An unconstrained wearable smart sensing device and method for ed patients

Abstract

This invention relates to a restraint-free wearable intelligent sensing device and method for patients with erectile dysfunction (ED), belonging to the field of medical monitoring equipment and technology. The device includes an underwear-like main structure, a data acquisition unit, a micro-control module, a power supply module, and an electrical stimulation module. The underwear-like main structure has a data acquisition and monitoring area composed of multiple annular fiber sensing units arranged in a columnar elephant trunk structure. Each annular fiber sensing unit has an independent pressure-sensitive fiber sensing module. The data acquisition unit collects the wearer's pressure and temperature data in real time. The micro-control module is connected to the data acquisition unit to process and transmit the data collected. The method employs a multi-sensor signal processing stage algorithm and a cloud-based monitoring and closed-loop control stage algorithm. Based on the acquired loop-level monitoring data, it provides real-time feedback and prompts for adjustments, improving treatment convenience and personalization, and providing a more comprehensive, precise, and restraint-free solution for ED monitoring.

Description

Technical Field

[0001] This invention belongs to the field of medical monitoring equipment and technology, and relates to an unrestrained wearable intelligent sensing device and method for ED patients. Background Technology

[0002] Current clinical diagnosis of erectile dysfunction (ED) relies heavily on nocturnal penile erection monitoring technology. Traditional monitoring devices typically use rigid ring sensors that require mechanical fixation to the patient's penis. These devices have significant drawbacks: first, they are physically restrictive, complex to wear, and cause noticeable foreign body sensation, interfering with natural sleep and affecting the accuracy of monitoring results; second, they have a single sensing dimension, only acquiring information on local circumference changes and failing to capture the three-dimensional mechanical distribution characteristics of the erection process; third, the devices have poor breathability and are bulky, easily causing skin discomfort or even damage with prolonged wear, making reliable monitoring over multiple days difficult. Furthermore, existing electrical stimulation-assisted erection technologies mostly use rigid electrodes and external pulse generators, which are not only uncomfortable and difficult to integrate with monitoring systems, but also lack flexible fit and precise control capabilities, limiting their application in home or long-term monitoring scenarios.

[0003] While flexible fabric sensors, which have emerged in recent years, have improved wearing comfort to some extent, they still have fundamental limitations. The dense conductive structure used to achieve electrical performance severely hinders skin breathability and perspiration, increasing the risk of long-term biocompatibility issues; the limited number of sensor units and insufficient spatial resolution make it difficult to accurately reconstruct the dynamic changes in erectile biomechanics; at the same time, there is a lack of effective suppression of body movement interference, and noise generated by daily activities or turning over in sleep can easily mask true physiological signals. Summary of the Invention

[0004] In view of this, the purpose of the present invention is to provide an unrestrained wearable intelligent sensing device and method for patients with erectile dysfunction (ED).

[0005] To achieve the above objectives, the present invention provides the following technical solution: On one hand, a restraint-free wearable intelligent sensing device for ED patients is provided. This device includes an underwear-like main structure, a data acquisition unit, a micro-control module, a power supply module, and an electrical stimulation module. The underwear-like main structure has a cylindrical elephant trunk-shaped data acquisition and monitoring area. The data acquisition unit includes multiple annular fiber sensing units arranged to form the cylindrical elephant trunk-shaped monitoring area. Each annular fiber sensing unit has a built-in independent pressure-sensitive fiber sensing module. The data acquisition unit collects the wearer's pressure and temperature data in real time. The micro-control module is connected to the data acquisition unit to process and transmit the data collected. The electrical stimulation module includes a flexible electrode array, a pulse generator, and a controller. The flexible electrode array is centrally located at the front end of the cylindrical elephant trunk-shaped structure, and the pressure-sensitive fiber sensing module, composed of multiple annular fiber sensing units, is arranged along the axial direction of the cylindrical elephant trunk-shaped structure. The power supply module supplies power to each unit or module. The device also includes a cloud-based monitoring system for data analysis. The micro-control module transmits the data collected by the data acquisition unit to the cloud for analysis and feeds back the analysis results to the user terminal.

[0006] Furthermore, the main body structure, resembling underwear, consists of a front panel, a back panel, and a waistband. The front panel is the data acquisition and monitoring area of ​​the columnar elephant trunk structure, which is connected to the micro-control module via wires. The front panel is composed of a ring-shaped structure woven from temperature and pressure sensitive fibers made of temperature and pressure sensitive material, combined with highly breathable fabric. The back panel is made of highly breathable fiber fabric. The waistband area is the encapsulation area, which internally encapsulates the power module and the micro-control module in a detachable manner, and the outer layer is a waterproof coating.

[0007] Furthermore, the multiple ring-shaped fiber sensing units of the data acquisition unit are shaped in a biomimetic manner to fit the shape curve of the male reproductive organ, and each pressure-sensitive fiber sensing module inside includes a conductive elastic inner core and a temperature and pressure sensitive shell.

[0008] Furthermore, the micro control module is connected to the data acquisition unit, which includes a signal processing unit and a wireless transmission unit. The signal processing unit filters, amplifies, and standardizes the acquired signals, and the processed data is sent to the user's mobile device or cloud monitoring system through the wireless transmission unit. The micro control module and the power module are located on the waistband side of the underwear-shaped main structure.

[0009] Furthermore, the electrical stimulation module serves as the intervention execution end of the closed-loop system. The pulse generator produces therapeutic pulses to perform electrical stimulation; the controller is used to start and stop electrical stimulation treatment according to the corresponding algorithm; and the flexible electrode array is used to stimulate the nerves of the erectile corpus cavernosum.

