An adaptive recommendation method for stretching schemes, a smart mattress, and a storage medium.

By collecting sleeping posture data through a smart mattress to estimate muscle tension index and generate personalized stretching programs, the problem of insufficient matching of stretching courses in existing fitness apps is solved, and more efficient and safer morning stretching is achieved.

CN123100951APending Publication Date: 2026-11-17DONGGUAN DERUCCI BEDDING CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202611515447.1
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2026-09-28
Publication Date
2026-11-17

AI Technical Summary

Technical Problem

Existing fitness apps' morning stretching courses lack a matching basis that is appropriate for each user's individual condition, resulting in a discrepancy between the stretching movements and the user's actual needs, and insufficient effectiveness and safety.

Method used

By collecting the user's historical sleep cycle sleeping posture time series through a smart mattress, the nocturnal tension index of each muscle group is estimated, the target muscle group is identified, and personalized stretching movements are matched from a pre-built stretching movement library to generate a personalized stretching program.

Benefits of technology

It improves the matching degree between stretching movements and users' actual needs, enhances the pertinence and effectiveness of stretching, and reduces the safety risks caused by mismatched stretching parts or improper stretching.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN123100951A_ABST
    Figure CN123100951A_ABST
Patent Text Reader

Abstract

This application relates to the field of sleep bedding, and discloses an adaptive recommendation method for stretching programs, a smart mattress, and a storage medium. The method includes: obtaining a user's sleep monitoring report from historical sleep cycles, the sleep monitoring report including a sleep posture time series, which characterizes the temporal distribution of different sleep postures within historical sleep cycles; estimating the nocturnal tension index of each muscle group based on the sleep monitoring report; identifying at least one muscle group as a target muscle group based on the nocturnal tension index; selecting target stretching movements matching the target muscle group from a stretching movement library, generating a target stretching program, and pushing it to a preset terminal. This application uses the sleep posture time series as the matching basis, which can generate stretching programs that match the user's own sleep state, thereby improving the targeting and effectiveness of stretching and reducing safety risks caused by mismatched stretching areas or improper stretching.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] This application relates to the field of sleep bedding technology, and in particular to an adaptive recommendation method for stretching schemes, a smart mattress, and a storage medium. Background Technology

[0002] With the increasing awareness of health management among residents, morning stretching has gradually become an important part of people's daily health management. After a night's sleep, the body's muscles are in a relatively static state. Appropriate morning stretching helps restore muscle elasticity and improve joint mobility, which is of great significance for maintaining daytime physical activity and quality of life.

[0003] Currently, many fitness apps on the market offer morning stretching courses, which users can choose to follow along with.

[0004] However, existing fitness apps typically offer stretching courses based on fixed movement sequences or preset course categories. These courses are generally generic, forcing users to either choose from preset options or rely on subjective judgment to determine which areas to stretch. Due to the lack of a matching framework tailored to individual user conditions, stretching movements often deviate from the user's actual needs, resulting in insufficient effectiveness and safety.

[0005] Therefore, improvements to existing technologies are necessary.

[0006] The above information is provided as background information only to aid in understanding this application and does not constitute an assertion or admission that any of the above content can be used as prior art relative to this application. Summary of the Invention

[0007] This application provides an adaptive recommendation method for stretching programs, as well as a smart mattress and storage medium, to address the problems of existing stretching courses failing to automatically match users' actual needs and lacking in stretching effectiveness and safety.

[0008] To achieve the above objectives, this application provides the following technical solution: In a first aspect, embodiments of this application provide an adaptive recommendation method for stretching schemes, including: Obtain a user's sleep monitoring report within a historical sleep cycle. The sleep monitoring report includes at least a sleep position time series, which is used to characterize the temporal distribution of different sleep positions within the historical sleep cycle. Based on the sleep monitoring report, estimate the nighttime tension index of each muscle group; Based on the nighttime tension index, at least one muscle group among the various muscle groups is identified as the target muscle group to be stretched. From a pre-built library of stretching exercises, target stretching exercises that match the target muscle group are selected, a target stretching plan is generated, and it is pushed to a preset terminal to guide the user to perform the stretching exercises.

