Multi-information fusion mattress control method and mattress

Abstract

The invention belongs to the field of furniture, and discloses a multi-information fusion mattress control method and a mattress, the mattress comprises a bottom coat layer, a support layer, a pressure pad identification layer and a top coat layer arranged from top to bottom; the supporting layer comprises a plurality of air bag assemblies, the air bag assemblies are divided into a plurality of stress subareas corresponding to physiological curves of a user, and each stress subarea is provided with an air pressure sensor used for collecting a one-dimensional air pressure distribution data set; the pressure pad identification layer comprises a pressure pad identification matrix formed by m rows and n columns of pressure sensing units, and is used for collecting body pressure distribution data of a user and generating a two-dimensional pressure distribution matrix; the control assembly is connected with the supporting layer and the pressure pad recognition layer, comprises a calculation unit, an air pump, an electromagnetic valve and an air pressure sensor, and is used for recognizing the macroscopic sleeping posture state and the microcosmic action change of the user according to the two-dimensional pressure distribution matrix and the one-dimensional air pressure distribution data set; and the air pump and the electromagnetic valve are controlled to inflate and deflate the corresponding air bag assembly according to the identification result.

Description

Technical Field

[0001] This invention belongs to the field of furniture, and in particular relates to a mattress control method and mattress with multi-information fusion. Background Technology

[0002] As people's living standards improve, their demands for sleep quality are also increasing. Traditional mattresses typically use a fixed-firm support structure, which cannot adaptively adjust to the user's sleeping position and physical condition. This can easily lead to excessive local pressure, affecting blood circulation and causing sleep discomfort.

[0003] While some adjustable smart mattresses have emerged in related technologies, most of them use a single sensor for status recognition, which has limited recognition accuracy and a single adjustment strategy, making it impossible to achieve precise personalized support. Summary of the Invention

[0004] In view of this, the present invention discloses a mattress control method and mattress based on multi-information fusion, which can solve the shortcomings of related technologies.

[0005] To achieve the above objectives, the present invention discloses the following technical solution: According to a first aspect of the present invention, a multi-information fusion mattress control method is proposed, applied to a mattress control component. The mattress includes, from top to bottom, a bottom outer layer, a support layer, a pressure pad identification layer, and a top outer layer. The support layer includes multiple airbag assemblies, which are divided into multiple pressure zones. Each pressure zone is equipped with a pressure sensor for collecting a one-dimensional pressure distribution dataset. The pressure pad identification layer includes a pressure pad identification matrix composed of m rows and n columns of pressure sensing units, used to collect user body pressure distribution data and generate a two-dimensional pressure distribution matrix. The control component is connected to the support layer and the pressure pad identification layer and includes a computing unit, an air pump, a solenoid valve, and a pressure sensor. The method includes: Acquire the user's physiological information, and divide the multiple airbag components in the support layer into force zones corresponding to the user's physiological curve based on the physiological information; Establish a mapping relationship between the row data of the pressure pad identification matrix and the stress zone; In response to the acquired two-dimensional pressure distribution matrix and the one-dimensional air pressure distribution dataset, the system identifies the user's macroscopic sleeping posture and microscopic movement changes, and controls the air pump and solenoid valve to inflate and deflate the corresponding airbag components based on the identification results.

[0006] Preferably, when the user's overall sleeping posture remains unchanged, the step of controlling the air pump and solenoid valve to inflate and deflate the corresponding airbag assembly based on the recognition result includes: Calculate the air pressure change in each stress zone and the pressure characteristic value change in the corresponding pressure pad matrix area; Based on the user's physiological information and current sleeping position, calculate the adaptive weighting factor for each pressure zone; The equivalent body pressure change of each stress zone is calculated based on the pressure change, pressure characteristic value change, and adaptive weighting factor. Based on the equivalent body pressure change, it is determined whether to perform inflation or deflation operations on the corresponding stress zone.

[0007] Preferably, determining whether to perform inflation or deflation operations on the corresponding stress zone based on the equivalent body pressure change includes: Determine the preset adjustment threshold for each stress zone; If the change in equivalent body pressure exceeds the preset adjustment threshold of the corresponding force zone, and the change in equivalent body pressure is positive, then an air release operation is performed; if the change in equivalent body pressure is negative, then an air inflation operation is performed.

[0008] Preferably, the step of calculating the equivalent body pressure change of each stress zone based on the pressure change, the pressure characteristic value change, and the adaptive weighting factor includes: The formula for calculating the equivalent body pressure change is as follows: ΔP_e(j)=|ΔP_s(j)|+K(j)×|ΔP_a(j)|; Wherein, ΔP_e(j) is the equivalent volume pressure change corresponding to force zone j, ΔP_a(j) is the air pressure change corresponding to force zone j, and ΔP_s(j) is the pressure characteristic value change corresponding to force zone j. The formula for calculating the change in the pressure characteristic value is as follows: ΔP_s(j)=P_s(j,t)-P_s(j,t-ΔT); P_s(j,t) = ; Where P_s(j,t) represents the weighted average pressure value of the characteristic values ​​of the pressure state of the area covered by the pressure pad matrix corresponding to the j-th stress zone at time t; P_mat(m,n,t) represents the pressure value measured by a single pressure pad sensor located in the m-th row and n-th column of the pressure pad matrix at time t; M_j represents the set of all rows belonging to the j-th stress zone; w(m,n) represents the weight of each pressure pad sensor position (m,n); denominator This represents the sum of all weight coefficients; The formula for calculating the change in air pressure is as follows: ΔP_a(j)=P_a(j,t)-P_a(j,t-ΔT); Where P_s(j,t) represents the weighted average pressure value of the airbag component pressure change in the j-th stress zone during time t.

[0009] Preferably, the step of controlling the air pump and solenoid valve to inflate and deflate the corresponding airbag assembly based on the identification result includes: When a change in the user's macroscopic sleeping posture is detected, the support curve is reconstructed as a whole based on the user's new sleeping posture. When the user's subtle changes in movement are detected, the local airbag components are precisely fine-tuned.