[0010] Furthermore, the cloud-based monitoring system, serving as the monitoring and decision-making hub of the closed-loop system, includes a receiving unit, an analysis unit, a display unit, and a threshold alarm unit. The receiving unit receives wirelessly transmitted data from the micro-control module and transmits it to the display unit. The analysis unit analyzes the standardized data transmitted by the WeChat control module and transmits the analysis results to the display unit. The display unit visualizes the pressure and temperature data, as well as the final analysis results, in the form of charts or images. The threshold alarm unit triggers an alarm when the data exceeds the threshold set by the user, reminding the user to take appropriate measures.

[0011] On the other hand, a restraint-free wearable intelligent sensing method for ED patients is also provided. This method is mounted on the aforementioned restraint-free wearable intelligent sensing device, wherein... The method includes a multi-ring sensing signal processing stage. The multi-ring sensing signal processing algorithm is built into the micro control module. The multi-ring sensing signal processing algorithm combines several ring-shaped fiber sensing units arranged along the axial direction to differentiate the signals collected by different ring-shaped fiber sensing units and complete the conversion and standardization from the original electrical signal to pressure or temperature physical quantities. The method also includes a cloud monitoring and closed-loop control stage. The algorithm for the cloud monitoring and closed-loop control stage is mounted on the cloud monitoring system. It centrally stores, extracts spatiotemporal features, assesses risks and sets dynamic thresholds for the multi-loop temperature and pressure data uploaded by the micro-control module, and feeds back the monitoring results and intervention strategies to the electrical stimulation module.

[0012] Furthermore, in the multi-loop sensor signal processing stage, the process is as follows: Assume that it is provided along the axial direction The first ring-shaped fiber sensing unit, the first Each ring-shaped fiber sensing unit is denoted as a channel. , At the sampling time The original electrical signal output by this channel is denoted as . ; The block synchronously samples all the annular fiber sensing units at a preset sampling frequency to form a multi-channel time series:

[0013] Each channel signal is subjected to moving average filtering to suppress high-frequency noise and random jitter. Let the moving window length be... The filtered signal is:

[0014] Perform first-order difference processing on the filtered signal:

[0015] Filtering and first-order differential processing are performed independently on each ring sensing channel, achieving ring-level preprocessing of the original signal. For each annular fiber sensing unit, a calibration model is established between electrical quantities and pressure or temperature, where the first... The electrical quantity-pressure relationship of each ring is expressed as follows:

[0016] in, For a moment The instantaneous resistance value, This is the reference resistance for the loop in its resting state. and In order to target the The parameters of each loop were obtained through calibration experiments. This corresponds to the pressure value; No. The electrical quantity-temperature relationship of each ring is expressed as follows:

[0017] in, These are temperature-dependent electrical quantities. , For the first Temperature calibration coefficients for each ring-shaped fiber sensing unit; Pressure sequence for each loop during the baseline period. Calculate the mean and standard deviation :

[0018]

[0019] in, For the baseline sample set, Number of sample points In the real-time phase, the real-time pressure data is standardized to obtain dimensionless standardized pressure:

[0020] Standardized multi-circular sequences It can reflect the degree of deviation of the current state from the individual's resting state. Different weights are assigned to each channel based on the location and reliability of the ring. Furthermore, each ring is divided into a root region, a middle region, and a distal region based on its anatomical location, and each region is assigned a different weight.

[0021] By adjusting the assigned weights, the short-term variance and the degree of difference with adjacent rings are calculated for each ring within the sliding time window. When the variance of a certain ring fiber sensing unit is continuously abnormal or the pressure difference with adjacent rings exceeds a preset threshold, the ring is marked as a low reliability channel, and its weight is reduced or temporarily blocked in subsequent data fusion.

[0022] Furthermore, the risk level assessment process during the cloud-based monitoring and closed-loop control phase is as follows: Receive multi-loop normalized pressure sequence uploaded from the microcontroller module and corresponding pressure values Based on window length and step length The data is segmented, the first... The sample set corresponding to each time window is:

[0023] Within each time window, the cloud extracts time-domain features for each ring-shaped sensing channel, forming a channel feature vector. Time-domain features include, but are not limited to: Standardized mean pressure:

[0024] Pressure variance:

[0025] Peak pressure and peak-to-trough difference:

[0026] Then the channel feature vector Represented as:

[0027] The coordinates of the geometric centers of each ring along the axial direction are defined as follows: And within each time window, the following spatial features are constructed: Pressure center location:

[0028] in, For the first in the window The average pressure of each ring, and the location of the pressure center indicate whether the pressure is mainly concentrated at the root, distal end or middle section; Axial pressure gradient:

[0029] gradient vector It is used to reflect whether there is unevenness in local collapse or segmented erection along the axial direction. Multi-ring synchronization index: Calculates the pairwise correlation coefficients of each channel within the calculation window. And based on this, the overall synchronicity index is obtained:

[0030] in, A value greater than or equal to the preset value indicates that the signal change trends of each loop are consistent. If the value is lower than the preset value, it indicates the presence of local abnormalities or body movement interference; The time-domain features of each ring are concatenated with the aforementioned spatial features to construct a multi-dimensional comprehensive feature vector:

[0031] An erectile quality assessment model was established based on clinically labeled data, using a support vector machine as its foundation. Its decision function is expressed as follows:

[0032] in, For the training sample feature vector, For tags, For Lagrange multipliers, For kernel function, For bias terms; Map the output of the decision function to a probability value of erectile dysfunction:

[0033] Based on historical follow-up data and individual baseline information, multi-level dynamic probability thresholds are set. and the corresponding duration threshold When satisfied At that time, determine the current risk level and output the risk level. .

