Action recognition method, device and equipment based on air bag and storage medium
The airbag air pressure data change rate is used to identify the movements on the smart mattress, which solves the problems of high sensor cost and complexity, and achieves low-cost and high-accuracy action recognition, improving product competitiveness and the accuracy of sleep reporting.
Patent Information
- Application Number
- CN202411209237.0
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-30
- Publication Date
- 2024-11-12
AI Technical Summary
Existing smart mattresses realize motion recognition through additional sensors, resulting in high costs and increased product complexity, making it difficult to identify the movements of the human body and the electric bed at low cost and high accuracy.
By collecting the air pressure change value of the air bag, dividing the air pressure data area, calculating the change rate of the air pressure data, identifying the target action, and realizing action recognition without additional sensors.
It reduces the cost and complexity of the mattress, improves the competitiveness of the product, realizes accurate identification of the movements of the human body and the electric bed, and enhances the accuracy of sleep reports and the linkage effect of smart homes.
Smart Images

Figure CN118924070A_ABST
Abstract
Description
Technical Field
[0001] The embodiments of the present invention relate to the technical field of smart mattresses, and in particular to an airbag-based motion recognition method, device, equipment and storage medium. Background Art
[0002] In order to make people sleep better, everything from beds to mattresses is gradually developing towards intelligence and humanization. Therefore, many adjustable smart mattresses have emerged on the market. Many mattresses are adjusted by airbags, but correspondingly, the detection of triggering smart adjustment has become a very important part. How to realize the recognition of human body movements and electric bed movements with low cost, high reliability and high accuracy has become the focus of competition among various companies. At present, smart mattresses on the market all use additional sensors to detect specific movements, which will bring problems such as high cost and complicated mattress technology. Summary of the invention
[0003] The present invention provides an airbag-based motion recognition method, device, equipment and storage medium, which can recognize the motion on the airbag only through the air pressure data of the airbag, without adding sensors, thus reducing costs.
[0004] In a first aspect, an embodiment of the present invention provides an airbag-based motion recognition method, comprising:
[0005] The air pressure change value of the airbag is collected at a preset frequency to obtain a plurality of air pressure data;
[0006] Dividing the air pressure data into a plurality of data regions according to a preset region length;
[0007] Determining the data area corresponding to the target action among the multiple data areas;
[0008] Calculating the change rate of a plurality of air pressure data in the data area corresponding to the target action;
[0009] The target action is identified based on the change rate.
[0010] Optionally, the target motion includes electric bed motion and human body motion;
[0011] Determining the data area corresponding to the target action among the multiple data areas includes:
[0012] Among the plurality of data areas, determining the data area corresponding to human body motion and the data area corresponding to electric bed motion;
[0013] Calculating the change rate of a plurality of air pressure data in the data area corresponding to the target action includes:
[0014] respectively calculating the change rates of a plurality of air pressure data in the data area corresponding to the human body motion and the change rates of a plurality of air pressure data in the data area corresponding to the electric bed motion;
[0015] According to the change rate, identifying the target action includes:
[0016] identifying a human body movement according to a change rate of a plurality of air pressure data in the data area corresponding to the human body movement;
[0017] The electric bed motion is identified based on the change rate of the plurality of air pressure data in the data area corresponding to the electric bed motion.
[0018] Optionally, among the plurality of data areas, determining the data area corresponding to the human body motion and the data area corresponding to the electric bed motion comprises:
[0019] respectively calculating the discreteness of the plurality of data regions;
[0020] Determine the data region whose discreteness is greater than a preset discreteness as the data region corresponding to the human body motion;
[0021] The data region whose discreteness is less than or equal to the preset discreteness is determined as the data region corresponding to the electric bed action.
[0022] Optionally, respectively calculating the discreteness of the plurality of data regions includes:
[0023] Calculate the average value of the air pressure data in each of the data areas respectively;
[0024] Based on the formula According to the average value of the air pressure data in each data area Calculate the discrete degree AD of each data area s 2; where x is the number of air pressure data in the data area, n is a positive integer and 0≤n≤x, AD buff It is any of the air pressure data in the data area.
[0025] Optionally, determining the data area corresponding to the target action in the plurality of data areas includes:
[0026] Among the multiple data areas, determining the data area corresponding to when the action occurs;
[0027] In the data area corresponding to when the action occurs, the data area corresponding to the target action is determined.
[0028] Optionally, among the multiple data areas, determining the data area corresponding to when the action occurs includes:
[0029] respectively calculating effective values of a plurality of the air pressure data in each of the data areas;
[0030] Calculate the difference between the maximum effective value and the minimum effective value of each data area respectively;
[0031] The data region where the difference is greater than a preset change amount is determined as the data region corresponding to when the action occurs.
[0032] Optionally, respectively calculating the effective values of the plurality of air pressure data in each of the data regions comprises:
[0033] Taking the first air pressure data in the data area as the target data, calculating the average value of the target data and a preset number of air pressure data after the target data as the effective value of the target data;
[0034] All the air pressure data in the data area are taken as the target data in sequence to obtain the valid values of all the air pressure data in the data area.
