Intelligent control method and system of intelligent hot compress device

Abstract

This invention relates to the field of equipment control technology and discloses an intelligent control method and system for an intelligent moist heat compress device. The method includes: constructing a set of partitioned bending and fitting state parameters; generating a set of partitioned target heat and humidity control parameters; performing partitioned adjustment demand determination; performing dynamic redistribution of partitioned heat and humidity output; performing partitioned closed-loop equalization adjustment based on the partitioned dynamic correction output instruction set; and outputting the partitioned closed-loop equalization control result. Compared to existing moist heat compress devices that often use a single heat source, especially under bending surfaces such as the knee and elbow joints and dynamic flexion and extension conditions, this invention addresses the problem of uneven heat and humidity distribution caused by surface bending and fitting changes. By sensing the partitioned fitting state and generating partitioned target heat and humidity parameters, it achieves adaptive adjustment of heat and humidity output for each control partition, thus avoiding the problem of uneven heat and humidity distribution caused by surface bending and fitting changes.

Description

Technical Field

[0001] This invention relates to the field of equipment control technology, and in particular to an intelligent control method and system for an intelligent hot compress device. Background Technology

[0002] Currently, moist heat therapy devices are widely used in medical physiotherapy, rehabilitation nursing, and home-based treatment scenarios. They mainly work by synergistically heating and humidifying the human body surface to promote improved local circulation, tissue relaxation, and discomfort relief. However, most existing moist heat therapy devices adopt an integrated heating structure, a single-channel steam output structure, or a uniform parameter control method. During the control process, they usually only adjust the overall temperature or overall output intensity, without adequately considering the actual differences in the surface shape of the treatment area, changes in the fit, and differences in local heat and moisture distribution.

[0003] For example, when a moist heat therapy device is applied to areas with significant bending, such as the knee, elbow, and ankle joints, the varying curvature, wrinkles, and inconsistent adhesion of the treatment area can lead to significant differences in the transfer of heat and moisture across different regions. In areas with tighter adhesion, heat and moisture tend to accumulate more easily, resulting in higher local temperatures or humidity levels. Conversely, in peripheral or loosely fitted areas, insufficient heat transfer and inadequate moisture coverage are more likely. Furthermore, during treatment, patients may experience slight flexion, extension, rotation, or postural adjustments, causing continuous changes in the contact state between areas and further exacerbating the imbalance in local heat and moisture output.

[0004] Therefore, there is an urgent need for an intelligent control method for a smart moist heat therapy device that can still achieve dynamic distribution and closed-loop balanced adjustment of zoned heat and moisture output even under changes in the fit of the treatment site and dynamic changes in joint posture, so as to improve the balance, stability and adaptability of heat and moisture effects during moist heat therapy. Summary of the Invention

[0005] To address the aforementioned technical shortcomings, the purpose of this invention is to propose an intelligent control method for an intelligent moist heat compress device. This method aims to solve the technical problems that existing moist heat compress devices often use a single heat source, especially in bending surfaces such as the knee and elbow joints and under dynamic flexion and extension conditions, making it difficult to achieve uniform heat and humidity distribution in different areas and easily leading to localized overheating or insufficient heat at the edges.

[0006] To solve the above-mentioned technical problems, the present invention adopts the following technical solution: The present invention provides an intelligent control method for an intelligent hot compress device.

[0007] The intelligent control method of the intelligent hot compress device includes: Step S10: Obtain the initial state data of the partition after the intelligent moist heat compress device is attached to the curved treatment area, perform the partition fitting state modeling task based on the initial state data of the partition, and output the partition bending fitting state parameter set. Step S20: Based on the partitioned bending and fitting state parameter set, the partitioned heat transfer demand assessment mechanism is used to perform the partitioned target thermal and humidity parameter generation task, and output the partitioned target thermal and humidity control parameter set; Step S30: Execute the partition output preprocessing task based on the partition target thermal and humidity control parameter set, and output the partition initial thermal and humidity output instruction set; Step S40: Based on the initial heat and humidity output instruction set of the partition, the partition dynamic reallocation mechanism is used to execute the partition heat and humidity output reallocation task, and the partition dynamic correction output instruction set is output. Step S50: Execute the partitioned thermal and humidity closed-loop regulation task based on the partitioned dynamic correction output instruction set, and output the partitioned closed-loop equalization control result.

[0008] Preferably, step S10, which involves acquiring the initial state data of the partitions after the intelligent moist heat therapy device is attached to the curved treatment area, performing a partition adhesion state modeling task based on the initial state data, and outputting a partition curved adhesion state parameter set, specifically includes: Step S101: Obtain the initial surface temperature, initial relative humidity, initial contact pressure, partition installation position data, and initial joint flexion state data of each control zone after the intelligent moist heat therapy device is attached to the flexed treatment area. Step S102: Based on the partition installation position data and initial joint flexion state data of each control partition, determine the local bending degree of each control partition and the fit change relationship between adjacent partitions; Step S103: Based on the initial surface temperature, initial relative humidity, initial contact pressure, local bending degree, and the bonding change relationship between adjacent zones of each control zone, construct a set of zone bending bonding state parameters.