[0034] Furthermore, the closed-loop control process of the electrical stimulation module based on the monitoring results during the cloud-based monitoring and closed-loop control phase is as follows: Risk probability Mapped to the electrical stimulation intensity control variable, a piecewise linear control strategy is adopted, and the electrical stimulation intensity... satisfy:

[0035] in, , This is the gain coefficient. The initial stimulus intensity is of medium level. This is the preset safety limit.

[0036] The beneficial effects of this invention are as follows: This invention improves and integrates structural design and three levels of "sensing-monitoring-intervention". At the sensing level, a unique biomimetic elephant trunk structure is used to divide the monitoring area into multiple ring-shaped fiber sensing units, each ring being an independent pressure-sensitive fiber sensing module. Thanks to the material's excellent elasticity and softness, it can tightly wrap the entire penile area without applying any restraint or pressure, achieving high-density, layered monitoring along the axial direction. The overall structure is thin, flexible, and highly breathable, significantly improving wearing comfort and a restrained experience. At the monitoring level, this invention uploads multi-ring temperature and pressure data to a cloud monitoring system in real time via a micro-control module. Utilizing multi-dimensional temporal and spatial characteristics, it continuously monitors and intelligently analyzes the erection process, achieving a refined assessment of erectile morphology, intensity, and stability in cases of erectile dysfunction (ED), and constructing an individualized dynamic threshold and risk warning mechanism. At the intervention level, this invention deeply couples a flexible electrode array and an electrical stimulation pulse generator with the aforementioned monitoring system. Based on the monitoring results, it grades and adaptively adjusts the electrical stimulation intensity and mode, forming a closed-loop treatment path of "sensing-monitoring-intervention-reassessment".

[0037] Other advantages, objectives, and features of the invention will be set forth in part in the description which follows, and in part will be apparent to those skilled in the art from the following examination, or may be learned from practice of the invention. The objectives and other advantages of the invention can be realized and obtained through the following description. Attached Figure Description

[0038] To make the objectives, technical solutions, and advantages of the present invention clearer, the preferred embodiments of the present invention will be described in detail below with reference to the accompanying drawings, wherein: Figure 1 This is a schematic diagram of the overall modular structure of the unconstrained wearable intelligent sensing device according to an embodiment of the present invention; Figure 2 This is a schematic diagram of the underwear-shaped main body structure according to an embodiment of the present invention; Figure 3 This is a schematic diagram of the fine structure of the data acquisition and monitoring area of ​​the columnar elephant trunk structure in an embodiment of the present invention; Figure 4 This is a schematic diagram of the hardware module of the micro control module according to an embodiment of the present invention; Figure 5 This is a schematic diagram illustrating the risk level assessment process during the cloud-based monitoring and closed-loop control phase in an embodiment of the present invention. Figure 6 This is a schematic diagram of the process of performing closed-loop control of the electrical stimulation module based on the monitoring results during the cloud monitoring and closed-loop control stage according to an embodiment of the present invention. Detailed Implementation

[0039] The following specific examples illustrate the implementation of the present invention. Those skilled in the art can easily understand other advantages and effects of the present invention from the content disclosed in this specification. The present invention can also be implemented or applied through other different specific embodiments, and various details in this specification can be modified or changed based on different viewpoints and applications without departing from the spirit of the present invention. It should be noted that the illustrations provided in the following embodiments are only schematic representations of the basic concept of the present invention. Unless otherwise specified, the following embodiments and features can be combined with each other.

[0040] The accompanying drawings are for illustrative purposes only and are schematic diagrams, not actual pictures. They should not be construed as limiting the invention. To better illustrate the embodiments of the invention, some parts in the drawings may be omitted, enlarged, or reduced, and do not represent the actual product dimensions. It is understandable to those skilled in the art that some well-known structures and their descriptions may be omitted in the drawings.

[0041] In the accompanying drawings of the embodiments of the present invention, the same or similar reference numerals correspond to the same or similar components. In the description of the present invention, it should be understood that if terms such as "upper," "lower," "left," "right," "front," and "rear" indicate the orientation or positional relationship based on the orientation or positional relationship shown in the drawings, they are only for the convenience of describing the present invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, the terms used to describe positional relationships in the drawings are only for illustrative purposes and should not be construed as limiting the present invention. For those skilled in the art, the specific meaning of the above terms can be understood according to the specific circumstances.

[0042] Please see Figures 1-6 This invention relates to an unconstrained wearable intelligent sensing device and method for patients with erectile dysfunction (ED).

[0043] Example 1 This embodiment first provides a constraint-free wearable intelligent sensing device for patients with erectile dysfunction (ED). For example... Figure 1As shown, the device includes an underwear-shaped main structure, a data acquisition unit, a micro-control module, a power supply module, and an electrical stimulation module. The underwear-shaped main structure has a cylindrical elephant trunk-shaped data acquisition and monitoring area. The data acquisition unit includes multiple annular fiber sensing units arranged to form the cylindrical elephant trunk-shaped monitoring area. Each annular fiber sensing unit has a built-in independent pressure-sensitive fiber sensing module. The data acquisition unit collects the wearer's pressure and temperature data in real time. The micro-control module is connected to the data acquisition unit to process and transmit the data collected. The electrical stimulation module includes a flexible electrode array, a pulse generator, and a controller. The flexible electrode array is centrally located at the front end of the cylindrical elephant trunk-shaped structure, while the pressure-sensitive fiber sensing module, composed of multiple annular fiber sensing units, is arranged along the axial direction of the cylindrical elephant trunk-shaped structure. The power supply module supplies power to each unit or module.

