Dressing recommendation method and system based on 3D human body measurement

Abstract

The invention is suitable for the technical field of intelligent dressing, provides a dressing recommendation method and system based on 3D human body measurement, and realizes dynamic optimization of sportswear recommendation by combining 3D human body measurement data of a user and historical operation data of wearable equipment. Acquiring a basic flexibility parameter according to the target exercise item and the core exercise part of the user; through motion trend analysis, the decreasing rate of the motion duration of the user is extracted as a first optimization factor; the motion trend and the fatigue state of the user are effectively combined, and multi-dimensional dynamic adjustment is achieved. Compared with the prior art, the method has the advantages that the current body state and the future exercise requirement of the user are accurately adapted, the recommended sportswear is more scientific and better meets the actual requirement, and meanwhile the wearing comfort and the functional experience of the user are improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of intelligent clothing, and particularly relates to a clothing recommendation method and system based on 3D body measurement. Background Art

[0002] In the technical field of intelligent clothing, the wide application of 3D body measurement technology and intelligent wearable devices provides technical support for personalized clothing recommendation. 3D body measurement technology can accurately capture the body size data of users and generate three-dimensional human models for clothing size adaptation and design optimization. At the same time, intelligent wearable devices can long-term record the motion data of users, including exercise intensity, frequency and physiological status, providing important references for understanding the exercise habits of users. These technologies have been initially applied in clothing recommendation and health management, bringing convenient services to users.

[0003] However, there are still great deficiencies in the existing technology in terms of sports clothing recommendation. The current recommendation methods often rely on the static body size data of users, ignoring the dynamic needs of key body parts during exercise, especially the matching problem between the flexibility of clothing and users' exercise habits. In addition, although intelligent wearable devices record a large amount of exercise data, they are mostly used for statistical analysis or health assessment and are not effectively used for flexibility optimization in clothing recommendation. The traditional recommendation methods fail to dynamically combine the exercise trends and fatigue status of users, resulting in a lack of pertinence in adjusting the flexibility parameters of clothing and being unable to fully meet the comfort and functionality requirements of users in different exercise scenarios. Summary of the Invention

[0004] The purpose of the present invention is to provide a clothing recommendation method and system based on 3D body measurement, aiming to solve the problems raised in the background art.

[0005] The present invention is implemented as follows. A clothing recommendation method based on 3D body measurement, the method includes:

[0006] Determine the category of sports clothing required by the user, and based on this, deduce the target sports event and the corresponding core sports parts of the user. Obtain the basic flexibility parameters related to the core sports parts based on 3D body measurement technology, and at the same time obtain the historical operation data recorded by the user's wearable device;

[0007] Draw a motion trend line chart based on the historical operation data, and analyze the change trend of the motion trend line chart. If it shows that the motion trend presents a continuous decreasing trend, calculate the average slope of the motion trend line chart and use it as the first optimization factor;

[0008] Analyze the user's historical operation data, filter out the muscle fatigue state data when the user reaches a specific intensity level in the target sports event, calculate the average value of the muscle fatigue state, compare this average value with the preset muscle fatigue reference threshold, quantify the difference between the two, and use this difference as the second optimization factor;

[0009] Combine the first optimization factor and the second optimization factor to comprehensively adjust the basic flexibility parameter, and finally calculate the optimized dynamic flexibility parameter.

[0010] As a further limitation of the technical solution of the embodiment of the present invention, the step of drawing a sports trend line chart based on the historical operation data, analyzing the change trend of the sports trend line chart, and if the displayed sports trend shows a continuous decreasing trend, calculating the average slope of the sports trend line chart and using it as the first optimization factor includes:

[0011] Analyze the historical operation data recorded by the user's wearable device, select the local data within the specified time window, extract the timestamps and exercise durations of the user's each target sports event from the local data, and apply data denoising processing to filter out outliers and noise interference, and organize to obtain a time series data set;

[0012] Based on the time series data set, draw a sports trend line chart with time as the horizontal axis and exercise duration as the vertical axis;

[0013] Analyze the change trend of the sports trend line chart. If the change trend shows a continuous decrease, calculate the average slope of the sports trend line chart to quantify the rate of decrease of the sports trend, and use it as the first optimization factor.

[0014] As a further limitation of the technical solution of the embodiment of the present invention, the step of analyzing the user's historical operation data, filtering out the muscle fatigue state data when the user reaches a specific intensity level in the target sports event, calculating the average value of the muscle fatigue state, comparing this average value with the preset muscle fatigue reference threshold, quantifying the difference between the two, and using this difference as the second optimization factor includes:

[0015] Analyze the user's historical operation data, filter out the records related to the target sports event, and further filter out the exercise segments that meet the intensity requirements according to the set intensity threshold, and extract the muscle fatigue state data from these exercise segments. The muscle fatigue state data includes the heart rate recovery duration;

[0016] Statistically analyze the heart rate recovery durations of all the filtered exercise segments, calculate their average value to quantify the user's overall muscle fatigue level;

[0017] Compare the calculated average muscle fatigue state with a preset reference fatigue threshold, quantify the difference between the two, and use this difference as the second optimization factor.

[0018] As a further limitation of the technical solution of the embodiment of the present invention, the steps of comprehensively adjusting the basic flexibility parameter in combination with the first optimization factor and the second optimization factor, and finally calculating the optimized dynamic flexibility parameter include:

[0019] Combine the first optimization factor and the second optimization factor, call the flexibility parameter optimization formula, comprehensively adjust the basic flexibility parameter, and calculate the optimized dynamic flexibility parameter;

[0020] Apply the optimized dynamic flexibility parameter to clothing recommendation based on 3D body measurement.

[0021] As a further limitation of the technical solution of the embodiment of the present invention, the flexibility parameter optimization formula is: F opt = F base ×(1 + S trend ×C1 + S fatigue ×C2), where Fopt refers to the dynamic flexibility parameter, Fbase refers to the basic flexibility parameter, S trend refers to the first optimization factor, that is, the average slope of the motion trend line graph, C1 refers to the adjustment coefficient related to the motion trend, S fatigue refers to the second optimization factor, that is, the difference between the average value of the muscle fatigue state and the preset muscle fatigue reference threshold, and C2 refers to the adjustment coefficient related to the muscle fatigue state;

[0022] In the flexibility parameter optimization formula, where n refers to the total number of times the user performs the target sports item in the local data, and T i refers to the duration of the i-th target sports item;

[0023] In the flexibility parameter optimization formula, where R avg refers to the average value of the muscle fatigue state, and R ref refers to the preset reference fatigue threshold.