[0009] Preferably, step S20, which involves using a partitioned heat transfer demand assessment mechanism to generate partitioned target thermal and humidity parameters based on the partitioned bending and fitting state parameter set, and outputting the partitioned target thermal and humidity control parameter set, specifically includes: Step S201: Construct the equivalent heat transfer demand coefficient for each control zone based on the partition bending fit state parameter set; Step S202: Obtain the initial humidity status parameters and local vapor retention trends of each control zone; Step S203: Generate and output the target thermal and humidity control parameter set for the zone based on the initial humidity state parameters, local vapor retention trend and equivalent heat transfer demand coefficient.

[0010] Preferably, in step S202, the equivalent heat transfer demand coefficient is calculated as follows: ; in, Indicates the first The equivalent heat transfer demand coefficient of the control zone, Indicates the first The local bending characterization value of the control zone, This represents the maximum local curvature value within the current treatment area. Indicates the first The contact pressure characterization value of the control zone, This represents the maximum contact pressure value within the current treatment area. Indicates the first The surface temperature characterization value of the control zone, This indicates the preset treatment baseline temperature. , , These are the weighting coefficients, and , To prevent positive numbers with a denominator of zero.

[0011] Preferably, step S30, which involves performing a partition output preprocessing task based on the partition target thermal and humidity control parameter set and outputting the partition initial thermal and humidity output instruction set, specifically includes: Step S301: Collect the current real-time temperature and humidity status of each control zone; Step S302: Based on the current real-time temperature and humidity status of each control zone and the target temperature and humidity control parameters of the zone, determine the zone adjustment requirements and output the initial heating adjustment requirements and initial steam adjustment requirements corresponding to each control zone. Step S303: Based on the initial heating and steam regulation requirements corresponding to each control zone, the Mamdani fuzzy inference method is used to perform zone heat and humidity output preset processing, and the zone initial heat and humidity output instruction set is output.

[0012] Preferably, in step S40, the step of performing the partitioned heat and humidity output redistribution task based on the partitioned initial humidity output instruction set using a partitioned dynamic redistribution mechanism, and outputting the partitioned dynamically corrected output instruction set, specifically includes: Step S401: During the execution of the initial thermal and humidity output instruction set for the partition, continuously collect joint posture change data and real-time contact state change data of each control partition, and calculate the joint angle change Δθ between adjacent sampling times, where: ; This represents the joint pose angle data at the current sampling moment. This represents the joint pose angle data at the next sampling time. Step S402: Based on the joint posture change data and the real-time contact state change data of each control zone, identify the fit redistribution trend of each control zone and determine whether the preset dynamic redistribution triggering condition is met. Step S403: When the dynamic redistribution triggering condition is met, based on the initial thermal and humidity output instruction set of each control zone and the bonding redistribution trend of each control zone, the thermal and humidity output of each control zone is redistributed to generate a dynamic correction output instruction set for the zone; wherein, the first The dynamic correction output command for the control partition is determined as follows: ;in, Indicates the first The initial thermal and humidity output command characterization value for the control zone. Indicates the first The dynamic correction output instruction characterization value of the control partition, This is the redistribution adjustment coefficient. This is the contact redistribution factor, used to characterize the adhesion redistribution trend of the control zone.

[0013] Preferably, the contact redistribution factor The calculation method is as follows: ; in, Indicates the first The contact pressure characterization value of the control zone at the current sampling time. Indicates the first The contact pressure characterization value of the control zone at the next sampling time. Indicates the first The local bending characterization value of the control partition at the current sampling time. Indicates the first The local bending characterization value of the control partition at the next sampling time. and These are the weighting coefficients. To prevent positive numbers with a denominator of zero; The dynamic reallocation trigger condition is: when or When the dynamic reallocation trigger condition is met, it is determined that the condition is satisfied; among which, The preset threshold for triggering joint angle changes; The preset contact redistribution trigger threshold.

[0014] The present invention also provides an intelligent control system for an intelligent hot compress device, comprising: The partitioned bending and fitting state construction module is used to obtain the initial state data of the partitions after the intelligent moist heat compress device is attached to the bending treatment area, perform the partitioned fitting state modeling task based on the initial state data of the partitions, and output the partitioned bending and fitting state parameter set. The partitioned heat transfer demand assessment module is used to perform the partitioned target thermal and humidity parameter generation task based on the partitioned bending and fitting state parameter set using the partitioned heat transfer demand assessment mechanism, and output the partitioned target thermal and humidity control parameter set. The partitioned heat and humidity output preprocessing module is used to perform partitioned output preprocessing tasks based on the partitioned target heat and humidity control parameter set and output the partitioned initial heat and humidity output instruction set. The partition dynamic reallocation module is used to execute the partition heat and humidity output reallocation task based on the partition initial heat and humidity output instruction set using the partition dynamic reallocation mechanism, and output the partition dynamic correction output instruction set. The partitioned closed-loop equalization adjustment module is used to execute the partitioned thermal and humidity closed-loop adjustment task based on the partitioned dynamic correction output instruction set, and output the partitioned closed-loop equalization control result.