[0044] like Figure 2 The diagram shows the structural design of the underwear-like main body. This main body is made of highly breathable fabric (such as Coolmax fiber or bamboo fiber), and its overall design conforms to the curves of the human body, ensuring comfort and stability during wear. The underwear-like main body includes a front panel, a back panel, and a waistband. The front panel is the data acquisition and monitoring area of ​​the columnar elephant trunk structure, which is connected to the micro-control module via wires. The front panel consists of a ring-shaped structure woven from temperature and pressure sensitive fibers made of temperature and pressure sensitive material, combined with highly breathable fabric. Its special three-dimensional design adapts to the physiological structure of the genital area, ensuring a good fit to the skin. The pressure-sensitive fiber material is the core functional component of the underwear. It is connected to the micro-control module via wires to ensure stable signal transmission. The back panel is made of highly breathable fiber fabric; the waistband area is the encapsulation area, internally housing the power module and micro-control module, with an outer waterproof coating. The micro-control module and power module are located on the side of the waistband of the underwear, both independently encapsulated to ensure detachability.

[0045] Existing pressure monitoring devices are mostly used in industrial or medical fields, and are typically rigid or semi-rigid structures, making them uncomfortable to wear and difficult to use for extended periods. Furthermore, these devices often lack real-time pressure data monitoring and remote transmission capabilities, failing to meet users' needs for immediate access to health data. Currently, there are no products specifically designed for pressure monitoring in the male genital area that integrate pressure-sensitive materials into everyday clothing (such as underwear). This patent describes male sexual function monitoring underwear that achieves real-time monitoring of pressure and temperature in the genital area through a combination of highly breathable fabric and pressure-sensitive fiber materials. Users can view the monitoring data via mobile devices, and doctors can conduct remote diagnoses via a cloud server. This design not only improves the user's health monitoring experience but also provides a scientific basis for the early detection and intervention of male sexual dysfunction.

[0046] like Figure 3 A detailed structural diagram of the acquisition and monitoring area of ​​the columnar elephant trunk structure is shown. Its core, with a biomimetic shape, conforms to the physiological curve of the male reproductive organ, providing a tight yet unrestricted fit during erection and naturally extending with the organ's shape. The pressure-sensitive fiber sensing module includes a conductive elastic inner core and a temperature- and pressure-sensitive shell. The conductive inner core is preferably a conductive filament formed from thermoplastic polyurethane (TPU) as the matrix, mixed with carbon nanotubes, conductive carbon black, metal powder, or a combination thereof. By controlling the filler addition amount and extrusion process, the diameter of the inner core filament can be preferably 0.10–0.30 mm, and the line resistance is preferably controlled below 10 Ω / cm. The temperature- and pressure-sensitive shell incorporates temperature-sensitive polymers, including polyvinyl alcohol (PVA) as the fiber-forming skeleton, poly(N-isopropylacrylamide) (PNIPAm) or its copolymers as the temperature-sensitive component, and conductive fillers such as MXene, graphene oxide / reduced graphene oxide, or carbon nanotubes.

[0047] In specific preparation, a continuous wet coaxial spinning process is used. Specifically, dried and wound TPU conductive filaments are used as the inner core and introduced into the central channel of the coaxial spinneret via a tension-controlled feeding mechanism; a pre-prepared and fully dispersed aqueous spinning solution is used as the shell solution and is pumped into the annular outer channel of the coaxial spinneret via a metering pump. Diameters of 200-500 mm are prepared using the wet spinning process. The fibers possess both ≥200% elongation at break and stable mechanoelectric / thermoelectric response characteristics. The fibers are wound into ring-shaped structures with an inner diameter of 3-5 cm and a width of 0.5-1 cm. Each ring unit is an independent sensing unit, with a pressure response sensitivity ≥5% / kPa and a temperature response sensitivity ≥2% / ℃. Eight to ten ring units are arranged in layers with an axial spacing of 0.3-0.5 cm, nested along the biomimetic "elephant trunk" physiological curve to form a "columnar elephant trunk" structure, enabling layered monitoring of the penile region.

[0048] Multiple functional fibers are woven into a "temperature and pressure sensing functional fiber fabric" and applied to the penis monitoring area of ​​underwear. Thanks to the elasticity and softness of the fibers themselves, the fabric can tightly wrap the entire penile area without applying any restraint or pressure. Simultaneously, "multi-ring independent sensing units" are distributed in layers along the axial direction, achieving high-density, all-around temperature and pressure information capture, accurately reflecting the physiological dynamics of different areas of the penis (such as the mechanical and temperature changes during erection). Furthermore, the fabric's "lightweight, flexible, and highly breathable" characteristics significantly improve wearing comfort, supporting long-term, all-weather continuous monitoring, ensuring the naturalness and accuracy of physiological data collection. This breaks through the spatial limitations of traditional "single-point / area sensing," providing a more comprehensive and refined unconstrained solution for ED monitoring, greatly expanding its application scenarios in clinical diagnosis and home health management. Achieving unconstrained monitoring from the root of structural design realizes "fabric as sensor."

