A method and related equipment for intelligent mattress sleep comfort adaptation based on multidimensional feature matching
By using a multi-dimensional feature matching method, basic human body data of users is obtained and processed in three levels to generate intelligent matching results for mattress firmness and zone level. This solves the problem of lack of scientific basis in existing mattress recommendations and achieves personalized and accurate matching of sleep feel.
Patent Information
- Application Number
- CN202611494007.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2026-09-23
- Publication Date
- 2026-11-17
AI Technical Summary
Existing mattress recommendation technologies cannot accurately and scientifically match individual needs, ignoring differences in age, BMI, gender, body type, and other dimensions, resulting in poor fit and failing to meet the healthy sleep needs of different groups.
By using a multi-dimensional feature matching method, the user's basic human feature data is obtained, and three levels of decision processing are performed sequentially based on age, BMI, and gender/body type to generate intelligent adaptation results for mattress firmness and zone levels, including the integration of the first-level mattress firmness recommendation range, the second-level mattress firmness recommendation range, and mattress zone values.
It significantly improves the personalization and scientific rigor of mattress sleep comfort recommendations. Through a multi-dimensional decision-making system, it accurately matches the sleep needs of different groups of people, improving the poor adaptability problem in traditional technologies and taking into account both spinal health and sleep comfort.
Smart Images

Figure CN123100950A_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of intelligent assessment technology, and in particular to a method and related equipment for intelligent mattress sleep comfort adaptation based on multi-dimensional feature matching. Background Technology
[0002] The firmness and support of a mattress directly determine the comfort of sleep and spinal health, making proper mattress selection crucial for ensuring quality sleep and maintaining good posture. However, existing mattress matching recommendation technologies still have many shortcomings, making it difficult to achieve accurate and scientific personalized matching.
[0003] Current mattress recommendation systems are too simplistic, relying mostly on weight or age alone to match mattress firmness. They fail to address the differences in sleep comfort needs arising from musculoskeletal degeneration and changes in soft tissue elasticity across different age groups, neglecting systematic quantitative research on the relationship between age and mattress firmness. Age is not included as a core adaptation dimension in the matching system. Furthermore, some BMI-related selection schemes only offer qualitative suggestions, lacking quantitative verification of the correlation between BMI and mattress firmness preferences through statistical methods such as correlation analysis, hypothesis testing, and stratified regression, significantly reducing the accuracy of mattress recommendations. In addition, current technologies ignore the physiological differences between men and women, failing to consider differences in body shape parameters such as fat distribution, muscle morphology, skeletal structure, and waist-to-hip ratio, and shoulder-to-hip ratio, to build a differentiated body type classification system and zoned support adaptation schemes. Most importantly, current technologies lack a prioritization and hierarchical integration logic for the three core dimensions of age, BMI, and gender / body type, lacking a systematic and comprehensive matching decision-making system. This results in mattress sleep comfort recommendations lacking scientific basis, poor adaptability, and failing to meet the personalized healthy sleep needs of different groups.
[0004] In summary, the technical problems existing in the relevant technologies need to be improved. Summary of the Invention
[0005] The main purpose of this application is to propose a smart mattress sleeping comfort adaptation method and related equipment based on multi-dimensional feature matching, which can refine the recommendation scheme layer by layer according to human characteristics, accurately match multiple dimensions from age to BMI to gender and body type, and significantly improve the personalization and scientific basis of mattress sleeping comfort recommendations.
[0006] To achieve the above objectives, one aspect of this application proposes a method for intelligent mattress comfort adaptation based on multi-dimensional feature matching, the method comprising the following steps: Obtain the user's basic human characteristics data, which includes age, gender, height, weight, waist circumference, hip circumference, and shoulder circumference; Based on the user's age and age-related quantitative results, a first-level decision-making process is performed on the user to obtain a first-level recommended range for mattress firmness. Based on age threshold, body mass index, and the quantitative results of body mass index correlation, a second-level decision-making process is performed on the user to obtain a second-level recommended range for mattress firmness. Based on the basic human body feature data, the user undergoes a third-level decision-making process to obtain mattress zoning values; The recommended ranges for mattress firmness at the first level, the recommended ranges for mattress firmness at the second level, and the mattress zone values are integrated to obtain the intelligent mattress comfort matching result; the intelligent mattress comfort matching result includes human characteristics, mattress firmness, and mattress zone level.
[0007] Preferably, the step of performing a first-level decision-making process on the user based on the user's age and age-related quantitative results to obtain a first-level recommended range for mattress firmness includes the following steps: Based on the age-related quantitative results, the pre-collected subject sample data are subjected to correlation verification to obtain significance determination results; the age-related quantitative results include Pearson correlation coefficient and age-group target group index; The user's age is compared with a threshold based on the significance determination result to obtain the age threshold determination result; The age threshold determination result is matched with the preset age-based firmness correspondence rules to obtain the recommended firmness range of the first-level mattress.
[0008] Preferably, the step of performing a second-level decision-making process on the user based on age threshold, body mass index, and the correlation quantification result of body mass index to obtain a second-level mattress firmness recommendation range includes the following steps: Based on the correlation quantification results of the body mass index, the user's body mass index is classified into different groups to obtain the body mass index group category. By performing a matching query on the aforementioned body mass index population category, a set of candidate mattress firmness value ranges is obtained; The set of candidate mattress firmness values is filtered and corrected based on the age threshold to obtain the recommended firmness range for the second-level mattress.
[0009] Preferably, the step of classifying the user's body mass index (BMI) into different population groups based on the BMI correlation quantification results to obtain the BMI population category includes the following steps: The user's body mass index is compared with a threshold to obtain the body mass index threshold determination result; The body mass index threshold determination results are then subjected to category mapping to obtain the body mass index population category.
[0010] Preferably, the step of performing third-level decision processing on the user based on the basic human characteristic data to obtain mattress zoning values includes the following steps: The user's waist circumference, hip circumference, and shoulder circumference are calculated to obtain the waist-to-hip ratio and shoulder-to-hip ratio; Based on the user's gender, waist-to-hip ratio, shoulder-to-hip ratio, and body mass index, the user's body type is determined. The mattress partition value is obtained by performing a lookup table based on the user's gender and body type.
[0011] Preferably, the step of performing a lookup table based on the user's gender and body type to obtain the mattress partition values includes the following steps: The mattress partition values are obtained by performing a matching search based on the user's gender and body type. Based on the mattress partition values, a matching and determination process is performed on the preset mattress partition level mapping rules to obtain the mattress partition values.
[0012] Preferably, the process of integrating the first-level mattress firmness recommendation range, the second-level mattress firmness recommendation range, and the mattress zone values to obtain the intelligent mattress comfort adaptation result includes the following steps: The recommended firmness ranges of the first-level mattress and the second-level mattress are fused to obtain the recommended firmness value of the target mattress. The recommended firmness value of the target mattress and the mattress zone value are combined and matched to obtain the mattress zone level corresponding to the user's body type. The recommended firmness value of the target mattress, the mattress zone level, and the user's basic human characteristics data are structured and integrated to obtain the intelligent mattress sleep comfort adaptation result.