[0015] The present invention also provides an intelligent control device for an intelligent moist heat compress device, comprising: a memory, a processor, and an intelligent control program for the intelligent moist heat compress device stored in the memory and executable on the processor. When the intelligent control program for the intelligent moist heat compress device is executed by the processor, an intelligent control method for the intelligent moist heat compress device is implemented.

[0016] The present invention also provides a computer program product, including an intelligent control program for an intelligent moist heat compress device, wherein the intelligent control program for the intelligent moist heat compress device, when executed by a processor, implements the intelligent control method for the intelligent moist heat compress device.

[0017] The beneficial effects of this invention are as follows: By acquiring joint posture change data and real-time contact state data of each control zone, this invention constructs zone bending fit state parameters, and generates zone target heat and humidity control parameters based on these parameters. This allows the heat output and humidity output of each control zone to be adjusted in a targeted manner according to the actual fit state under the bending surface, thereby avoiding the problems of overheating in the central area, insufficient heat in the edge area, or local condensation concentration in the bending area that occur in the traditional integral output method, and improving the distribution balance of heat and humidity effects in the treatment area.

[0018] This invention introduces dynamic redistribution processing based on contact redistribution factors and closed-loop equalization adjustment of zones during the execution of the initial heat and humidity output command of each zone. This allows the heat and humidity output of each control zone to be corrected in real time and continuously tend to be balanced when the joint flexion, extension or contact state changes. This avoids the problem of heat and humidity output lag or local imbalance caused by dynamic posture changes, and improves the stability and adaptability of the moist heat compress process. Attached Figure Description

[0019] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0020] Figure 1 This is a flowchart illustrating the first embodiment of the intelligent control method for an intelligent moist heat therapy device according to the present invention.

[0021] Figure 2 This is a schematic diagram of the intelligent control method for an intelligent moist heat compress device according to the present invention. Detailed Implementation

[0022] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0023] Example 1: As Figure 1 The diagram shown is a flowchart illustrating the first embodiment of the intelligent control method for the intelligent moist heat compress device of the present invention, and presents the first embodiment of the intelligent control method for the intelligent moist heat compress device of the present invention.

[0024] In the first embodiment, the intelligent control method of the intelligent hot compress device includes: Step S10: Obtain the initial state data of the partition after the intelligent moist heat compress device is attached to the curved treatment area, perform the partition fitting state modeling task based on the initial state data of the partition, and output the partition bending fitting state parameter set. It should be noted that the initial state data of the partitions refers to the state information of each control partition collected by the sensing unit inside the device at the initial moment after the intelligent moist heat therapy device is attached to the curved treatment area. This includes the initial temperature value, initial humidity value, contact pressure characterization value, and local surface curvature characterization value of each control partition. The contact pressure characterization value is used to characterize the tightness of the fit between each control partition and the human skin, and can be obtained through a flexible pressure sensing element or a capacitive pressure detection unit. The local surface curvature characterization value is used to characterize the curvature of the surface of the treatment area, and can be calculated based on the multi-point spacing change or the bending angle measurement result. The partition fit state modeling task refers to the unified characterization processing of the above-mentioned multiple state parameters to form a partition bending fit state parameter set that can reflect the fit differences and surface characteristics of each control partition, for use in the subsequent control parameter generation process.

[0025] Understandably, by jointly modeling the initial temperature, initial humidity, contact pressure, and local curvature of each control zone, the differences in heat transfer paths and moisture diffusion conditions in each region can be obtained at the initial stage of control. This provides a direct basis for generating the target heat and humidity control parameters for subsequent zones. On this basis, different control zones can correspond to different adjustment needs, so that subsequent output control no longer depends on a uniform setting, but is differentiated based on the actual fit state. This is conducive to improving the balance of heat and humidity distribution in the treatment area and reducing the risk of local abnormal concentration.

[0026] It should be understood that, compared to traditional technologies that rely solely on overall temperature feedback or single sensor information for control, this embodiment introduces contact pressure characterization values ​​and local surface curvature characterization values ​​to provide a detailed description of the multi-zone bonding state under curved surfaces. Furthermore, it completes zone modeling at the initial control stage, thus avoiding the accumulation of control deviations caused by neglecting bonding differences in traditional methods. Simultaneously, since this embodiment uses the set of bending bonding state parameters for each zone as the basic input during subsequent control, the control logic can dynamically adjust according to changes in the bonding state, thereby maintaining a relatively stable thermal and humidity effect even in curved areas and scenarios with changing postures.