[0024] A clothing recommendation system based on 3D body measurement, the system includes: a data acquisition module, a line graph analysis module, a muscle fatigue state analysis module, and a flexibility parameter adjustment module, where:

[0025] A data acquisition module, configured to determine the category of sports clothing required by a user, and based on this, deduce the user's target sports event and the corresponding core sports parts, acquire basic flexibility parameters related to the core sports parts based on 3D body measurement technology, and at the same time acquire historical operation data recorded by the user's wearable device;

[0026] A line graph analysis module, configured to draw a sports trend line graph based on the historical operation data, and analyze the change trend of the sports trend line graph. If the displayed sports trend shows a continuous decreasing trend, calculate the average slope of the sports trend line graph and use it as the first optimization factor;

[0027] A muscle fatigue state analysis module, configured to parse the user's historical operation data, filter out the muscle fatigue state data when the user reaches a specific intensity level in the target sports event, calculate the average value of the muscle fatigue state, compare the average value with a preset muscle fatigue reference threshold, quantify the difference between the two, and use this difference as the second optimization factor;

[0028] A flexibility parameter adjustment module, configured to comprehensively adjust the basic flexibility parameters by combining the first optimization factor and the second optimization factor, and finally calculate the optimized dynamic flexibility parameters.

[0029] As a further limitation of the technical solution of the embodiment of the present invention, the line graph analysis module specifically includes:

[0030] A first data parsing unit, configured to parse the historical operation data recorded by the user's wearable device, select local data within a specified time window, extract the time stamp and exercise duration of the user's each target sports event from the local data, and apply data denoising processing to filter out outliers and noise interference, and organize to obtain a time series data set;

[0031] A line graph drawing unit, configured to draw a sports trend line graph based on the time series data set, with time as the horizontal axis and exercise duration as the vertical axis;

[0032] An average slope calculation unit, configured to analyze the change trend of the sports trend line graph. If the change trend shows a continuous decrease, calculate the average slope of the sports trend line graph to quantify the rate of decrease of the sports trend and use it as the first optimization factor.

[0033] As a further limitation of the technical solution of the embodiment of the present invention, the muscle fatigue state analysis module specifically includes:

[0034] The second data analysis unit is used to analyze the user's historical operation data, filter out the records related to the target sports event, and further filter out the exercise segments that meet the intensity requirements according to the set intensity threshold, and extract muscle fatigue state data from these exercise segments. The muscle fatigue state data includes the heart rate recovery duration;

[0035] The average value determination unit is used to count the heart rate recovery durations of all filtered exercise segments, calculate their average value to quantify the user's overall muscle fatigue level;

[0036] The difference degree calculation unit is used to compare the calculated average value of the muscle fatigue state with the preset reference fatigue threshold, quantify the difference degree between the two, and use this difference degree as the second optimization factor.

[0037] As a further limitation of the technical solution of the embodiment of the present invention, the muscle fatigue state analysis module specifically includes:

[0038] The flexibility parameter adjustment unit is used to combine the first optimization factor and the second optimization factor, call the flexibility parameter optimization formula, comprehensively adjust the basic flexibility parameters, and calculate the optimized dynamic flexibility parameters;

[0039] The flexibility parameter application unit is used to apply the optimized dynamic flexibility parameters to the clothing recommendation based on 3D body measurement.

[0040] As a further limitation of the technical solution of the embodiment of the present invention, the flexibility parameter optimization formula is: F opt = F base ×(1 + S trend ×C1 + S fatigue ×C2), where Fopt refers to the dynamic flexibility parameter, Fbase refers to the basic flexibility parameter, S trend refers to the first optimization factor, that is, the average slope of the motion trend line graph, C1 refers to the adjustment coefficient related to the motion trend, S fatigue refers to the second optimization factor, that is, the difference degree between the average value of the muscle fatigue state and the preset muscle fatigue reference threshold, C2 refers to the adjustment coefficient related to the muscle fatigue state;

[0041] In the flexibility parameter optimization formula, where n refers to the total number of times the user performs the target sports event in the local data, T i refers to the exercise duration of the i-th target sports event;

[0042] In the flexibility parameter optimization formula, where R avg refers to the average value of the muscle fatigue state, R refRefers to a preset reference fatigue threshold.

[0043] Compared with the prior art, the present invention has the following beneficial effects:

[0044] By combining the user's 3D body measurement data and the historical operation data of the wearable device, the present invention realizes the dynamic optimization of sports clothing recommendations. According to the user's target sports event and core sports parts, basic flexibility parameters are obtained; through sports trend analysis, the rate of decrease in the user's sports duration is extracted as the first optimization factor; at the same time, based on the degree of difference in muscle fatigue states, the second optimization factor is extracted. Finally, by combining the two optimization factors, the basic flexibility parameters are comprehensively adjusted to dynamically generate optimized flexibility parameters for clothing recommendations.

[0045] The present invention effectively combines the user's sports trends and fatigue states to achieve multi-dimensional dynamic adjustment. Compared with traditional technologies, its advantage lies in accurately adapting to the user's current physical state and future sports needs, making the recommended sports clothing more scientific and more in line with actual needs, while enhancing the user's wearing comfort and functional experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] Figure 1 Is a flowchart of the method provided by an embodiment of the present invention;

[0047] Figure 2 Is a flowchart of determining the first optimization factor based on the historical operation data recorded by the user's wearable device in the method provided by an embodiment of the present invention;

[0048] Figure 3 Is a flowchart of determining the second optimization factor based on the historical operation data recorded by the user's wearable device in the method provided by an embodiment of the present invention;

[0049] Figure 4 Is a flowchart of calculating the dynamic flexibility parameter in the method provided by an embodiment of the present invention;

[0050] Figure 5 Is an application architecture diagram of the system provided by an embodiment of the present invention;

[0051] Figure 6 Is a structural block diagram of the line graph analysis module in the system provided by an embodiment of the present invention;

[0052] Figure 7 Is a structural block diagram of the muscle fatigue state analysis module in the system provided by an embodiment of the present invention;

[0053] Figure 8 Is a structural block diagram of the flexibility parameter adjustment module in the system provided by an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0054] In order to make the objectives, technical solutions and advantages of the present invention more clearly understood, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0055] Figure 1 The flowchart of the method provided by the embodiment of the present invention is shown.

[0056] Specifically, a clothing recommendation method based on 3D body measurement, the method specifically includes the following steps:

[0057] Step S100, determine the category of sports clothing required by the user, and based on this, deduce the user's target sports item and the corresponding core sports part, obtain the basic flexibility parameters related to the core sports part based on 3D body measurement technology, and at the same time obtain the historical operation data recorded by the user's wearable device.

[0058] In the embodiment of the present invention, the object of the present invention is the user group who clearly selects sports category clothing. These users usually have clear sports needs or habits, such as running, yoga or fitness. At the same time, such users usually wear intelligent wearable devices, such as smart watches, sports bracelets or other devices supporting sports data monitoring, to record relevant data (such as steps, heart rate, exercise intensity, etc.) during their exercise. In addition, these users have the habit of frequently using wearable devices, enabling the device to accumulate their sports data for a long time, providing a reliable historical reference basis for the system to analyze their sports characteristics and needs. This feature ensures the accuracy and practicality of the present invention in data acquisition and analysis.