[0049] The miniature control module is connected to the data acquisition unit, which includes a signal processing unit and a wireless transmission unit. The signal processing unit filters, amplifies, and digitizes the acquired signals to ensure data accuracy and stability. The processed data is then transmitted wirelessly (e.g., via Bluetooth or Wi-Fi) to the user's mobile device or cloud server. Figure 4 The diagram shows the hardware module of the microcontroller. As the sensing end of the closed-loop system, the microcontroller is responsible for real-time acquisition, preprocessing, and individualized standardization of signals from the multi-ring temperature and pressure fiber sensing unit, providing high-quality basic data for subsequent cloud-based monitoring and intervention decisions. The signal processing unit is the core of the microcontroller, responsible for preprocessing the acquired analog signals. This includes filtering circuits, amplification circuits, and an analog-to-digital converter (ADC). The wireless transmission unit is responsible for sending the processed data to the user's mobile device or cloud server. It is also connected to the power supply module, providing a stable power supply for the entire microcontroller.

[0050] The power module uses a small rechargeable lithium battery to provide a stable power supply for the micro control module and data acquisition unit. The battery is designed to be removable for easy charging and replacement by the user. The wireless transmission unit is responsible for transmitting the processed pressure and temperature data to the user's mobile device or cloud server in real time, ensuring the real-time nature and accessibility of the data.

[0051] The microcontroller module and power module are encapsulated on the side of the underwear waistband. The microcontroller module is connected to a pressure-sensitive fabric via flexible wires, which are wrapped in waterproof and sweat-proof material to ensure durability. The microcontroller module and power module are independently packaged for easy assembly and disassembly. The entire module is connected to a data acquisition unit formed by pressure-sensitive fibers in the underwear via flexible wires, forming a complete sensing system. Furthermore, the microcontroller module also serves as the sensing end of the closed-loop system, responsible for acquiring and preprocessing the monitoring data.

[0052] As the intervention execution end of the closed-loop system, the electrical stimulation module dynamically adjusts the intensity, frequency, and mode of electrical stimulation based on the risk assessment results and individualized control parameters returned by the cloud monitoring system. It also continuously receives data feedback from the sensing end during the stimulation process, enabling real-time evaluation and adaptive adjustment of the intervention effect.

[0053] The device is also equipped with a cloud monitoring system. The micro control module transmits the data collected by the data acquisition unit to the cloud for analysis and feeds back the analysis results to the user terminal.

[0054] The cloud-based monitoring system, serving as the monitoring and decision-making hub of a closed-loop system, comprises a receiving unit, an analysis unit, a display unit, and a threshold alarm unit. The receiving unit receives wireless data from the micro-control module and transmits it to the display unit. The display unit visualizes pressure and temperature data in charts or graphs, helping users intuitively understand the monitoring results. The threshold alarm unit triggers an alarm when data exceeds user-defined thresholds (such as pressure or temperature limits), reminding the user to take appropriate measures. This design not only improves data visualization but also provides users with a more intuitive and reliable health monitoring experience through an intelligent alarm mechanism.

[0055] The entire system operates by having a micro-control module, acting as the sensing end, collect, preprocess, and personalize the data from the multi-ring temperature and pressure fiber sensing unit in real time; a cloud-based monitoring system, acting as the monitoring and decision-making center, intelligently analyzes and assesses the risks of multi-dimensional spatiotemporal characteristics to form personalized dynamic thresholds and intervention strategies; and an electrical stimulation module, acting as the intervention execution end, implements real-time, graded, and adaptive electrical stimulation adjustments based on the risk level and control instructions fed back from the cloud, and then feeds back the physiological response after intervention to the sensing end.

[0056] By closing the data and control flows between the aforementioned sensing, monitoring, and intervention processes, this invention constructs an integrated closed-loop system that differs from traditional devices that "only record, without a closed loop." This system enables continuous sensing, dynamic monitoring, and intelligent intervention of nocturnal erectile function. This invention can predict health risks and generate personalized suggestions, forming a "sensing-processing-early warning-optimization" closed loop. It achieves accurate and real-time genital health monitoring while ensuring wearability comfort.

[0057] Example 2 This embodiment provides a sensing method for an unrestrained wearable smart sensing device for ED patients, which includes at least a multi-ring sensing signal processing stage. The multi-ring sensing signal processing algorithm is built into a micro control module. The multi-ring sensing signal processing algorithm combines several axially arranged ring-shaped fiber sensing units to differentiate the signals collected by different ring-shaped fiber sensing units and complete the conversion and standardization from the original electrical signals to physical quantities such as pressure / temperature.

[0058] In this embodiment, a [feature] is provided along the axial direction. The first ring-shaped fiber sensing unit, the first Each ring-shaped fiber sensing unit is denoted as a channel. (in ), at the sampling time At this point, the original electrical signal (such as resistance or voltage) output by this channel is denoted as... .

[0059] The micro-control module synchronously samples all the annular fiber sensing units at a preset sampling frequency to form a multi-channel time series:

[0060] Preferably, to suppress high-frequency noise and random jitter, the micro-control module performs moving average filtering on the signals of each channel. Let the moving window length be... The filtered signal is:

[0061] To eliminate low-frequency body motion and slow baseline drift, this embodiment performs first-order differential processing on the filtered signal, resulting in:

[0062] The filtering and first-order differential processing described above are performed independently on each ring sensing channel, achieving ring-level preprocessing of the original signal.

[0063] In a preferred embodiment, to achieve differentiated processing for different annular fiber sensing units, this embodiment establishes a calibration model for the relationship between electrical quantities and pressure / temperature for each annular fiber sensing unit. Taking pressure calibration as an example, the first... The resistance-pressure relationship of each ring can be expressed as:

[0064] in, For a moment The instantaneous resistance value, This is the reference resistance for the loop in its resting state. and In order to target the The parameters of each loop were obtained through calibration experiments. This corresponds to the pressure value.