[0013] Preferably, the step of jointly matching and querying the recommended firmness value of the target mattress and the mattress zone value to obtain the mattress zone level corresponding to the user's body type includes the following steps: The mattress zoning value and the user's body type are compared and determined to obtain the mattress zoning baseline level; The mattress zoning baseline level is corrected based on the recommended firmness value of the target mattress to obtain the mattress zoning level.
[0014] To achieve the above objectives, another aspect of this application proposes a smart mattress sleep comfort adaptation system based on multi-dimensional feature matching, the system comprising: The data acquisition module is used to acquire the user's basic human characteristics data, which includes age, gender, height, weight, waist circumference, hip circumference, and shoulder circumference. The first-level decision processing module is used to perform first-level decision processing on the user based on the user's age and age-related quantitative results to obtain the first-level mattress firmness recommendation range; The second-level decision processing module is used to perform second-level decision processing on the user based on age threshold, body mass index and body mass index correlation quantification results, and obtain the second-level mattress firmness recommendation range. The third-level decision processing module is used to perform third-level decision processing on the user based on the basic human body feature data to obtain mattress zoning values. The result output module is used to integrate the first-level mattress firmness recommendation range, the second-level mattress firmness recommendation range, and the mattress zone value to obtain the intelligent mattress comfort adaptation result; the intelligent mattress comfort adaptation result includes human characteristics, mattress firmness, and mattress zone level.
[0015] To achieve the above objectives, another aspect of this application proposes an electronic device comprising a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the method described above.
[0016] This application includes at least the following beneficial effects: This application provides a method and related equipment for intelligent mattress sleep comfort adaptation based on multi-dimensional feature matching. This solution establishes a three-level progressive adaptation decision system based on age priority, body mass index (BMI) stratification, and gender-based body type zoning by collecting multi-dimensional basic human features, thus overcoming the shortcomings of traditional technologies that rely solely on single-parameter matching. Firstly, age is used as the core decision-making factor at the first level. The significant correlation between age and mattress firmness is used to prioritize the determination of the adaptation benchmark, aligning with the differences in sleep support needs caused by physiological degeneration of bones and soft tissues in different age groups, thus solving the problem of existing technologies neglecting the core adaptation value of age. Secondly, the second level of decision-making combines age threshold screening with quantitative matching based on BMI. This abandons traditional qualitative adaptation methods and relies on the quantitative results of BMI correlation to accurately match firmness ranges, significantly improving the accuracy of mattress firmness recommendations and addressing the shortcomings of insufficient precision in traditional adaptation schemes. Simultaneously, the third level of body type zoning decision-making is completed using body shape data such as waist circumference, hip circumference, and shoulder circumference, specifically adapting to the physiological differences in male and female body shapes, solving the shortcomings of existing technologies that do not differentiate between genders and body types and lack differentiated zoning support recommendations. Ultimately, by integrating the three-level decision-making results, an integrated adaptation result is formed that includes human characteristics, mattress firmness, and zone level. This constructs a multi-dimensional, prioritized, and quantifiable scientific adaptation logic, completely solving the problems of traditional technologies such as lack of hierarchical comprehensive matching schemes, chaotic recommendation logic, and poor adaptability. It effectively takes into account the spinal health and sleep comfort of different groups of people, and greatly improves the scientificity and accuracy of personalized intelligent mattress adaptation. Attached Figure Description
[0017] Figure 1 This is a flowchart of the intelligent mattress sleep comfort adaptation method based on multi-dimensional feature matching provided in the embodiments of this application; Figure 2 This is a schematic diagram of the calculation results of the hierarchical regression model; Figure 3 This is a diagram illustrating the mattress recommendation process; Figure 4 This is a diagram of a mattress recommendation system; Figure 5 This is a schematic diagram of the intelligent mattress sleep comfort adaptation system based on multi-dimensional feature matching provided in the embodiments of this application; Figure 6 This is a schematic diagram of the hardware structure of the electronic device provided in the embodiments of this application. Detailed Implementation
[0018] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of this application and are not intended to limit it. In the following description, when referring to the accompanying drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with those of this application; they are merely examples of apparatuses and methods consistent with some aspects of the embodiments of this application.
[0019] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein is for the purpose of describing embodiments of this application only and is not intended to limit this application.
[0020] Before providing a detailed description of the embodiments of this application, some of the nouns and terms involved in the embodiments of this application will be explained first. The nouns and terms involved in the embodiments of this application are subject to the following interpretations.
[0021] BMI: Body Mass Index, calculated by dividing weight (kg) by the square of height (m), is used to characterize the degree of fatness or thinness of a person and is the second-level decision indicator for mattress firmness matching.
[0022] TGI Index: Target Group Index, which reflects the strength of the target group's preference for mattress type. The higher the value, the stronger the group's preference for this type of mattress. It is used to verify the adaptation rules.
[0023] Figure 1 This is an optional flowchart of the intelligent mattress sleep comfort adaptation method based on multi-dimensional feature matching provided in the embodiments of this application. Figure 1 The method may include, but is not limited to, steps S110 to S150.
[0024] Step S110: Obtain the user's basic human body feature data, including age, gender, height, weight, waist circumference, hip circumference, and shoulder circumference; Step S120: Based on the user's age and age-related quantitative results, perform first-level decision processing on the user to obtain the first-level mattress firmness recommendation range; Step S130: Based on the age threshold, body mass index (BMI), and the BMI correlation quantification results, perform a second-level decision-making process for the user to obtain a second-level recommended range for mattress firmness. Step S140: Perform third-level decision processing on the user based on basic human body characteristic data to obtain mattress zoning values; Step S150: Integrate the recommended range of mattress firmness for the first level, the recommended range of mattress firmness for the second level, and the mattress zone values to obtain the intelligent mattress comfort matching result; the intelligent mattress comfort matching result includes human characteristics, mattress firmness, and mattress zone level.
[0025] Steps S110 to S160, as illustrated in this embodiment, involve acquiring basic human characteristic data of the user, including age, gender, height, weight, waist circumference, hip circumference, and shoulder circumference. Then, based on the user's age and age-related quantitative results, a first-level decision-making process is performed to output a first-level recommended mattress firmness range. Subsequently, a second-level decision-making process is executed, combining age thresholds, body mass index (BMI), and BMI-related quantitative results to obtain a second-level recommended mattress firmness range. A third-level decision-making process is then performed using the aforementioned basic human characteristic data to obtain mattress partition values. Finally, the first-level and second-level recommended mattress firmness ranges and mattress partition values are integrated to generate a smart mattress comfort matching result. This result includes human characteristics, mattress firmness, and mattress partition levels. By sequentially determining the recommended firmness range and mattress partition values through three levels of hierarchical decision-making, personalized intelligent matching of mattress comfort is achieved by comprehensively considering multi-dimensional human characteristic parameters.