[0010] Preferably, the airbag assembly in the support layer is physically isolated laterally and / or longitudinally by an insulating sponge assembly.

[0011] Preferably, the physiological information includes at least one of the following: BMI index, gender, height, weight, and body type.

[0012] Preferably, the pressure sensing units of the pressure pad identification matrix are arranged in a differentiated density distribution, wherein the distribution density in the shoulder and back area and waist area corresponding to the user is higher than that in the leg area.

[0013] Preferably, the support layer further includes a head support assembly and a tail support sponge assembly, and the control assembly is disposed within the tail support sponge assembly.

[0014] According to a second aspect of the present invention, a mattress is provided, the mattress comprising, from top to bottom, a bottom outer layer L10, a support layer L20, a pressure pad identification layer L40, and a top outer layer L50; The support layer L20 includes multiple airbag components L2013, which are divided into multiple pressure zones corresponding to the user's physiological curve. Each pressure zone is equipped with a pressure sensor to collect a one-dimensional pressure distribution dataset. The pressure pad identification layer L40 includes a pressure pad identification matrix L401 composed of m rows and n columns of pressure sensing units, which is used to collect user body pressure distribution data and generate a two-dimensional pressure distribution matrix. Control component L2015, connected to the support layer L20 and the pressure pad recognition layer L40, includes a computing unit, an air pump, a solenoid valve, and a pressure sensor. It is used to identify the user's macroscopic sleeping posture and microscopic movement changes based on the two-dimensional pressure distribution matrix and the one-dimensional pressure distribution dataset, and to control the air pump and solenoid valve to inflate and deflate the corresponding airbag component L2013 based on the identification results.

[0015] According to a third aspect of the present invention, an electronic device is provided, comprising: processor; Memory used to store processor-executable instructions; The processor implements the steps of the method as described in the first aspect by running the executable instructions.

[0016] According to a fourth aspect of the invention, a computer-readable storage medium is provided having computer instructions stored thereon that, when executed by a processor, implement the steps of the method as described in the first aspect.

[0017] As can be seen from the above technical solutions, the multi-information fusion mattress control method disclosed in this invention: This method overcomes the limitations of single-sensor technology by fusing two types of data, improving the accuracy and reliability of user status recognition (especially subtle movements). On the other hand, the hierarchical adjustment strategy avoids frequent or excessive overall adjustments, reduces sleep disturbances, and achieves smooth, humanized, and accurate adaptive support, thereby improving user experience and sleep quality. Attached Figure Description

[0018] Figure 1 This is a schematic diagram of a mattress structure provided in an exemplary embodiment; Figure 2 This is a schematic diagram of a mattress side structure provided in an exemplary embodiment; Figure 3 This is a schematic diagram of another mattress side structure provided in an exemplary embodiment; Figure 4 This is a schematic diagram of yet another mattress side structure provided in an exemplary embodiment; Figure 5 This is a flowchart of a multi-information fusion mattress control method provided in an exemplary embodiment; Figure 6 This is a schematic diagram of a pressure matrix distribution provided in an exemplary embodiment; Figure 7 This is a schematic diagram of a pressure matrix distribution with different regional densities provided in an exemplary embodiment; Figure 8 This is a flowchart illustrating a specific control method for a mattress, as provided in an exemplary embodiment. Figure 9 This is a schematic structural diagram of a device provided in an exemplary embodiment. Detailed Implementation

[0019] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numerals in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with one or more embodiments of the present invention. Rather, they are merely examples of apparatuses and methods consistent with some aspects of one or more embodiments of the present invention as detailed in the appended claims.

[0020] It should be noted that the steps of the corresponding methods in other embodiments are not necessarily performed in the order shown and described in this invention. In some other embodiments, the methods may include more or fewer steps than those described in this invention. Furthermore, a single step described in this invention may be broken down into multiple steps in other embodiments; and multiple steps described in this invention may be combined into a single step in other embodiments.

[0021] To further illustrate the present invention, the following embodiments are provided: As people's living standards improve, their demands for sleep quality are also increasing. Traditional mattresses typically use a fixed-firm support structure, which cannot adaptively adjust to the user's sleeping position and physical condition. This can easily lead to excessive local pressure, affecting blood circulation and causing sleep discomfort.

[0022] While some adjustable smart mattresses have emerged in related technologies, most rely on a single sensor for status recognition, resulting in limited accuracy and a simplistic adjustment strategy that fails to provide precise personalized support. For example, single pressure pad recognition technology, which only identifies common sleeping positions such as lying flat or on one's side, lacks accurate recognition and adaptive adjustment for real-time pressure comfort changes when the user experiences subtle movements or static shifts. This leads to low levels of intelligence and personalization. Alternatively, single air pressure recognition technology, where the air pressure value of a single airbag or air spring represents all pressure distribution details within that area, suffers from low spatial resolution and cannot accurately reconstruct fine body postures. Furthermore, posture recognition algorithms that rely solely on air pressure data suffer from severely unreliable recognition due to the "many-to-one" mapping between air pressure changes and body posture. Different postures may produce similar air pressure patterns.

[0023] To address the shortcomings of related technologies, this invention proposes a mattress control method based on multi-information fusion.

[0024] Figure 1 This is a schematic diagram of a mattress structure provided in an exemplary embodiment. Figure 1As shown, the mattress includes, from top to bottom, a bottom outer layer L10, a support layer L20, a pressure pad identification layer L40, and a top outer layer L50.

[0025] The bottom outer layer L10 is located at the very bottom of the mattress. It is combined with the top outer layer L50 through processes such as zippers or sewing. It mainly provides bottom support and protection for the mattress and enhances the appearance of the bottom layer.

[0026] The mattress support layer L20, located above the bottom outer layer L10, is the system's execution and feedback mechanism, responsible for providing dynamically adjustable support force and providing feedback on the mechanical state. The support layer L20 includes multiple airbag assemblies L2013, which are divided into multiple pressure zones corresponding to the user's physiological curves. Each pressure zone is equipped with a pressure sensor to collect a one-dimensional pressure distribution dataset.