[0035] Optionally, calculating the change rate of a plurality of air pressure data in the data area corresponding to the target action includes:
[0036] Based on the formula Calculate the average AD of the change rate of multiple air pressure data in the data area corresponding to the target action cr ; Wherein, x is the number of air pressure data in the data area, n is a positive integer and 0≤n≤x, AD buff It is any of the air pressure data in the data area.
[0037] Optionally, identifying the target action according to the change rate includes:
[0038] The mean value of the rate of change AD cr When it is a positive number, the target action is identified as the action of going to bed;
[0039] The mean value of the rate of change AD cr When it is a negative number, the target action is identified as the action of getting out of bed.
[0040] In a second aspect, an embodiment of the present invention further provides an airbag-based motion recognition device, comprising:
[0041] An air pressure data acquisition module, used to collect the air pressure change value of the airbag at a preset frequency to obtain a plurality of air pressure data;
[0042] A data region division module, used for dividing the air pressure data into a plurality of data regions according to a preset region length;
[0043] A data region determination module, used to determine the data region corresponding to the target action among the multiple data regions;
[0044] a change rate calculation module, for calculating the change rate of a plurality of air pressure data in the data area corresponding to the target action;
[0045] The target action recognition module recognizes the target action according to the change rate.
[0046] In a third aspect, an embodiment of the present invention further provides an airbag-based motion recognition device, comprising:
[0047] one or more processors;
[0048] A storage device for storing one or more programs;
[0049] When the one or more programs are executed by the one or more processors, the one or more processors implement the airbag-based motion recognition method as described in any one of the first aspects of the present invention.
[0050] In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the airbag-based motion recognition method as described in any one of the first aspects of the present invention.
[0051] The embodiment of the present invention provides an airbag-based motion recognition method, device, equipment and storage medium. The method first collects the air pressure change value of the airbag at a preset frequency to obtain multiple air pressure data, and then divides the air pressure data into multiple data areas with a preset area length. In the multiple data areas, the data area corresponding to the target action is determined, and the change rate of the multiple air pressure data in the data area corresponding to the target action is calculated; finally, the target action is identified according to the change rate; the above technical solution solves the problem that the existing airbag needs to use additional sensors to realize air pressure detection and motion recognition, which brings high costs and complex products; the technical solution of the present invention only realizes specific motion recognition through the air pressure data of the airbag, without the need for additional sensors, and is applied to smart mattresses, which greatly reduces the cost of mattresses and the complexity of products, and improves the competitiveness of products. BRIEF DESCRIPTION OF THE DRAWINGS
[0052] Figure 1 is a flow chart of an airbag-based motion recognition method provided in Embodiment 1 of the present invention;
[0053] Figure 2 is a flow chart of an airbag-based motion recognition method provided in Embodiment 2 of the present invention;
[0054] Figure 3It is an airbag pressure data waveform diagram provided by an embodiment of the present invention;
[0055] Figure 4 It is an effective value waveform diagram of air bag pressure data provided by an embodiment of the present invention;
[0056] Figure 5 It is a waveform diagram of the discrete degree of air bag pressure data provided by an embodiment of the present invention;
[0057] Figure 6 is a flow chart of an airbag-based motion recognition method provided in Embodiment 3 of the present invention;
[0058] Figure 7 is a waveform diagram of the airbag air pressure data change rate provided by an embodiment of the present invention;
[0059] Figure 8 is a schematic structural diagram of an airbag-based motion recognition device provided by Embodiment 4 of the present invention;
[0060] Fig. 9 It is a structural schematic diagram of an airbag-based motion recognition device provided in Embodiment 5 of the present invention. DETAILED DESCRIPTION
[0061] The present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments. It is to be understood that the specific embodiments described herein are only used to explain the present invention, rather than to limit the present invention. It should also be noted that, for ease of description, only parts related to the present invention, rather than all structures, are shown in the accompanying drawings.
[0062] The terms used in the embodiments of the present invention are only for the purpose of describing specific embodiments, and are not intended to limit the present invention. It should be noted that the directional words such as "upper", "lower", "left", "right" and the like described in the embodiments of the present invention are described at the angles shown in the accompanying drawings and should not be understood as limitations on the embodiments of the present invention. In addition, in the context, it is also necessary to understand that when it is mentioned that an element is formed "on" or "under" another element, it can not only be directly formed "on" or "under" another element, but also indirectly formed "on" or "under" another element through an intermediate element. The terms "first", "second", etc. are only used for descriptive purposes and do not represent any order, quantity or importance, but are only used to distinguish different components. For those of ordinary skill in the art, the specific meanings of the above terms in the present invention can be understood in specific circumstances.
[0063] The term “including” and its variations used in the present invention are open inclusions, that is, “including but not limited to.” The term “based on” means “based at least in part on.” The term “one embodiment” means “at least one embodiment.”