[0026] In some embodiments, in step S110, basic human characteristic data of the user is obtained, including age, gender, height, weight, waist circumference, hip circumference and shoulder circumference data. Based on the collected height and weight data, the body mass index (BMI) is calculated, BMI = weight (kg) / height (m)². The collected data and the calculated BMI are summarized to finally obtain the user's basic human characteristic data including age, gender, height, weight, waist circumference, hip circumference and shoulder circumference.
[0027] In some embodiments, step S120 involves performing a first-level decision-making process on the user based on their age and age-related quantitative results to obtain a first-level recommended range for mattress firmness. This includes the following steps: performing correlation verification on pre-collected subject sample data based on the age-related quantitative results to obtain a significance determination result; the age-related quantitative results include the Pearson correlation coefficient and the target group index for each age group. The linear correlation between age and mattress firmness is calculated using the Pearson correlation coefficient formula, which is: ; In the formula, x represents the subject's age, and y represents the subject's preferred mattress firmness. , The values represent the age and optimal mattress firmness of the i-th subject, respectively, with n being the sample size. The sample yielded r = -0.154, indicating a negative correlation between age and mattress firmness. A t-test was then conducted to determine if the correlation was due to sampling error. The t-statistic formula is as follows: ; Substituting the values, we get t≈-2.63; the formula for calculating the p-value in a two-tailed test is: ; in The t-distribution represents the cumulative probability. When the degrees of freedom are greater than 120, the t-distribution approximates a standard normal distribution. The two-sided p-value corresponding to |t|=2.63 is 0.009. Since p=0.009 is less than 0.05, we reject the null hypothesis that age and mattress firmness are unrelated and obtain a significant negative correlation between the two. That is, the older the age, the more the subjects prefer mattresses with lower firmness values and higher firmness. Meanwhile, the correlation was further verified using the TGI index by age group. The baseline value of the TGI index is 100. An index greater than 100 indicates that the group's preference for firmer mattresses is higher than the overall average. As shown in Table 1, the TGI indices for the 20-24, 25-29, 30-34, and 35-39 age groups are 68.78, 103.17, 99.14, and 100.30, respectively, none of which are significantly higher than the baseline value. The TGI indices for the 40-44, 45-49, 50-54, and 60 and above age groups are 151.32, 226.98, 141.87, and 226.98, respectively, all of which are significantly higher than the baseline value, verifying that 40 years old is the age preference dividing threshold.
[0028]
[0029] Table 1 Based on the significance determination results, the user's age is compared against a threshold to obtain the age threshold determination result. The user's age data is obtained and compared against the 40-year-old cutoff threshold obtained from the aforementioned significance determination; if the user's age is greater than or equal to 40 years old, they are determined to be in the elderly group; if the user's age is less than 40 years old, they are determined to be in the young group. The determination result is used for subsequent matching of soft and hard rules.
[0030] The age threshold determination result is matched with the preset age-based firmness correspondence rules to obtain the first-level mattress firmness recommendation range. As shown in Table 2, Table 2 shows the relationship between mattress firmness numerical ranges and classifications. The preset correspondence rules between mattress firmness numerical ranges and types are as follows: the numerical range (0,2] corresponds to a firm mattress, the range (2,4] corresponds to a slightly firm mattress, the range (4,6] corresponds to a medium mattress, the range (6,8) corresponds to a slightly soft mattress, and the range (8,10) corresponds to a soft mattress. When the age threshold determination result is that the user's age is ≥40 years old, the matched firmness numerical range X≤4, i.e., a firm or slightly firm mattress, is used as the first-level mattress firmness recommendation range; when the age threshold determination result is that the user's age is <40 years old, the first-level decision does not output a fixed firmness range, and the process proceeds to the second-level decision to continue to complete the mattress firmness adaptation.
[0031]
[0032] Table 2 The TGI index has a baseline value of 100. A value greater than 100 indicates that this group prefers firmer mattresses than the overall average. A clear dividing line is observed at age 40: the TGI index for all age groups under 40 (68.78-103.17) is not significantly higher than 100; while the TGI index for all age groups 40 and above (141.87-226.98) is significantly higher than 100. This indicates that preferences increase with age: after age 40, the TGI index shows a fluctuating upward trend. The TGI index for the 45-49 age group and the 60 and above group reaches as high as 226.98.
[0033] In some embodiments, step S130 involves performing a second-level decision-making process on the user based on an age threshold, body mass index (BMI), and BMI correlation quantification results to obtain a second-level recommended mattress firmness range. This includes the following steps: classifying the user's BMI into different population groups based on the BMI correlation quantification results to obtain a BMI population category; performing a matching query on the BMI population category to obtain a set of candidate mattress firmness value ranges; and filtering and correcting the candidate mattress firmness value ranges based on an age threshold to obtain a second-level recommended mattress firmness range. Classifying the user's BMI into different population groups based on the BMI correlation quantification results includes the following steps: performing a threshold comparison on the user's BMI to obtain a BMI threshold determination result; and mapping the BMI threshold determination result to a category to obtain a BMI population category.
[0034] Specifically, this embodiment first performs a threshold comparison on the user's Body Mass Index (BMI) to obtain a BMI threshold determination result, and then performs category mapping on the BMI threshold determination result to obtain the BMI population category. More specifically, population classification is carried out based on the BMI correlation quantification results, which include the Pearson correlation coefficient, TGI preference index, and hierarchical regression model results. The linear correlation between BMI and mattress firmness is calculated using the Pearson correlation coefficient formula, which is: ; Where x represents the subject's BMI, and y represents the subject's preferred mattress firmness. , Here, BMI and optimal mattress firmness are the observed values for the i-th subject, respectively, and n is the sample size. The sample yielded r = -0.126, indicating a negative correlation between BMI and mattress firmness. A t-test was then conducted to determine if the correlation was due to sampling error. The t-statistic formula is as follows: ; Substituting the values, we get t≈-2.14; the formula for calculating the p-value in a two-tailed test is: ; The calculated P value was approximately 0.031. Since P = 0.031 is less than 0.05, the null hypothesis that BMI and mattress firmness are unrelated was rejected, leading to the conclusion that there is a significant negative correlation between the two. That is, the higher the BMI, the more likely the subjects are to prefer mattresses with lower firmness values and higher firmness. A stratified regression model was used to verify the independent contribution of BMI. After controlling for age and weight, the results were ΔR² = 0.019, ΔF(1,185) = 3.712, and P = 0.013. ΔR² = 0.019 indicates that after excluding the influence of age and weight, BMI can explain 1.9% of the variation in mattress firmness on its own, and the ΔF test proves that this contribution is statistically significant. The total R² of the stratified regression was 5.7%, influenced by the collinearity between BMI and weight. This application's embodiment uses a combination of TGI qualitative analysis and correlation testing to determine the fit logic. Different BMI groups have corresponding TGI indices for various mattress firmnesses. The TGI baseline value is 100; an index greater than 100 indicates that the group's preference for the corresponding mattress firmness is higher than the overall average. As shown in Table 3, Table 3 is a mapping table of BMI and mattress firmness. The preset BMI classification thresholds are: BMI < 18.5 is underweight, 18.5 ≤ BMI < 22 is underweight, 22 ≤ BMI < 24 is overweight, 24 ≤ BMI < 28 is overweight, and BMI ≥ 28 is obese. The user's BMI is compared with the above thresholds to complete the threshold determination and map the corresponding BMI population category.