[0027] Airbag components include, but are not limited to, pocket springs, foam, airbags, or air springs.

[0028] In one scenario, the airbag assembly in the support layer is physically isolated laterally and / or longitudinally by an insulating foam assembly. For example... Figure 1 As shown, the air spring isolation foam assembly L2012 and air spring assembly L2013 constitute the core components of the mattress support layer. Physically, they are divided into multiple independently controlled pressure zones, typically including areas corresponding to key physiological curves of the human body, such as the shoulders and back, waist, hips, and legs. Each air spring is isolated laterally and longitudinally by an independent isolation foam assembly to prevent friction and noise between the air springs during inflation, deflation, or when the user turns over.

[0029] The pressure pad identification layer L40 includes a pressure pad identification matrix L401 composed of m rows and n columns of pressure sensing units, which is used to collect user body pressure distribution data and generate a two-dimensional pressure distribution matrix.

[0030] The control components L2015 and L2013 air spring assemblies are connected to the L2015 control component via air pipes.

[0031] It can be built into the inside or outside of the mattress. For better illustration, this embodiment uses a control component built into the mattress as an example. In this embodiment, the support layer L20 includes a head support component L2011, an air spring insulating foam component L2012, an air spring component L2013, a tail support foam component L2014, and a control component L2015. The control component is installed and fixed inside the tail support foam component L2014.

[0032] The control component L2015 is a comprehensive control center integrating a computing unit, air pump, solenoid valve assembly, and air pressure sensor. Its core function is to run the multi-source information fusion adaptive algorithm proposed in this invention. Specifically, the control component collects internal air pressure data from the air springs supporting each force zone of layer L20 in real time through its built-in air pressure sensor. Simultaneously, it receives full matrix pressure data from layer L40. The algorithm performs spatiotemporal registration, feature extraction, and fusion calculation on these two types of heterogeneous data (e.g., calculating the "equivalent body pressure change") to accurately determine the user's real-time state (macroscopic turning over or microscopic movement). Based on this determination, the system activates corresponding graded dynamic adjustment strategies (such as "sleeping posture adjustment mode" or "micro-adjustment mode") and issues precise inflation / deflation commands to the corresponding airbag zones by controlling the air pump and solenoid valves on specific pathways, ultimately achieving closed-loop control of adaptive support adjustment.

[0033] This design allows each pressure zone to be independently inflated and deflated, enabling precise, localized adjustment of support stiffness. Furthermore, each pressure zone functions as a closed mechanical system, with its internal air pressure changing in real time with changes in the user's posture. Therefore, this layer is not only a controlled object but also a crucial state sensor, indirectly reflecting the mechanical changes exerted on the mattress by the user's weight distribution and movements.

[0034] The tail support foam assembly L2014 mainly provides support for the tail area and provides an installation position for the control assembly L2015.

[0035] Another situation, such as Figure 2 As shown, the support layer L20 can be divided into L2021 head support assembly, L2022 air spring isolation foam assembly, L2023 air spring assembly, L2024 tail support foam assembly, L2025 control assembly, and L2026 filled pocket spring or foam assembly. Since the leg area is not a key physiological curve support adjustment area, the L2026 filled pocket spring or foam assembly can be used to cover the leg support area. This reduces mattress costs and, more importantly, decreases the number of air springs in the leg area where inflation / deflation adjustment is less sensitive, improving the inflation / deflation efficiency of air springs in other areas.

[0036] In another case, such as Figure 3 As shown, the support layer L20 can also be divided into L2031 head support assembly, L2032 airbag isolation foam assembly, L2033 airbag assembly, L2034 tail support foam assembly, and L2035 control assembly. Compared to Figure 2 The main difference lies in the L2032 airbag insulation foam assembly and the L2033 airbag assembly. The advantage is that the entire airbag manufacturing process is simpler and the cost is lower. In another case, such as Figure 4 As shown, the support layer L20 can also be divided into L2041 head support assembly, L2042 airbag isolation foam assembly, L2043 airbag assembly, L2044 tail support foam assembly, L2045 control assembly, and L2046 filled pocket spring or foam assembly. The leg area, which is not a critical physiological curve support adjustment area, is covered by the L2046 filled pocket spring or foam assembly. Furthermore, the simple manufacturing process of the entire airbag system allows for greater cost reduction, simplifies the mattress manufacturing process, and improves the inflation and deflation efficiency of air springs in other areas.

[0037] Furthermore, the mattress can also have a comfort layer L30, located above the support layer L20. This layer serves two purposes: firstly, to balance the foreign body sensation caused by the air spring material, and secondly, to provide the mattress with a pressure relief comfort experience through air inflation and deflation adjustment. This comfort layer may include, but is not limited to, latex, memory foam, air fiber, or sponge. The choice of material and thickness of this comfort layer is related to the air inflation and deflation adjustment experience of the mattress's air springs.

[0038] Figure 5 This is a flowchart illustrating a multi-information fusion mattress control method as provided in an exemplary embodiment. Figure 5 As shown, this method is applied to the control component of a mattress, which includes, from top to bottom, a bottom outer layer, a support layer, a pressure pad recognition layer, and a top outer layer. The support layer includes multiple airbag assemblies, which are divided into multiple pressure zones. Each pressure zone is equipped with a pressure sensor to collect a one-dimensional pressure distribution dataset. The pressure pad recognition layer includes a pressure pad recognition matrix composed of m rows and n columns of pressure sensing units, used to collect user body pressure distribution data and generate a two-dimensional pressure distribution matrix. The control component is connected to the support layer and the pressure pad recognition layer and includes a computing unit, an air pump, a solenoid valve, and a pressure sensor. The method includes at least the following steps: Step 501: Obtain the user's physiological information, and divide the multiple airbag components in the support layer into force zones corresponding to the user's physiological curve based on the physiological information.

