag. The airbag shape parameters and airbag pressure can be used to determine the airbag height, thereby improving the user experience of using the target bedding. The user body state parameters may include the body parameters of the user in the optimal state of using the target bedding. The user body state parameters may include the head height, neck height, waist height, etc.

[0070] In the embodiments of the present invention, the height required by the user at the corresponding position can be determined through the airbag shape parameters and airbag pressure at different positions in the target bedding, and this height can be used as the user body state parameters. It can be understood that taking the target bedding as a pillow, there may be a matching relationship between the head and neck height of the user and the pressure of the airbag in the pillow. Assuming the airbag is a cylinder, the ideal gas state equation can be expressed as: P×V = n×R×T

[0071] Wherein, P represents the pressure of the gas, V represents the volume of the gas, n represents the amount of substance of the gas, R is the gas constant, and T represents the absolute temperature of the gas. Here, since the airbags in the head and neck are relatively small, the influence of T can be ignored. At this time, the formula can be expressed as:

[0072] P×V=n×R

[0073] At this time, the relationship between pressure and volume is:

[0074] P=(n×R) / V

[0075] For a cylindrical airbag, its volume can be expressed as:

[0076] V=π×r2×h

[0077] Wherein, r represents the radius of the airbag, and h represents the height of the airbag. For a pillow, the height h of the airbag is fixed. Therefore, the following conclusion can be drawn:

[0078] When the volume of the airbag changes due to actions such as placing the upper pillow, at this time, the internal volume V of the airbag decreases, that is, the radius r changes. At this time, the pressure P will rise, and the surface tension of the pillow surface also changes with the rise of the pressure. The corresponding relationship is as follows:

[0079] P=2Kγ / r

[0080] From the above formula, it can be obtained that γ=(P×r) / 2K

[0081] Wherein, P represents the gas pressure inside the airbag, K is a calculation coefficient, which is obtained after test calibration, γ represents the surface tension of the airbag surface, and r represents the radius of the cylindrical airbag. It can be seen that when the volume of the gas in the pillow is fixed, the gas pressure and the height of the pillow are inversely proportional. Therefore, when a person lies on the pillow, if sufficient support and height for the human head and neck are to be achieved, the pressure P and r of the pillow must reach a one-to-one corresponding relationship. Based on this, a large amount of user data can be collected for statistics, the adaptation data of different human bodies to the pillow height is matched, and the pressure of the pillow and the height required by the user are matched according to the above formula.

[0082] Step 340: Train a preset multi-layer perceptron network model according to the user's body state parameters and the user's historical body state parameters to obtain the output pressure value of the output.

[0083] In an embodiment of the present invention, the collected user body state parameters and the user's historical body state parameters can be input into a pre-built preset multi-layer perceptron network model. The weights and structure of the preset multi-layer perceptron network model can be pre-configured according to the type of the target bedding. The preset multi-layer perceptron network model can process the input user body state parameters and the user's historical body state parameters to generate corresponding output pressure values.

[0084] Step 350: If the output pressure value meets the training completion condition, the preset multi-layer perceptron network model is used as the preset neural network model; otherwise, the preset multi-layer perceptron network model is adjusted according to the gap between the output pressure value and the training completion condition, and then the preset neural network model is continued to be trained.

[0085] Among them, the training completion condition can be a condition for determining the completion of the training of the preset neural network model. In some embodiments of the invention, the training completion condition may include that the loss function of the preset multi-layer perceptron network model is less than a specified threshold.

[0086] In an embodiment of the present invention, a loss value can be determined based on the output pressure value and the loss function of the preset multi-layer perceptron network model. When the loss function is less than the specified threshold, it can be determined that the output pressure value meets the training completion condition, and the preset multi-layer perceptron network model can be used as the preset neural network model; otherwise, the weight parameters in the preset multi-layer perceptron network model can be increased or decreased according to the output pressure value, and the preset multi-layer perceptron network model is re-trained.