[0059] The category of sports clothing required by the user is deduced based on the selected fitting type and target needs. For example, when the user selects to try on high-elastic compression clothing, the system recognizes that the possible target sports are running, high-intensity training or similar dynamic sports; if loose and comfortable clothing is selected, it may correspond to activities that require flexibility such as yoga and meditation. The system combines the selected clothing type of the user and their historical sports data to deduce the main sports item (i.e., the target sports item) of the user, such as running, yoga or weightlifting. Through the analysis of the load characteristics of different sports items on body parts in existing sports science research, the system further determines the core sports parts corresponding to these sports, such as the knee joint and ankle joint during running, and the shoulder and waist during yoga.

[0060] 3D body measurement technology can directly collect the flexibility data of users for the core movement parts, including the range of joint motion, limb proportions, and postural characteristics. These parameters are derived from existing technologies, such as the standardized measurement of joint movement angles, dynamic postural modeling, etc., which have been widely applied in the fields of human kinematics and health assessment. By analyzing the user's body model generated by 3D scanning, the system can obtain the basic flexibility parameters for the core movement parts, providing data support for recommending the most suitable clothing for the user. For example, knee support is needed during running, and more shoulder elasticity is required during yoga.

[0061] The historical running data of the user comes from the intelligent wearable devices they have used for a long time, such as smart watches or sports bracelets. These devices can record the start and end times of the user's movement, heart rate changes, steps, movement patterns (such as running, cycling, or stationary), and more high-frequency data based on sensors. These data are synchronized to the cloud through the device and the supporting software to form a complete user movement profile. The system can call the data related to the target movement in these profiles and conduct comprehensive analysis in combination with the user's real-time needs and 3D measurement models, so as to more accurately recommend sports clothing that meets the requirements.

[0062] Furthermore, the clothing recommendation method based on 3D body measurement further includes the following steps:

[0063] Step S200, draw a movement trend line chart based on the historical running data, and analyze the change trend of the movement trend line chart. If it shows that the movement trend presents a continuous decreasing trend, calculate the average slope of the movement trend line chart and use it as the first optimization factor.

[0064] Specifically, Figure 2 shows the flow chart for determining the first optimization factor based on the historical running data recorded by the user's wearable device.

[0065] Among them, drawing a movement trend line chart based on the historical running data and analyzing the change trend of the movement trend line chart. If it shows that the movement trend presents a continuous decreasing trend, calculating the average slope of the movement trend line chart and using it as the first optimization factor specifically includes the following steps:

[0066] Step S201, analyze the historical running data recorded by the user's wearable device, select the local data within the specified time window, extract the timestamps and movement durations of the user's each target movement item from the local data, and apply data denoising processing to filter out outliers and noise interference, and organize to obtain a time series data set;

[0067] Step S202, based on the time series data set, draw a movement trend line chart with time as the horizontal axis and movement duration as the vertical axis;

[0068] Step S203: Analyze the changing trend of the motion trend line chart. If the changing trend shows a continuous decrease, calculate the average slope of the motion trend line chart to quantify the rate of the decreasing motion trend, and use it as the first optimization factor.

[0069] In the embodiments of the present invention, when parsing the historical operation data recorded by the user's wearable device, it is necessary to select the local data within the specified time window to centrally analyze the user's motion behavior during a specific time period. The significance of this selection is that it can reduce the interference of irrelevant data, highlight the analysis of the user's recent motion patterns, and thus more accurately reflect the user's current motion habits and trend changes. By extracting the timestamps and motion durations of the target motion items and applying data denoising processing, the noise data caused by device errors, user abnormal behaviors, or environmental interferences can be filtered out to ensure the quality and credibility of the dataset. The sorted time series dataset provides a reliable basis for subsequent drawing of the motion trend line chart and analysis of its changing trend.

[0070] After drawing the motion trend line chart with time as the horizontal axis and motion duration as the vertical axis, the system can intuitively display the time changing trend of the user in the target motion item. If the number of times the user performs the target motion is less than the preset analysis times standard, there is insufficient data support, and at this time, the analysis is of little significance, and the system will abandon the trend analysis and recommend clothing according to the initial flexibility parameters. If the data volume reaches the analysis standard, it is judged whether there is a significant continuous change in the user's motion pattern by analyzing the changing trend of the line chart. If the changing trend is not a continuous decrease, it means that the user's motion duration has not shown a significant decrease, and the system will consider that the user's motion state remains stable, so it still recommends clothing according to the initial flexibility parameters without additional adjustment.

[0071] Analyzing the changing trend of the motion trend line chart and calculating the average slope are of great significance. If the changing trend of the line chart shows a continuous decrease, calculating its average slope can quantify the rate of the decreasing user motion trend. The average slope of the decreasing trend is used as the first optimization factor to dynamically adjust the flexibility parameters, so as to provide targeted support for the recommended sports clothing. For example, when the user's motion duration significantly decreases, the optimization factor can prompt the system to recommend clothing with lower flexibility and suitable for the decreased exercise intensity. The advantage of this process is that the system dynamically adjusts the recommendation strategy according to the user's actual motion trend, making the recommendation result more in line with the user's current motion needs and improving the accuracy and scientific nature of personalized recommendations.

[0072] Furthermore, the clothing recommendation method based on 3D body measurement further includes the following steps:

[0073] Step S300: Analyze the user's historical exercise data, filter out the muscle fatigue state data when the user reaches a specific intensity level in the target sports event, calculate the average value of the muscle fatigue state, compare this average value with the preset muscle fatigue reference threshold, quantify the difference between the two, and use this difference as the second optimization factor.

[0074] Specifically, Figure 3 FIG. shows a flowchart for determining the second optimization factor based on the historical exercise data recorded by the user's wearable device.

[0075] Among them, analyzing the user's historical exercise data, filtering out the muscle fatigue state data when the user reaches a specific intensity level in the target sports event, calculating the average value of the muscle fatigue state, comparing this average value with the preset muscle fatigue reference threshold, quantifying the difference between the two, and using this difference as the second optimization factor specifically includes the following steps:

[0076] Step S301: Analyze the user's historical exercise data, filter out the records related to the target sports event, and further filter out the exercise segments that meet the intensity requirements according to the set intensity threshold. Extract the muscle fatigue state data from these exercise segments, and the muscle fatigue state data includes the heart rate recovery duration;

[0077] Step S302: Statistically analyze the heart rate recovery durations of all the filtered exercise segments, calculate their average value to quantify the user's overall muscle fatigue level;

[0078] Step S303: Compare the calculated average value of the muscle fatigue state with the preset reference fatigue threshold, quantify the difference between the two, and use this difference as the second optimization factor.