[0027] For example, when the knee joint is in a flexed position of approximately 60°, the control zone located on the anterior side of the patella is usually in close contact with the skin. The control zones located on the medial and lateral sides of the knee joint have a bending transition, and the corresponding local surface curvature values ​​are significantly higher than those of the anterior region. In this case, by modeling the contact state of the zones, contact state parameters corresponding to different control zones can be obtained. For example, the anterior region corresponds to a higher contact coefficient, and the lateral region corresponds to a lower contact coefficient. Based on the modeling results, in the subsequent control process, the heat and humidity output of the lateral region can be appropriately increased, while the output of the anterior region can be appropriately restricted, thereby avoiding the problems of overheating in the anterior region and insufficient heat and humidity in the lateral region, and thus improving the balance of heat and humidity distribution in the overall treatment area.

[0028] Step S20: Based on the partitioned bending and fitting state parameter set, the partitioned heat transfer demand assessment mechanism is used to perform the partitioned target thermal and humidity parameter generation task, and output the partitioned target thermal and humidity control parameter set; It should be noted that the partition bending and bonding state parameter set is a set of parameters output in step S10 that characterizes the initial bonding differences, bending differences, and initial thermal and humidity differences of each control partition. The partition heat transfer demand assessment mechanism refers to the process of analyzing the heat transfer capacity and moisture coverage capacity of each control partition under the current bonding conditions, and determining the subsequent heat output target and humidity output target of each control partition accordingly. The partition target thermal and humidity control parameter set refers to the set of target control parameters set for each control partition, including the target temperature parameter, target humidity parameter, and control reference parameter related to subsequent output adjustment for each control partition. The target temperature parameter is used to limit the heat action target range of the corresponding control partition, the target humidity parameter is used to limit the moisture action target range of the corresponding control partition, and the control reference parameter is used to provide parameter basis for the partition output preprocessing task in step S30. The partitioned heat transfer demand assessment mechanism does not assign the same heat and humidity target to all control partitions. Instead, it determines the compensation demand for each control partition based on the tightness of the fit, the degree of bending transition, and the differences in the initial temperature and humidity state, so as to ensure that the subsequent heat and humidity output is targeted.

[0029] Understandably, by implementing the zoned heat transfer demand assessment mechanism, the differences in the bonding states of each control zone identified in step S10 can be further transformed into differences in target thermal and humidity parameters that can be directly used for control. In other words, "different states in different zones" can be further transformed into "different output targets in different zones." During this process, control zones with tighter bonding, higher initial temperatures, or smaller local bending transitions can maintain relatively stable target thermal and humidity parameters, while control zones with looser bonding, lower initial temperatures, or more pronounced local bending transitions can achieve higher heat compensation or higher humidity coverage requirements. Therefore, the technical role of step S20 is to explicitly translate the state identification results obtained in step S10 into zoned control targets, enabling subsequent step S30 to no longer use a uniform setpoint for overall output, but instead to perform zoned output processing based on the target differences of different control zones, thereby improving the balance of heat and humidity distribution within the treatment area.

[0030] It should be understood that, compared to the traditional approach of uniformly setting the overall temperature and steam output intensity before starting moist heat therapy, this step uses a zoned heat transfer demand assessment mechanism to first evaluate the heat transfer compensation and humidity coverage requirements of each control zone, and then generates target heat and humidity parameters for each control zone. Therefore, it avoids the problems of "heat accumulation in the central area while insufficient heat in the side areas" or "local humidity retention while insufficient edge coverage" found in traditional techniques. Especially in curved treatment areas, where the adhesion conditions between control zones differ, using a uniform target value would inevitably lead to significant deviations in subsequent outputs. This step, by completing the target allocation at the beginning of the control chain, establishes the subsequent control process on a basis of clearly defined zone-by-zone targets, thereby mitigating the imbalance tendencies easily generated by traditional control methods from the outset and improving the initial rationality of the heat and humidity distribution across the entire treatment area.

[0031] For example, when the intelligent heat therapy device is applied to the front and sides of the knee joint, step S10 may yield the following characteristics: the contact state of the central control zone on the front side is relatively tight, and the initial temperature is relatively high, while the contact state of the control zones on the left and right sides is relatively loose, the local bending transition is larger, and the initial temperature is relatively low. Based on this set of parameters for the bending and fitting state of the zones, step S20 can set the target temperature parameter of the central control zone on the front side to a relatively gentle target level, and set the target temperature parameter of the control zones on the left and right sides to a higher compensation level; at the same time, the target humidity parameter is appropriately lowered for the inner transition zone where moisture tends to stagnate, and the target humidity parameter is appropriately raised for the edge zone. Through this zone-by-zone generation of target heat and humidity control parameter sets, differentiated control can be reflected in the initial stage of the subsequent output process, avoiding the inherent imbalance caused by uniform output.

