Temperature Detection and Control Method and Medium for Skin Heat Therapy Itching Relief Device

Abstract

The present invention discloses a temperature detection and control method and medium for a skin heat therapy itching relief device, relating to the technical field of intelligent control, including: activating the control interaction channel of the skin heat therapy itching relief device; constructing the device application scenario; making a multi-stage temperature control collaborative decision for the skin heat therapy itching relief device to establish a device temperature control collaborative strategy space; based on the device temperature control multi-layer optimization network, performing multi-level joint optimization on the device temperature control collaborative strategy space to obtain the optimization result of the device temperature control strategy; based on the target user, controlling the skin heat therapy itching relief device according to the optimization result of the device temperature control strategy to obtain control monitoring data; and performing optimized control on the skin heat therapy itching relief device based on the control monitoring data. The present invention solves the technical problems in the prior art that when detecting and controlling the temperature of the skin heat therapy itching relief device, the temperature control accuracy is low, the adaptability is poor, and it is difficult to dynamically optimize, and achieves the technical effect of improving the user experience.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent control, and particularly relates to a temperature detection and control method and medium for a skin heat therapy and itching relief device. Background Art

[0002] Skin heat therapy and itching relief devices are increasingly widely used in skin care and health management. Such devices usually perform heat therapy on the skin through heating elements to relieve itching, promote blood circulation or assist in treatment. However, when detecting and controlling the temperature of skin heat therapy and itching relief devices in the prior art, there are generally problems such as low temperature control accuracy, poor adaptability, and difficulty in dynamic optimization. Traditional devices lack the ability to dynamically adapt to user individual characteristics, environmental changes, and heat therapy tasks. The control strategies are single and static, and it is difficult to cope with complex and changing usage scenarios, resulting in unsatisfactory device operation effects and affecting the user experience. Summary of the Invention

[0003] This application provides a temperature detection and control method and medium for a skin heat therapy and itching relief device, which is used to solve the technical problems of low temperature control accuracy, poor adaptability, and difficulty in dynamic optimization existing in the prior art when detecting and controlling the temperature of a skin heat therapy and itching relief device.

[0004] In view of the above problems, this application provides a temperature detection and control method and medium for a skin heat therapy and itching relief device.

[0005] In the first aspect of this application, a temperature detection and control method for a skin heat therapy and itching relief device is provided. The method includes:

[0006] Activating the control interaction channel of the skin heat therapy and itching relief device. The skin heat therapy and itching relief device includes a power supply unit, a control unit, and a heating element. The control interaction channel includes a data interaction layer, multiple usage scenario factors, and multiple control stage factors. The multiple usage scenario factors include user characteristics, the user's environment, and the heat therapy task. The multiple control stage factors include an initial heating stage, a constant temperature control stage, and a cooling and ending stage; based on the data interaction layer, according to the multiple usage scenario factors, performing heat therapy request feature interaction on the target user to construct a device application scenario; activating a multi-stage temperature control decision computing power constraint network, and combining the device application scenario and the multiple control stage factors to perform multi-stage temperature control collaborative decision-making on the skin heat therapy and itching relief device to establish a device temperature control collaborative strategy space; based on the device temperature control multi-level optimization network, performing multi-level joint optimization on the device temperature control collaborative strategy space to obtain a device temperature control strategy optimization result; based on the target user, controlling the skin heat therapy and itching relief device according to the device temperature control strategy optimization result to obtain control monitoring data; and performing optimized control on the skin heat therapy and itching relief device based on the control monitoring data.

[0007] In a second aspect of the present application, there is provided a computer-readable storage medium storing a computer program, which when executed by a processor, implements the temperature detection control method for a skin thermotherapy itching relief device provided by the present application.