[0064] It should be noted that the concepts such as "first" and "second" mentioned in the present invention are only used to distinguish the corresponding contents, and are not used to limit the order or interdependence.
[0065] It should be noted that the modifications of "one" and "plurality" mentioned in the present invention are illustrative rather than restrictive, and those skilled in the art should understand that, unless otherwise clearly indicated in the context, it should be understood as "one or more".
[0066] Figure 1 It is a flow chart of an airbag-based motion recognition method provided in Embodiment 1 of the present invention. The method can be applied to the case of airbag-based motion recognition. The method can be executed by an airbag-based motion recognition device, wherein the device can be implemented by software and / or hardware.
[0067] refer to Figure 1 ,The airbag-based motion recognition methods include:
[0068] S110, collecting the air pressure change value of the airbag at a preset frequency to obtain a plurality of air pressure data.
[0069] Specifically, different actions on the airbag will bring different pressure changes, which will in turn cause different air pressure data of the airbag. Therefore, it is necessary to collect the air pressure change value of the airbag at a preset frequency to obtain multiple air pressure data in order to identify the actions occurring on the airbag based on the air pressure data.
[0070] S120, dividing the air pressure data into a plurality of data regions according to a preset region length.
[0071] Specifically, since the air pressure change caused by the action on the airbag is continuous rather than an instantaneous change, in order to more accurately identify the action on the airbag, the air pressure data needs to be divided into multiple data areas. When any data area changes overall, it can be determined that an action has occurred on the airbag, thereby achieving more accurate identification of the action on the airbag.
[0072] S130: Determine a data region corresponding to a target action among multiple data regions.
[0073] The target action can be understood as the action that is desired to be captured and caused by the adjustment of the human body or the electric bed.
[0074] Specifically, after the air pressure data generated on the airbag is divided into multiple areas, it is now necessary to identify the target action occurring on the airbag. Therefore, it is first necessary to determine the air pressure data change area generated by the target action to further identify the target action.
[0075] S140, calculating the change rates of the plurality of air pressure data in the data area corresponding to the target action.
[0076] Specifically, since different actions cause different changes in air pressure data, the corresponding change rates will also be different, so the change rate of the air pressure data can be calculated to identify specific actions based on the change rate.
[0077] S150: Identify the target action according to the change rate.
[0078] For example, when the action on the airbag gradually disappears, the pressure will gradually decrease, and the corresponding pressure data will also gradually decrease, so its rate of change is a negative number, so the specific action can be identified based on the rate of change.
[0079] In an optional embodiment of the present invention, when applied to an airbag mattress, it can identify human movements, including getting into bed, getting out of bed, and body movements (turning over). For example, identifying whether human movements occur and the time and number of times they occur can make the sleep report issued by the airbag mattress more accurate; identifying whether human movements occur can also achieve more accurate smart home linkage effects, such as automatically turning on the night light when getting out of bed and adjusting the air conditioner to a suitable temperature mode when going to bed.
[0080] In another optional embodiment of the present invention, when applied to an electric bed with an airbag mattress, the airbag pressure can be automatically adjusted after the movement of the electric bed is recognized. For example, when it is recognized that the electric bed is bending, the airbag mattress is automatically deflated, and when it is flattened, it is automatically inflated, so that the airbag pressure can be self-balanced.
[0081] In other optional embodiments of the present invention, when applied to an airbag sofa, human body movements can be recognized, including sitting on the sofa, leaving the sofa, the number of passengers, the seating position, etc.; when applied to an airbag pillow, human body movements can be recognized, including the body being on the pillow and leaving the pillow, etc.
[0082] An airbag-based motion recognition method according to an embodiment of the present invention first collects air pressure change values of the airbag at a preset frequency to obtain multiple air pressure data, then divides the air pressure data into multiple data areas with a preset area length, determines the data area corresponding to the target action in the multiple data areas, and calculates the change rate of the multiple air pressure data in the data area corresponding to the target action; finally, identifies the target action according to the change rate; the above technical solution solves the problem that the existing airbag needs to use additional sensors to realize air pressure detection and motion recognition, which brings high costs and complex products; the technical solution of the present invention only realizes specific motion recognition through the air pressure data of the airbag, without the need for additional sensors, and is applied to smart mattresses, which greatly reduces the cost of mattresses and the complexity of products, and improves the competitiveness of products.
[0083] Embodiment 2
[0084] Figure 21 is a flow chart of an airbag-based motion recognition method provided in Embodiment 2 of the present invention. Embodiment 2 is optimized based on the above embodiments.
[0085] The above step S130, determining the data area corresponding to the target action in multiple data areas, is concretized as follows: determining the data area corresponding to when the action occurs in multiple data areas; and determining the data area corresponding to the target action in the data area corresponding to when the action occurs.