[0032] Step S30: Execute the partition output preprocessing task based on the partition target thermal and humidity control parameter set, and output the partition initial thermal and humidity output instruction set; It should be noted that the target temperature and humidity control parameter set for each control zone is the set of parameters output in step S20, used to describe the target temperature and humidity states that each control zone should achieve; the zone output preprocessing task refers to comparing and analyzing the real-time temperature and humidity states of each control zone with their corresponding target temperature and humidity control parameters before formally executing dynamic adjustment, identifying the initial heating adjustment requirements and initial steam adjustment requirements of each control zone, and further converting these adjustment requirements into output instructions that can be executed by the device; the initial temperature and humidity output instruction set for each zone refers to the instruction set consisting of the initial heating control instructions and initial steam control instructions corresponding to each control zone, used to drive each control zone into an initial temperature and humidity output state that matches its target.

[0033] Understandably, the technical function of step S30 is to transform "target parameters" into "execution instructions." Since the set of zoned target temperature and humidity control parameters output in step S20 is essentially still data at the control target level, while the actual operation of the device requires specific drive instructions for each control zone, step S30 needs to determine the adjustment requirements of each control zone based on the current real-time temperature and humidity status, and map the determination result to the initial temperature and humidity output instruction. Through this step, on the one hand, a one-to-one correspondence can be established between the target temperature and humidity parameters and the actual execution behavior; on the other hand, before formally entering the attitude change scenario, each control zone can first reach an initial output level matching its contact state, thus providing a stable and traceable control starting point for the dynamic reallocation in step S40.

[0034] Step S40: Based on the initial heat and humidity output instruction set of the partition, the partition dynamic reallocation mechanism is used to execute the partition heat and humidity output reallocation task, and the partition dynamic correction output instruction set is output. It should be noted that the initial heat and humidity output command set for the partitions is the set of initial control commands output in step S30 and already in execution. The partition dynamic redistribution mechanism refers to a processing mechanism that continuously monitors joint posture changes and contact state changes of each control partition during the execution of the initial heat and humidity output commands for the partitions, and redistributes the heat and humidity output of each control partition when a redistribution of the fit relationship is identified. The partition heat and humidity output redistribution task refers to the task of dynamically correcting the original partition output path and output intensity based on the new state of the control partition during execution. The partition dynamic correction output command set refers to the set of control commands formed after redistribution, used to replace or correct the original initial heat and humidity output commands, including the dynamic correction heating output command and the dynamic correction steam output command corresponding to each control partition. The core of this step is that the control system does not assume that the patient remains completely still during treatment, but considers the posture changes of the bending part during treatment as an important factor affecting the heat and humidity distribution, and adjusts the partition output in real time in response to these changes.

[0035] Understandably, the technical function of step S40 is to promptly convert changes in posture, such as flexion, extension, rotation, or slight changes in the treatment area into output redistribution actions, thereby maintaining the regional adaptability of the heat and moisture effect. In actual treatment, once the joint posture changes, areas that were previously tightly fitted may be further compressed, while areas that were previously loosely fitted may re-attach. If the control logic still uses the initial output command generated in step S30, subsequent heat and moisture output will quickly deviate from the new actual fit. Therefore, this step continuously collects joint posture change data and real-time contact state change data to identify the fit redistribution trend of each control zone. When the triggering conditions are met, it regenerates the dynamic correction output command set for each zone, enabling the output distribution to change synchronously with the actual posture, thereby maintaining the dynamic consistency of the heat and moisture effect in the treatment area.

[0036] It should be understood that, compared to traditional techniques where control commands remain largely unchanged after being set during hot and moist compresses, or where overall corrections are only made when the overall temperature exceeds limits, this step directly introduces "posture changes" and "contact changes" into the zoned control chain. It then executes zone-by-zone output corrections through a dynamic redistribution mechanism, thus avoiding the control lag problem that occurs in traditional techniques under joint flexion and extension conditions. Especially in areas such as the knee and elbow, even slight postural adjustments by the patient can cause significant changes in the local area's contact relationship. If the initial control commands are still relied upon, it can easily lead to overheating in some areas, insufficient heating in others, or increased moisture retention. This step, through dynamic redistribution, ensures that the control results always revolve around the "current contact state" rather than the "initial contact state," thereby significantly improving the adaptability of the control results in flexion treatment scenarios.

[0037] For example, during knee joint treatment, the patient initially has a flexion of approximately 45°. Step S30 generates an initial heat and moisture output command set for each zone based on this flexion. When the patient flexes further to approximately 65° during treatment, the contact between the anterior central control zone and the skin may increase, while the force distribution and fit of the lateral control zones may also change. At this point, after step S40 continuously collects joint posture change data and real-time contact state change data for each control zone, it can identify a tendency for heat to accumulate in the anterior central control zone, while the lateral edge control zone shows improved fit and a potential for increased heat and moisture output. Based on this, the system can redistribute the original initial heat and moisture output command set, for example, by lowering the dynamic correction heating output command for the anterior central control zone and simultaneously raising the dynamic correction steam output command for the edge control zone, thus making the heat and moisture output during treatment more consistent with the new fit distribution.

[0038] Step S50: Execute the partitioned thermal and humidity closed-loop regulation task based on the partitioned dynamic correction output instruction set, and output the partitioned closed-loop equalization control result.