[0008] One or more technical solutions provided in the present application have at least the following technical effects or advantages:

[0009] The present application activates the control interaction channel of the skin thermotherapy itching relief device. The skin thermotherapy itching relief device includes a power supply unit, a control unit, and a heating element. The control interaction channel includes a data interaction layer, multiple usage scenario factors, and multiple control stage factors. The multiple usage scenario factors include user characteristics, the user's environment, and the thermotherapy task. The multiple control stage factors include an initial heating stage, a constant temperature control stage, and a cooling end stage. Based on the data interaction layer, according to the multiple usage scenario factors, perform thermotherapy request feature interaction with the target user to construct a device application scenario. Activate the multi-stage temperature control decision computing power constraint network, and combine the device application scenario and the multiple control stage factors to perform multi-stage temperature control collaborative decision-making on the skin thermotherapy itching relief device, and establish a device temperature control collaborative strategy space. Based on the device temperature control multi-level optimization network, perform multi-level joint optimization on the device temperature control collaborative strategy space to obtain the device temperature control strategy optimization result. Based on the target user, control the skin thermotherapy itching relief device according to the device temperature control strategy optimization result to obtain control monitoring data. Optimize the control of the skin thermotherapy itching relief device based on the control monitoring data. The present invention solves the technical problems of low temperature control accuracy, poor adaptability, and difficulty in dynamic optimization existing in the prior art when performing temperature detection control on the skin thermotherapy itching relief device. By activating the control interaction channel, constructing the device application scenario, combining the multi-stage temperature control decision computing power constraint network and the device temperature control multi-level optimization network, it realizes precise temperature control collaborative decision-making and optimization control of the skin thermotherapy itching relief device, ensures the efficiency, safety, and stability of the temperature control process, and achieves the technical effect of improving the user experience. Description of the Drawings

[0010] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0011] Figure 1 It is a schematic flowchart of the temperature detection control method for a skin thermotherapy itching relief device provided by an embodiment of the present application;

[0012] Figure 2 It is a schematic flowchart of establishing a device temperature control collaborative strategy space in the temperature detection control method for a skin thermotherapy itching relief device provided by an embodiment of the present application. Specific Embodiments

[0013] The present application provides a temperature detection and control method and medium for a skin heat therapy and itching relief device, aiming to solve the technical problems of low temperature control accuracy, poor adaptability, and difficulty in dynamic optimization in the existing technology when detecting and controlling the temperature of a skin heat therapy and itching relief device. By activating the control interaction channel, constructing the device application scenario, and combining the multi-stage temperature control decision computing power constraint network and the device temperature control multi-layer optimization network, the precise temperature control collaborative decision-making and optimization control of the skin heat therapy and itching relief device are realized, ensuring the efficiency, safety, and stability of the temperature control process, and achieving the technical effect of improving the user experience.

[0014] Next, the technical solutions in the embodiments of the present application will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present application.

[0015] It should be noted that any variations of the terms "including" and "having" are intended to cover non-exclusive inclusions. For example, a process, method, medium, product, or server that includes a series of steps or units does not necessarily have to be limited to those clearly listed steps or units, but may include other steps or modules that are not clearly listed or are inherent to these processes, methods, products, or devices.

[0016] Embodiment 1, as Figure 1 shown, the present application provides a temperature detection and control method for a skin heat therapy and itching relief device, and the method includes:

[0017] Step S100: Activate the control interaction channel of the skin heat therapy and itching relief device. Among them, the skin heat therapy and itching relief device includes a power supply unit, a control unit, and a heating element. The control interaction channel includes a data interaction layer, multiple usage scenario factors, and multiple control stage factors. The multiple usage scenario factors include user characteristics, the environment where the user is located, and the heat therapy task. The multiple control stage factors include the initial temperature rise stage, the constant temperature control stage, and the cooling end stage.

[0018] In the embodiment of the present application, first, the control interaction channel of the skin heat therapy and itching relief device is activated. The control interaction channel is used to connect the power supply unit, the control unit, and the heating element of the device to realize the interaction and matching between user needs and device operations.

[0019] The skin heat therapy and itching relief device is composed of a power supply unit, a control unit, and a heating element. The control interaction channel is its core logic framework, including a data interaction layer, multiple usage scenario factors, and multiple control stage factors.