[0086] In multiple data areas, the data area corresponding to the action will be determined, which is further refined into:
[0087] Calculate the effective values of multiple air pressure data in each data area respectively; calculate the difference between the maximum effective value and the minimum effective value of each data area respectively; and determine the data area with a difference greater than a preset change amount as the data area corresponding to the action.
[0088] The change rate of multiple air pressure data in the data area corresponding to the target action is calculated as follows:
[0089] respectively calculating the change rates of a plurality of air pressure data in the data area corresponding to the human body motion and the change rates of a plurality of air pressure data in the data area corresponding to the electric bed motion;
[0090] According to the rate of change, the target action is identified and specified as follows:
[0091] Recognize human body movements according to the change rates of a plurality of air pressure data in a data area corresponding to the human body movements;
[0092] The electric bed motion is identified based on the change rates of the plurality of air pressure data in the data region corresponding to the electric bed motion.
[0093] For details not yet provided in this embodiment, please refer to Embodiment 1.
[0094] refer to Figure 2 , the method comprising:
[0095] S210, collecting the air pressure change value of the airbag at a preset frequency to obtain a plurality of air pressure data.
[0096] S220, dividing the air pressure data into a plurality of data regions according to a preset region length.
[0097] S230, respectively calculating the effective values of the plurality of air pressure data in each data area.
[0098] Specifically, since different actions on the airbag will generate different air pressure data, the accuracy of the air pressure data is crucial when identifying specific actions based on the air pressure data. Abnormal glitches or spikes may exist in the air pressure data, so it is necessary to calculate the effective value of the air pressure data to reduce the impact of abnormal data and obtain more accurate air pressure data.
[0099] For example, Figure 3 is an airbag pressure data waveform diagram provided by an embodiment of the present invention, Figure 4 is an effective value waveform diagram of airbag pressure data provided by an embodiment of the present invention, refer to Figure 3 , Figure 4 ,After calculating the effective value of the air pressure data, it can be seen that the ,air pressure changes in the area where the movement occurs are more obvious. Therefore, the ,effective value of the air pressure data can more accurately ,identify whether the mattress moves.
[0100] S240, respectively calculating the difference between the maximum effective value and the minimum effective value of each data region.
[0101] Specifically, since the difference between the maximum effective value and the minimum effective value in each data area reflects the maximum change in the air pressure data in that area, it is necessary to calculate the difference between the maximum effective value and the minimum effective value of each data area respectively, and then use the difference between the maximum effective value and the minimum effective value, that is, the maximum change value of each data area, to determine whether the area is the area where the action occurs.
[0102] S250: Determine a data region whose difference is greater than a preset change amount as a data region corresponding to when the action occurs.
[0103] Among them, the preset change amount can be understood as a pre-set change amount. The data area greater than the change amount is the data area corresponding to when the action occurs. If the data change value does not reach the data area of the change amount, it is determined that the action occurring on the airbag is too small and can be ignored.
[0104] S260, respectively calculating the discreteness of each data region corresponding to when the action occurs.
[0105] Specifically, since the degree of discreteness represents the deviation of multiple air pressure data in the data area, that is, when larger air pressure data or smaller air pressure data suddenly appears in the data area, the corresponding degree of discreteness of the data area is larger, and when multiple air pressure data in the data area change evenly, the corresponding degree of discreteness is smaller.
[0106] S270: Determine a data region whose discreteness is less than or equal to a preset discreteness as a data region corresponding to the electric bed action.
[0107] Specifically, since the electric bed is often in uniform motion when in motion, the deviations between the multiple air pressure data in the corresponding data area are small, and the corresponding discreteness is also small. Therefore, a preliminary test can be conducted to set a discreteness according to the experimental results, and the data area less than the discreteness is the data area where the electric bed motion occurs.
[0108] S271, calculating the change rate of multiple air pressure data in the data area corresponding to the electric bed movement.
[0109] S272. Identify the movement of the electric bed according to the rate of change.
[0110] S280: Determine a data region whose discreteness is greater than a preset discreteness as a data region corresponding to a human body motion.
[0111] Specifically, when the human body moves on the mattress, the air pressure of the mattress does not change uniformly, and there will be sudden changes in the value. Correspondingly, the deviation between the multiple air pressure data in the data area is large, so the discreteness is large; when the electric bed moves, its movement is often uniform, and the deviation between the multiple air pressure data in the corresponding data area is small, and the corresponding discreteness is also small. Therefore, a preliminary experiment can be conducted to set a discreteness according to the experimental results. The data area greater than the discreteness is the data area where the human body moves.
[0112] S281. Calculate the change rates of multiple air pressure data in the data area corresponding to the human body movement.
[0113] S282. Identify human body movements based on the rate of change.
[0114] The embodiments of the present invention can accurately identify human body movements, and the sleep report data issued is more accurate; and a more precise smart home linkage effect can be achieved. For example, it can recognize that the night light is automatically turned on when getting out of bed, and the air conditioner is adjusted to a suitable temperature mode when going to bed.