[0039] It should be noted that the dynamic correction output instruction set for the partitions is the set of partition control instructions output in step S40, which has been corrected by incorporating attitude changes and contact changes. The partition thermal-humidity closed-loop adjustment task refers to, after the execution of the dynamic correction output instructions, continuing to collect the real-time temperature, real-time humidity, and real-time contact status of each control partition, evaluating the balance of thermal-humidity distribution in the current treatment area, and further performing incremental or decremental corrections on the corresponding control partitions when the evaluation results do not meet the preset balance conditions. The partition closed-loop balance control result refers to the final control result obtained after closed-loop adjustment, which makes the thermal-humidity effects of each control partition in the treatment area more balanced. It can be reflected as the control state after the output of each control partition tends to stabilize, or as the real-time balance control state during the continuous correction process. In other words, step S50 is a subsequent closed-loop processing that verifies and continuously corrects the control effect based on the dynamic redistribution in step S40.

[0040] Understandably, the technical role of step S50 is to prevent the system from ending control solely based on the target generation and dynamic redistribution of the preceding steps. Instead, it further determines whether the control has truly achieved the goal of balanced heat and humidity distribution based on the actual execution results. Because the heat transfer and moisture diffusion processes on the surface of human tissue inherently have a lag, even if step S40 has corrected the output based on posture changes, residual differences in the actual effects of different control zones may still exist. Therefore, closed-loop regulation is still needed to further eliminate this residual deviation. Through this step, the system can perform corresponding correction processes for areas with high temperature, low temperature, high humidity, and low humidity, gradually bringing the heat and humidity distribution of each control zone closer to equilibrium, thereby ensuring a more stable effect throughout the entire treatment area.

[0041] It should be understood that, compared to traditional technologies that rely solely on one-time settings or simple threshold switching control, this step incorporates the "actual execution result" back into the control input through closed-loop equalization adjustment. This allows the system to continuously refine its corrections around the current thermal and moisture equilibrium state, thus avoiding the common problem of accumulated output deviations in traditional technologies. Especially when both curved treatment sites and dynamic posture scenarios coexist, even if the initial control is relatively accurate, new deviations may still occur due to local heat transfer differences, changes in moisture diffusion paths, or fine adjustments to contact states. This step, through continuous evaluation and closed-loop adjustment, can not only compensate for these deviations.

[0042] For example, after knee joint treatment has been ongoing for some time, even though step S40 has already corrected the output for dynamic posture changes, the following situation may still occur within the treatment area: the real-time temperature of the anterior central control zone is slightly higher than the average temperature of all zones, while the real-time humidity of the lateral edge control zone is still slightly lower than the average humidity of all zones. At this point, step S50 can further collect the real-time temperature, real-time humidity, and real-time contact status of each control zone to evaluate the degree of heat and humidity distribution balance in the current treatment area. If the evaluation results indicate that the balance condition has not yet been met, output reduction correction can be performed on the anterior central control zone, and humidity compensation correction can be performed on the lateral edge control zone, thereby further reducing the temperature and humidity differences between the control zones. Through this closed-loop balance adjustment process, the problem of local heat and humidity imbalance remaining in the later stages of treatment can be avoided, and the entire moist heat treatment process can be made closer to the balanced and stable target state in actual effect.

[0043] Example 2: Furthermore, the intelligent control system for the intelligent moist heat compress device provided by the present invention employs the intelligent control method for the intelligent moist heat compress device described in the above embodiments, which can solve the technical problem of intelligent control of an intelligent moist heat compress device. The beneficial effects of the intelligent control system for the intelligent moist heat compress device provided by the present invention are the same as the beneficial effects of the intelligent control method for the intelligent moist heat compress device described in the above embodiments, and other technical features in the intelligent control system for the intelligent moist heat compress device are the same as those disclosed in the methods of the above embodiments, and will not be repeated here.

[0044] Example 3: This invention provides an intelligent control device for an intelligent moist heat therapy device. Please refer to... Figure 2A smart control device for a smart moist heat compress device includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, which are executed by the at least one processor to enable the at least one processor to execute the smart control method for a smart moist heat compress device as described in Embodiment 1 above. The smart control device for a smart moist heat compress device in this embodiment of the invention may include, but is not limited to, mobile terminals such as mobile phones, laptops, digital radio receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Description), PMPs (Portable Media Players), in-vehicle terminals (e.g., in-vehicle navigation terminals), and fixed terminals such as digital TVs and desktop computers. The smart control device for a smart moist heat compress device is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments of the invention. The smart control device for a smart moist heat compress device may include a processing device 1001 (e.g., a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory 1002 or a program loaded from a storage device 1003 into a random access memory 1004. The random access memory 1004 also stores various programs and data required for the operation of the intelligent control device of the intelligent thermal compress device. The processing device 1001, read-only memory 1002, and random access memory 1004 are interconnected via bus 1005. I / O interface 1006 is also connected to the bus. Typically, the following systems can be connected to I / O interface 1006: input devices 1007 including, for example, touchscreens, touchpads, keyboards, mice, image sensors, microphones, accelerometers, gyroscopes, etc.; output devices 1008 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; storage devices 1003 including, for example, magnetic tapes, hard disks, etc.; and communication devices 1009. Communication device 1009 allows the intelligent control device of the intelligent thermal compress device to communicate wirelessly or wiredly with other devices to exchange data. Although the figure shows an intelligent control device of an intelligent thermal compress device with various systems, it should be understood that it is not required to implement or possess all the systems shown. More or fewer systems can be implemented or possessed alternatively.