[0087] Step 360: When it is determined that the target bedding enters the use state, monitor the air pressure change state in the target bedding.

[0088] Step 370: Read the change curve corresponding to the air pressure change state.

[0089] In an embodiment of the present invention, the change curve of the air pressure change state can be read.

[0090] Step 380: Determine the user body state parameters corresponding to each air pressure value in the change curve according to the airbag shape parameters of the target bedding.

[0091] Specifically, according to the air pressure values at different times in the change curve, the user body state parameters can be determined through the air pressure value and the airbag shape parameters of the target bedding. The user body state parameters can be information such as the neck height, head height, and waist height provided by the target bedding at different times.

[0092] Step 390: Input each user body state parameter into the preset neural network model, and collect the target air pressure value output by the preset neural network model.

[0093] In an embodiment of the present invention, the determined user body state parameters can be input into a preset neural network model, and the preset neural network model can determine the target air pressure value corresponding to the above user body state parameters.

[0094] Step 3100: Adjust the target bedding according to the target air pressure value.

[0095] Embodiment Four

[0096] Figure 4 FIG. is a flowchart of another bedding control method according to Embodiment Four of the present invention. The embodiment of the present invention is a concretization based on the above-mentioned embodiment of the invention. The embodiment of the present invention introduces in detail the process of adjusting the target bedding. Refer to Figure 4 The method provided by the embodiment of the present invention specifically includes the following steps:

[0097] Step 410: When it is determined that the target bedding enters the use state, monitor the air pressure change state in the target bedding.

[0098] Step 420: Determine the target air pressure value of the target bedding according to the preset neural network model under the air pressure change state.

[0099] Step 430: Determine the deflation threshold according to the target bedding and the target air pressure value.

[0100] Among them, the deflation threshold can be the air pressure threshold that the target bedding reaches through deflation.

[0101] In an embodiment of the present invention, corresponding deflation thresholds can be configured for the target bedding under different target air pressure values. When adjusting the target bedding, the corresponding deflation threshold can be found according to the target bedding and the target air pressure value.

[0102] Step 440: Control the electromagnetic valve of the target bedding to perform deflation processing according to the deflation threshold.

[0103] In an embodiment of the present invention, the electromagnetic valve of the target bedding can be controlled to deflate until the air pressure value in the target bedding is less than or equal to the deflation threshold.

[0104] Step 450: When the deflation processing is completed, control the air pump of the target bedding to inflate the airbag of the target bedding according to a preset inflation waveform until the air pressure of the airbag meets the target air pressure value.

[0105] Among them, the preset inflation waveform can be the waveform of the output power for controlling the operation of the air pump, and the preset inflation waveform can be a linear output waveform or a non-linear output waveform.

[0106] Specifically, after the target bedding controls the solenoid valve to deflate, it can control the air pump to work according to a preset inflation waveform, so that the air pressure in the target bedding increases, so that the air pressure in the target bedding meets the target air pressure value.

[0107] In the embodiment of the present invention, after determining that the target bedding enters the use state, the air pressure change state is detected, the corresponding target air pressure value is determined according to the air pressure change state and the preset neural network model, the deflation threshold corresponding to the target bedding and the target air pressure value is determined, and the solenoid valve is controlled to control the airbag of the target bedding to deflate to the deflation threshold. After the deflation is completed, the air pump is controlled to inflate the airbag of the target bedding to the target air pressure value according to the preset inflation waveform, so as to realize the air pressure adjustment of the target bedding, enhance the adaptability of the target bedding to the user, improve the user's bedtime experience, and improve the user's sleep quality.

[0108] Further, on the basis of the above-mentioned invention embodiment, the preset inflation waveform is a pulse width modulation wave, and the air pressure output duty ratio of the preset inflation waveform is determined based on the type of the target bedding.