[0115] The technical solution of the embodiment of the present invention first calculates the effective values of multiple air pressure data in each data area, and calculates the difference between the maximum effective value and the minimum effective value of each data area, and determines the data area with a difference greater than a preset change amount as the data area corresponding to the action. Then, the discrete degrees of each data area corresponding to the action are calculated respectively, and the data area with a discrete degree greater than the preset discrete degree is determined as the data area corresponding to the human body action, and the data area with a discrete degree less than or equal to the preset discrete degree is determined as the data area corresponding to the electric bed action, thereby further increasing the recognition accuracy of the action occurring on the mattress.
[0116] Optionally, the effective values of multiple air pressure data in each data area are calculated respectively, including:
[0117] Taking the first air pressure data in the data area as the target data, calculating the average value of the target data and a preset number of air pressure data after the target data as the effective value of the target data;
[0118] All the air pressure data in the data area are taken as target data in turn to obtain the valid values of all the air pressure data in the data area.
[0119] Exemplarily, when calculating the effective value of air pressure data in a certain data area, if the preset number is 4, when calculating the effective value of the first air pressure data, the first air pressure data and the four air pressure data following it are averaged, and the average is the effective value of the air pressure data; when calculating the effective value of the second air pressure data, the second air pressure data and the four air pressure data following it are averaged, and the average is the effective value of the air pressure data, and so on, to obtain the effective value of each air pressure data.
[0120] Optionally, calculating the discreteness of each data region corresponding to when the action occurs includes:
[0121] Calculate the average value of air pressure data in the data area;
[0122] Based on the formula Based on the average value of air pressure data in each data area Calculate the discrete degree AD of each data area s 2; where x is the number of air pressure data in the data area, n is a positive integer and 0≤n≤x, AD buff Any air pressure data in the data area.
[0123] Specifically, Figure 5 is a waveform diagram of the discrete degree of airbag pressure data provided by an embodiment of the present invention, referring to Figure 5 It can be seen that the air pressure changes more obviously in the area where the action occurs, and the discrete degree of the changed air pressure data is also different. Therefore, the electric bed action and human body action can be identified based on the discrete degree of the air pressure data.
[0124] Embodiment 3
[0125] Figure 6 1 is a flow chart of an airbag-based motion recognition method provided in Embodiment 3 of the present invention. Embodiment 3 is optimized based on the above embodiments.
[0126] The above step S140, calculating the change rate of multiple air pressure data in the data area corresponding to the target action, is refined as follows:
[0127] Based on the formula Calculate the average AD of the change rate of multiple air pressure data in the data area corresponding to the target actioncr ; where x is the number of air pressure data in the data area, n is a positive integer and 0≤n≤x, AD buff Any air pressure data in the data area.
[0128] The above step S150, identifying the target action according to the change rate, is refined as follows: cr When it is a positive number, the target action is identified as the action of going to bed; when the mean value of the rate of change AD cr When it is a negative number, the target action is identified as getting out of bed.
[0129] For details not yet provided in this embodiment, please refer to Embodiment 1.
[0130] refer to Figure 6 , the method comprising:
[0131] S310, collecting the air pressure change value of the airbag at a preset frequency to obtain a plurality of air pressure data.
[0132] S320, dividing the air pressure data into a plurality of data regions according to a preset region length.
[0133] S330: Determine a data region corresponding to the target action among multiple data regions.
[0134] S340, based on formula Calculate the average AD of the change rate of multiple air pressure data in the data area corresponding to the target action cr .
[0135] Specifically, since the change in airbag pressure caused by an action is not an instantaneous process but a continuous process, the average of the change rates of multiple air pressure data in the data area corresponding to the target action can accurately reflect the specific target action. Figure 7 is a waveform diagram of the airbag pressure data change rate provided by an embodiment of the present invention, with reference to Figure 7 , it can be clearly seen that the rate of change is positive and negative, and the rate of change in the area where the air pressure changes is also different. Therefore, the specific target action can be identified by the rate of change of the air pressure data.
[0136] S350, average AD of the rate of change cr When it is a positive number, the target action is identified as the action of going to bed.
[0137] For example, when applied to an airbag mattress, when someone gets on the bed, the air pressure of the airbag under the mattress will increase within a period of time, and the air pressure data will also change accordingly. At this time, the overall change trend of multiple air pressure data in the data area corresponding to the target action is also gradually increasing, so the average value AD of the change rate is calculated. cr When it is a positive number, the target action can be identified as the action of going to bed.
[0138] S360, average AD of the rate of change cr When it is a negative number, the target action is identified as getting out of bed.
[0139] For example, when someone leaves the bed, the air pressure of the airbag under the mattress will decrease within a period of time, and the air pressure data will also change accordingly. At this time, the overall change trend of multiple air pressure data in the data area corresponding to the target action is gradually decreasing, so the average value AD of the change rate is calculated. cr When it is a negative number, the target action can be identified as getting out of bed.