[0045] Example 4: This invention also provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the intelligent control method for an intelligent moist heat compress device as described above. The computer program product provided by this invention can solve the technical problem of intelligent control of an intelligent moist heat compress device. Compared with the prior art, the beneficial effects of the computer program product provided by this invention are the same as the beneficial effects of the intelligent control method for an intelligent moist heat compress device provided in the above embodiments, and will not be repeated here.

[0046] In particular, according to the embodiments disclosed in this invention, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments disclosed in this invention include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device, or installed from storage device 1003, or installed from read-only memory 1002. When the computer program is executed by processing device 1001, it performs the functions defined in the methods of the embodiments disclosed in this invention.

[0047] It should be understood that the various parts disclosed in this invention can be implemented using hardware, software, firmware, or a combination thereof. In the description of the above embodiments, specific features, structures, materials, or characteristics may be combined in any suitable manner in one or more embodiments or examples.

[0048] Obviously, those skilled in the art can make various modifications and variations to this invention without departing from its spirit and scope. Therefore, if these modifications and variations fall within the scope of the claims of this invention and their equivalents, this invention also intends to include these modifications and variations.

Claims

1. A smart control method for an intelligent moist heat therapy device, characterized in that, The methods include: Step S10: Obtain the initial state data of the partition after the intelligent moist heat compress device is attached to the curved treatment area, perform the partition fitting state modeling task based on the initial state data of the partition, and output the partition bending fitting state parameter set. Step S20: Based on the partitioned bending and fitting state parameter set, the partitioned heat transfer demand assessment mechanism is used to perform the partitioned target thermal and humidity parameter generation task, and output the partitioned target thermal and humidity control parameter set; Step S30: Execute the partition output preprocessing task based on the partition target thermal and humidity control parameter set, and output the partition initial thermal and humidity output instruction set; Step S40: Based on the initial heat and humidity output instruction set of the partition, the partition dynamic reallocation mechanism is used to execute the partition heat and humidity output reallocation task, and the partition dynamic correction output instruction set is output. Step S50: Execute the partitioned thermal and humidity closed-loop regulation task based on the partitioned dynamic correction output instruction set, and output the partitioned closed-loop equalization control result.

2. The intelligent control method for an intelligent moist heat therapy device as described in claim 1, characterized in that, Step S10, which involves acquiring the initial state data of the partitions after the intelligent moist heat therapy device is applied to the curved treatment area, performing a partition adhesion state modeling task based on the initial state data, and outputting a partition curved adhesion state parameter set, specifically includes: Step S101: Obtain the initial surface temperature, initial relative humidity, initial contact pressure, partition installation position data, and initial joint flexion state data of each control zone after the intelligent moist heat therapy device is attached to the flexed treatment area. Step S102: Based on the partition installation position data and initial joint flexion state data of each control partition, determine the local bending degree of each control partition and the fit change relationship between adjacent partitions; Step S103: Based on the initial surface temperature, initial relative humidity, initial contact pressure, local bending degree, and the bonding change relationship between adjacent zones of each control zone, construct a set of zone bending bonding state parameters.

3. The intelligent control method for an intelligent moist heat therapy device as described in claim 1, characterized in that, Step S20, which involves generating target thermal and humidity parameters for a given zone based on the zoned bending and fitting state parameter set using a zoned heat transfer demand assessment mechanism, and outputting the target thermal and humidity control parameter set for the zone, specifically includes: Step S201: Construct the equivalent heat transfer demand coefficient for each control zone based on the partition bending fit state parameter set; Step S202: Obtain the initial humidity status parameters and local vapor retention trends of each control zone; Step S203: Generate and output the target thermal and humidity control parameter set for the zone based on the initial humidity state parameters, local vapor retention trend and equivalent heat transfer demand coefficient.

4. The intelligent control method for an intelligent moist heat therapy device as described in claim 3, characterized in that, In step S202, the equivalent heat transfer demand coefficient is calculated as follows: ； in, Indicates the first The equivalent heat transfer demand coefficient of the control zone, Indicates the first The local bending characterization value of the control zone, This represents the maximum local curvature value within the current treatment area. Indicates the first The contact pressure characterization value of the control zone, This represents the maximum contact pressure value within the current treatment area. Indicates the first The surface temperature characterization value of the control zone, This indicates the preset treatment baseline temperature. , , These are the weighting coefficients, and , To prevent positive numbers with a denominator of zero.