[0009] Optionally, estimating the nocturnal tension index of each muscle group based on the sleep monitoring report includes: Determine the target sleeping positions included in the sleeping position time series and the cumulative duration of each target sleeping position; Based on a pre-built model of the relationship between sleeping posture and muscles, the tension contribution coefficient of each target sleeping posture to each muscle group is determined; the tension contribution coefficient is used to characterize the contribution of the corresponding sleeping posture to the degree of adaptive shortening of each muscle group. For each muscle group, the cumulative tension component of the current muscle group is calculated based on the tension contribution coefficient and cumulative duration of the current muscle group under each target sleeping position. The cumulative tension components of the current muscle group under all target sleeping position types are summed to obtain the total cumulative tension of the current muscle group. The total cumulative tension is normalized to obtain the nighttime tension index of the current muscle group.

[0010] Optionally, estimating the nighttime tension index of each muscle group based on the sleep monitoring report further includes: correcting the tension contribution coefficient before calculating the cumulative tension component of the current muscle group; The correction method includes: determining the age group to which the user belongs; determining a correction coefficient corresponding to the user based on the age group, wherein the correction coefficient is positively correlated with the age group; and multiplying the stress contribution coefficient by the correction coefficient to obtain the corrected stress contribution coefficient.

[0011] Optionally, the step of identifying at least one muscle group among the various muscle groups as the target muscle group to be stretched based on the nighttime tension index includes: Obtain a pre-constructed myofascial chain association table, which is used to define the myofascial chains to which each muscle group belongs and the association relationships between muscle groups on the same myofascial chain. The muscle groups whose nighttime tension index is higher than a preset tension threshold are defined as core muscle groups. The core muscle group and the associated muscle groups that are on the same myofascial chain as the core muscle group are identified as the target muscle group.

[0012] Optionally, the step of selecting target stretching movements that match the target muscle group from a pre-built stretching movement library includes: Obtain user characteristic information, which includes at least one of age, gender, menstrual cycle status, physical fitness level, historical stretching records, and user feedback data; Based on the target muscle group and the user's physical fitness characteristics, matching stretching movements are selected from the stretching movement library and identified as the target stretching movements.

[0013] Optionally, the user feedback data includes at least one of action completion rate, subjective feeling score, and discomfort feedback information.

[0014] Optionally, the sleep monitoring report may also include sleep quality assessment results; The adaptive recommendation method further includes: when the sleep quality assessment result does not meet the preset sleep quality conditions, reducing the difficulty level of the target stretching movement, and / or reducing the number of the target stretching movements.

[0015] Optionally, the preset sleep quality conditions include at least one of the following: The duration of deep sleep is not less than the preset duration threshold; The number of times you wake up at night should not exceed a preset threshold. Sleep efficiency is not lower than the preset efficiency threshold; The percentage of REM sleep is not lower than the preset percentage threshold.

[0016] Secondly, embodiments of this application provide a smart mattress, including a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the adaptive recommendation method for stretching schemes as described in any of the above.

[0017] Thirdly, embodiments of this application provide a computer-readable storage medium storing computer-executable instructions thereon, which are executed by a computer processor to implement the adaptive recommendation method for stretching schemes described in any of the above embodiments.

[0018] Compared with the prior art, this application has the following beneficial effects: This application uses the sleeping posture time series collected by the smart mattress as input, and obtains the nighttime tension index by quantifying the cumulative contribution of each sleeping posture to the shortening of muscle groups. Based on this, the target muscle groups that need to be stretched are determined, and the corresponding stretching movements are automatically matched from the stretching movement library to generate a personalized plan.