[0035]
[0036] Table 3 A matching query was performed on the body mass index (BMI) groups to obtain a set of candidate mattress firmness ranges. As shown in Table 4, the preset Table 4 shows the TGI index of different BMI groups for various mattress firmnesses. For underweight individuals (BMI < 18.5), the candidate firmness range is 3-10; for normal underweight individuals (BMI ≤ 22), the candidate firmness range is 3-8; for normal overweight individuals (BMI ≤ 24), the candidate firmness range is 2-7; for overweight individuals (BMI ≤ 28), the candidate firmness range is ≤ 6; and for obese individuals (BMI ≥ 28), the candidate firmness range is ≤ 5. This yields the set of candidate mattress firmness ranges for the corresponding BMI groups.
[0037]
[0038] Table 4 The candidate mattress firmness ranges are filtered and corrected based on an age threshold to obtain a second-level recommended mattress firmness range. This embodiment only applies to users under 40 years old who are considered for the first-level decision. The candidate firmness ranges are ultimately limited by the age threshold, eliminating ranges that conflict with age preferences, and the corrected range is output as the second-level recommended mattress firmness range.
[0039] like Figure 2 As shown, Figure 2 The results of the hierarchical regression model are presented. Hierarchical regression analysis shows that, after controlling for age and weight, BMI significantly improves the predictive power of mattress firmness (ΔR²=0.019, P=0.013). However, the overall model's explanatory power is limited (total R²=5.7%), possibly due to some collinearity between BMI and weight. Therefore, the subsequent relationship between BMI and mattress firmness will not directly use the hierarchical regression model results, but will instead define the logical relationship between BMI and mattress firmness using a combination of qualitative and quantitative methods.
[0040] In some embodiments, step S140 involves performing third-level decision processing on the user based on basic anthropometric data to obtain mattress zoning values. This includes the following steps: calculating the user's waist, hip, and shoulder circumferences to obtain the waist-to-hip ratio (WHR) and shoulder-to-hip ratio (SHR). In this step, the waist, hip, and shoulder measurements are extracted from the user's basic anthropometric data to calculate the WHR and SHR. The WHR is the ratio of waist circumference to hip circumference, and the SHR is the ratio of shoulder circumference to hip circumference. The obtained WHR and SHR will be used as input parameters for subsequent body shape determination processing.
[0041] Based on the user's gender, waist-to-hip ratio, shoulder-to-hip ratio, and body mass index (BMI), the user's body type is determined. This application embodiment uses two independent body type determination logics based on gender, as shown in Tables 5 and 6. For female users, body type is determined by a combination of shoulder-to-hip ratio, waist-to-hip ratio, and BMI: a shoulder-to-hip ratio between 0.9 and 1.1 and a waist-to-hip ratio less than 0.75 is classified as X-type; a shoulder-to-hip ratio greater than 1.1 and a waist-to-hip ratio less than 0.85, or a shoulder-to-hip ratio less than 0.9 and a waist-to-hip ratio less than 0.85, is classified as A-type; a shoulder-to-hip ratio between 0.9 and 1.1 and a waist-to-hip ratio between 0.75 and 0.85 is classified as H-type; a waist-to-hip ratio between 0.85 and 0.9 is classified as light O-type; and a waist-to-hip ratio greater than 0.9 and a BMI greater than 24, or a BMI greater than 26, is classified as heavy O-type. For male users, the body type is determined using the shoulder-to-waist ratio, waist-to-hip ratio, and BMI: a shoulder-to-waist ratio less than 1.2 and a waist-to-hip ratio less than 0.85 are classified as H-type; a waist-to-hip ratio between 0.85 and 0.9 is classified as O-type; a waist-to-hip ratio greater than 0.9 or a BMI greater than 24 is also classified as O-type; a shoulder-to-waist ratio between 1.2 and 1.4 and a waist-to-hip ratio less than 0.85 is classified as inverted triangle; a shoulder-to-waist ratio greater than 1.4 and a waist-to-hip ratio between 0.8 and 0.85, or a waist-to-hip ratio less than 0.8, is classified as strong inverted triangle. The determination process allows for some users who cannot complete the body type classification; the resulting body type will be used for subsequent table lookup.
[0042]
[0043] Table 5
[0044] Table 6 The mattress zoning values are obtained by looking up a table based on the user's gender and body type. This includes the following steps: matching and searching based on the user's gender and body type to obtain mattress zoning values. As shown in Table 7, Table 7 records the mattress zoning levels and value ranges corresponding to different genders and body types. For women with H-type and A-type bodies, the mattress zoning level is no zoning or light zoning, with a value of 0-0.3; for women with light O-type bodies, the corresponding level is medium zoning, with a value of 0.3-0.5; for women with heavy O-type bodies, the corresponding level is heavy or heavy zoning, with a value ≥0.5; for women with X-type bodies, the corresponding level is medium, heavy, or heavy zoning, with a value ≥0.4. For men with H-type bodies, the corresponding level is no zoning or light zoning, with a value of 0-0.3; for men with O-type bodies, the corresponding level is light or medium zoning, with a value of 0.1-0.5; for men with inverted triangle bodies, the corresponding level is medium or heavy zoning, with a value of 0.4-0.8; for men with strong inverted triangle bodies, the corresponding level is heavy or heavy zoning, with a value ≥0.5. The system retrieves the corresponding mattress partition values by matching gender and body type.
[0045]
[0046] Table 7 Based on the mattress zoning values, a matching and determination process is performed according to the preset mattress zoning level mapping rules to obtain the mattress zoning values. As shown in Table 8, Table 8 establishes the correspondence between mattress zoning levels and mattress zoning values: mattress zoning value equal to 0 corresponds to no zoning; mattress zoning value ≤ 0.3 corresponds to light zoning; mattress zoning value 0.3-0.5 corresponds to medium zoning; mattress zoning value 0.5-0.8 corresponds to heavy zoning; mattress zoning value ≥ 0.8 corresponds to heavy zoning. The mattress zoning values obtained in the previous step are matched and determined with the interval rules in Table 8 to finally obtain the mattress zoning values.