[0079] In the embodiment of the present invention, the set intensity threshold is derived based on the characteristics of the target sports event and the user's physical ability. According to existing sports science research, different sports events have different intensity requirements. For example, high-intensity running may be based on the heart rate reaching more than 75% of the maximum heart rate, while weightlifting may be judged based on the acceleration recorded by the sensor reaching a certain specific threshold. The setting of the intensity threshold needs to combine the typical exercise load characteristics of the sports event itself and the distribution of similar exercise intensities in the user's historical data to ensure that the filtered segments can truly reflect the user's high-intensity exercise state.

[0080] In addition to the heart rate recovery duration, the muscle fatigue state data may also include other physiological indicators, such as the respiratory recovery time, lactate clearance rate, or subjective fatigue score. The calculation process should be consistent, and relevant parameters need to be extracted from the post-exercise recovery data and quantified in the form of time or ratio. For example, the respiratory recovery time can be calculated by the time when the respiratory rate returns to the resting level from the end of exercise, and the lactate clearance rate can be determined by the time when the blood lactate level returns to the basal value after exercise. All these indicators can reflect the muscle fatigue state from different dimensions, and the calculation method is consistent with the heart rate recovery duration to ensure data unity.

[0081] The reason why the average value of the heart rate recovery duration of all selected exercise segments is statistically calculated and used to quantify the user's overall muscle fatigue level is that the average value can comprehensively reflect the user's recovery ability after multiple high-intensity exercises. The length of the recovery time is directly related to the user's fatigue degree and physical adaptability. A longer average recovery time means a higher fatigue degree after exercise for the user, while a shorter recovery time indicates a stronger physical adaptability of the user. Therefore, the average value is an effective statistical indicator that can provide holistic quantitative data for subsequent analysis.

[0082] The preset reference fatigue threshold is derived based on the recovery ability standard of healthy exercise populations or the user's historical recovery ability performance. The recovery time data of healthy individuals in existing sports physiology research can be combined as a reference value. For example, a decrease of 20 beats per minute within 1 minute of heart rate recovery may be used as a standard value. In addition, the user's long-term data can also be used to dynamically adjust the threshold. For example, the average heart rate recovery duration of the user over a long period can be used as their personalized reference value.

[0083] The significance of using the difference degree as an optimization factor is that it can dynamically reflect the deviation between the user's actual physical state and the ideal reference value, helping the system to more accurately adapt to the user's needs. By quantifying the difference degree between the two, the system can determine whether the user needs sports clothing with higher flexibility to relieve fatigue, or whether the flexibility requirement can be appropriately reduced to expand the recommended options. The advantage of this dynamic optimization is that it can adjust the recommendation strategy based on the user's actual physiological performance, making the recommendation more scientific and personalized, avoiding a one-size-fits-all static recommendation method, and providing the user with a more comfortable and suitable choice of sports clothing.

[0084] Furthermore, the 3D body measurement-based clothing recommendation method further includes the following steps:

[0085] Step S400, combining the first optimization factor and the second optimization factor to comprehensively adjust the basic flexibility parameters, and finally calculating the optimized dynamic flexibility parameters.

[0086] Specifically, Figure 4A flowchart for calculating dynamic flexibility parameters is shown.

[0087] Among them, by combining the first optimization factor and the second optimization factor, the basic flexibility parameters are comprehensively adjusted, and finally calculating the optimized dynamic flexibility parameters specifically includes the following steps:

[0088] Step S401: Combine the first optimization factor and the second optimization factor, call the flexibility parameter optimization formula, and comprehensively adjust the basic flexibility parameters to calculate the optimized dynamic flexibility parameters;

[0089] Step S402: Apply the optimized dynamic flexibility parameters to clothing recommendations based on 3D body measurements.

[0090] The flexibility parameter optimization formula is: F opt = F base ×(1 + S trend ×C1 + S fatigue ×C2), where Fopt refers to the dynamic flexibility parameter, F base refers to the basic flexibility parameter, S trend refers to the first optimization factor, that is, the average slope of the motion trend line graph, C1 refers to the adjustment coefficient related to the motion trend, S fatigue refers to the second optimization factor, that is, the difference between the average value of the muscle fatigue state and the preset muscle fatigue reference threshold, C2 refers to the adjustment coefficient related to the muscle fatigue state;

[0091] In the flexibility parameter optimization formula, where n refers to the total number of times the user performs the target sports event in the local data, T i refers to the duration of the i-th target sports event;

[0092] In the flexibility parameter optimization formula, where R avg refers to the average value of the muscle fatigue state, R ref refers to the preset reference fatigue threshold.

[0093] In the embodiments of the present invention, by combining the first optimization factor and the second optimization factor, the basic flexibility parameters are comprehensively adjusted. Through the flexibility parameter optimization formula, the analysis results of the movement trend and the muscle fatigue state are linked together, making the adjustment process more dynamic and personalized. The first optimization factor can accurately predict the change of the user's movement demand in the next period of time by quantifying the change of the user's movement trend, especially the decreasing rate of the movement duration; the second optimization factor reflects the current physical recovery ability through the difference degree of the user's actual fatigue state. The combination of these two optimization factors enables the adjustment of the flexibility parameters to not only adapt to the user's future movement trend but also meet the current physiological state requirements of the user, achieving the balance and pertinence of dynamic adjustment.

[0094] This linkage mechanism makes up for two major deficiencies in the prior art. First, traditional clothing recommendation systems mostly rely on static data or single factors (such as body size or clothing classification) for matching, and it is difficult to dynamically adapt to the changes in the user's movement habits or body states. By incorporating both the movement trend and the fatigue state into the analysis, the present invention realizes multi-dimensional data linkage, avoiding the errors or limitations that may be brought by a single optimization factor. Second, the prior art usually lacks the ability to predict the user's future needs and cannot consider the dynamic adjustment of the user's movement intensity change or fatigue degree in the recommendation. By introducing the first optimization factor, the present invention integrates the prediction of the future trend into the recommendation process, making up for the short-sightedness of traditional methods.

[0095] The advantage of this linkage adjustment is that the optimized dynamic flexibility parameters are more in line with the actual needs of the user. For example, when the user's movement trend decreases and the fatigue state is high, the recommended clothing will increase flexibility to provide higher comfort and relief; when the user's movement trend is stable and the fatigue state is low, the recommended clothing can reduce the flexibility requirement, broaden the clothing selection range, and at the same time ensure movement support. Through this dynamic optimization, the system not only improves the accuracy and scientific nature of the recommendation but also enhances the comfort and diversity of the user experience, making the recommendation result more practical and intelligent.