[0020] The multi - usage - scenario factors cover user characteristics (such as skin sensitivity), the environment where the user is located (such as the environmental temperature indoors or outdoors), and the thermotherapy tasks (such as relieving itching or fatigue). The multi - control - stage factors are divided into an initial heating stage (rapid heating), a constant - temperature control stage (temperature remains stable), and a cooling - down ending stage (stable temperature drop to end).

[0021] Step S200: Based on the data interaction layer, according to the multi - usage - scenario factors, perform thermotherapy request feature interaction for the target user to construct a device application scenario.

[0022] In the embodiment of the present application, based on the data interaction layer, the skin thermotherapy itching - relieving device collects the surface temperature of the user's skin through an infrared temperature sensor. This non - contact temperature detection method can quickly obtain temperature information and avoid direct pressure on the skin. At the same time, a capacitive touch sensor is used to detect the contact state between the device and the skin to confirm that the device is correctly attached to the skin. The collected skin temperature and contact - state data are transmitted to the data interaction layer of the device as key inputs of user characteristics.

[0023] Then, the device continuously monitors the temperature and humidity of the environment where the user is located through a temperature - humidity sensor. Combining with a positioning module, such as GPS, it determines whether the user is indoors or outdoors. The environmental information is parsed through a rule library inside the device. For example, under high - humidity conditions, the device is marked as a "high - heat - dissipation environment".

[0024] After that, the user selects a specific thermotherapy task through the physical buttons of the device or the APP interface, such as quickly relieving itching or relieving muscle fatigue. The device extracts the corresponding operation parameters, such as the heating rate, target temperature range, and constant - temperature time, from the internal task - parameter database according to the user's selection. These task parameters are associated with user characteristics and environmental information in the data interaction layer to form a complete interaction result.

[0025] Finally, the device constructs a specific device application scenario by integrating user characteristics, environmental conditions, and task requirements. For example, for a skin - sensitive user who selects the task of quickly relieving itching and is located in a high - humidity outdoor environment, an application scenario of "rapidly heating to 40°C with low power and maintaining a constant temperature for a short time" is generated.

[0026] Through the above process, the construction of the device application scenario is completed.

[0027] Step S300: Activate the multi - stage temperature - control decision - making computing power constraint network, and perform multi - stage temperature - control collaborative decision - making on the skin thermotherapy itching - relieving device in combination with the device application scenario and the multi - control - stage factors to establish a device temperature - control collaborative strategy space.

[0028] In the embodiment of the present application, to activate the multi-stage temperature control decision computing power constraint network, first, the multi-factor control stage factors are analyzed, and the decision constraint computing powers for the initial heating stage, constant temperature control stage, and cooling ending stage are calculated respectively. Based on the decision constraint computing power in the initial stage, combined with the device application scenario, the device formulates the control decision for the initial heating stage and constructs the temperature control decision space for the initial stage; similarly, based on the decision constraint computing power in the constant temperature stage and the decision constraint computing power in the cooling stage, the device sequentially completes the control decisions for the constant temperature stage and the cooling stage, and constructs the temperature control decision space for the constant temperature stage and the temperature control decision space for the cooling stage respectively.

[0029] Subsequently, using the decision constraint computing powers of the initial stage, constant temperature stage, and cooling stage, the overall temperature control collaborative decision computing power is calculated. Finally, based on this collaborative decision computing power, the device makes a random decision combination for the temperature control decision spaces of the three stages to generate the temperature control collaborative strategy for the entire process of the device, and thus establishes the temperature control collaborative strategy space for the device.