[0019] Compared to existing technologies where users can only choose stretching exercises from fixed courses based on subjective feelings, this application uses an objective sleep posture time sequence as the matching basis, so that the stretching exercises correspond to the muscle shortening state actually caused by the user's sleep the previous night, effectively improving the matching degree between stretching exercises and actual needs; users do not need to judge the parts that need to be stretched themselves, and can directly obtain a stretching plan that matches their own sleep state, thereby improving the pertinence and effectiveness of stretching, and reducing the safety risks caused by mismatched stretching parts or improper stretching.

[0020] This application has other features and advantages that will be apparent from or will be set forth in detail in the accompanying drawings and following detailed description, which together serve to explain the particular principles of this application. Attached Figure Description

[0021] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0022] Figure 1 This is a flowchart of the adaptive recommendation method for stretching schemes provided in the embodiments of this application. Detailed Implementation

[0023] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0024] Please refer to Figure 1 This application provides an adaptive recommendation method for stretching schemes, including: S1. Obtain the user's sleep monitoring report within the historical sleep cycle. The sleep monitoring report includes at least a sleep position time series, which is used to characterize the time distribution of different sleep positions within the historical sleep cycle.

[0025] Historical sleep cycles refer to a sleep period that a user has completed before the current time. These can be the previous night's sleep period or multiple consecutive nights' sleep periods.

[0026] The sleep monitoring report is generated by the smart mattress; the smart mattress collects body pressure distribution data without interference during the user's sleep through a built-in sensor array, and identifies the user's current sleeping position based on the body pressure distribution pattern.

[0027] The specific content of the sleep position time series may include: identifiable sleep position types (such as supine, left lateral, right lateral, prone, etc.), the start and end time points of each sleep position type, the duration of each sleep position type, and the switching order between sleep position types.

[0028] S2. Based on the sleep monitoring report, estimate the nighttime tension index of each muscle group.

[0029] It is important to note that research has found a causal relationship between different sleeping positions and the tension of various muscle groups: when a user maintains a certain sleeping position for an extended period, specific muscle groups undergo adaptive changes due to prolonged shortening, resulting in muscle shortening—that is, the muscles lose some range of motion due to being in a shortened position for an extended period. For example, the prone sleeping position causes the muscles around the cervical and lumbar spine to be in a twisted or overextended state, while the side-lying curled-up position causes the hip flexors to be in a shortened position for a prolonged period. Prolonged shortening of muscles leads to a decrease in the number of sarcomeres, an increase in the proportion of connective tissue, and increased muscle stiffness. This cumulative effect persists even after sleep ends, requiring stretching intervention to alleviate and restore tension. Therefore, the nocturnal tension index of various muscle groups can be estimated by analyzing the time series of sleeping positions in sleep monitoring reports.

[0030] The Nighttime Tension Index is a numerical indicator that is quantitatively calculated based on the duration of each sleeping position type during a user's historical sleep cycle. It is used to characterize the degree of shortening of various muscle groups due to the accumulation of nighttime sleeping positions.

[0031] S3. Based on the nighttime tension index, identify at least one muscle group from each muscle group as the target muscle group to be stretched.

[0032] Since the nighttime tension index reflects the degree of shortening of various muscle groups due to accumulated sleeping postures during historical sleep cycles, it can be used as a basis for determining the muscle groups to be stretched: the higher the tension index, the more likely the muscle group needs to be intervened through stretching.

[0033] S4. From the pre-built stretching exercise library, select target stretching exercises that match the target muscle group, generate the target stretching plan, and push it to the preset terminal to guide the user to perform the stretching exercise.

[0034] The stretching exercise library pre-stores multiple stretching exercise entries, each containing at least a target muscle group tag. The target muscle group tag identifies the anatomically targeted muscle group of the stretching exercise. Based on exercise science, each stretching exercise corresponds to one or more specific muscle groups. When a user performs a corresponding stretching exercise on a particular muscle group, that muscle group will receive stretching stimulation, thereby relieving its shortening state. Therefore, this step uses the target muscle group as a search criterion to match stretching exercises anatomically targeting that specific muscle group from the stretching exercise library.