[0039] In one embodiment, the physiological information includes at least one of the following: BMI, sex, height, weight, and body type.

[0040] Step 502: Establish the mapping relationship between the row data of the pressure pad identification matrix and the stress zone.

[0041] Step 503: In response to the acquired two-dimensional pressure distribution matrix and the one-dimensional air pressure distribution dataset, identify the user's macroscopic sleeping posture and microscopic movement changes, and control the air pump and solenoid valve to inflate and deflate the corresponding airbag components according to the identification results.

[0042] Based on the recognition results, the air pump and solenoid valve are controlled to inflate and deflate the corresponding airbag components, including: when a change in the user's macroscopic sleeping posture is detected, the support curve is reconstructed as a whole according to the user's new sleeping posture; when a change in the user's microscopic movements is detected, the local airbag components are precisely fine-tuned.

[0043] In this embodiment, the method overcomes the limitations of single-sensor technology by fusing two types of data, thereby improving the accuracy and reliability of user status recognition (especially subtle movements). On the other hand, the hierarchical adjustment strategy avoids frequent or excessive overall adjustments, reduces sleep disturbances, and achieves smooth, humanized, and accurate adaptive support, thereby improving user experience and sleep quality.

[0044] In one embodiment, the airbag assembly in the support layer is physically isolated laterally and / or longitudinally by an insulating foam assembly. In this embodiment, the lateral and / or longitudinal isolation provided by the insulating foam assembly effectively prevents multiple independent airbags from rubbing against each other and generating noise during inflation, deflation, or when the user turns over, ensuring a quiet sleeping environment and improving the mattress's reliability and durability.

[0045] In one embodiment, the pressure sensing units of the pressure pad identification matrix are arranged in a differentiated density distribution, wherein the distribution density in the shoulder and back area and waist area corresponding to the user is higher than that in the leg area.

[0046] like Figure 6 As shown, the pressure pad recognition matrix L401 can be a flexible pressure pad recognition matrix evenly distributed horizontally and vertically, composed of m × n L4010 pressure sensing units. Further, each of the m rows of L4012a10 pressure sensing units maps to the center position of each row of air spring assemblies in the L20 mattress support layer in the vertical direction of the mattress; the n columns of L4012a20 pressure sensing units are evenly distributed and mapped to the left and right areas of each row of air spring assemblies in the L20 mattress support layer. The m rows and n columns of pressure sensing units are analyzed by the pressure pad matrix algorithm analysis unit L4011 and communicate with the L2015 control component via a local wired connection, thereby realizing the recognition and detection of the user's real-time pressure value.

[0047] like Figure 7 As shown, the pressure pad identification matrix L401 can be a flexible pressure pad identification matrix with differentiated density distribution in the horizontal and vertical directions, and is composed of m × n L4010 pressure sensing units.

[0048] Furthermore, the m-row pressure sensing units are distributed at unequal densities along the longitudinal direction of the mattress, based on the ergonomic characteristics of human height, in the shoulder, back, waist, hip, and leg areas. The distribution is denser closer to the shoulder and waist areas, including: L4012b10, which maps to L20131 shoulder and back air spring or airbag assembly, is located at the longitudinal center of each row of air spring assemblies in the vertical direction of the mattress, and at the longitudinal center between each row of air spring assemblies; L4012b11, which maps to L20132 lumbar and back transition air spring or airbag assembly 1, is located at the longitudinal center of the air spring assembly in the vertical direction of the mattress; L4012 maps to L20133 lumbar and back transition air spring or airbag assembly 2, L20134 lumbar and hip transition air spring or airbag assembly 1, and L20135 lumbar and hip transition air spring or airbag assembly 2. b12, located at the longitudinal center of each row of air spring assemblies in the vertical direction of the mattress and at the longitudinal center between each row of air spring assemblies; L4012b13, which maps to L20136 hip air spring or airbag assembly and L20137 hip and leg transition air spring or airbag assembly 1, are located at the longitudinal center of each row of air spring assemblies in the vertical direction of the mattress; L4012b14, which maps to L20138 hip and leg transition air spring or airbag assembly 2 and L20139 leg air spring or airbag assembly, is located at the longitudinal center of the middle row of air spring assemblies in the vertical direction of the mattress.

[0049] n rows of pressure sensing units can be distributed in the horizontal direction of the mattress according to the characteristics of common sleep areas, with unequal density on the left and right sides of the center of the pillow. The closer to the center, the denser the distribution. These include: high-density areas L4012b22 and L4012b23, medium-density areas L4012b21 and L4012b24, and low-density areas L4012b20 and L4012b25.

[0050] The m-row, n-column pressure sensing units can be analyzed by the pressure pad matrix algorithm analysis unit L4011 and communicate with the control component L2015 via a local wired connection, thereby realizing the identification and detection of the user's real-time pressure value.

[0051] In one embodiment, the support layer further includes a head support assembly and a tail support sponge assembly, and the control assembly is disposed within the tail support sponge assembly.

[0052] The following is combined Figure 8 The specific process of mattress control is described. For example... Figure 8 As shown, the specific control method for a mattress may include the following steps: S100, Mattress system parameter settings.

[0053] After the system is powered on, the mattress system parameters are set through the user interaction unit. These parameters include user static information, mattress comfort information, and adaptive settings.

[0054] User static information refers to information such as BMI, gender, height, weight, and body type pre-entered by the user. Preferably, the purpose of setting user static information is to provide a more accurate user model library mapping reference for pressure pad pressure matrix status recognition and supporting air spring air pressure status recognition, thereby providing more accurate status recognition.

[0055] Mattress feel information refers to the user's preferred mattress feel under static support conditions. Preferably, setting mattress feel information can provide a user-preferred benchmark for subsequent pressure matrix data and air spring pressure data under supine, side-lying, and micro-movement states.