[0030] Further, as Figure 2 shown, in the method provided by the embodiment of the application, to activate the multi-stage temperature control decision computing power constraint network, and perform multi-stage temperature control collaborative decision on the skin heat therapy and itching relief device by combining the device application scenario and the multi-factor control stage factors, and establish the temperature control collaborative strategy space for the device, further includes:

[0031] Performing decision constraint computing power analysis on the multi-factor control stage factors based on the multi-stage temperature control decision computing power constraint network to obtain the decision constraint computing power for the initial stage, the decision constraint computing power for the constant temperature stage, and the decision constraint computing power for the cooling stage; based on the decision constraint computing power for the initial stage, performing an initial heating stage control decision on the skin heat therapy and itching relief device according to the device application scenario, and constructing the temperature control decision space for the initial stage; based on the decision constraint computing power for the constant temperature stage, performing a constant temperature stage control decision on the skin heat therapy and itching relief device according to the device application scenario, and constructing the temperature control decision space for the constant temperature stage; based on the decision constraint computing power for the cooling stage, performing a cooling stage control decision on the skin heat therapy and itching relief device according to the device application scenario, and constructing the temperature control decision space for the cooling stage; calculating the temperature control collaborative decision computing power based on the decision constraint computing power for the initial stage, the decision constraint computing power for the constant temperature stage, and the decision constraint computing power for the cooling stage; and making a random decision combination for the temperature control decision space for the initial stage, the temperature control decision space for the constant temperature stage, and the temperature control decision space for the cooling stage based on the temperature control collaborative decision computing power to generate the temperature control collaborative strategy space for the device.

[0032] In the embodiment of the present application, based on the multi-stage temperature control decision computing power constraint network, by analyzing the multi-factor control stage factors, the calculation of the decision constraint computing powers for the initial stage, constant temperature stage, and cooling stage is completed, and the temperature control decision spaces for each stage are gradually constructed, and finally the temperature control collaborative strategy space for the device is generated.

[0033] Specifically, the multi-order temperature control decision power constraint network is first used to analyze the initial heating stage, constant temperature control stage and cooling end stage, and the decision constraint computing power of the initial stage, the constant temperature stage decision constraint computing power and the cooling stage decision constraint computing power are obtained respectively. For example, the decision constraint computing power of the initial stage is 30, the constant temperature stage is 50, and the cooling stage is 20, which means that a corresponding number of temperature control decisions can be generated in each stage. Then, based on the decision constraint computing power of the initial stage, combined with the device application scenario (such as the user's skin sensitivity, ambient temperature, etc.), the control decision of the skin thermal therapy antipruritic device in the initial heating stage is made. The specific process includes retrieving the historical decision records of the equipment, extracting the initial stage temperature control decisions that meet the current application scenarios, and forming an initial stage temperature control decision sample set; then cleaning the sample set, removing outliers and redundant data, and generating a structured initial stage temperature control decision sample domain; then identifying the characteristic parameters of the temperature control interval (such as heating rate, target temperature range, etc.) based on the sample domain, and constructing the initial stage temperature control constraint domain; finally, generating a corresponding number of initial heating strategies within the constraint domain according to the initial stage decision constraint computing power, and completing the initial stage temperature control decision space.

[0034] In the same way, based on the decision-constrained computing power of the constant temperature stage and the cooling stage, combined with the equipment application scenario, the control decisions of the constant temperature stage and the cooling stage are completed in sequence, and the temperature control decision space of the constant temperature stage and the temperature control decision space of the cooling stage are built respectively. In the constant temperature stage, the decisions generated by the equipment cover different combinations of target temperature and constant temperature time; in the cooling stage, the decisions generated cover a variety of strategies from rapid cooling to gradual cooling.

[0035] After completing the construction of the temperature control decision space for each stage, integrate the decision constraint computing power of the initial stage, constant temperature stage, and cooling stage to calculate the overall temperature control collaborative decision computing power. When calculating, first find the sum of the decision constraint computing power of the three stages; secondly, divide the maximum value of the three stages by the minimum value to get the computing power ratio; then multiply the computing power ratio by the total computing power; finally, round up the result to get the temperature control collaborative decision computing power. For example, if the initial stage is 30, the constant temperature stage is 50, and the cooling stage is 20, the total is 100, the ratio of the maximum value to the minimum value is 50÷20=2.5, and the result is 2.5×100=250. After rounding, the collaborative decision computing power is 250.