[0035] In summary, this application uses the sleeping posture time series collected by the smart mattress as input, quantifies the cumulative contribution of each sleeping posture to muscle group shortening to obtain the nighttime tension index, determines the target muscle groups that need to be stretched, and automatically matches the corresponding stretching movements from the stretching movement library to generate a personalized plan.

[0036] Compared to existing technologies where users can only choose stretching exercises from fixed courses based on subjective feelings, this application uses an objective sleep posture time sequence as the matching basis, so that the stretching exercises correspond to the muscle shortening state actually caused by the user's sleep the previous night, effectively improving the matching degree between stretching exercises and actual needs; users do not need to judge the parts that need to be stretched themselves, and can directly obtain a stretching plan that matches their own sleep state, thereby improving the pertinence and effectiveness of stretching, and reducing the safety risks caused by mismatched stretching parts or improper stretching.

[0037] Further, in an optional implementation, step S2, based on the sleep monitoring report, estimates the nocturnal tension index of each muscle group, including: S21. Determine the target sleeping positions included in the sleeping position time series and the cumulative duration of each target sleeping position.

[0038] The target sleeping position refers to the actual sleeping position type that appears in the sleeping position time series. Since the same sleeping position type may appear multiple times throughout the night and be separated by other sleeping positions, this embodiment needs to merge them by sleeping position type before calculation, and add up the duration of the same sleeping position type in each time period to obtain the cumulative duration of the target sleeping position.

[0039] For example, if a user alternates between sleeping on their right side, lying on their back, and then back on their right side during the night, the total duration of sleeping on the right side is the sum of the durations of the two sleeping positions.

[0040] S22. Based on the pre-built sleeping posture and muscle association model, determine the tension contribution coefficient of each target sleeping posture to each muscle group; the tension contribution coefficient is used to characterize the contribution of the corresponding sleeping posture to the degree of adaptive shortening of each muscle group.

[0041] The sleeping posture and muscle association model is pre-built based on exercise science knowledge to define the correspondence between each sleeping posture type and the muscle groups affected by it, as well as the contribution of each sleeping posture type to the adaptive shortening of the corresponding muscle groups.

[0042] Adaptive shortening refers to the length adaptation of muscles caused by prolonged periods in a shortened position, manifested as muscle tension and decreased range of motion.

[0043] The tension contribution coefficient can be positive or negative. A positive value indicates that the muscle group is in a shortened position under the corresponding sleeping position and makes a positive contribution to adaptive shortening. A negative value indicates that the muscle group is in a lengthened position under the corresponding sleeping position and makes a negative contribution to adaptive shortening.

[0044] S23. For each muscle group, calculate the cumulative tension component of the current muscle group based on the tension contribution coefficient and cumulative duration of the current muscle group under each target sleeping position; sum the cumulative tension components of the current muscle group under all target sleeping position types to obtain the total cumulative tension of the current muscle group; normalize the total cumulative tension to obtain the nighttime tension index of the current muscle group.

[0045] In this step, the cumulative tension component refers to the amount of tension contribution generated by a certain muscle group under a single target sleeping position due to the continuous accumulation of tension in that position. It can be obtained by multiplying the current muscle group's tension contribution coefficient under that target sleeping position by the cumulative duration of that target sleeping position. Summing up the cumulative tension components of the same muscle group under all target sleeping position types yields the total cumulative tension of that muscle group throughout the entire historical sleep cycle.

[0046] Since the total accumulated tension of different muscle groups may vary in numerical range, to facilitate subsequent comparison and ranking, the total accumulated tension is normalized and mapped to a preset numerical range to obtain the nocturnal tension index of that muscle group. Normalization can be achieved using linear normalization, extreme value normalization, or other conventional normalization methods.