[0096] The technical solution of the present invention is further illustrated by an example below:

[0097] Suppose a user selects to try on running clothing. First, the system generates basic flexibility parameters for the user through 3D body measurement technology. Suppose the initial value of the basic flexibility parameter is 20. Subsequently, the system analyzes the user's historical exercise data, selects relevant running exercise segments within a specified time window, extracts the duration of each run, and plots a line graph of the exercise trend. By analyzing the line graph, it is found that the user's exercise trend shows a continuous decrease. The system calculates that the average slope of the decreasing exercise duration is -0.1, and the adjustment coefficient set for exercise trend correction is 0.5. Through calculation, the correction value of the exercise trend to the flexibility parameter is -0.05.

[0098] At the same time, the system further filters out the user's high-intensity running exercise segments, extracts the data of the heart rate recovery duration after exercise, and calculates that the average value of the user's heart rate recovery duration is 80 seconds. Comparing it with the preset reference fatigue threshold of 60 seconds, the deviation degree of the fatigue state is calculated to be 0.33. Combining the adjustment coefficient of 0.3 for fatigue state correction, the correction value of the fatigue state to the flexibility parameter is +0.099.

[0099] Finally, the system comprehensively adjusts the two correction values with the basic flexibility parameter. Adding -0.05 and +0.099 gives a total correction value of +0.049. Combining with the basic flexibility parameter of 20, the optimized dynamic flexibility parameter is calculated to be 20.98. The system applies this optimized dynamic flexibility parameter to the clothing recommendation of 3D body measurement. The recommended running clothing can better fit the user's exercise trend and fatigue state, providing support while taking into account the user's comfort requirements.

[0100] Furthermore, Figure 5 The application architecture diagram of the system provided by the embodiment of the present invention is shown.

[0101] Among them, in another preferred embodiment provided by the present invention, a clothing recommendation system based on 3D body measurement includes:

[0102] A data acquisition module 100, configured to determine the category of sports clothing required by the user, and deduce the user's target sports event and the corresponding core sports parts based on this, obtain the basic flexibility parameters related to the core sports parts based on 3D body measurement technology, and at the same time obtain the historical operation data recorded by the user's wearable device.

[0103] In the embodiments of the present invention, the target users are those who clearly select sportswear of specific categories. These users usually have clear sports needs or habits, such as running, yoga, or fitness. At the same time, such users usually wear smart wearable devices, such as smart watches, sports bracelets, or other devices that support sports data monitoring, to record relevant data during their sports processes (such as steps, heart rate, exercise intensity, etc.). In addition, these users have the habit of frequently using wearable devices, enabling the devices to accumulate their sports data over a long period, providing a reliable historical reference for the system to analyze their sports characteristics and needs. This feature ensures the accuracy and practicality of the present invention in data acquisition and analysis.

[0104] The category of sports clothing required by the user is derived based on the selected fitting type and target needs. For example, when the user selects to try on high-elastic compression clothing, the system identifies that the possible target sports are running, high-intensity training, or similar dynamic sports; if loose and comfortable clothing is selected, it may correspond to activities that require flexibility such as yoga and meditation. The system combines the clothing type selected by the user and their historical sports data to derive the main sports item (i.e., the target sports item) the user is engaged in, such as running, yoga, or weightlifting. By analyzing the load characteristics of different sports items on body parts in existing sports science research, the system further determines the core sports parts corresponding to these sports, such as the knee joint and ankle joint during running, and the shoulder and waist during yoga.

[0105] 3D body measurement technology can directly collect the flexibility data of the user for the core sports parts, including the range of joint motion, limb proportions, and posture characteristics. These parameters are from existing technologies, such as the standardized measurement of joint motion angles and dynamic posture modeling, which have been widely used in the fields of human kinematics and health assessment. By analyzing the user's body model generated by 3D scanning, the system can obtain the basic flexibility parameters for the core sports parts, providing data support for recommending the most suitable clothing for the user. For example, knee support is required during running, and more shoulder elasticity is needed during yoga.

[0106] The user's historical running data comes from the smart wearable devices they have used for a long time, such as smart watches or sports bracelets. These devices can record the start and end times of the user's sports, heart rate changes, steps, sports modes (such as running, cycling, or stationary), and more high-frequency data based on sensors. These data are synchronized to the cloud through the device and the supporting software to form a complete user sports profile. The system can call the data related to the target sports in these profiles and conduct comprehensive analysis in combination with the user's real-time needs and 3D measurement models, so as to more accurately recommend sports clothing that meets the requirements.

[0107] Furthermore, the clothing recommendation system based on 3D body measurement further includes:

[0108] The line graph analysis module 200 is used to draw a line graph of the movement trend based on historical operation data, analyze the change trend of the line graph of the movement trend. If it shows that the movement trend presents a continuous decreasing trend, calculate the average slope of the line graph of the movement trend and use it as the first optimization factor.

[0109] Specifically, Figure 6 The structural block diagram of the line graph analysis module 200 in the system provided by the embodiment of the present invention is shown.

[0110] Among them, in the preferred embodiment provided by the present invention, the line graph analysis module 200 specifically includes:

[0111] The first data parsing unit 201 is used to parse the historical operation data recorded by the user's wearable device, select the local data within the specified time window, extract the timestamps and movement durations of the user's each target movement item from the local data, and apply data denoising processing to filter out outliers and noise interference, and organize to obtain a time series data set;

[0112] The line graph drawing unit 202 is used to draw a line graph of the movement trend based on the time series data set, with time as the horizontal axis and movement duration as the vertical axis.

[0113] The average slope calculation unit 203 is used to analyze the change trend of the line graph of the movement trend. If the change trend shows a continuous decrease, calculate the average slope of the line graph of the movement trend to quantify the rate of the decreasing movement trend, and use it as the first optimization factor.

[0114] In the embodiment of the present invention, when parsing the historical operation data recorded by the user's wearable device, it is necessary to select the local data within the specified time window to centrally analyze the user's movement behavior within a specific time period. The significance of this selection is to reduce the interference of irrelevant data, highlight the analysis of the user's recent movement rules, and thus more accurately reflect the user's current movement habits and trend changes. By extracting the timestamps and movement durations of the target movement item and applying data denoising processing, noise data caused by device errors, user abnormal behaviors or environmental interference can be filtered out to ensure the quality and credibility of the data set. The organized time series data set provides a reliable basis, laying a data foundation for subsequent drawing of the line graph of the movement trend and analysis of its change trend.

[0115] After plotting a line graph of the motion trend with time on the horizontal axis and the duration of the motion on the vertical axis, the system can visually display the trend of time changes of the user in the target sports event. If the number of times the user performs the target sport is less than the preset analysis frequency standard, there is insufficient data support, and at this time, the analysis is of little significance. The system will abandon the trend analysis and recommend clothing according to the initial flexibility parameters. If the amount of data reaches the analysis standard, it is judged whether there is a significant continuous change in the user's exercise pattern by analyzing the change trend of the line graph. If the change trend is not continuously decreasing, it means that the duration of the user's exercise has not decreased significantly. The system will consider that the user's exercise state remains stable. Therefore, clothing is still recommended according to the initial flexibility parameters without additional adjustment.