[0047]
[0048] Table 8 In some embodiments, in step S150, after obtaining the first-level mattress firmness recommendation range, the second-level mattress firmness recommendation range, and the mattress zone value, these three types of results are integrated to generate a smart mattress comfort adaptation result. This smart mattress comfort adaptation result includes human characteristics, mattress firmness, and mattress zone level. First, interval fusion processing is performed on the first-level mattress firmness recommendation range and the second-level mattress firmness recommendation range to obtain the target mattress firmness recommendation value. In this embodiment, the mattress firmness test was conducted according to GB / T43007-2023 "Test and Evaluation Method for Mattress Firmness Grade Distribution". Before testing, the mattress sample was pretreated in an environment with a temperature of (23±2)℃ and a relative humidity of (50±5)% for no less than 72 hours. The mattress was divided into five areas along its length: head, back, waist, hips, and legs, with a test point set at the center of each area. A circular pad was used to load the mattress at a uniform speed of (90±5)mm / min. The load was unloaded after reaching 1000N. This loading and unloading cycle was repeated three times, and the loading curve was collected. The average slope of the loading curve and the firmness influence factor K were calculated to determine the mattress firmness grade. The mattress zone values were collected using the same testing method as the mattress firmness values. The maximum and minimum values were extracted from the zone values of all test points on the same mattress, and the extreme values were calculated as reference values for the mattress zones for zone grade determination mapping.
[0049] After calculating the recommended firmness value for the target mattress, a joint matching query is performed on the recommended firmness value and the mattress zoning value to obtain the mattress zoning level corresponding to the user's body type. The joint matching query process consists of two steps: the first step compares and determines the mattress zoning value and the user's body type to obtain the mattress zoning baseline level; the second step corrects the mattress zoning baseline level based on the recommended firmness value of the target mattress to obtain the final mattress zoning level. In this application embodiment, the adaptation relationship corresponding to each level of decision-making is verified based on sample data. The first level, the correlation between age and mattress firmness, is based on 2000 test sample data. The Pearson correlation coefficient between age and mattress firmness values is calculated, and the TGI index is used to analyze the preference of different age groups for various firmness mattresses. The second level, the correlation between BMI range and mattress firmness type, is based on 2000 sample data. The Pearson correlation coefficient between BMI range and mattress firmness type is calculated. Using a hierarchical regression model, the independent contribution of BMI to firmness selection is verified under the premise of controlling for age and weight variables. At the same time, the TGI index is used to analyze the preference tendency of different BMI groups for different firmness mattresses. The third level, the adaptation relationship between gender, body type, and mattress zone level, is based on 2000 test sample data. The TGI index is used to analyze the preference characteristics of different body types for each zone level.
[0050] Finally, the recommended mattress firmness, mattress zone levels, and the user's basic anatomy data are structurally integrated to generate a smart mattress comfort matching result. This result includes anatomy characteristics, mattress firmness, and mattress zone levels—a comprehensive matching solution. This comprehensive matching solution integrates all the results from the first, second, and third level decisions, achieving an integrated recommendation of mattress firmness and zone levels based on multiple user anatomy characteristics.
[0051] The solutions of the embodiments of the present invention will be described in detail and explained below with reference to specific application examples: This application embodiment collected 2000 valid test samples for correlation verification. The sample ages covered multiple age groups: 20-24 years, 25-29 years, 30-34 years, 35-39 years, 40-44 years, 45-49 years, 50-54 years, and 60 years and above. The sample BMI covered all ranges: underweight (BMI<18.5), normal underweight (18.5≤BMI<22), normal overweight (22≤BMI<24), overweight (24≤BMI<28), and obese (BMI≥28). Basic profile data of each subject was collected, including age, height, weight, sleep status, and physical condition. Waist circumference, hip circumference, and shoulder circumference were measured on-site. The test mattresses were divided into two groups for time-segmented testing. A pressure detection pad, i.e., a body pressure distribution measurement system, was placed on top of the mattresses to collect body pressure distribution data of the subjects in two positions: natural supine (right-side lying) and standard side-lying. Three core pressure assessment indicators were defined to quantify the mattress support and fit performance. The first indicator is peak pressure ratio. Calculation formula: ; in This is a set of pressure value arrays for key areas of the body, including the shoulders, waist, and hips. The first indicator is the sum of pressure values from all test points across the body; a smaller peak pressure ratio indicates lower stress concentration in that area and better mattress pressure relief performance. The second indicator is the contact support area. The first indicator is the total contact area where the interface pressure exceeds a preset threshold of 0.5 kPa under static pressure conditions on the human body. A larger contact area results in better mattress support and stress dispersion, and lower average pressure on the human body. The third indicator is the left-right symmetry index. Calculation formula: ; in and The pressure scores are calculated for the corresponding shoulder, back, waist, and hip areas on the left and right sides of the subject's body, respectively. A lower left-right symmetry index indicates better neutral support from the mattress in maintaining the neutral physiological curvature of the spine and preventing lateral flexion and torsion. A comprehensive comfort scoring model is constructed based on these pressure indicators. The formula is: ; in , , The weighting coefficients represent the contribution percentages of peak pressure suppression capability, conformal support capability, and spinal neutrality maintenance capability, respectively. In this embodiment, the analytic hierarchy process (AHP) is used to process expert scoring data to obtain the weights. =0.35, =0.40, =0.25. Subjects experienced all the test mattresses in turn and collected pressure data in two postures. The mattress with the highest comprehensive score was the best mattress, the second best mattress was the second best mattress, and the worst mattress was the lowest comprehensive score. The objective pressure data corresponding to the best mattress was cross-compared with the subject's subjective comfort experience. When the pressure index rating and subjective preference were consistent, the subject's final most comfortable mattress was determined. The measured firmness value and zone values of the mattress were extracted as the baseline data for correlation analysis and the construction of Tables 1 to 8. The mattress firmness test was performed according to GB / T43007-2023 "Test and Evaluation Method for Mattress Firmness Grade Distribution". The mattress sample was placed in an environment with a temperature of (23±2)℃ and a relative humidity of (50±5)% for no less than 72h. The mattress was divided into 5 zones along its length: head, shoulders and back, waist, hips and legs. The test point was set at the center of each zone. The circular pad was lowered at a uniform speed of (90±5)mm / min. After the load reached 1000N, it was unloaded. The loading and unloading cycle was repeated 3 times, and the loading curve was recorded. The formula for calculating the average slope T of the loading curve is: Unit: N / mm; in This represents the slope of the tangent line at 210N on the loading curve. This represents the slope of the tangent line at 275N on the loading curve. This represents the slope of the tangent at 340N on the loading curve. The formula for calculating the hardness influence factor K is: ; in The total area enclosed by the loading curve and the x-axis within the range of 0N-450N, in N. mm. Hardness rating The calculation formula is: ; When the calculated hardness grade is less than 1, take =1; When the calculated result is greater than or equal to 1, it is rounded according to GB / T8170 standard, retaining the integer part. Correlation analysis results show that the Pearson correlation coefficient between age and mattress firmness value is r=-0.154, P=0.009, indicating a significant negative correlation between the two; TGI analysis results by age group: the TGI for firm mattresses is 151.32 for the 40-44 age group, 226.98 for the 45-49 age group, 141.87 for the 50-54 age group, and 226.98 for the 60 years and above, all higher than the 100 baseline, proving that people over 40 years old clearly prefer firm mattresses. The Pearson correlation coefficient between BMI range and mattress firmness type was -0.126, P=0.031, indicating a significant negative correlation. After controlling for age and weight, stratified regression analysis showed that BMI made a significant independent contribution to mattress firmness selection, ΔR²=0.019, ΔF(1,185)=3.712, P=0.013, and the overall model F(3,185)=3.653, P=0.014.