[0056] Furthermore, users can customize the mattress's adaptive settings according to their preferences. These settings can include adaptive on / off settings, adaptive recognition sensitivity settings, and adaptive adjustment sensitivity settings. The adaptive recognition sensitivity includes multiple recognition time window sensitivities to meet the needs of different users for adaptive detection response. Preferably, this embodiment offers three levels of recognition sensitivity: high, medium, and low. For example, high corresponds to a response time of 3 seconds, meaning the system recognizes the user's macroscopic turning or microscopic movements every 3 seconds. Medium corresponds to a response time of 30 seconds, meaning the system recognizes the user's macroscopic turning or microscopic movements every 30 seconds. Low corresponds to a response time of 60 seconds, meaning the system recognizes the user's macroscopic turning or microscopic movements every 60 seconds. Furthermore, the adaptive adjustment sensitivity includes multiple levels of inflation / deflation adjustment target sensitivity to meet the needs of different users for adaptive adjustment target comfort. Preferably, this embodiment offers three levels of adjustment sensitivity: high, medium, and low. For example, high corresponds to 100% of the target air pressure, medium corresponds to 75% of the target air pressure, and low corresponds to 50% of the target air pressure.

[0057] Jump to S200 to continue execution.

[0058] S200, air spring zone and position data mapping of key human body parts.

[0059] The core of a zoned mattress is providing the right support in the right places. The position of a person's shoulders, back, waist, hips, and legs on the mattress directly depends on their height. After obtaining relevant information such as the user's gender, height, weight, and body type, a zoned mattress is designed to provide the correct support. Figure 2This paper presents a schematic diagram of the support distribution structure of an adaptive recognition and intervention smart mattress control system based on the fusion of multi-source information on pressure distribution and air pressure changes. Preferably, height thresholds HH1 and HH2 are set, with HH1 = 150cm and HH2 = 190cm. For individuals shorter than HH1, the preferred combination is L20131 for the shoulders and back, L20132 and L20133 for the waist, L20134-L20136 for the hips, and L20137-L20139 for the legs; alternatively, for individuals of moderate height, greater than or equal to HH1 and less than or equal to HH2, the preferred combination is L20131-L20132 for the shoulders and back, L201... Combinations 33~L20134 represent the waist, combinations L20135~L20137 represent the hips, and combinations L20138~L20139 represent the legs; alternatively, for individuals whose height is greater than HH2, combinations L20131~L20133 represent the shoulders and back, combinations L20134~L20135 represent the waist, combinations L20136~L20138 represent the hips, and combinations L20139 represent the legs.

[0060] L20132~L20138 can also intelligently identify and adjust based on the output results of the pressure pad's predictive model, providing users with more precise ergonomic support anytime, anywhere.

[0061] L20131 can also be fixed in combination with L20132 for the shoulders and back, L20133 and L20134 for the waist, L20135~L20137 for the hips, and L20138~L20139 for the legs, to meet the mattress pressure zone needs of most users.

[0062] Jump to S300 to continue execution.

[0063] S300, data mapping of pressure pad matrix and air spring partition.

[0064] Taking a group of people of moderate height, greater than or equal to HH1 and less than or equal to HH2, with combinations L20131~L20132 for the shoulders and back, L20133~L20134 for the waist, L20135~L20137 for the hips, and L20138~L20139 for the legs as an example, the 11 rows of pressure pads are pre-divided according to their physical positions into rows corresponding to the 4 air spring force zones. The data mapping relationship between the pressure pad matrix and the air spring zones is as follows: Air spring zones L20131~L20132 (shoulder and back area) — rows 1 to 3 of pressure pad matrix data L4012a10; Air spring zones L20133~L20134 (waist area) — rows 4 to 5 of pressure pad matrix data L4012a10; Air spring zones L20135~L20137 (hip area) — rows 6 to 8 of pressure pad matrix data L4012a10; Air spring zones L20138~L20139 (leg area) — rows 9 to 11 of pressure pad matrix data L4012a10; Taking a group of people of moderate height, greater than or equal to HH1 and less than or equal to HH2, with combinations L20131~L20132 for the shoulders and back, L20133~L20134 for the waist, L20135~L20137 for the hips, and L20138~L20139 for the legs as an example, the 11 rows of pressure pads are pre-divided according to their physical positions into rows corresponding to the 4 air spring force zones. The data mapping relationship between the pressure pad matrix and the air spring zones is as follows: Air spring zones L20131~L20132 (shoulder and back area) — pressure pad matrix row data L4012b10 and L4012b11; Air spring zones L20133~L20134 (waist area) — pressure pad matrix row data L4012b12, rows 1 to 3; Air spring zones L20135~L20137 (hip area) — pressure pad matrix row data L4012b12, rows 4 to 5 and L4012b13; Air spring zones L20138~L20139 (leg area) — pressure pad matrix row data L4012b14.

[0065] Jump to S400.

[0066] S400, determines whether the adaptive function is enabled.

[0067] The system checks whether the adaptive function is enabled. If the adaptive function is enabled, it jumps to S500 to continue execution. Otherwise, it jumps to S700 to continue execution.

[0068] S500, data acquisition and preprocessing.

[0069] With the mattress adaptive function enabled, the mattress control box system activates real-time data acquisition of the pressure pad matrix unit and air spring pressure unit every ΔT time interval, preferably ΔT=1~10s.

[0070] Real-time data includes, but is not limited to, the state data of the pressure pad matrix: lying flat, side-lying, other postures, and being out of bed; real-time data also includes the pressure data of the pressure pad matrix: an m-by-n pressure matrix P_mat(m, n, t). This matrix reflects the two-dimensional pressure distribution matrix on the mattress surface.

[0071] Real-time data also includes data supporting the air springs or airbags: air pressure values ​​P_a(j, t) for each longitudinal zone (such as the shoulders, back, waist, hips, and legs). This air pressure value reflects the one-dimensional pressure distribution of the mattress support system.

[0072] Jump to S600.

[0073] S600 determines whether the user is currently in bed and in a supine or side-lying sleeping position.