[0109] In the embodiment of the present invention, the target bedding can control the air pump based on the pulse width modulation wave. The air pressure output duty ratio of the pulse width modulation wave can be determined by the type of the target bedding. The air pressure output duty ratio can be the ratio of the working time of the air pump to the total time. In some embodiments of the invention, the air pressure output duty ratio of the pulse width modulation wave of the preset inflation waveform may not be unique. When the target bedding gradually approaches the target air pressure value, a pulse width modulation wave with a lower air pressure output duty ratio can be gradually selected to control the air pump to inflate.

[0110] Embodiment Five

[0111] The embodiment of the present invention provides an example of a bedding control method. In the embodiment of the present invention, the bedding can be a pillow. The embodiment of the present invention can accurately adapt the head height and neck height of the human body by collecting the neck and head pressures when the human body lies on the pillow, without any extra components, and only needs to collect the changes in the pressures of the neck and head airbags to achieve the function. The specific bedding control method can include the following steps:

[0112] Step 1: Collection and calculation of the first pressure after the user lies on the pillow. Specifically, after the pillow is powered on, the air pump of the pillow pre-charges the airbags of the head and neck, and at the same time, the MCU of the pillow continuously collects the pressure of the neck airbag, and can perform digital filtering calculation and waveform processing on the collected pressure waveform. When a person lies on the pillow, the neck airbag of the pillow will generate a pressure change waveform. At this time, the MCU will determine that the user has lain on the pillow according to the result of the waveform calculation. See Figure 5, this waveform is the waveform change curve of the user's neck after the first time lying on the pillow. The MCU samples at a cycle of 0.1 seconds, and the calculation window is 20 seconds, that is, the MCU can process the pressure change waveform of the pillow within 20 seconds. First, the MCU performs three-level digital filtering on the waveform, and the processed waveform is as follows Figure 6 As shown, the stability of the processed waveform is significantly better than that of the original unoptimized waveform. After the waveform filtering is completed, the MCU calculates the waveform change rate and change trend. At this time, when the user makes a lying-on-pillow action, if the change trend of the waveform is positive and the change rate is greater than a certain threshold, and the pressure remains stable within 20 seconds and there is no large change again, it is determined that the user is lying on the pillow. See Figure 7 , to determine whether the user is lying on the pillow can be specifically judged by indicators such as the variance, standard deviation or change rate of the waveform. By different judgments on the waveform change rate and pressure change, the state of the user on the pillow is determined.

[0113] Step 2: Height output and height adjustment during the lying-on-pillow process. Specifically, when the user is stable on the pillow, the pillow enters the body movement monitoring state and records the current head airbag pressure and neck airbag pressure. The current head pressure and neck pressure can be recorded to generate a digital waveform, which is automatically calculated every 10 seconds. After the user's final sleeping position stabilizes, the pillow will collect the airbag pressures of the head and neck and start neural network calculation to output the optimal target pressure of the current user. At this time, the pillow will accurately adjust the pressure of the pillow according to the output target pressure. During the adjustment process, the system of the pillow will collect the pressure change curve of the neck airbag of the pillow during the adjustment process and accurately control the air pump to inflate through the PID motor control algorithm, and finally reach the target pressure. Achieve the effect that the airbag pressures and heights of the head and neck of the pillow are perfectly fitted to the human body.

[0114] Based on the above-mentioned invention embodiments, after the user lies on the pillow, neural network calculation can be performed based on the pressure information of the head and neck airbags collected by the pillow to output the final target pressure and height. The specific process includes the following steps:

[0115] 1. The determination of the target pressure and height is realized through a Multilayer Perceptron (MLP) model. The input layer of the MLP model is the head pressure and neck pressure after the user lies on the pillow stably. The MLP model is trained and generated based on the corresponding relationship between the pressures of the head airbag and neck airbag and the height change. This MLP model can be trained and generated through historical user data and the currently collected user lying-on-pillow data.