[0065] For temperature signals, this embodiment can use a linear calibration model:

[0066] in, These are temperature-dependent electrical quantities (resistance or voltage). , For the first Temperature calibration coefficient of each ring-shaped fiber sensing unit.

[0067] By establishing calibration models between electrical quantities and pressure / temperature, respectively, the "ring-by-ring conversion" of electrical signals to pressure and temperature is realized, compensating for the response differences caused by manufacturing differences, pre-stretching state, and fit of the annular fiber sensing units at different locations.

[0068] In one alternative implementation, this embodiment automatically identifies resting periods during the initial stage of user wear, using this as an individualized baseline. Specifically, within the baseline period, the pressure sequence for each loop is... Calculate the mean and standard deviation :

[0069]

[0070] in, For the baseline sample set, This represents the number of sample points.

[0071] The real-time pressure data is standardized to obtain dimensionless standardized pressure:

[0072] Standardized multi-circular sequences It can reflect the degree of deviation of the current state from the individual's resting state, which facilitates the comparison between different individuals and different nighttime monitoring data.

[0073] In a preferred embodiment, to reflect the differentiated processing of signals from different annular fiber sensing units, this embodiment further assigns different weights to each channel based on the location and reliability of the annulus. Specifically, each annulus can be divided into a root region, a middle region, and a distal region according to its anatomical location, and each region can be assigned different weights:

[0074] To improve the reliability of multi-ring fusion results, this embodiment calculates the short-term variance and the difference between each ring and its adjacent rings within a sliding time window. When the variance of a certain ring fiber sensing unit is continuously abnormal or the pressure difference with the adjacent ring exceeds a preset threshold, the ring is marked as a low-reliability channel, and its weight is reduced or temporarily shielded in subsequent data fusion, thereby reducing the impact of abnormal situations such as poor contact and local folding on the overall interpretation results.

[0075] Unlike existing technologies that treat all sensing channels as having a consistent response and use a uniform threshold for processing, this embodiment uses a "ring-by-ring calibration + ring-by-ring standardization + ring-by-ring weighting and reliability control" approach. This allows the algorithm design to fully utilize the structural arrangement of multiple ring-shaped fiber sensing units, enabling differentiated processing of signals from different rings and improving the accuracy and robustness of pressure and temperature estimation.

[0076] Example 3 This embodiment further supplements the sensing method of the unrestrained wearable smart sensing device for ED patients in Embodiment 2. Based on the acquired multi-loop standardized data, it provides a cloud monitoring and closed-loop control algorithm, which is mounted on a cloud monitoring system.

[0077] The cloud-based monitoring and closed-loop control algorithm, based on the obtained multi-loop standardized data, performs a comprehensive spatiotemporal assessment of the erection process and links with the electrical stimulation module to achieve closed-loop intervention control. Figure 5 This is a schematic diagram of the cloud monitoring and analysis process of the present invention. The cloud monitoring system, as the monitoring and decision-making center of the closed-loop system, centrally stores, extracts spatiotemporal features, assesses risks and sets dynamic thresholds for the multi-loop temperature and pressure data uploaded by the micro-control module, and feeds back the monitoring results and intervention strategies to the electrical stimulation module, thereby completing the closed-loop central function of "monitoring-decision-instruction".

[0078] In this embodiment, the cloud monitoring system receives a multi-loop standardized pressure sequence uploaded from the micro-control module. and corresponding pressure values To perform time series analysis, the cloud uses a window length... and step length The data is segmented, the first... The sample set corresponding to each time window is:

[0079] Within each time window, the cloud extracts time-domain features for each ring-shaped sensing channel, forming a channel feature vector. The time-domain features include, but are not limited to: Standardized mean pressure:

[0080] Pressure variance:

[0081] Peak pressure and peak-to-trough difference:

[0082] Therefore, it can be written as:

[0083] In a preferred embodiment, to fully utilize the spatial distribution information of multiple ring-shaped sensing units, this embodiment marks the coordinates of the geometric center of each ring along the axial direction as follows: And within each time window, the following spatial features are constructed: Pressure center location:

[0084] in, For the first in the window The average pressure of each ring. The location of the pressure center can indicate whether the pressure is mainly concentrated at the root, distal end, or middle segment.

[0085] Axial pressure gradient:

[0086] The above gradient vector It is used to reflect whether there are uneven phenomena such as local collapse or segmented erection along the axial direction.

[0087] Multi-ring synchronization index: In one specific implementation, this embodiment calculates the pairwise correlation coefficients of each channel within the window using the following formula. And based on this, the overall synchronicity index is obtained:

[0088] Among them, the higher This indicates that the signal changes in each ring have a consistent trend, and the lower value... This indicates the presence of local abnormalities or bodily movement disturbances.

[0089] In this embodiment, the time-domain features of each ring are concatenated with the aforementioned spatial features to construct a multi-dimensional comprehensive feature vector:

[0090] In a preferred embodiment, the cloud-based monitoring system establishes an erection quality assessment model based on clinically labeled data, using support vector machines (SVM), neural network models, and other methods. Taking the SVM model as an example, its decision function can be expressed as:

[0091] in, For the training sample feature vector, For tags, For Lagrange multipliers, For kernel function, This is a bias term.

[0092] To facilitate risk classification, this embodiment maps the output of the decision function to a probability value of erectile dysfunction:

[0093] In one specific embodiment, the cloud system sets multi-level dynamic probability thresholds based on historical follow-up data and individual baseline information. and the corresponding duration threshold When the following conditions are met, determine the current risk level and output the corresponding risk level. :

[0094] Example 4 This embodiment further supplements the sensing method of the unrestrained wearable intelligent sensing device for ED patients provided in Embodiment 3, and provides closed-loop control of the electrical stimulation module based on the monitoring results.