[0116] Analyzing the change trend of the line graph of the motion trend and calculating the average slope are of great significance. If the change trend of the line graph shows a continuous decrease, calculating its average slope can quantify the rate of decrease in the user's motion trend. The average slope of the decreasing trend is used as the first optimization factor to dynamically adjust the flexibility parameters, so as to provide targeted support for the recommended sports clothing. For example, when the duration of the user's exercise decreases significantly, the optimization factor can prompt the system to recommend clothing with lower flexibility and suitable for the decreased exercise intensity. The advantage of this process is that the system dynamically adjusts the recommendation strategy according to the user's actual exercise trend, making the recommendation result more in line with the user's current exercise needs and improving the accuracy and scientific nature of personalized recommendations.

[0117] Furthermore, the clothing recommendation system based on 3D body measurement further includes:

[0118] A muscle fatigue state analysis module 300, which is used to analyze the user's historical operation data, screen out the muscle fatigue state data when the user reaches a specific intensity level in the target sports event, calculate the average value of the muscle fatigue state, compare this average value with the preset muscle fatigue reference threshold, quantify the difference between the two, and use this difference as the second optimization factor.

[0119] Specifically, Figure 7 The structural block diagram of the muscle fatigue state analysis module 300 in the system provided by the embodiment of the present invention is shown.

[0120] Among them, in the preferred embodiment provided by the present invention, the muscle fatigue state analysis module 300 specifically includes:

[0121] A second data analysis unit 301, which is used to analyze the user's historical operation data, screen out the records related to the target sports event, and further screen out the exercise segments that meet the intensity requirements according to the set intensity threshold, and extract the muscle fatigue state data from these exercise segments. The muscle fatigue state data includes the heart rate recovery duration;

[0122] An average value determination unit 302 is configured to count the heart rate recovery durations of all the selected exercise segments and calculate their average value to quantify the overall muscle fatigue level of the user.

[0123] A difference degree calculation unit 303 is configured to compare the calculated average value of the muscle fatigue state with a preset reference fatigue threshold, quantify the difference degree therebetween, and use the difference degree as a second optimization factor.

[0124] In the embodiment of the present invention, the set intensity threshold is derived based on the characteristics of the target exercise item and the physical ability of the user. According to existing sports science research, different exercise items have different requirements for intensity. For example, for high-intensity running, the heart rate reaching more than 75% of the maximum heart rate may be used as a benchmark, while for weightlifting, it may be judged based on the acceleration recorded by the sensor reaching a certain specific threshold. The setting of the intensity threshold needs to combine the typical exercise load characteristics of the exercise item itself and the distribution of similar exercise intensities in the user's historical data, so as to ensure that the selected segments can truly reflect the user's high-intensity exercise state.

[0125] The muscle fatigue state data may include other physiological indicators in addition to the heart rate recovery duration, such as the respiratory recovery time, the lactate clearance rate, or the subjective fatigue score. The calculation process should be consistent, and relevant parameters need to be extracted from the post-exercise recovery data and quantified in the form of time or ratio. For example, the respiratory recovery time can be calculated by the time when the respiratory rate returns to the resting level from the end of the exercise, and the lactate clearance rate can be measured by the time when the blood lactate level returns to the baseline value after the exercise. All these indicators can reflect the muscle fatigue state from different dimensions, and the calculation method is the same as that of the heart rate recovery duration to ensure the unity of the data.

[0126] The reason why counting the heart rate recovery durations of all the selected exercise segments and calculating their average value can quantify the overall muscle fatigue level of the user is that the average value can comprehensively reflect the user's recovery ability after multiple high-intensity exercises. The length of the recovery time is directly related to the user's fatigue degree and physical adaptability. A longer average recovery time means a higher fatigue degree of the user after exercise, while a shorter recovery time indicates a stronger physical adaptability of the user. Therefore, the average value is an effective statistical indicator and can provide integral quantitative data for subsequent analysis.

[0127] The preset reference fatigue threshold is derived based on the recovery ability standard of healthy exercise populations or the user's historical recovery ability performance. The recovery time data of healthy individuals in existing sports physiology research can be combined as a reference value. For example, a decrease of 20 beats per minute in heart rate recovery within 1 minute may be used as a standard value. In addition, the user's long-term data can also be used to dynamically adjust the threshold. For example, the average heart rate recovery duration of the user over a long period can be used as their personalized reference value.

[0128] The significance of using the degree of difference as an optimization factor is that it can dynamically reflect the deviation between the user's actual physical state and the ideal reference value, helping the system to more accurately adapt to the user's needs. By quantifying the degree of difference between the two, the system can determine whether the user needs clothing with higher flexibility to relieve fatigue, or whether the flexibility requirement can be appropriately reduced to expand the recommended options. The advantage of this dynamic optimization is that it can adjust the recommendation strategy based on the user's actual physiological performance, making the recommendation more scientific and personalized, avoiding a one-size-fits-all static recommendation method, and providing the user with a more comfortable and suitable choice of sports clothing.

[0129] Furthermore, the 3D body measurement-based clothing recommendation system further includes:

[0130] A flexibility parameter adjustment module 400, configured to comprehensively adjust the basic flexibility parameters by combining the first optimization factor and the second optimization factor, and finally calculate the optimized dynamic flexibility parameters.

[0131] Specifically, Figure 8 FIG. shows the structural block diagram of the flexibility parameter adjustment module 400 in the system provided by the embodiment of the present invention.

[0132] Among them, in the preferred embodiment provided by the present invention, the flexibility parameter adjustment module 400 specifically includes:

[0133] A flexibility parameter adjustment unit 401, configured to comprehensively adjust the basic flexibility parameters by combining the first optimization factor and the second optimization factor, and call the flexibility parameter optimization formula to calculate the optimized dynamic flexibility parameters;

[0134] A flexibility parameter application unit 402, configured to apply the optimized dynamic flexibility parameters to the 3D body measurement-based clothing recommendation.

[0135] The flexibility parameter optimization formula is: F opt = F base ×(1 + S trend ×C1 + S fatigue ×C2), where Fopt refers to the dynamic flexibility parameter, F base refers to the basic flexibility parameter, S trendRefers to the first optimization factor, i.e., the average slope of the movement trend line graph. C1 refers to the adjustment coefficient related to the movement trend, S fatigue Refers to the second optimization factor, i.e., the degree of difference between the average value of the muscle fatigue state and the preset muscle fatigue reference threshold. C2 refers to the adjustment coefficient related to the muscle fatigue state;

[0136] In the flexibility parameter optimization formula, where n refers to the total number of times the user performs the target sports event in the local data, T i refers to the duration of the i-th target sports event;

[0137] In the flexibility parameter optimization formula, where R avg refers to the average value of the muscle fatigue state, R ref refers to the preset reference fatigue threshold.