[0047] Using the above method, this application embodiment transforms the objective record of "what sleeping posture and how long" in the sleeping posture time series into a quantitative indicator of "the extent of shortening of each muscle group due to the accumulation of sleeping posture at night"; the cumulative effect of different sleeping postures is reflected by weighting the cumulative duration, and the comparability between each muscle group is made through normalization, thereby providing an objective, unified and sortable quantitative basis for subsequently determining the target muscle group to be stretched.

[0048] Considering the differences in muscle viscoelasticity and muscle recovery ability among users of different ages, the degree of muscle shortening caused by the same sleeping position and the same cumulative duration is not the same for users of different ages. For example, older users usually have higher muscle tension and stiffness than younger users, and are more prone to adaptive shortening under the same sleeping position conditions.

[0049] Therefore, in one optional implementation, step S2, which estimates the nighttime tension index of each muscle group based on the sleep monitoring report, further includes: correcting the tension contribution coefficient before calculating the cumulative tension component of the current muscle group. The correction method includes: determining the user's age group; determining the correction coefficient corresponding to the user based on the age group, with the correction coefficient being positively correlated with the age group; and multiplying the stress contribution coefficient by the correction coefficient to obtain the corrected stress contribution coefficient.

[0050] In practical applications, a mapping table between age groups and correction coefficients can be pre-constructed. This table is divided into multiple age groups, each corresponding to a correction coefficient, with the correction coefficient increasing as age increases. For example, age groups can be divided into youth, middle-aged, and elderly groups, with the correction coefficients increasing sequentially from youth to middle-aged to elderly. After determining the user's age group, the corresponding correction coefficient can be obtained by querying the mapping table. This correction coefficient is then multiplied by the tension contribution coefficient of each muscle group for that user to obtain the corrected tension contribution coefficient. The cumulative tension component is subsequently calculated using this corrected tension contribution coefficient.

[0051] In other words, this application's embodiments further incorporate an individual age dimension into the mapping between "sleeping posture and muscle groups." Because the muscle viscoelasticity and recovery capabilities of users of different ages vary, applying a uniform tension contribution coefficient to all users might lead to an underestimation of tension accumulation in older users or an overestimation in younger users, resulting in a discrepancy between the identified target muscle groups and the actual areas requiring stretching. Therefore, this application's embodiments correct this by ensuring that the revised nighttime tension index more accurately reflects the actual impact of the user's age group on muscle shortening. This makes the subsequently identified target muscle groups more closely match the user's actual physical condition, improving the accuracy and individual suitability of the recommended stretching exercises.

[0052] Furthermore, in an optional implementation, step S3, based on the nighttime tension index, identifies at least one muscle group among the various muscle groups as the target muscle group to be stretched, including: obtaining a pre-constructed myofascial chain association table, which is used to define the myofascial chains to which each muscle group belongs and the association relationships between muscle groups on the same myofascial chain; identifying muscle groups with a nighttime tension index higher than a preset tension threshold as core muscle groups; and identifying the core muscle groups and associated muscle groups on the same myofascial chain as the target muscle groups.

[0053] It's important to explain that a myofascial chain refers to a chain-like structure formed by muscles, ligaments, and related soft tissues connected directly or indirectly by fascia in a specific layer and direction. Multiple myofascial chains exist in the human body. Muscle groups within each chain form force transmission pathways through fascial connections. When a muscle group in a chain becomes shortened or tense, this tension can be transmitted distally along the myofascial chain, causing compensatory tension in other muscle groups on the same chain. For example, the posterior superficial line (superficial dorsal line) from the foot to the top of the head includes the plantar fascia, gastrocnemius and Achilles tendon, hamstrings, sacrotuberous ligament, lumbosacral fascia, and erector spinae muscles. These structures form a continuous force transmission pathway through fascial connections. Tension in any link of the chain can affect the tension state of other links on the same chain. Studies have shown that applying stretching or myofascial release intervention to a specific muscle group within a myofascial chain can improve the flexibility of distal muscle groups on the same chain, exhibiting a "distant effect."