[0116] 2. Before each use of the pillow, the user can control the pillow to pre-inflate to a standard pressure. After the user lies on the pillow, the collected data can be processed according to the trained MLP model to determine the pressure on the head and neck.

[0117] 3. According to the determined pressure on the head and neck above, referring to Figure 8 , the solenoid valve of the pillow can be controlled to open, realizing the deflation process of the airbag in the pillow. At this time, the air pressure in the airbag drops rapidly. When the pillow deflates to the corresponding threshold, the MCU can control the air pump to make the air pump output a PWM wave to inflate the pillow airbag. The output frequency of the PWM wave is controlled by the motor PID algorithm. By adjusting the inflation speed in real-time according to the collected airbag pressure during the inflation process, the closer to the target pressure, the lower the duty cycle of the PWM output, and the precise adjustment of the airbag pressure in the pillow can be achieved.

[0118] III. Monitoring the action of getting off the pillow. When the user's body movement is detected, the pressure digital waveforms of the neck and head airbags will be collected. When the result obtained from the waveform processing meets the getting-off-the-pillow condition, at this time, it is determined that the user has got off the pillow, and then the MCU will pre-inflate the pillow again for the next time the user lies on the pillow.

[0119] Embodiment Six

[0120] Figure 9 is a schematic structural diagram of a bedding control device according to Embodiment Six of the present invention. As Figure 9 shown, the device includes:

[0121] A state detection module 501, configured to monitor the air pressure change state in the target bedding when it is determined that the target bedding enters the use state.

[0122] An air pressure determination module 502, configured to determine the target air pressure value of the target bedding according to a preset neural network model under the air pressure change state.

[0123] An adjustment control module 503, configured to adjust the target bedding according to the target air pressure value.

[0124] In the embodiment of the present invention, the state detection module obtains the air pressure change state in the target bedding when the target bedding enters the working state. The air pressure determination module determines the target air pressure value of the target bedding according to the air pressure change state and the preset neural network model. The adjustment control module adjusts the target bedding according to the target air pressure value, so that the state of the target bedding adapts to the user's body parameters, which can enhance the intelligence level of the bedding and thus improve the user's sleep quality.

[0125] Further, on the basis of the above-mentioned embodiment of the invention, the state detection module 501 includes:

[0126] A pressure acquisition unit for acquiring the real-time pressure value of the target bedding after power-on according to a preset time period.

[0127] A state determination unit for determining that the target bedding enters the usage state when the waveform of the pressure curve formed by the real-time pressure values satisfies a preset characteristic condition.

[0128] A state determination unit for acquiring the airbag pressures of the head airbag and the neck airbag of the target bedding; using the change curve of the airbag pressure over time as the air pressure change state.

[0129] Further, on the basis of the above-mentioned invention embodiments, the preset characteristic condition includes:

[0130] There exists a change rate of the real-time pressure value at a first moment being greater than a first threshold, and after the first moment, the fluctuation range of the change rate of the real-time pressure value satisfies being less than a second threshold.

[0131] Further, on the basis of the above-mentioned invention embodiments, it further includes: a model training module for reading the user's historical state parameters corresponding to the target bedding; acquiring the airbag pressure inside the target bedding when the target bedding enters the usage state; determining the user's body state parameters according to the airbag shape parameters of the target bedding and the airbag pressure; training a preset multi-layer perceptron network model according to the user's body state parameters and the user's historical body state parameters to obtain an output pressure value; if the output pressure value meets the training completion condition, using the preset multi-layer perceptron network model as the preset neural network model, otherwise, adjusting the preset multi-layer perceptron network model according to the gap between the output pressure value and the training completion condition and then continuing to train the preset neural network model.

[0132] Further, on the basis of the above-mentioned invention embodiments, the air pressure determination module 502 includes:

[0133] A change curve unit for reading the change curve corresponding to the air pressure change state.

[0134] A parameter determination unit for determining the user's body state parameters corresponding to each air pressure value in the change curve according to the airbag shape parameters of the target bedding.