[0052] After obtaining the recommended firmness value of the target mattress, a joint matching query is performed on the recommended firmness value and the mattress zoning value to obtain the mattress zoning level corresponding to the user's body type. The joint matching query is implemented in two steps: the first step compares and determines the mattress zoning value and the user's body type to obtain the mattress zoning baseline level; the second step corrects the mattress zoning baseline level based on the recommended firmness value of the target mattress to obtain the mattress zoning level. This embodiment relies on the TGI index analysis results of the aforementioned 2000 samples to establish an adaptation mapping relationship between gender body type and mattress zoning level. The mattress zoning values are obtained using the GB / T43007-2023 test method, which is completely consistent with mattress firmness. The extreme values of all test points of the same mattress are extracted as zoning reference values for comparison and determination of the zoning baseline level.
[0053] Finally, the recommended mattress firmness, mattress zone levels, and the user's basic anatomy data are structurally integrated to obtain the intelligent mattress comfort matching result. This result includes anatomy characteristics, mattress firmness, and mattress zone levels. This intelligent mattress comfort matching result integrates three levels of decision-making outputs: the first level (age), the second level (BMI), and the third level (body type and gender), achieving integrated intelligent recommendation of mattress firmness and zone levels based on the user's multi-dimensional anatomy characteristics.
[0054] In some embodiments, based on the user's age and age-related quantitative results, a first-level decision-making process is performed to obtain a first-level mattress firmness recommendation range. In this embodiment, age is set as the highest priority adaptation dimension. First, user age data is acquired, and a threshold comparison is performed using 40 years old as the judgment threshold. When the user's age is greater than or equal to 40, a firm or hard mattress with a firmness value range X≤4 is directly output as the first-level recommendation result. This adaptation is based on sample TGI validation data; for people over 40, the TGI index for firm mattresses is higher than 140 for all age groups, and the preference increases continuously with age. The underlying physiological logic is that middle-aged and elderly people experience intervertebral disc water loss, decreased muscle elasticity, and weakened bone support capacity, significantly increasing their need for firm mattress support. Prioritizing age-based decision-making ensures the spinal support needs of middle-aged and elderly individuals. If the user's age is less than 40, the firmness range is not locked, and the process directly proceeds to the subsequent BMI second-level decision-making process.
[0055] Based on age thresholds, body mass index (BMI), and BMI correlation quantification results, a second-level decision-making process is performed on users to obtain a second-level recommended mattress firmness range. This embodiment first collects user height and weight data to calculate BMI values. Users are then categorized into five groups based on preset standards: underweight, normal underweight, normal overweight, overweight, and obese. Next, a preset table (Table 3) is consulted to match the corresponding firmness range and convert it to the corresponding firmness type. This matching logic relies on TGI preference analysis and hierarchical regression validation results. After controlling for age and weight variables, BMI has independent explanatory power for mattress firmness selection. Physiologically, the higher the BMI, the greater the pressure exerted by the body on the mattress contact surface, making it more prone to body sinking and spinal collapse. Therefore, high BMI individuals are suited to mattresses with lower firmness values and stronger support, while low BMI individuals are suited to mattresses with a wider firmness range, achieving precise firmness matching based on body weight and posture.
[0056] Based on basic anthropometric data, a third-level decision-making process is performed on the user to obtain mattress zoning values. This application embodiment obtains user gender, waist circumference, hip circumference, and shoulder circumference data, calculates waist-to-hip ratio and shoulder-to-hip ratio—core body posture parameters—and uses gender-differentiated judgment logic to identify the user's specific body type. Women are categorized as X-shaped, A-shaped, H-shaped, light O-shaped, and heavy O-shaped; men are categorized as H-shaped, O-shaped, inverted triangle, and strong inverted triangle. Based on the user's gender and determined body type, the body type-zoning adaptation table 7 is consulted to match the corresponding zoning value range and convert it into a standard mattress zoning level. This adaptation relationship is verified based on the TGI index analysis of 2000 test samples. Differentiated zoning support schemes are customized for the differences in skeletal structure and fat distribution between different genders and body types. For example, women with a heavy O-shaped body require high-intensity waist and hip zoning support, while men with a strong inverted triangle body type are adapted to shoulder and back zoning support, accurately matching the local pressure and pressure relief needs of different body types.
[0057] The first-level mattress firmness recommendation range, the second-level mattress firmness recommendation range, and the mattress zone values are integrated to obtain the intelligent mattress comfort adaptation result. This embodiment summarizes the three-level decision results step by step, integrating age-based firmness recommendations, BMI-based firmness range recommendations, and gender / body type-based zone level recommendations. It simultaneously collects basic human profile information such as user age, BMI, gender, and body type, and includes a summary of statistical verification evidence for each dimension. Finally, a complete comprehensive mattress comfort adaptation solution is generated and displayed externally through a display unit, achieving multi-dimensional, hierarchical, and scientific intelligent mattress comfort adaptation output.
[0058] In some embodiments, such as Figure 3 As shown, basic anatomy data of the user is acquired, including age, gender, height, weight, waist circumference, hip circumference, and shoulder circumference. This embodiment uses a data acquisition module to collect this anatomy data. This module includes an electronic scale to measure weight, a height measuring device to measure height, and a measuring tape to measure waist circumference, hip circumference, and shoulder circumference. It also includes a data entry interface for entering age, sleep patterns, and physical condition information. The data calculation module calculates BMI based on the acquired height and weight, calculates the waist-to-hip ratio based on waist and hip circumference, and calculates the shoulder-to-hip ratio based on shoulder circumference and hip circumference. The storage module stores multiple data tables, including Tables 1 to 8.
[0059] Based on the user's age and age-related quantitative results, the first-level decision processing is performed to obtain the first-level mattress firmness recommendation range. The decision execution module executes a three-level decision logic. The first-level decision reads the user's age data and determines whether the age is greater than or equal to 40 years old. If the age is ≥40 years old, a firm or hard mattress recommendation is directly output. If the age is less than 40 years old, the second-level decision is initiated. The age and BMI parameters work together to output the mattress firmness range.