5. The intelligent control method for an intelligent moist heat therapy device as described in claim 1, characterized in that, Step S30, which involves performing a partition output preprocessing task based on the partition target thermal and humidity control parameter set and outputting the partition initial thermal and humidity output instruction set, specifically includes: Step S301: Collect the current real-time temperature and humidity status of each control zone; Step S302: Based on the current real-time temperature and humidity status of each control zone and the target temperature and humidity control parameters of the zone, determine the zone adjustment requirements and output the initial heating adjustment requirements and initial steam adjustment requirements corresponding to each control zone. Step S303: Based on the initial heating and steam regulation requirements corresponding to each control zone, the Mamdani fuzzy inference method is used to perform zone heat and humidity output preset processing, and the zone initial heat and humidity output instruction set is output.

6. The intelligent control method for an intelligent moist heat therapy device as described in claim 1, characterized in that, In step S40, the step of performing a partitioned thermal and humidity output redistribution task based on the partitioned initial humidity output instruction set using a partitioned dynamic redistribution mechanism, and outputting a partitioned dynamically corrected output instruction set, specifically includes: Step S401: During the execution of the initial thermal and humidity output instruction set for the partition, continuously collect joint posture change data and real-time contact state change data of each control partition, and calculate the joint angle change Δθ between adjacent sampling times, where: ; This represents the joint pose angle data at the current sampling moment. This represents the joint pose angle data at the next sampling time. Step S402: Based on the joint posture change data and the real-time contact state change data of each control zone, identify the fit redistribution trend of each control zone and determine whether the preset dynamic redistribution triggering condition is met. Step S403: When the dynamic redistribution triggering condition is met, based on the initial thermal and humidity output instruction set of each control zone and the bonding redistribution trend of each control zone, the thermal and humidity output of each control zone is redistributed to generate a dynamic correction output instruction set for the zone; wherein, the first The dynamic correction output command for the control partition is determined as follows: ;in, Indicates the first The initial thermal and humidity output command characterization value for the control zone. Indicates the first The dynamic correction output instruction characterization value of the control partition, This is the redistribution adjustment coefficient. This is the contact redistribution factor, used to characterize the adhesion redistribution trend of the control zone.

7. The intelligent control method for an intelligent moist heat therapy device as described in claim 6, characterized in that, The contact redistribution factor The calculation method is as follows: ； in, Indicates the first The contact pressure characterization value of the control zone at the current sampling time. Indicates the first The contact pressure characterization value of the control zone at the next sampling time. Indicates the first The local bending characterization value of the control partition at the current sampling time. Indicates the first The local bending characterization value of the control partition at the next sampling time. and These are the weighting coefficients. To prevent positive numbers with a denominator of zero; The dynamic reallocation trigger condition is: when or When the dynamic reallocation trigger condition is met, it is determined that the condition is satisfied; among which, The preset threshold for triggering joint angle changes; The preset contact redistribution trigger threshold.

8. An intelligent control system for an intelligent moist heat compress device, applied to the intelligent control method for an intelligent moist heat compress device according to any one of claims 1 to 7, characterized in that, The intelligent control system of the intelligent hot compress device includes: The partitioned bending and fitting state construction module is used to obtain the initial state data of the partitions after the intelligent moist heat compress device is attached to the bending treatment area, perform the partitioned fitting state modeling task based on the initial state data of the partitions, and output the partitioned bending and fitting state parameter set. The partitioned heat transfer demand assessment module is used to perform the partitioned target thermal and humidity parameter generation task based on the partitioned bending and fitting state parameter set using the partitioned heat transfer demand assessment mechanism, and output the partitioned target thermal and humidity control parameter set. The partitioned heat and humidity output preprocessing module is used to perform partitioned output preprocessing tasks based on the partitioned target heat and humidity control parameter set and output the partitioned initial heat and humidity output instruction set. The partition dynamic reallocation module is used to execute the partition heat and humidity output reallocation task based on the partition initial heat and humidity output instruction set using the partition dynamic reallocation mechanism, and output the partition dynamic correction output instruction set. The partitioned closed-loop equalization adjustment module is used to execute the partitioned thermal and humidity closed-loop adjustment task based on the partitioned dynamic correction output instruction set, and output the partitioned closed-loop equalization control result.

9. An intelligent control device for an intelligent hot compress device, characterized in that, The intelligent control device of the intelligent moist heat compress device includes: a memory, a processor, and an intelligent control program of the intelligent moist heat compress device stored in the memory and executable on the processor. When the intelligent control program of the intelligent moist heat compress device is executed by the processor, it implements an intelligent control method of the intelligent moist heat compress device according to any one of claims 1 to 7.

10. A computer program product, characterized in that, The computer program product includes an intelligent control program for an intelligent moist heat compress device, which, when executed by a processor, implements an intelligent control method for an intelligent moist heat compress device as described in any one of claims 1 to 7.

Images