[0074] There are already many mature technologies for pressure pad matrix that can accurately output common lying-flat, side-lying sleeping positions and the state of being out of bed. This embodiment will directly use the output state of the pressure pad matrix as the judgment of lying-flat and side-lying positions, and will not provide further explanation in this embodiment.

[0075] Based on the status data of the pressure pad matrix, if the user is currently in bed and in a supine or side-lying sleeping position, the process will proceed to S800 to continue execution. Otherwise, the process will proceed to S700 to continue execution.

[0076] S700, maintain the current sleeping sensation.

[0077] If the user's adaptive function is turned off, or the user is out of bed, or the user is in bed in a non-flat or side-lying position, the current sleep sensation will remain unchanged.

[0078] Jump to S100 to continue execution.

[0079] S800, judgment of changes in lying or side-lying position when turning over. The mattress control box system identifies changes in the user's lying or side-lying position at regular intervals based on the user's set adaptive recognition sensitivity. If the user changes their lying or side-lying position, the system jumps to step S900 to continue execution. Otherwise, it jumps to step S1000 to continue execution.

[0080] S900 allows users to adjust their sleeping position to either flat or side-lying.

[0081] If the user changes their lying or side-lying position, the mattress control box system adjusts the air springs in the corresponding force zones based on the user's adaptive adjustment sensitivity settings, the user's current lying or side-lying sleeping position, and information such as the user's gender, height, weight, and body type, using a cloud-based user lying and side-lying sleeping position adjustment model library.

[0082] Jump to S100 to continue execution.

[0083] S1000 identifies changes in pressure distribution when the user makes subtle movements or experiences minor changes in pressure distribution without turning over.

[0084] When the user's macroscopic sleeping posture remains unchanged, the step of controlling the air pump and solenoid valve to inflate and deflate the corresponding airbag components based on the recognition results includes: calculating the air pressure change of each pressure zone and the pressure characteristic value change of the corresponding pressure pad matrix area; calculating the adaptive weighting factor of each pressure zone based on the user's physiological information and current sleeping posture; calculating the equivalent body pressure change of each pressure zone based on the air pressure change, pressure characteristic value change, and adaptive weighting factor, and determining whether to perform an inflation or deflation operation on the corresponding pressure zone based on the equivalent body pressure change.

[0085] Furthermore, determining whether to perform an inflation or deflation operation on the corresponding stress zone based on the equivalent body pressure change includes: determining a preset adjustment threshold for each stress zone; if the equivalent body pressure change exceeds the preset adjustment threshold of the corresponding stress zone, and the equivalent body pressure change is positive, then an deflation operation is performed; if the equivalent body pressure change is negative, then an inflation operation is performed.

[0086] Within a fixed time window △T, if the user's lying flat or side-lying turning position does not change.

[0087] Obtain the air pressure characteristic value P_a(j, t) corresponding to each air spring section j, and calculate the characteristic value P_s(j, t) representing the pressure state of the pressure pad matrix coverage area corresponding to each air spring section j: P_s(j,t) = ; Where P_s(j,t) represents the weighted average pressure value of the characteristic values ​​of the pressure state of the pressure pad matrix covering the j-th pressure zone within time t; P_mat(m,n,t) represents the pressure value measured by a single pressure pad sensor located in the m-th row and n-th column of the pressure pad matrix at time t.

[0088] M_j represents the set of all rows belonging to the j-th force zone. For example, the waist air spring corresponds to the 4th and 5th rows of the pressure pad, so M_j = {4, 5}.

[0089] w(m, n) represents the weight of each pressure pad sensor location (m, n). For users with high BMI (overweight), pressure is concentrated in the midsection of the body (waist, hips), so higher weights should be assigned to the central locations of these areas to more sensitively capture changes. For users with low BMI (underweight), pressure is significant at bony prominences such as the shoulders and hips, so higher weights should be assigned to these points. The weight matrix can be pre-set based on typical pressure distribution models for different BMI groups.

[0090] denominator This represents the sum of all weight coefficients.

[0091] Furthermore, within a fixed time window △T, the change in each air spring section j is calculated: Air pressure change of air spring: ΔP_a(j) = P_a(j, t) - P_a(j, t-ΔT); The change in the characteristic value of the pressure pad is: ΔP_s(j) = P_s(j, t) - P_s(j, t-ΔT); Jump to S1100 to continue execution.

[0092] S1100, calculate the adaptive weighting factor K of the air spring pressure and the comprehensive equivalent body pressure change ΔP_e.

[0093] The air pressure adaptive weighting factor K of the supporting air spring is an adaptive factor related to the user's BMI and sleeping posture.

[0094] K(j)=Base(BMI) × Posture_Factor(j); Base(BMI): Base weight - BMI function. The higher the BMI, the stronger the pressure of the body on the supporting air spring, the stronger the air pressure change ΔP_a signal caused by the same body movement, and the higher its "confidence" or "weight".

[0095] For example, BMI < 18.5: Base = 1.0 (underweight, weak barometric pressure signal, low weight); 18.5 ≤ BMI ≤ 25: Base = 1.5 (normal); BMI>25: Base = 2.0 (Overweight, strong barometric signal, high weight).

[0096] Preferably, Posture_Factor(j): sleeping posture factor - zoning function. When lying on your side, the air pressure signal of the zoning areas that bear the main weight (such as the shoulders, back, and hips) is more sensitive than that of the non-weight-bearing zoning areas.

[0097] For example, when lying flat, all partitions have Posture_Factor = 1.0; When lying on your side, the shoulder, back, and hip areas should be divided as follows: Posture_Factor = 1.8 (high-pressure area, sensitive). Waist region: Posture_Factor = 1.5 (sub-high pressure region, slightly sensitive); Leg partition: Posture_Factor = 1.0.