[0135] An air pressure determination unit for inputting each of the user's body state parameters into the preset neural network model and acquiring the target air pressure value output by the preset neural network model.

[0136] Further, on the basis of the above-mentioned invention embodiments, the adjustment control module 503 includes:

[0137] A deflation threshold unit for determining a deflation threshold according to the target bedding and the target air pressure value.

[0138] A deflation control unit for controlling the solenoid valve of the target bedding to perform deflation processing according to the deflation threshold.

[0139] An inflation control unit for, when the deflation processing is completed, controlling the air pump of the target bedding to inflate the airbag of the target bedding according to a preset inflation waveform until the air pressure of the airbag meets the target air pressure value.

[0140] Further, on the basis of the above-mentioned invention embodiments, the preset inflation waveform is a pulse width modulation wave, and the air pressure output duty ratio of the preset inflation waveform is determined according to the type of the target bedding.

[0141] The bedding control device provided by the embodiments of the present invention can execute the bedding control method provided by any embodiment of the present invention, and has the corresponding functional modules and beneficial effects for executing the method.

[0142] Embodiment Seven

[0143] Figure 10 It is a schematic structural diagram of an electronic device according to the bedding control method provided by the embodiments of the present invention. The electronic device is intended to represent various forms of digital computers, such as, laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as, personal digital processors, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are only examples and are not intended to limit the implementation of the present invention described and / or claimed herein.

[0144] As Figure 10 shown, the electronic device 10 includes at least one processor 11, and a memory communicatively connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc. Among them, the memory stores a computer program executable by the at least one processor, and the processor 11 can execute various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 into the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. The input / output (I / O) interface 15 is also connected to the bus 14.

[0145] Multiple components in the electronic device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a disk, an optical disc, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0146] The processor 11 can be various general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as the bedding control method.

[0147] In some embodiments, the bedding control method can be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as the storage unit 18. In some embodiments, part or all of the computer program can be loaded and / or installed onto the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the bedding control method described above can be executed. Alternatively, in other embodiments, the processor 11 can be configured to execute the bedding control method by any other suitable means (e.g., by means of firmware).

[0148] The various embodiments of the systems and technologies described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-chip (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include: being implemented in one or more computer programs, which can be executed and / or interpreted on a programmable system including at least one programmable processor, the programmable processor can be a dedicated or general-purpose programmable processor, can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit the data and instructions to the storage system, the at least one input device, and the at least one output device.

[0149] A computer program for implementing the method of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general purpose computer, a special purpose computer, or other programmable data processing apparatus, such that the computer programs, when executed by the processor, cause the functions / operations specified in the flowchart and / or block diagram to be implemented. The computer programs may be executed entirely on the machine, partly on the machine, as a stand-alone software package partly on the machine and partly on a remote machine or entirely on the remote machine or server.

[0150] In the context of the present invention, a computer-readable storage medium may be a tangible medium that can contain or store a computer program for use by or in connection with an instruction execution system, apparatus, or device. The computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. Alternatively, the computer-readable storage medium may be a machine-readable signal medium. More specific examples of the machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0151] In order to provide interaction with a user, the systems and techniques described herein may be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or a trackball) by which the user can provide input to the electronic device. Other kinds of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).

[0152] The systems and techniques described herein can be implemented in a computing system including backend components (e.g., as a data server), or a computing system including middleware components (e.g., an application server), or a computing system including frontend components (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described herein), or a computing system including any combination of such backend components, middleware components, or frontend components. The components of the system can be interconnected to each other by digital data communication in any form or medium (e.g., a communication network). Examples of communication networks include: local area network (LAN), wide area network (WAN), blockchain network, and the Internet.

[0153] A computing system can include a client and a server. The client and the server are generally far from each other and typically interact through a communication network. The client-server relationship is created by computer programs running on respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or a cloud host, which is a host product in the cloud computing service system, solving the defects of difficult management and weak business scalability existing in traditional physical hosts and VPS services.