[0036] According to the calculated temperature control collaborative decision-making power, a decision is randomly selected from the temperature control decision space of the initial stage, constant temperature stage, and cooling stage, and combined to form a complete equipment temperature control collaborative strategy. Through multiple random combinations, until the number of generated strategies reaches the temperature control collaborative decision-making power, such as 250. Finally, the generation of the equipment temperature control collaborative strategy space is completed.

[0037] Further, in the method provided by the application embodiment, based on the multi-stage temperature control decision computing power constraint network, the decision constraint computing power analysis of the multi-factor control stage factor is performed to obtain the initial stage decision constraint computing power, the constant temperature stage decision constraint computing power, and the cooling stage decision constraint computing power, and it further includes:

[0038] The target user performs an importance score on the multi-factor control stage factor to obtain a multi-stage factor importance score, where the multi-stage factor importance score includes an initial stage importance score, a constant temperature stage importance score, and a cooling stage importance score; load a multi-stage factor importance score sample set and a multi-stage temperature control decision constraint computing power sample set; use the multi-stage factor importance score sample set as input data and the multi-stage temperature control decision constraint computing power sample set as output data to train a BP neural network, and build the multi-stage temperature control decision computing power constraint network; input the multi-stage factor importance score into the multi-stage temperature control decision computing power constraint network to obtain a multi-stage temperature control decision constraint computing power, where the multi-stage temperature control decision constraint computing power includes the initial stage decision constraint computing power, the constant temperature stage decision constraint computing power, and the cooling stage decision constraint computing power.

[0039] In the embodiment of the present application, first, the target user scores the multi-factor control stage factor of the device. The user scores the importance of the initial heating stage, the constant temperature stage, and the cooling stage through the device's interaction interface, such as physical buttons or an APP, according to their own needs. For example, in the scenario of quickly relieving itching, the user may attach more importance to the initial heating stage and score 8 points, while the constant temperature stage and the cooling stage are scored 5 points and 3 points respectively. These scores reflect the user's demand priorities for each stage, and the user's scores are respectively recorded as the initial stage importance score, the constant temperature stage importance score, and the cooling stage importance score.

[0040] Then, a multi-stage factor importance score sample set and a multi-stage temperature control decision constraint computing power sample set are loaded from the historical database. The importance score sample set contains the scoring records of historical users, describing the preferences of users for each stage's needs in different scenarios; the decision constraint computing power sample set records the actual computing power data allocated by the device under each scoring condition, which is used to represent the number of temperature control decisions required for each stage when the device meets the user's needs. For example, the computing power allocation corresponding to a certain scoring combination (initial stage 9 points, constant temperature stage 6 points, cooling stage 2 points) may be 40 for the initial stage, 30 for the constant temperature stage, and 10 for the cooling stage.

[0041] Subsequently, a mapping model between the multi-level factor importance score and the multi-level temperature control decision constraint computing power is established using a BP neural network, namely the multi-level temperature control decision computing power constraint network. The input layer of the network receives the user score vector (such as [8, 5, 3]), and the output layer generates the computing power allocation value for each stage. During the training process, the multi-level factor importance score sample set is used as the input, and the decision constraint computing power sample set is used as the output. The network adjusts the weights and biases to learn the mapping relationship between the score and the computing power allocation, and finally generates the multi-level temperature control decision computing power constraint network.

[0042] Finally, the current importance score of the target user (such as 8 points in the initial stage, 5 points in the constant temperature stage, and 3 points in the cooling stage) is input into the trained multi-level temperature control decision computing power constraint network to generate the multi-level temperature control decision constraint computing power. For example, the corresponding computing power values output may be 35 in the initial stage, 25 in the constant temperature stage, and 15 in the cooling stage, respectively, indicating the number of temperature control decisions that the device needs to generate in each stage. These computing power allocation values directly represent the control complexity of each stage when the device meets the user's needs.