[0138] In the embodiments of the present invention, by combining the first optimization factor and the second optimization factor, the basic flexibility parameters are comprehensively adjusted. Through the flexibility parameter optimization formula, the analysis results of the movement trend and the muscle fatigue state are linked, making the adjustment process more dynamic and personalized. The first optimization factor can accurately predict the change of the user's movement demand in the future period by quantifying the change of the user's movement trend, especially the decreasing rate of the movement duration; the second optimization factor reflects the current physical recovery ability through the degree of difference of the user's actual fatigue state. The combination of these two optimization factors enables the adjustment of the flexibility parameters to not only adapt to the user's future movement trend but also meet the user's current physiological state requirements, realizing the balance and pertinence of dynamic adjustment.

[0139] This linkage mechanism makes up for two major deficiencies in the prior art. First, traditional clothing recommendation systems mostly rely on static data or single factors (such as body size or clothing classification) for matching, and it is difficult to dynamically adapt to the changes in the user's movement habits or body states. By incorporating both the movement trend and the fatigue state into the analysis, the present invention realizes multi-dimensional data linkage, avoiding the errors or limitations that may be brought by a single optimization factor. Second, the prior art usually lacks the ability to predict the user's future needs and cannot consider the dynamic adjustment of the user's movement intensity change or fatigue degree in the recommendation. By introducing the first optimization factor, the present invention integrates the prediction of the future trend into the recommendation process, making up for the short-sightedness of traditional methods.

[0140] The advantage of this linkage adjustment is that the optimized dynamic flexibility parameters better meet the actual needs of users. For example, when the user's exercise trend declines and the fatigue level is high, the recommended clothing will increase flexibility to provide higher comfort and relief; when the user's exercise trend is stable and the fatigue level is low, the recommended clothing can reduce the flexibility requirement, broaden the clothing selection range, and ensure exercise support at the same time. Through this dynamic optimization, the system not only improves the accuracy and scientific nature of the recommendation, but also enhances the comfort and diversity of the user experience, making the recommendation results more practical and intelligent.

[0141] The following further illustrates the technical solution of the present invention through an example:

[0142] Suppose a user chooses to try on running clothing. The system first generates basic flexibility parameters for the user through 3D body measurement technology. Suppose the initial value of the basic flexibility parameter is 20. Subsequently, the system analyzes the user's historical exercise data, selects relevant running exercise segments within a specified time window, extracts the duration of each run, and plots a line graph of the exercise trend. By analyzing the line graph, it is found that the user's exercise trend shows a continuous decreasing state. The system calculates that the average slope of the decreasing exercise duration is -0.1, and the adjustment coefficient set for the exercise trend correction is 0.5. Through calculation, the correction value of the exercise trend to the flexibility parameter is -0.05.

[0143] At the same time, the system further screens the user's high-intensity running exercise segments, extracts the data of the heart rate recovery duration after exercise, and calculates that the average value of the user's heart rate recovery duration is 80 seconds. Comparing it with the preset reference fatigue threshold of 60 seconds, the deviation degree of the fatigue state is calculated to be 0.33. Combining the adjustment coefficient of 0.3 for the fatigue state correction, the correction value of the fatigue state to the flexibility parameter is +0.099.

[0144] Finally, the system comprehensively adjusts the two correction values with the basic flexibility parameter. Adding -0.05 and +0.099 gives a total correction value of +0.049. Combining with the basic flexibility parameter of 20, the optimized dynamic flexibility parameter is calculated to be 20.98. The system applies this optimized dynamic flexibility parameter to the clothing recommendation of 3D body measurement. The recommended running clothing can better fit the user's exercise trend and fatigue state, taking into account the user's comfort requirements while providing support.

[0145] It should be understood that although the steps in the flowcharts of the embodiments of the present invention are shown in sequence according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless there is a clear indication in this article, the execution of these steps has no strict order limit, and these steps can be executed in other orders. Moreover, at least a part of the steps in each embodiment may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily executed at the same moment, but can be executed at different moments. The execution order of these sub-steps or stages is not necessarily sequential, but can be executed alternately or in turn with at least a part of other steps or sub-steps or stages of other steps.

[0146] Those of ordinary skill in the art can understand that all or part of the processes of implementing the methods in the above embodiments can be completed by instructing relevant hardware through a computer program. The program can be stored in a non-volatile computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above methods. Among them, any reference to a memory, storage, database, or other medium used in the embodiments provided in the present application can include non-volatile and / or volatile memories. Non-volatile memories can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memories can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), Rambus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and Rambus dynamic RAM (RDRAM), etc.

[0147] The technical features of the above-described embodiments can be combined arbitrarily. For the sake of brevity of description, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered as the scope described in this specification.

[0148] The above-described embodiments merely represent several implementation manners of the present invention. The description thereof is relatively specific and detailed, but it should not be construed as a limitation on the scope of the patent for the present invention. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present invention, several modifications and improvements can still be made, and these all belong to the protection scope of the present invention. Therefore, the protection scope of the patent for the present invention shall be subject to the appended claims.

[0149] The foregoing is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims

1. A clothing recommendation method based on 3D body measurement, characterized in that, The method includes: Determine the category of sports clothing required by the user, and based on this, deduce the user's target sports event and the corresponding core sports parts. Obtain the basic flexibility parameters related to the core sports parts based on 3D body measurement technology, and at the same time obtain the historical operation data recorded by the user's wearable device; Draw a sports trend line chart based on the historical operation data, and analyze the change trend of the sports trend line chart. If the displayed sports trend shows a continuous decreasing trend, calculate the average slope of the sports trend line chart and use it as the first optimization factor; Analyze the user's historical operation data, screen out the muscle fatigue state data when the user reaches a specific intensity level in the target sports event, calculate the average value of the muscle fatigue state, compare this average value with the preset muscle fatigue reference threshold, quantify the difference between the two, and use this difference as the second optimization factor; Combine the first optimization factor and the second optimization factor to comprehensively adjust the basic flexibility parameters, and finally calculate the optimized dynamic flexibility parameters.

2. The dressing recommendation method based on 3D body measurement according to claim 1, wherein, The steps of drawing a sports trend line chart based on the historical operation data, and analyzing the change trend of the sports trend line chart. If the displayed sports trend shows a continuous decreasing trend, calculate the average slope of the sports trend line chart and use it as the first optimization factor include: Analyze the historical operation data recorded by the user's wearable device, select the local data within the specified time window, extract the timestamp and exercise duration of the user's each target sports event from the local data, and apply data denoising processing to filter out outliers and noise interference, and organize to obtain a time series data set; Based on the time series data set, draw a sports trend line chart with time as the horizontal axis and exercise duration as the vertical axis; Analyze the change trend of the sports trend line chart. If the change trend shows a continuous decrease, calculate the average slope of the sports trend line chart to quantify the rate of decrease of the sports trend, and use it as the first optimization factor.