[0060] Based on age thresholds, body mass index (BMI), and BMI correlation quantification results, a second-level decision-making process is performed on the user to obtain a second-level mattress firmness recommendation range. The second-level decision is based on the user's BMI, referring to Table 2, and outputs the corresponding firmness recommendation results. Gender and body type parameters work together to output the mattress zone range.
[0061] Based on basic anatomy data, a third-level decision-making process is performed on the user to obtain mattress zoning values. This third-level decision, based on the user's gender and determined body type, queries Table 7 to output recommended mattress zoning levels. The mattress firmness range and zoning range are then input into the mattress database for matching and retrieval.
[0062] The recommended mattress firmness ranges for the first and second levels, along with mattress zone values, are integrated to obtain intelligent mattress comfort matching results. These results include human body characteristics, mattress firmness, and mattress zone levels. After matching with the mattress database, recommended mattresses are output. The output module displays the comprehensive matching solution in text, charts, or a visual interface. This example provides a recommended case: the input gender is male, age 34, weight 79kg, height 181cm, calculated BMI is 24.11, body shape is determined to be inverted triangle, and recommended mattress models CDE610 and CDZ818 are output after matching.
[0063] In some embodiments, such as Figure 4 As shown, basic anatomy data of users is obtained, including age, gender, height, weight, waist circumference, hip circumference, and shoulder circumference. This embodiment first collects the subject's height, weight, waist circumference, hip circumference, and shoulder circumference in a standard standing posture. Simultaneously, the most comfortable mattress is tested in the subject's standard lying and side-lying postures, and mattress firmness and zone values are tested concurrently. Based on the collected sample data, studies are conducted sequentially on the relationship between age and mattress firmness, the relationship between BMI and mattress firmness, and the relationship between gender × body type and mattress zones. Then, the multidimensional indicators are stratified and summarized.
[0064] Based on the user's age and age-related quantitative results, a first-level decision-making process is performed to obtain the first-level recommended mattress firmness range. This application constructs a three-level decision logic: "Age → BMI → Gender × Body Type," with age set as the first priority adaptation dimension. Statistical analysis based on 2000 test samples shows a significant negative correlation between age and mattress firmness, with a Pearson correlation coefficient r = -0.154 and P = 0.009. Individuals over 40 years old show a clear preference for firmer mattresses (TGI ≥ 141.87), which is then translated into actionable decision rules to achieve quantitative adaptation based on age.
[0065] Based on age thresholds, body mass index (BMI), and the quantitative results of BMI correlation, a second-level decision-making process is performed on users to obtain a second-level recommended range for mattress firmness. This application employs hypothesis testing, correlation analysis, and hierarchical regression for quantitative verification to establish a mapping relationship between BMI ranges and mattress firmness types. BMI is significantly correlated with firmness type (r = -0.126, P = 0.031). After controlling for age and weight variables, hierarchical regression shows that BMI has an independent and significant contribution to firmness selection (ΔR² = 0.019, ΔF(1,185) = 3.712, P = 0.013). Combined with TGI analysis, this clarifies the preferences of different BMI groups and improves the credibility of BMI-based recommendations.
[0066] Based on basic anthropometric data, a third-level decision-making process is performed on users to obtain mattress zoning values. This solution establishes a differentiated body type classification system that distinguishes between male and female physiological differences. Women are categorized into H-type, A-type, light O-type, heavy O-type, and X-type; men are categorized into H-type, O-type, inverted triangle, and strong inverted triangle. A mapping between body type and mattress zoning levels is established based on TGI analysis of 2000 samples, addressing recommendation biases caused by generic body type classifications.
[0067] This solution integrates the recommended mattress firmness ranges for the first and second levels, along with mattress zone values, to obtain intelligent mattress comfort matching results. These results include human body characteristics, mattress firmness, and mattress zone levels. This proposed solution relies on a three-tiered progressive decision-making process, refining recommendations layer by layer from macro-level factors like age and meso-level factors like BMI to micro-level factors like gender and body type. Compared to single-dimensional recommendations, this approach considers age adaptability, weight support, and body type zone needs, enhancing the personalization and scientific rigor of mattress recommendations.
[0068] Please see Figure 5 This application also provides a mattress intelligent comfort adaptation system based on multi-dimensional feature matching, which can implement the above-mentioned method. The system includes: The data acquisition module is used to acquire the user's basic human characteristics data, which includes age, gender, height, weight, waist circumference, hip circumference, and shoulder circumference. The first-level decision processing module is used to perform first-level decision processing on users based on their age and age-related quantitative results, and obtain the first-level mattress firmness recommendation range; The second-level decision processing module is used to perform second-level decision processing on users based on age thresholds, body mass index, and the quantitative results of body mass index correlation, to obtain the second-level mattress firmness recommendation range. The third-level decision processing module is used to perform third-level decision processing on the user based on basic human body characteristic data to obtain mattress zoning values. The results output module integrates the first-level mattress firmness recommendation range, the second-level mattress firmness recommendation range, and the mattress zone values to obtain the intelligent mattress comfort adaptation results. The intelligent mattress comfort adaptation results include human characteristics, mattress firmness, and mattress zone levels.
[0069] It is understood that the content of the above method embodiments is applicable to this system embodiment. The specific functions implemented in this system embodiment are the same as those in the above method embodiments, and the beneficial effects achieved are also the same as those achieved in the above method embodiments.
[0070] This application also provides an electronic device, which includes a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the above-described method. This electronic device can be any smart terminal, including tablet computers, in-vehicle computers, etc.
[0071] It is understood that the content of the above method embodiments is applicable to this device embodiment. The specific functions implemented by this device embodiment are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.
[0072] Please see Figure 6 , Figure 6 The hardware structure of an electronic device according to another embodiment is illustrated. The electronic device includes: The processor 601 can be implemented using a general-purpose CPU (Central Processing Unit), microprocessor, application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of this application. The memory 602 can be implemented as a read-only memory (ROM), a static storage device, a dynamic storage device, or a random access memory (RAM). The memory 602 can store the operating system and other applications. When the technical solutions provided in the embodiments of this specification are implemented through software or firmware, the relevant program code is stored in the memory 602 and is called and executed by the processor 601 using the methods described in the embodiments of this application. The input / output interface 603 is used to implement information input and output; The communication interface 604 is used to enable communication and interaction between this device and other devices. Communication can be achieved through wired means (such as USB, network cable, etc.) or wireless means (such as mobile network, WIFI, Bluetooth, etc.). Bus 605 transmits information between various components of the device (e.g., processor 601, memory 602, input / output interface 603, and communication interface 604); The processor 601, memory 602, input / output interface 603, and communication interface 604 are connected to each other within the device via bus 605.