[0140] In the embodiment of the present invention, by calculating the mean of the rate of change of the air pressure data, when the mean of the rate of change is a positive number, the target action is identified as the action of getting into bed, and when the mean of the rate of change is a negative number, the target action is identified as the action of getting out of bed, thereby identifying the specific target action and further improving the recognition accuracy.
[0141] Embodiment 4
[0142] Figure 8 It is a structural schematic diagram of an airbag-based motion recognition device provided in Embodiment 4 of the present invention. The device can be applicable to the case of airbag-based motion recognition, wherein the device can be implemented by software and / or hardware and is generally integrated on an airbag-based motion recognition device.
[0143] like Figure 8 As shown, the device comprises:
[0144] The air pressure data acquisition module 410 is used to collect the air pressure change value of the airbag at a preset frequency to obtain a plurality of air pressure data;
[0145] A data region division module 420 is used to divide the air pressure data into a plurality of data regions according to a preset region length;
[0146] A data region determination module 430 is used to determine a data region corresponding to a target action among multiple data regions;
[0147] A change rate calculation module 440 is used to calculate the change rate of multiple air pressure data in the data area corresponding to the target action;
[0148] The target action recognition module 450 is used to recognize the target action according to the change rate.
[0149] In this embodiment, the device first uses the air pressure data acquisition module to collect the air pressure change value of the airbag at a preset frequency to obtain multiple air pressure data; then uses the data area division module to divide the air pressure data into multiple data areas with a preset area length; uses the data area determination module to determine the data area corresponding to the target action in the multiple data areas; uses the change rate calculation module to calculate the change rate of multiple air pressure data in the data area corresponding to the target action; finally, uses the action recognition module to identify the target action according to the change rate. The above technical solution solves the problem that the existing airbag needs to use additional sensors to realize air pressure detection and action recognition, which brings high costs and complex products; the technical solution of the present invention only realizes specific action recognition through the air pressure data of the airbag, without the need for additional sensors, and is applied to smart mattresses, which greatly reduces the cost of mattresses and the complexity of products, and improves the competitiveness of products.
[0150] The separation of human movements and electric bed movements, and the identification of specific human movements, without the need for additional sensors, greatly reduces the cost of mattresses and product complexity, and improves product competitiveness.
[0151] The data area determination module 430 includes:
[0152] The motion separation unit is used to determine the data area corresponding to the human body motion and the data area corresponding to the electric bed motion among the multiple data areas.
[0153] The change rate calculation module 440 is specifically used to respectively calculate the change rates of a plurality of air pressure data in the data area corresponding to the human body motion and the change rates of a plurality of air pressure data in the data area corresponding to the electric bed motion;
[0154] The target motion recognition module 450 is specifically used to recognize the motion of the electric bed according to the change rate of a plurality of air pressure data in the data area corresponding to the motion of the electric bed.
[0155] The action separation unit is specifically used for:
[0156] Calculate the discreteness of multiple data areas respectively;
[0157] Determine a data region with a discreteness greater than a preset discreteness as a data region corresponding to a human body action;
[0158] A data region whose discreteness is less than or equal to a preset discreteness is determined as a data region corresponding to the electric bed action.
[0159] The action separation unit is also used for:
[0160] Calculate the average value of air pressure data in each data area respectively;
[0161] Based on the formula Based on the average value of air pressure data in each data area Calculate the discrete degree AD of each data area s 2; where x is the number of air pressure data in the data area, n is a positive integer and 0≤n≤x, AD buff Any air pressure data in the data area.
[0162] The data area determination module 430 includes:
[0163] An action occurrence data region determining unit, used to determine, from among multiple data regions, a data region corresponding to when an action occurs;
[0164] The data region separation unit is used to determine the data region corresponding to the human body movement and the data region corresponding to the electric bed movement in the data region corresponding to the movement.
[0165] Optionally, the action occurrence data area determination unit is specifically configured to:
[0166] Calculate the effective values of multiple air pressure data in each data area respectively;
[0167] Calculate the difference between the maximum valid value and the minimum valid value of each data area respectively;
[0168] The data region whose difference is greater than the preset variation is determined as the data region corresponding to the action occurring.
[0169] The action occurrence data area determination unit is further used for:
[0170] Taking the first air pressure data in the data area as the target data, calculating the average value of the target data and a preset number of air pressure data after the target data as the effective value of the target data;
[0171] All the air pressure data in the data area are taken as target data in turn to obtain the valid values of all the air pressure data in the data area.
[0172] Optionally, the data area separation unit is specifically used to:
[0173] Calculate the discrete degree of each data area corresponding to the action;
[0174] Determine a data region with a discreteness greater than a preset discreteness as a data region corresponding to a human body action;
[0175] A data region whose discreteness is less than or equal to a preset discreteness is determined as a data region corresponding to the electric bed action.
[0176] Optionally, the data area separation unit is further used for:
[0177] Calculate the average value of air pressure data in the data area;
[0178] Based on the formula According to the average value of air pressure data in the data area Calculate the discrete degree AD of the data area corresponding to the action s 2; where x is the number of air pressure data in the data area, n is a positive integer and 0≤n≤x, AD buff Any air pressure data in the data area.