[0095] As the intervention execution end of the closed-loop system, the electrical stimulation module in this embodiment will consider the risk probability. This is mapped to the electrical stimulation intensity control quantity. Figure 6 This is a schematic diagram of the electrical stimulation treatment process of the present invention. Taking a piecewise linear control strategy as an example, the electrical stimulation intensity... satisfy:

[0096] in, , This is the gain coefficient. The initial stimulus intensity is of medium level. This is the preset safety limit.

[0097] In a preferred embodiment, this embodiment can also incorporate multi-ring spatial features to directionally control the spatial distribution of electrical stimulation. When the pressure in a certain axial region (such as a specific set of ring sensing units) is detected to be consistently lower than normal, higher intensity or higher frequency electrical stimulation can be preferentially applied to the electrode array in the corresponding region to achieve targeted intervention.

[0098] In summary, the mechanism of the cloud-based monitoring system in this embodiment is based on a closed-loop structure. The cloud-based monitoring system transmits the aforementioned monitoring results and decision information to the terminal in real-time or near real-time, including: the current risk level, the suggested electrical stimulation intensity range, and stimulation mode adjustment strategies. The electrical stimulation module adjusts its output parameters accordingly, while the sensing end continues to upload actual physiological response data after intervention. The cloud then incorporates the new data into subsequent monitoring and model updates, thus forming a dynamic closed loop of "monitoring—assessment—strategy update—re-monitoring." The closed-loop control algorithm not only utilizes the temporal characteristics of multi-loop sensor signals but also introduces spatial features such as pressure center, axial pressure gradient, and multi-loop synchronicity. It uses a machine learning model for risk assessment and then links with the electrical stimulation module to achieve closed-loop operation. Compared to conventional algorithms that only perform fixed threshold judgments on single-channel waveforms, this embodiment can provide more refined erectile morphology analysis and more personalized intervention strategies, exhibiting higher accuracy and clinical application value.

[0099] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.

Claims

1. A restraint-free wearable intelligent sensing device for patients with erectile dysfunction (ED), characterized in that: The device includes an underwear-like main structure, a data acquisition unit, a micro-control module, a power supply module, and an electrical stimulation module. The underwear-like main structure has a columnar elephant trunk-shaped data acquisition and monitoring area. The data acquisition unit includes multiple annular fiber sensing units arranged to form the columnar elephant trunk-shaped monitoring area. Each annular fiber sensing unit has a built-in independent pressure-sensitive fiber sensing module. The data acquisition unit collects the wearer's pressure and temperature data in real time. The micro-control module is connected to the data acquisition unit to process and transmit the data collected. The electrical stimulation module includes a flexible electrode array, a pulse generator, and a controller. The flexible electrode array is centrally located at the front end of the columnar elephant trunk-shaped structure, while the pressure-sensitive fiber sensing module, composed of multiple annular fiber sensing units, is arranged along the axial direction of the columnar elephant trunk-shaped structure. The power supply module supplies power to each unit or module. The device also includes a cloud-based monitoring system for data analysis. The micro-control module transmits the data collected by the data acquisition unit to the cloud for analysis and feeds back the analysis results to the user terminal.

2. The unrestrained wearable intelligent sensing device for ED patients according to claim 1, characterized in that: The main body structure, resembling underwear, consists of a front panel, a back panel, and a waistband. The front panel is the data acquisition and monitoring area of ​​the columnar elephant trunk structure, which is connected to the micro-control module via wires. The front panel is composed of a ring structure woven from temperature and pressure sensitive fibers made of temperature and pressure sensitive material, combined with highly breathable fabric. The back panel is made of highly breathable fiber fabric. The waistband is an encapsulation area, which internally encapsulates the power module and the micro-control module in a detachable manner, and the outer layer is a waterproof coating.

3. The unrestrained wearable intelligent sensing device for ED patients according to claim 1, characterized in that: The data acquisition unit has multiple ring-shaped fiber sensing units shaped in a biomimetic form to fit the shape curve of the male reproductive organ. Each pressure-sensitive fiber sensing module inside includes a conductive elastic inner core and a temperature and pressure sensitive shell.

4. The unrestrained wearable intelligent sensing device for ED patients according to claim 1, characterized in that: The micro control module is connected to the data acquisition unit, which includes a signal processing unit and a wireless transmission unit. The signal processing unit filters, amplifies, and standardizes the acquired signals, and the processed data is sent to the user's mobile device or cloud monitoring system through the wireless transmission unit. The micro control module and power module are located on the waistband side of the underwear-shaped main structure.

5. The unrestrained wearable intelligent sensing device for ED patients according to claim 1, characterized in that: The electrical stimulation module serves as the intervention execution end of the closed-loop system. The pulse generator produces therapeutic pulses to perform electrical stimulation; the controller is used to start and stop electrical stimulation treatment according to the corresponding algorithm; and the flexible electrode array is used to stimulate the nerves of the erectile corpus cavernosum.

6. The unrestrained wearable intelligent sensing device for ED patients according to claim 1, characterized in that: The cloud-based monitoring system, serving as the monitoring and decision-making hub of a closed-loop system, includes a receiving unit, an analysis unit, a display unit, and a threshold alarm unit. The receiving unit receives wirelessly transmitted data from the micro-control module and transmits it to the display unit. The analysis unit analyzes the standardized data transmitted by the WeChat control module and transmits the analysis results to the display unit. The display unit visualizes the pressure and temperature data, as well as the final analysis results, in the form of charts or images. The threshold alarm unit triggers an alarm when the data exceeds the threshold set by the user, reminding the user to take appropriate measures.