[0098] Preferably, for example, when a user with a BMI of 28 (slightly overweight) lies on their side, the weights of each body part are as follows: K(shoulder and back) = 2.0 × 1.8 = 3.6, K(waist) = 2.0 × 1.5 = 3.0, K(hips) = 2.0 × 1.8 = 3.6, K(legs) = 2.0 × 1.0 = 2.0; Furthermore, the equivalent volume pressure change ΔP_e is calculated: ΔP_e(j) = |ΔP_s(j)| + K(j)×|ΔP_a(j)| Preferably, assuming the shoulder and back area ΔP_s = 0.4 kPa and ΔP_a = 0.2 kPa, ΔP_e(shoulder and back) = 0.4 + 3.6 × 0.2 = 0.4 + 0.54 = 1.12 kPa.

[0099] Jump to S1200 to continue execution.

[0100] S1200. Fine-tuning mode is activated when the user makes slight movements or experiences minor changes in pressure distribution without turning over.

[0101] When the user makes slight movements or experiences minor changes in pressure distribution while not rolling over, the control component executes the air spring fine-adjustment mode. To reduce ineffective adjustments during frequent, very slight movements or minor changes in pressure distribution when the user is not rolling over, a global trigger threshold ΔP_threshold is set.

[0102] Every ΔT time interval, traverse all air spring partitions j, if any one or more partitions exist.

[0103] ΔP_e(j)≥ΔP_threshold(j) indicates that there are slight movements or subtle changes in pressure distribution when the user is not turning over.

[0104] Set the air spring adjustment amount ΔPadjust(j) in the fine adjustment mode, ΔPadjust(j) = Sign(-ΔP_s(j))×μ×ΔP_e(j).

[0105] Sign(-ΔP_s(j)) is the sign function. When the change in the pressure pad characteristic value of the pressure pad matrix area corresponding to air spring section j is positive, ΔP_s(j)>0, Sign(ΔP_s(j))=1, and the corresponding Sign(-ΔP_s(j))=-1, indicating that the corresponding air spring section j is deflated. When the change in the pressure pad characteristic value of the pressure pad matrix area corresponding to air spring section j is zero, ΔP_s(j)=0, and the corresponding Sign(-ΔP_s(j))=0, indicating that the corresponding air spring section j is not inflated or deflated. When the change in the pressure pad characteristic value of the pressure pad matrix area corresponding to air spring section j is negative, ΔP_s(j)<0, Sign(ΔP_s(j))=-1, and the corresponding Sign(-ΔP_s(j))=1, indicating that the corresponding air spring section j is inflated. Preferably, μ is the inflation / deflation compensation coefficient for the fine-tuning mode, and is preferably 0.1~1; Preferably, ΔP_e(j) represents the equivalent body pressure change, which is used to provide a reference for the supplementary gas pressure during the fine-tuning mode.

[0106] For example, setting the threshold ΔP_threshold(j) = 0.8 kPa, and the inflation / deflation compensation coefficient μ = 0.5 in the fine-tuning mode, then continuing from the previous example, ΔP_s(shoulder and back) = 0.4 kPa, and ΔP_e(shoulder and back) = 1.12 kPa.

[0107] Therefore, ΔPadjust (shoulder and back) = Sign(-0.4)×0.5×1.12 = (-1)×0.5×1.12=0.56kPa, which means that the target air pressure of the fine adjustment mode is increased by 0.56kPa based on the previous air pressure state.

[0108] After executing all air spring zone fine adjustment modes, jump to S100 to continue execution.

[0109] Figure 9 This is a schematic structural diagram of a device provided in an exemplary embodiment. Please refer to... Figure 9 At the hardware level, the device includes a processor 901, an internal bus 902, a network interface 903, memory 904, and non-volatile memory 905, and may also include other hardware required for its functions. One or more embodiments of the present invention can be implemented in software, for example, the processor 901 reads the corresponding computer program from the non-volatile memory 905 into the memory 904 and then runs it. Of course, in addition to software implementation, one or more embodiments of the present invention do not exclude other implementation methods, such as logic devices or a combination of hardware and software, etc. That is to say, the execution subject of the following processing flow is not limited to each logic unit, but can also be hardware or logic devices.

[0110] The systems, devices, modules, or units described in the above embodiments can be implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer, which can take the form of a personal computer, laptop computer, cellular phone, camera phone, smartphone, personal digital assistant, media player, navigation device, email sending and receiving device, game console, tablet computer, wearable device, or any combination of these devices.

[0111] In a typical configuration, a computer includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0112] Memory may include non-persistent storage in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0113] Computer-readable media, including both permanent and non-permanent, removable and non-removable media, can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, disk storage, quantum memory, graphene-based storage media or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0114] For any other form of computer-readable medium (or computer-readable storage medium) as described above, computer instructions may be stored thereon, which, when executed by a processor, implement one or more of the above embodiments, thereby realizing the technical solution of the present invention.

[0115] The present invention also proposes a computer program that, when executed by a processor, implements one or more of the embodiments described above, thereby realizing the technical solution of the present invention. This computer program may be specifically recorded on the above-described or other computer-readable media, and the present invention does not impose any limitations on this.

[0116] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0117] The foregoing has described specific embodiments of the invention. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps described in the claims may be performed in a different order than that shown in the embodiments and may still achieve the desired results. Furthermore, the processes depicted in the drawings do not necessarily require the specific or sequential order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0118] The terminology used in one or more embodiments of the invention is for the purpose of describing particular embodiments only and is not intended to limit the invention. The singular forms “a,” “the,” and “the” used in one or more embodiments of the invention and in the appended claims are also intended to include the plural forms unless the context clearly indicates otherwise. It should also be understood that the term “and / or” as used herein refers to and includes any or all possible combinations of one or more associated listed items.

[0119] It should be understood that although the terms first, second, third, etc., may be used to describe various information in one or more embodiments of the present invention, such information should not be limited to these terms. These terms are only used to distinguish information of the same type from one another. For example, first information may also be referred to as second information without departing from the scope of one or more embodiments of the present invention, and similarly, second information may also be referred to as first information. Depending on the context, the word "if" as used herein may be interpreted as "when," "when," or "in response to a determination."