[0179] Optionally, the change rate calculation module 440 is specifically used to:
[0180] Based on the formula Calculate the average AD of the change rate of multiple air pressure data in the data area corresponding to the target action cr .
[0181] Optionally, the target action recognition module 450 is specifically configured to:
[0182] The mean AD of the rate of change cr When it is a positive number, the target action is identified as the action of going to bed;
[0183] The mean AD of the rate of change cr When it is a negative number, the target action is identified as getting out of bed.
[0184] The above-mentioned airbag-based motion recognition device can execute the airbag-based motion recognition method provided by any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.
[0185] Embodiment 5
[0186] Fig. 9 Schematic diagram of the structure of an airbag-based motion recognition device provided by Embodiment 5 of the present invention. Fig. 9 As shown, the device provided by the fifth embodiment of the present invention includes: one or more processors 51 and a storage device 52; the processor 51 in the device may be one or more, Fig. 9 A processor 51 is taken as an example; the storage device 52 is used to store one or more programs; the one or more programs are executed by the one or more processors 51, so that the one or more processors 51 implement the airbag-based motion recognition method as described in any one of the embodiments of the present invention.
[0187] The device may further include: an input device 53 and an output device 54 .
[0188] The processor 51, storage device 52, input device 53 and output device 54 in the device may be connected via a bus or other means. Fig. 9 The example of connecting through bus is taken in the following.
[0189] The storage device 52 in the device is a computer-readable storage medium that can be used to store one or more programs, which can be software programs, computer executable programs and modules, such as program instructions / modules corresponding to the airbag-based motion recognition method provided in Embodiment 1 or 2 of the present invention. The processor 51 executes various functional applications and data processing of the terminal device by running the software programs, instructions and modules stored in the storage device 52, that is, the airbag-based motion recognition method in the above method embodiment is implemented.
[0190] The storage device 52 may include a program storage area and a data storage area, wherein the program storage area may store an operating system and at least one application required for a function; the data storage area may store data created according to the use of the device, etc. In addition, the storage device 52 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other non-volatile solid-state storage device. In some instances, the storage device 52 may further include a memory remotely arranged relative to the processor 51, and these remote memories may be connected to the device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.
[0191] The input device 53 may be used to receive input digital or character information and generate key signal input related to user settings and function control of the device. The output device 54 may include a display device such as a display screen.
[0192] Furthermore, when one or more programs included in the above device are executed by the one or more processors 51, the program performs the following operations:
[0193] The air pressure change value of the airbag is collected at a preset frequency to obtain a plurality of air pressure data;
[0194] Divide the air pressure data into multiple data regions with preset region lengths;
[0195] Determine, among the multiple data regions, a data region corresponding to the target action;
[0196] Calculate the change rate of multiple air pressure data in the data area corresponding to the target action;
[0197] According to the rate of change, the target action is identified.
[0198] Embodiment 6
[0199] Embodiment 6 of the present invention provides a computer-readable storage medium having a computer program stored thereon. When the program is executed by a processor, it is used to execute an airbag-based motion recognition method, the method comprising: collecting air pressure change values of the airbag at a preset frequency to obtain multiple air pressure data; dividing the air pressure data into multiple data areas with preset area lengths; determining the data area corresponding to the target action in the multiple data areas; calculating the change rate of multiple air pressure data in the data area corresponding to the target action; and identifying the target action based on the change rate.
[0200] Optionally, when the program is executed by a processor, it can also be used to execute the airbag-based motion recognition method provided by any embodiment of the present invention.
[0201] The computer storage medium of the embodiment of the present invention may adopt any combination of one or more computer-readable media. The computer-readable medium may be a computer-readable signal medium or a computer-readable storage medium. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples (non-exhaustive list) of computer-readable storage media include: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM), a flash memory, an optical fiber, a portable CD-ROM, an optical storage device, a magnetic storage device, or any suitable combination of the above. The computer-readable storage medium may be any tangible medium containing or storing a program, which may be used by or in combination with an instruction execution system, device or device.
[0202] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, which carry computer-readable program code. Such propagated data signals may take a variety of forms, including but not limited to: electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.
[0203] The program code contained on the computer-readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, optical cable, radio frequency (RF), etc., or any suitable combination of the above.
[0204] Computer program code for performing the operations of the present invention may be written in one or more programming languages or a combination thereof, including object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).
[0205] Note that the above are only preferred embodiments of the present invention and the technical principles used. Those skilled in the art will understand that the present invention is not limited to the specific embodiments described herein, and that various obvious changes, readjustments and substitutions can be made by those skilled in the art without departing from the scope of protection of the present invention. Therefore, although the present invention has been described in more detail through the above embodiments, the present invention is not limited to the above embodiments, and may include more other equivalent embodiments without departing from the concept of the present invention, and the scope of the present invention is determined by the scope of the appended claims.