3. The dressing recommendation method based on 3D body measurement according to claim 1, characterized in that The steps of analyzing the user's historical operation data, screening out the muscle fatigue state data when the user reaches a specific intensity level in the target sports event, calculating the average value of the muscle fatigue state, comparing this average value with the preset muscle fatigue reference threshold, quantifying the difference between the two, and using this difference as the second optimization factor include: Analyze the user's historical operation data, screen out the records related to the target sports event, and further screen out the exercise segments that meet the intensity requirements according to the set intensity threshold. Extract the muscle fatigue state data from these exercise segments, and the muscle fatigue state data includes the heart rate recovery duration; Statistically analyze the heart rate recovery durations of all the screened exercise segments, calculate their average value to quantify the user's overall muscle fatigue level; Compare the calculated average value of the muscle fatigue state with the preset reference fatigue threshold, quantify the difference between the two, and use this difference as the second optimization factor.

4. The clothing recommendation method based on 3D body measurement according to claim 1, wherein The steps of combining the first optimization factor and the second optimization factor to comprehensively adjust the basic flexibility parameters, and finally calculate the optimized dynamic flexibility parameters include: Combined with the first optimization factor and the second optimization factor, call the flexibility parameter optimization formula to comprehensively adjust the basic flexibility parameters and calculate the optimized dynamic flexibility parameters; Apply the optimized dynamic flexibility parameters to clothing recommendations based on 3D body measurements.

5. The dressing recommendation method based on 3D body measurement according to claim 4, characterized in that The optimized formula for the flexibility parameter is: F opt = F base ×(1 + S trend ×C1 + S fatigue ×C2), where Fopt refers to the dynamic flexibility parameter, F base refers to the basic flexibility parameter, S trend refers to the first optimization factor, i.e., the average slope of the movement trend line graph, C1 refers to the adjustment coefficient related to the movement trend, S fatigue refers to the second optimization factor, i.e., the difference between the average value of the muscle fatigue state and the preset muscle fatigue reference threshold, C2 refers to the adjustment coefficient related to the muscle fatigue state; In the flexibility parameter optimization formula, where n refers to the total number of times the user performs the target sports event in the local data, and T i refers to the duration of the i-th target sports event; In the flexibility parameter optimization formula, where R avg refers to the average value of muscle fatigue state, and R ref refers to the preset reference fatigue threshold.

6. A dressing recommendation system based on 3D body measurement, characterized in that, The system includes: a data acquisition module, a line graph analysis module, a muscle fatigue state analysis module, and a flexibility parameter adjustment module, where: The data acquisition module is used to determine the category of sports clothing required by the user, and based on this, deduce the user's target sports item and the corresponding core sports part, obtain the basic flexibility parameters related to the core sports part based on 3D body measurement technology, and at the same time obtain the historical operation data recorded by the user's wearable device; The line graph analysis module is used to draw a sports trend line graph based on the historical operation data and analyze the change trend of the sports trend line graph. If it shows that the sports trend shows a continuous decreasing trend, calculate the average slope of the sports trend line graph and use it as the first optimization factor; The muscle fatigue state analysis module is used to analyze the user's historical operation data, filter out the muscle fatigue state data when the user reaches a specific intensity level in the target sports item, calculate the average value of the muscle fatigue state, compare this average value with the preset muscle fatigue reference threshold, quantify the difference between the two, and use this difference as the second optimization factor; The flexibility parameter adjustment module is used to combine the first optimization factor and the second optimization factor to comprehensively adjust the basic flexibility parameters and finally calculate the optimized dynamic flexibility parameters.

7. The dressing recommendation system based on 3D body measurement according to claim 6, wherein The line graph analysis module specifically includes: The first data analysis unit is used to analyze the historical operation data recorded by the user's wearable device, select the local data within the specified time window, extract the timestamp and exercise duration of the user's each target sports item from the local data, and apply data denoising processing to filter out outliers and noise interference, and organize to obtain a time series data set; The line graph drawing unit is used to draw a sports trend line graph based on the time series data set, with time as the horizontal axis and exercise duration as the vertical axis; The average slope calculation unit is used to analyze the change trend of the sports trend line graph. If the change trend shows a continuous decrease, calculate the average slope of the sports trend line graph to quantify the rate of decrease of the sports trend and use it as the first optimization factor.

8. The dressing recommendation system based on 3D body measurement according to claim 7, characterized in that The muscle fatigue state analysis module specifically includes: The second data analysis unit is used to analyze the user's historical operation data, filter out the records related to the target sports item, and further filter out the exercise segments that meet the intensity requirements according to the set intensity threshold, and extract the muscle fatigue state data from these exercise segments. The muscle fatigue state data includes the heart rate recovery duration; The average value determination unit is used to count the heart rate recovery durations of all the filtered exercise segments and calculate their average value to quantify the user's overall muscle fatigue level; The difference calculation unit is used to compare the calculated average value of the muscle fatigue state with the preset reference fatigue threshold, quantify the difference between the two, and use this difference as the second optimization factor.

9. The dressing recommendation system based on 3D body measurement according to claim 8, characterized in that The muscle fatigue state analysis module specifically includes: A flexibility parameter adjustment unit, which is used to combine a first optimization factor and a second optimization factor, call a flexibility parameter optimization formula, comprehensively adjust the basic flexibility parameters, and calculate the optimized dynamic flexibility parameters; A flexibility parameter application unit, which is used to apply the optimized dynamic flexibility parameters to clothing recommendations based on 3D body measurements.

10. The dressing recommendation system based on 3D body measurement according to claim 9, wherein The flexibility parameter optimization formula is: F opt = F base ×(1 + S trend ×C1 + S fatigue ×C2), where Fopt refers to the dynamic flexibility parameter, F base refers to the basic flexibility parameter, S trend refers to the first optimization factor, i.e., the average slope of the motion trend line graph, C1 refers to the adjustment coefficient related to the motion trend, S fatigue refers to the second optimization factor, i.e., the difference between the average value of the muscle fatigue state and the preset muscle fatigue reference threshold, C2 refers to the adjustment coefficient related to the muscle fatigue state; In the flexibility parameter optimization formula, where n refers to the total number of times the user performs the target sports event in the local data, and T i refers to the duration of the i-th target sports event; In the flexibility parameter optimization formula, where R avg refers to the average value of muscle fatigue state, and R ref refers to the preset reference fatigue threshold.

Images