[0054] Therefore, after identifying the core muscle groups, this embodiment further consults the myofascial chain association table to identify related muscle groups on the same myofascial chain as the core muscle groups as the target muscle groups to be stretched. This is because: the shortening state of the core muscle groups accumulated due to sleeping posture at night may cause compensatory tension in related muscle groups on the same chain through tension transmission of the myofascial chain; if only the core muscle groups are stretched while ignoring related muscle groups, the residual tension in the related muscle groups may make it difficult to fully relieve the shortening state of the core muscle groups. Including related muscle groups in the target muscle groups allows the stretching program to cover multiple links on the same myofascial chain, thereby more effectively restoring the tension balance of the entire myofascial chain and improving the overall stretching effect.

[0055] In another optional implementation, step S2 involves selecting target stretching movements that match the target muscle group from a pre-built stretching movement library, including: obtaining user characteristic information, which includes at least one of age, gender, menstrual cycle status, fitness level, historical stretching records, and user feedback data; and selecting matching stretching movements from the stretching movement library based on the target muscle group and the user's fitness characteristic information, and determining them as target stretching movements.

[0056] It should be noted that user feature information is used to further personalize stretching movements based on target muscle group matching, ensuring that the selected target stretching movements not only target the muscle groups the user needs to stretch, but also adapt to the user's own physical condition and historical performance. The function of each feature is explained below: Age is used to determine the upper limit of a user's exercise difficulty. Users of different ages have different muscle viscoelasticity characteristics, joint range of motion, and recovery ability. Older users usually have a lower upper limit of exercise difficulty than younger users. Therefore, when selecting stretching exercises, stretching exercises with a difficulty level higher than the user's upper limit of exercise difficulty should be excluded.

[0057] Gender can be used to adapt the difficulty and type of movements. Users of different genders have different muscle strength distribution, joint range of motion, and flexibility, and may have different tolerance levels for stretching even at the same fitness level. Therefore, the difficulty level of movements can be adjusted adaptively according to gender.

[0058] Menstrual status can be used to restrict movement types. When a user is menstruating, preset prohibited movement types during menstruation can be excluded, such as movements that put pressure on the abdomen, inverted movements, or violent twisting movements, or the difficulty level of corresponding stretching movements can be reduced to avoid discomfort or safety hazards.

[0059] Fitness levels can be used to determine the range of difficulty levels a user can perform. Fitness levels can be pre-determined based on a user's historical stretching records, exercise habits, or self-assessment information. The higher the fitness level, the higher the upper limit of the difficulty level of the movements that can be matched.

[0060] Historical stretching records can be used to determine a user's acceptance and performance ability for specific stretching movements. If a stretching movement has a high completion rate in the historical records, it can be prioritized for matching; if a stretching movement has a high skip rate in the historical records, its matching priority can be reduced or it can be replaced with an equivalent alternative.

[0061] User feedback data can be used to dynamically adjust stretching movements. User feedback data includes at least one of the following: movement completion rate, subjective comfort score, and discomfort feedback information; if a user reports discomfort with a certain stretching movement, that movement will be excluded or its difficulty level will be reduced in subsequent screening.

[0062] In practice, the target muscle group can be used as the search criteria to retrieve candidate stretching movements that match the target muscle group tag from the stretching movement library. Then, the candidate stretching movements can be filtered or sorted according to user feature information, such as excluding movements with a difficulty level higher than the upper limit of the movement difficulty, excluding movement types that are prohibited during menstruation, and prioritizing movements with a high historical completion rate, thereby obtaining the target stretching movement.

[0063] Therefore, this application embodiment further introduces user feature information for secondary adaptation on the basis of target muscle group matching, so that the final determined stretching action is not only aimed at the muscle groups that the user actually needs to stretch, but also adapted to the user's age, gender, menstrual state, physical fitness level and historical performance. This avoids the problem that the user cannot complete the stretching action or causes discomfort due to the excessive difficulty of the action or the inappropriate type of action, and further improves the individual adaptability and execution compliance of the stretching plan.