[0120] The above description is merely a preferred embodiment of one or more embodiments of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of one or more embodiments of the present invention should be included within the protection scope of one or more embodiments of the present invention.

Claims

1. A mattress control method based on multi-information fusion, characterized in that, A control component for a mattress, the mattress comprising, from top to bottom, a bottom outer layer, a support layer, a pressure pad recognition layer, and a top outer layer; the support layer includes multiple airbag assemblies, which are divided into multiple pressure zones, each pressure zone being equipped with a pressure sensor for collecting a one-dimensional pressure distribution dataset; the pressure pad recognition layer includes a pressure pad recognition matrix composed of m rows and n columns of pressure sensing units, used to collect user body pressure distribution data and generate a two-dimensional pressure distribution matrix; the control component is connected to the support layer and the pressure pad recognition layer, and includes a computing unit, an air pump, a solenoid valve, and a pressure sensor; the method includes: Acquire the user's physiological information, and divide the multiple airbag components in the support layer into force zones corresponding to the user's physiological curve based on the physiological information; Establish a mapping relationship between the row data of the pressure pad identification matrix and the stress zone; In response to the acquired two-dimensional pressure distribution matrix and the one-dimensional air pressure distribution dataset, the system identifies the user's macroscopic sleeping posture and microscopic movement changes, and controls the air pump and solenoid valve to inflate and deflate the corresponding airbag components based on the identification results.

2. The method according to claim 1, characterized in that, If the user's overall sleeping posture remains unchanged, the step of controlling the air pump and solenoid valve to inflate and deflate the corresponding airbag components based on the recognition result includes: Calculate the air pressure change in each stress zone and the pressure characteristic value change in the corresponding pressure pad matrix area; Based on the user's physiological information and current sleeping position, calculate the adaptive weighting factor for each pressure zone; The equivalent body pressure change of each stress zone is calculated based on the pressure change, pressure characteristic value change, and adaptive weighting factor. Based on the equivalent body pressure change, it is determined whether to perform inflation or deflation operations on the corresponding stress zone.

3. The method according to claim 2, characterized in that, The step of determining whether to perform inflation or deflation operations on the corresponding stress zone based on the equivalent body pressure change includes: Determine the preset adjustment threshold for each stress zone; If the change in equivalent body pressure exceeds the preset adjustment threshold of the corresponding force zone, and the change in equivalent body pressure is positive, then an air release operation is performed; if the change in equivalent body pressure is negative, then an air inflation operation is performed.

4. The method according to claim 2, characterized in that, The calculation of the equivalent body pressure change of each stress zone based on the pressure change, pressure characteristic value change, and adaptive weighting factor includes: The formula for calculating the equivalent body pressure change is as follows: ΔP_e(j)=|ΔP_s(j)|+K(j)×|ΔP_a(j)|; Wherein, ΔP_e(j) is the equivalent volume pressure change corresponding to force zone j, ΔP_a(j) is the air pressure change corresponding to force zone j, and ΔP_s(j) is the pressure characteristic value change corresponding to force zone j. The formula for calculating the change in the pressure characteristic value is as follows: ΔP_s(j)=P_s(j,t)-P_s(j,t-ΔT); P_s(j,t)= ; Where P_s(j,t) represents the weighted average pressure value of the characteristic values ​​of the pressure state of the area covered by the pressure pad matrix corresponding to the j-th stress zone at time t; P_mat(m,n,t) represents the pressure value measured by a single pressure pad sensor located in the m-th row and n-th column of the pressure pad matrix at time t; M_j represents the set of all rows belonging to the j-th stress zone; w(m,n) represents the weight of each pressure pad sensor position (m,n); denominator This represents the sum of all weight coefficients; The formula for calculating the change in air pressure is as follows: ΔP_a(j)=P_a(j,t)-P_a(j,t-ΔT); Where P_s(j,t) represents the weighted average pressure value of the airbag component pressure change in the j-th stress zone during time t.

5. The method according to claim 1, characterized in that, The step of controlling the air pump and solenoid valve to inflate and deflate the corresponding airbag components based on the identification result includes: When a change in the user's macroscopic sleeping posture is detected, the support curve is reconstructed as a whole based on the user's new sleeping posture. When the user's subtle changes in movement are detected, the local airbag components are precisely fine-tuned.

6. The method according to claim 1, characterized in that, The airbag assembly in the support layer is physically isolated laterally and / or longitudinally by an insulating sponge assembly.

7. The method according to claim 1, characterized in that, The physiological information includes at least one of the following: BMI, sex, height, weight, and body type.

8. The method according to claim 1, characterized in that, The pressure sensing units of the pressure pad identification matrix are arranged in a differentiated density distribution, with a higher distribution density in the shoulder and back areas and waist areas corresponding to the user than in the leg areas.

9. The method according to claim 1, characterized in that, The support layer also includes a head support assembly and a tail support sponge assembly, and the control assembly is disposed within the tail support sponge assembly.

10. A mattress, characterized in that, The mattress comprises, from top to bottom, a bottom outer layer (L10), a support layer (L20), a pressure pad identification layer (L40), and a top outer layer (L50). The support layer (L20) includes multiple airbag components (L2013), which are divided into multiple pressure zones corresponding to the user's physiological curve. Each pressure zone is equipped with a pressure sensor to collect a one-dimensional pressure distribution dataset. The pressure pad identification layer (L40) includes a pressure pad identification matrix (L401) composed of m rows and n columns of pressure sensing units, which is used to collect user body pressure distribution data and generate a two-dimensional pressure distribution matrix. The control component (L2015) is connected to the support layer (L20) and the pressure pad recognition layer (L40). The control component (L2015) includes a computing unit, an air pump, a solenoid valve and a pressure sensor. It is used to identify the user's macroscopic sleeping posture and microscopic movement changes based on the two-dimensional pressure distribution matrix and the one-dimensional pressure distribution dataset, and to control the air pump and solenoid valve to inflate and deflate the corresponding airbag component (L2013) according to the identification results.

Images