7. A constraint-free wearable intelligent sensing method for ED patients, characterized in that: The method is incorporated into the unconstrained wearable intelligent sensing device described in any one of claims 1-6, wherein... The method includes a multi-ring sensing signal processing stage. The multi-ring sensing signal processing algorithm is built into the micro control module. The multi-ring sensing signal processing algorithm combines several ring-shaped fiber sensing units arranged along the axial direction to differentiate the signals collected by different ring-shaped fiber sensing units and complete the conversion and standardization from the original electrical signal to pressure or temperature physical quantities. The method also includes a cloud monitoring and closed-loop control stage. The algorithm for the cloud monitoring and closed-loop control stage is mounted on the cloud monitoring system. It centrally stores, extracts spatiotemporal features, assesses risks and sets dynamic thresholds for the multi-loop temperature and pressure data uploaded by the micro-control module, and feeds back the monitoring results and intervention strategies to the electrical stimulation module.

8. The unconstrained wearable intelligent sensing method for ED patients according to claim 7, characterized in that: In the multi-loop sensor signal processing stage, the process is as follows: Assume that it is provided along the axial direction The first ring-shaped fiber sensing unit, the first Each ring-shaped fiber sensing unit is denoted as a channel. , At the sampling time The original electrical signal output by this channel is denoted as . ; The block synchronously samples all the annular fiber sensing units at a preset sampling frequency to form a multi-channel time series: Each channel signal is subjected to moving average filtering to suppress high-frequency noise and random jitter. Let the moving window length be... The filtered signal is: Perform first-order difference processing on the filtered signal: Filtering and first-order differential processing are performed independently on each ring sensing channel, achieving ring-level preprocessing of the original signal. For each annular fiber sensing unit, a calibration model is established between electrical quantities and pressure or temperature, where the first... The electrical quantity-pressure relationship of each ring is expressed as follows: in, For a moment The instantaneous resistance value, This is the reference resistance for the loop in its resting state. and In order to target the The parameters of each loop were obtained through calibration experiments. This corresponds to the pressure value; No. The electrical quantity-temperature relationship of each ring is expressed as follows: in, These are temperature-dependent electrical quantities. , For the first Temperature calibration coefficients for each ring-shaped fiber sensing unit; Pressure sequence for each loop during the baseline period. Calculate the mean and standard deviation : in, For the baseline sample set, Number of sample points In the real-time phase, the real-time pressure data is standardized to obtain dimensionless standardized pressure: Standardized multi-circular sequences It can reflect the degree of deviation of the current state from the individual's resting state. Different weights are assigned to each channel based on the location and reliability of the ring. Furthermore, each ring is divided into a root region, a middle region, and a distal region based on its anatomical location, and each region is assigned a different weight. By adjusting the assigned weights, the short-term variance and the degree of difference with adjacent rings are calculated for each ring within the sliding time window. When the variance of a certain ring fiber sensing unit is continuously abnormal or the pressure difference with adjacent rings exceeds a preset threshold, the ring is marked as a low reliability channel, and its weight is reduced or temporarily blocked in subsequent data fusion.

9. A restraint-free wearable intelligent sensing method for ED patients according to claim 8, characterized in that: The risk level assessment process during the cloud-based monitoring and closed-loop control phase is as follows: Receive multi-loop normalized pressure sequence uploaded from the microcontroller module and corresponding pressure values Based on window length and step length The data is segmented, the first... The sample set corresponding to each time window is: Within each time window, the cloud extracts time-domain features from each ring-shaped sensing channel to form a channel feature vector. Time-domain features include, but are not limited to: Standardized mean pressure: Pressure variance: Peak pressure and peak-to-trough difference: Then the channel feature vector Represented as: The coordinates of the geometric centers of each ring along the axial direction are defined as follows: And within each time window, the following spatial features are constructed: Pressure center location: in, For the first in the window The average pressure of each ring, and the location of the pressure center indicates whether the pressure is mainly concentrated at the root, distal end or middle section; Axial pressure gradient: gradient vector It is used to reflect whether there is unevenness in local collapse or segmented erection along the axial direction. Multi-ring synchronization index: Calculates the pairwise correlation coefficients of each channel within the calculation window. And based on this, the overall synchronicity index is obtained: in, A value greater than or equal to the preset value indicates that the signal change trends of each loop are consistent. If the value is lower than the preset value, it indicates the presence of local abnormalities or body movement interference; The time-domain features of each ring are concatenated with the aforementioned spatial features to construct a multi-dimensional comprehensive feature vector: An erectile quality assessment model was established based on clinically labeled data, using a support vector machine as its foundation. Its decision function is expressed as follows: in, For the training sample feature vector, For tags, For Lagrange multipliers, For kernel function, For bias terms; Map the output of the decision function to a probability value of erectile dysfunction: Based on historical follow-up data and individual baseline information, multi-level dynamic probability thresholds are set. and the corresponding duration threshold When satisfied At that time, determine the current risk level and output the risk level. .

10. A restraint-free wearable intelligent sensing method for ED patients according to claim 9, characterized in that: The closed-loop control process of the electrical stimulation module based on the monitoring results during the cloud-based monitoring and closed-loop control phase is as follows: Risk probability Mapped to the electrical stimulation intensity control variable, a piecewise linear control strategy is adopted, and the electrical stimulation intensity... satisfy: in, , This is the gain coefficient. The initial stimulus intensity is of medium level. This is the preset safety limit.

Images