[0064] It should be noted that the above-described implementation method for determining the target muscle group based on the myofascial chain association table and the above-described implementation method for selecting target stretching movements based on user feature information can be used individually or in combination. In the combined implementation, the target muscle group is first determined based on the myofascial chain association table, and then target stretching movements that match the target muscle group are selected from the stretching movement library based on user feature information.

[0065] Furthermore, in an optional implementation, the sleep monitoring report may also include sleep quality assessment results. Based on this, the adaptive recommendation method further includes: reducing the difficulty level of the target stretching movement and / or reducing the number of target stretching movements when the sleep quality assessment results do not meet preset sleep quality conditions.

[0066] For example, preset sleep quality conditions include at least one of the following: deep sleep duration is not less than a preset duration threshold; the number of nighttime awakenings is not more than a preset number threshold; sleep efficiency is not less than a preset efficiency threshold; and the proportion of REM sleep is not less than a preset proportion threshold.

[0067] Thus, when a user's sleep quality assessment results do not meet the preset sleep quality conditions, it indicates that the user's muscle recovery at night is insufficient or their overall fatigue level is high, resulting in a relatively decreased tolerance to stretching exercises. In this case, by reducing the difficulty level of the target stretching exercises and / or reducing the number of target stretching exercises, it is possible to avoid increasing the user's physical burden due to excessive stretching intensity or too many exercises. This allows the stretching program to be adapted to the user's actual physical condition that day, further improving the safety and comfort of the stretching program.

[0068] Secondly, embodiments of this application provide a smart mattress, including a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the adaptive recommendation method for stretching schemes described in any of the above embodiments.

[0069] The aforementioned smart mattress can perform the methods provided in any embodiment of this application, and has the corresponding functional modules and beneficial effects for performing the methods, which will not be elaborated further here.

[0070] It should be added that the target stretching plan generated by the smart mattress can be sent to the user's preset terminal, which will then present and guide the user to perform the stretching actions.

[0071] The preset terminal can be a mobile phone, tablet, smart TV, or smart wearable device. The smart mattress and the preset terminal can establish a data transmission link via wireless communication.

[0072] Thirdly, embodiments of this application provide a computer-readable storage medium storing computer-executable instructions thereon, which are executed by a computer processor to implement the adaptive recommendation method for stretching schemes described in any of the above embodiments.

[0073] Any combination of one or more computer-readable media may be used. A computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. A computer-readable storage medium can be, for example—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples (a non-exhaustive list) of computer-readable storage media include: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this document, a computer-readable storage medium can be any tangible medium that contains or stores a program that can be used by or in connection with an instruction execution system, apparatus, or device.

[0074] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. Computer-readable signal media may also be any computer-readable medium other than computer-readable storage media, capable of sending, propagating, or transmitting programs for use by or in connection with an instruction execution system, apparatus, or device.

[0075] The program code contained on a computer-readable medium may be transmitted using any suitable medium, including but not limited to wireless, wire, optical fiber, RF, or any suitable combination thereof.

[0076] Computer program code for performing the operations of this application can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, as well as conventional procedural programming languages ​​such as C or similar languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or connected to an external computer (e.g., via the Internet using an Internet service provider).

[0077] Finally, it should be noted that although the above embodiments have been described in the text and drawings of this application, this should not limit the scope of patent protection of this application. Any technical solutions that are based on the essential concept of this application and utilize the content described in the text and drawings of this application, resulting in equivalent structural or procedural substitutions or modifications, as well as the direct or indirect application of the technical solutions of the above embodiments to other related technical fields, are all included within the scope of patent protection of this application.