[0154] It should be understood that various forms of the processes shown above can be used, with steps reordered, added, or deleted. For example, the steps recited in the present invention can be executed in parallel, sequentially, or in a different order, as long as the desired results of the technical solution of the present invention can be achieved, and no limitation is made herein.

[0155] The above specific embodiments do not constitute a limitation on the protection scope of the present invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims

1. A bedding control method, characterized in that, The method includes: When it is determined that the target bedding enters the use state, monitoring the air pressure change state inside the target bedding; Reading the change curve corresponding to the air pressure change state; Determining the user body state parameters corresponding to each air pressure value in the change curve according to the airbag shape parameters of the target bedding; wherein, the user body state parameters include the height parameters of the optimal state required for the user to use the target bedding; Inputting each of the user body state parameters into a preset neural network model, and collecting the target air pressure value output by the preset neural network model; Adjusting the target bedding according to the target air pressure value.

2. The method according to claim 1, wherein The step of, when it is determined that the target bedding enters the use state, monitoring the air pressure change state inside the target bedding includes: Collecting the real-time pressure value of the target bedding after power-on according to a preset time period; When the waveform of the pressure curve formed by the real-time pressure values satisfies a preset feature condition, determining that the target bedding enters the use state; Collecting the airbag pressures of the head airbag and the neck airbag of the target bedding; Taking the change curve of the airbag pressure changing with time as the air pressure change state.

3. The method according to claim 2, wherein The preset feature condition includes: There is a change rate of the real-time pressure value at a first moment greater than a first threshold, and after the first moment, the fluctuation range of the change rate of the real-time pressure value satisfies being less than a second threshold.

4. The method according to claim 1, characterized in that, The training process of the preset neural network model includes: Reading the user historical state parameters corresponding to the target bedding; wherein, the user historical state parameters are the air pressure change states when the user used the target bedding in the past; Collecting the airbag pressure inside the target bedding when the target bedding enters the use state; Determining the user body state parameters according to the airbag shape parameters of the target bedding and the airbag pressure; Training a preset multi-layer perceptron network model according to the user body state parameters and the user historical state parameters to obtain an output pressure value; If the output pressure value meets the training completion condition, taking the preset multi-layer perceptron network model as the preset neural network model, otherwise, adjusting the preset multi-layer perceptron network model according to the gap between the output pressure value and the training completion condition and then continuing to train the preset neural network model.

5. The method according to claim 1, wherein The step of adjusting the target bedding according to the target air pressure value includes: Determining a deflation threshold according to the target bedding and the target air pressure value; Controlling the electromagnetic valve of the target bedding to perform deflation processing according to the deflation threshold; After completing the deflation processing, controlling the air pump of the target bedding to inflate the airbag of the target bedding according to a preset inflation waveform until the air pressure of the airbag meets the target air pressure value.

6. The method according to claim 5, wherein The preset inflation waveform is a pulse width modulation wave, and the air pressure output duty ratio of the preset inflation waveform is determined based on the type of the target bedding.

7. A bedding control device, characterized in that, The device includes: A state detection module, configured to monitor the air pressure change state inside the target bedding when it is determined that the target bedding enters the use state; A barometric pressure determination module, configured to read a change curve corresponding to the barometric pressure change state; determine user body state parameters corresponding to respective barometric pressure values within the change curve according to the airbag shape parameters of the target bedding; wherein the user body state parameters include height parameters of an optimal state required for a user to use the target bedding; input the respective user body state parameters into a preset neural network model, and collect a target barometric pressure value output by the preset neural network model; An adjustment control module, configured to adjust the target bedding according to the target barometric pressure value.

8. An electronic device, characterized in that, The electronic device includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the bedding control method according to any one of claims 1-6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions for causing a processor to execute the bedding control method according to any one of claims 1-6 when executed.

Images