Claims
1. An airbag-based motion recognition method, characterized in that: include: The air pressure change value of the airbag is collected at a preset frequency to obtain a plurality of air pressure data; Dividing the air pressure data into a plurality of data regions according to a preset region length; Determining the data area corresponding to the target action among the multiple data areas; Calculating the change rate of a plurality of air pressure data in the data area corresponding to the target action; The target action is identified based on the change rate.
2. The action recognition method according to claim 1, characterized in that: The target motion includes electric bed motion and human body motion; Determining the data area corresponding to the target action among the multiple data areas includes: Among the plurality of data areas, determining the data area corresponding to human body motion and the data area corresponding to electric bed motion; Calculating the change rate of a plurality of air pressure data in the data area corresponding to the target action includes: respectively calculating the change rates of a plurality of air pressure data in the data area corresponding to the human body motion and the change rates of a plurality of air pressure data in the data area corresponding to the electric bed motion; According to the change rate, identifying the target action includes: identifying a human body movement according to a change rate of a plurality of air pressure data in the data area corresponding to the human body movement; The electric bed motion is identified based on the change rate of the plurality of air pressure data in the data area corresponding to the electric bed motion.
3. The action recognition method according to claim 2, characterized in that: Determining the data area corresponding to the human body motion and the data area corresponding to the electric bed motion in the plurality of data areas comprises: respectively calculating the discreteness of the plurality of data regions; Determine the data region whose discreteness is greater than a preset discreteness as the data region corresponding to the human body motion; The data region whose discreteness is less than or equal to the preset discreteness is determined as the data region corresponding to the electric bed action.
4. The action recognition method according to claim 3, characterized in that: Calculating the discreteness of the plurality of data regions respectively includes: Calculate the average value of the air pressure data in each of the data areas respectively; Based on the formula According to the average value of the air pressure data in each data area Calculate the discrete degree AD of each data area s 2; where x is the number of air pressure data in the data area, n is a positive integer and 0≤n≤x, AD buff It is any of the air pressure data in the data area.
5. The action recognition method according to claim 1, characterized in that: Determining the data area corresponding to the target action among the multiple data areas includes: Among the multiple data areas, determining the data area corresponding to when the action occurs; In the data area corresponding to when the action occurs, the data area corresponding to the target action is determined.
6. The action recognition method according to claim 5, characterized in that: Determining, among the multiple data areas, the data area corresponding to when the action occurs, comprises: respectively calculating effective values of a plurality of the air pressure data in each of the data areas; Calculate the difference between the maximum effective value and the minimum effective value of each data area respectively; The data region where the difference is greater than a preset change amount is determined as the data region corresponding to when the action occurs.
7. The action recognition method according to claim 6, characterized in that: Respectively calculating the effective values of the plurality of air pressure data in each of the data regions, comprising: Taking the first air pressure data in the data area as the target data, calculating the average value of the target data and a preset number of air pressure data after the target data as the effective value of the target data; All the air pressure data in the data area are taken as the target data in sequence to obtain the valid values of all the air pressure data in the data area.
8. The action recognition method according to claim 1, characterized in that: Calculating the change rate of a plurality of air pressure data in the data area corresponding to the target action includes: Based on the formula Calculate the average AD of the change rate of multiple air pressure data in the data area corresponding to the target action cr ; Wherein, x is the number of air pressure data in the data area, n is a positive integer and 0≤n≤x, AD buff It is any of the air pressure data in the data area.
9. The action recognition method according to claim 8, characterized in that: According to the change rate, identifying the target action includes: The mean value of the rate of change AD cr When it is a positive number, the target action is identified as the action of going to bed; The mean value of the rate of change AD cr When it is a negative number, the target action is identified as the action of getting out of bed.
10. An airbag-based motion recognition device, characterized in that: include: An air pressure data acquisition module, used to collect the air pressure change value of the airbag at a preset frequency to obtain a plurality of air pressure data; A data region division module, used for dividing the air pressure data into a plurality of data regions according to a preset region length; A data region determination module, used to determine the data region corresponding to the target action among the multiple data regions; a change rate calculation module, used to calculate the change rate of a plurality of air pressure data in the data area corresponding to the target action; The target action recognition module is used to recognize the target action according to the change rate.
11. An airbag-based motion recognition device, characterized in that: include: one or more processors; A storage device for storing one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement the airbag-based motion recognition method as described in any one of claims 1-9.
12. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the airbag-based motion recognition method as described in any one of claims 1 to 9 is implemented.
Citation Information
Patent Citations
Human health data acquisition and analysis system for soft and hard adjustable mattress and method thereof
CN109157194A
User state sensing method and device, intelligent mattress and storage medium
CN115024615A
Mattress deformation adjusting method and device, mattress and storage medium
CN115039989A
Method and system for identifying getting-out-of-bed intention of array type air bag mattress
CN115429066A
Human health detection method and system based on mattress data and storage medium
CN116369874A