Claims

1. An adaptive recommendation method for stretching schemes, characterized in that, include: Obtain a user's sleep monitoring report within a historical sleep cycle. The sleep monitoring report includes at least a sleep position time series, which is used to characterize the temporal distribution of different sleep positions within the historical sleep cycle. Based on the sleep monitoring report, estimate the nighttime tension index of each muscle group; Based on the nighttime tension index, at least one muscle group among the various muscle groups is identified as the target muscle group to be stretched. From a pre-built library of stretching exercises, target stretching exercises that match the target muscle group are selected, a target stretching plan is generated, and it is pushed to a preset terminal to guide the user to perform the stretching exercises.

2. The adaptive recommendation method for stretching schemes according to claim 1, characterized in that, The estimation of the nocturnal tension index of each muscle group based on the sleep monitoring report includes: Determine the target sleeping positions included in the sleeping position time series and the cumulative duration of each target sleeping position; Based on a pre-built model of the relationship between sleeping posture and muscles, the tension contribution coefficient of each target sleeping posture to each muscle group is determined; the tension contribution coefficient is used to characterize the contribution of the corresponding sleeping posture to the degree of adaptive shortening of each muscle group. For each muscle group, the cumulative tension component of the current muscle group is calculated based on the tension contribution coefficient and cumulative duration of the current muscle group under each target sleeping position. The cumulative tension components of the current muscle group under all target sleeping position types are summed to obtain the total cumulative tension of the current muscle group. The total cumulative tension is normalized to obtain the nighttime tension index of the current muscle group.

3. The adaptive recommendation method for stretching schemes according to claim 2, characterized in that, The step of estimating the nighttime tension index of each muscle group based on the sleep monitoring report further includes: correcting the tension contribution coefficient before calculating the cumulative tension component of the current muscle group; The correction method includes: determining the age group to which the user belongs; determining a correction coefficient corresponding to the user based on the age group, wherein the correction coefficient is positively correlated with the age group; and multiplying the stress contribution coefficient by the correction coefficient to obtain the corrected stress contribution coefficient.

4. The adaptive recommendation method for stretching schemes according to claim 1, characterized in that, The step of identifying at least one muscle group among the various muscle groups as the target muscle group to be stretched based on the nighttime tension index includes: Obtain a pre-constructed myofascial chain association table, which is used to define the myofascial chains to which each muscle group belongs and the association relationships between muscle groups on the same myofascial chain. The muscle groups whose nighttime tension index is higher than a preset tension threshold are defined as core muscle groups. The core muscle group and the associated muscle groups that are on the same myofascial chain as the core muscle group are identified as the target muscle group.

5. The adaptive recommendation method for stretching schemes according to claim 1, characterized in that, The step of selecting target stretching movements from a pre-built stretching movement library that match the target muscle group includes: Obtain user characteristic information, which includes at least one of age, gender, menstrual cycle status, physical fitness level, historical stretching records, and user feedback data; Based on the target muscle group and the user's physical fitness characteristics, matching stretching movements are selected from the stretching movement library and identified as the target stretching movements.

6. The adaptive recommendation method for stretching schemes according to claim 5, characterized in that, The user feedback data includes at least one of the following: action completion rate, subjective feeling score, and discomfort feedback information.

7. The adaptive recommendation method for stretching schemes according to claim 1, characterized in that, The sleep monitoring report also includes sleep quality assessment results; The adaptive recommendation method further includes: when the sleep quality assessment result does not meet the preset sleep quality conditions, reducing the difficulty level of the target stretching movement, and / or reducing the number of the target stretching movements.

8. The adaptive recommendation method for stretching schemes according to claim 7, characterized in that, The preset sleep quality conditions include at least one of the following: The duration of deep sleep is not less than the preset duration threshold; The number of times you wake up at night should not exceed a preset threshold. Sleep efficiency is not lower than the preset efficiency threshold; The percentage of REM sleep is not lower than the preset percentage threshold.

9. A smart mattress, comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the adaptive recommendation method for stretching schemes as described in any one of claims 1-8.

10. A computer-readable storage medium having computer-executable instructions stored thereon, characterized in that, The computer-executable instructions are executed by a computer processor to implement the adaptive recommendation method for stretching schemes as described in any one of claims 1-8.