[0073] The embodiments described in this application are for the purpose of more clearly illustrating the technical solutions of the embodiments of this application, and do not constitute a limitation on the technical solutions provided by the embodiments of this application. As those skilled in the art will know, with the evolution of technology and the emergence of new application scenarios, the technical solutions provided by the embodiments of this application are also applicable to similar technical problems.
[0074] Those skilled in the art will understand that the technical solutions shown in the figures do not constitute a limitation on the embodiments of this application, and may include more or fewer steps than shown, or combine certain steps, or different steps.
[0075] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.
[0076] Those skilled in the art will understand that all or some of the steps in the methods disclosed above, as well as the functional modules / units in the systems and devices, can be implemented as software, firmware, hardware, or suitable combinations thereof.
[0077] The terms “first,” “second,” “third,” “fourth,” etc. (if present) in the specification and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms “comprising” and “having,” and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.
[0078] It should be understood that in this application, "at least one (item)" means one or more, and "more than" means two or more. "And / or" is used to describe the relationship between related objects, indicating that three relationships can exist. For example, "A and / or B" can represent three cases: only A exists, only B exists, and both A and B exist simultaneously, where A and B can be singular or plural. The character " / " generally indicates that the preceding and following related objects are in an "or" relationship. "At least one (item) of the following" or similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one (item) of a, b, or c can represent: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, and c can be single or multiple.
[0079] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.
[0080] The preferred embodiments of the present application have been described above with reference to the accompanying drawings, but this does not limit the scope of the claims of the present application. Any modifications, equivalent substitutions, and improvements made by those skilled in the art without departing from the scope and substance of the embodiments of the present application shall be within the scope of the claims of the present application.
Claims
1. A method for intelligent mattress sleep comfort adaptation based on multi-dimensional feature matching, characterized in that, The method includes the following steps: Obtain the user's basic human characteristics data, which includes age, gender, height, weight, waist circumference, hip circumference, and shoulder circumference; Based on the user's age and age-related quantitative results, a first-level decision-making process is performed on the user to obtain a first-level recommended range for mattress firmness. Based on age threshold, body mass index, and the quantitative results of body mass index correlation, a second-level decision-making process is performed on the user to obtain a second-level recommended range for mattress firmness. Based on the basic human body feature data, the user undergoes a third-level decision-making process to obtain mattress zoning values; The recommended ranges for mattress firmness at the first level, the recommended ranges for mattress firmness at the second level, and the mattress zone values are integrated to obtain the intelligent mattress comfort matching result; the intelligent mattress comfort matching result includes human characteristics, mattress firmness, and mattress zone level.
2. The method according to claim 1, characterized in that, The step of performing a first-level decision-making process on the user based on the user's age and age-related quantitative results to obtain a first-level recommended range for mattress firmness includes the following steps: Based on the age-related quantitative results, the pre-collected subject sample data are subjected to correlation verification to obtain significance determination results; the age-related quantitative results include Pearson correlation coefficient and age-group target group index; The user's age is compared with a threshold based on the significance determination result to obtain the age threshold determination result; The age threshold determination result is matched with the preset age-based firmness correspondence rules to obtain the recommended firmness range of the first-level mattress.
3. The method according to claim 1, characterized in that, The second-level decision-making process, based on age thresholds, body mass index (BMI), and BMI correlation quantification results, to obtain a second-level mattress firmness recommendation range, includes the following steps: Based on the correlation quantification results of the body mass index, the user's body mass index is classified into different groups to obtain the body mass index group category. By performing a matching query on the aforementioned body mass index population category, a set of candidate mattress firmness value ranges is obtained; The set of candidate mattress firmness values is filtered and corrected based on the age threshold to obtain the recommended firmness range for the second-level mattress.
4. The method according to claim 3, characterized in that, The step of classifying the user's body mass index (BMI) based on the correlation quantification results to obtain the BMI-based population category includes the following steps: The user's body mass index is compared with a threshold to obtain the body mass index threshold determination result; The body mass index threshold determination results are then subjected to category mapping to obtain the body mass index population category.
5. The method according to claim 1, characterized in that, The step of performing third-level decision processing on the user based on the basic human body feature data to obtain mattress zoning values includes the following steps: The user's waist circumference, hip circumference, and shoulder circumference are calculated to obtain the waist-to-hip ratio and shoulder-to-hip ratio; Based on the user's gender, waist-to-hip ratio, shoulder-to-hip ratio, and body mass index, the user's body type is determined. The mattress partition value is obtained by performing a lookup table based on the user's gender and body type.
6. The method according to claim 5, characterized in that, The step of performing a table lookup process based on the user's gender and body type to obtain the mattress partition value includes the following steps: The mattress partition values are obtained by performing a matching search based on the user's gender and body type. Based on the mattress partition values, a matching and determination process is performed on the preset mattress partition level mapping rules to obtain the mattress partition values.
7. The method according to claim 1, characterized in that, The process of integrating the first-level mattress firmness recommendation range, the second-level mattress firmness recommendation range, and the mattress zone values to obtain the intelligent mattress comfort adaptation result includes the following steps: The recommended firmness ranges of the first-level mattress and the second-level mattress are fused to obtain the recommended firmness value of the target mattress. The recommended firmness value of the target mattress and the mattress zone value are combined and matched to obtain the mattress zone level corresponding to the user's body type. The recommended firmness value of the target mattress, the mattress zone level, and the user's basic human characteristics data are structured and integrated to obtain the intelligent mattress sleep comfort adaptation result.
8. The method according to claim 7, characterized in that, The step of jointly matching the recommended firmness value of the target mattress with the mattress zone value to obtain the mattress zone level corresponding to the user's body type includes the following steps: The mattress zoning value and the user's body type are compared and determined to obtain the mattress zoning baseline level; The mattress zoning baseline level is corrected based on the recommended firmness value of the target mattress to obtain the mattress zoning level.
9. A smart mattress sleep comfort adaptation system based on multi-dimensional feature matching, characterized in that, The system includes: The data acquisition module is used to acquire the user's basic human characteristics data, which includes age, gender, height, weight, waist circumference, hip circumference, and shoulder circumference. The first-level decision processing module is used to perform first-level decision processing on the user based on the user's age and age-related quantitative results to obtain the first-level mattress firmness recommendation range; The second-level decision processing module is used to perform second-level decision processing on the user based on age threshold, body mass index and body mass index correlation quantification results, and obtain the second-level mattress firmness recommendation range. The third-level decision processing module is used to perform third-level decision processing on the user based on the basic human body feature data to obtain mattress zoning values. The result output module is used to integrate the first-level mattress firmness recommendation range, the second-level mattress firmness recommendation range, and the mattress zone value to obtain the intelligent mattress comfort adaptation result; the intelligent mattress comfort adaptation result includes human characteristics, mattress firmness, and mattress zone level.
10. An electronic device, characterized in that, The electronic device includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the method according to any one of claims 1 to 8.