[0043] Through the above process, based on the user importance score, combined with historical sample data and the BP neural network model, the multi-level temperature control decision constraint computing power is successfully generated, including the initial stage decision constraint computing power, the constant temperature stage decision constraint computing power, and the cooling stage decision constraint computing power.

[0044] Furthermore, in the method provided by the application embodiment, based on the initial stage decision constraint computing power, according to the device application scenario, the initial heating stage control decision of the skin heat therapy and itching relief device is carried out, and the initial stage temperature control decision space is built, which further includes:

[0045] Retrieve the initial heating stage control decision record of the skin heat therapy and itching relief device according to the device application scenario to obtain the initial stage temperature control decision sample set; perform discrete data cleaning on the initial stage temperature control decision sample set to obtain the initial stage temperature control decision sample domain; perform temperature control interval feature recognition on the initial stage temperature control decision sample domain to establish the initial stage temperature control constraint domain; based on the initial stage decision constraint computing power, perform the initial stage temperature control decision on the device application scenario according to the initial stage temperature control constraint domain to build the initial stage temperature control decision space.

[0046] In the embodiment of the present application, first, according to the current application scenario, such as user skin characteristics, environmental conditions, and task requirements, the historical decision records are retrieved to extract the records relevant to the current scenario, forming an initial-stage temperature control decision sample set. Specifically, it is implemented through a rule matching method based on conditional filtering. For example, the records that meet the conditions of "sensitive skin", "environmental temperature of 30°C", and "rapid heating requirement" are screened out. The sample set contains control parameters and effect data in the historical scenario. For example, the heating rate is 2°C / second, the target temperature is 40°C, and the heating time is 10 seconds.

[0047] Next, discrete data cleaning is performed on the data extracted from the sample set. During the cleaning process, abnormal data is removed by setting thresholds and rules. For example, the records with a heating rate exceeding the safety upper limit (such as above 5°C / second) and the invalid data with a target temperature below the normal range (such as below 35°C) are removed. At the same time, duplicate records are merged and classified to ensure the uniqueness and standardization of the data. After the cleaning is completed, an initial-stage temperature control decision sample domain is obtained, that is, a sample data set that has been standardized and has removed noise.

[0048] Then, temperature control interval feature recognition is performed based on the key parameters of the sample domain. This process extracts the interval ranges of the heating rate, target temperature, and heating time by analyzing the data distribution range. For example, according to the sample domain, the heating rate may be distributed between 1°C / second and 3°C / second, the target temperature is limited to 38°C to 45°C, and the heating time is 5 seconds to 15 seconds. Based on these analysis results, an initial-stage temperature control constraint domain is constructed to clarify the safety range and valid parameters for all decisions in the initial heating stage.

[0049] Finally, with the initial-stage decision constraint computing power (such as 30), the corresponding number of heating strategies are generated within the temperature control constraint domain. This step is completed through a parameter combination method. For example, the various interval values of the heating rate, target temperature, and heating time are combined to generate 30 different control strategies. These strategies may include "heating rate 1.5°C / second, target temperature 40°C, heating time 8 seconds" and "heating rate 2°C / second, target temperature 42°C, heating time 10 seconds", etc., covering a variety of combinations from rapid heating to slow heating. Finally, all the generated strategies are integrated to obtain the initial-stage temperature control decision space.

[0050] Step S400: Based on the device temperature control multi-layer optimization network, perform multi-level joint optimization on the device temperature control collaborative strategy space to obtain the device temperature control strategy optimization result.

[0051] In the embodiment of the present application, the device temperature control multi-layer optimization network includes a device temperature control prediction network, a temperature control expectation constraint optimization network, and a temperature control fitness optimization network. By analyzing and screening the temperature control features in the strategy space through the device temperature control prediction network and the temperature control expectation constraint optimization network, strategies that do not meet the constraint conditions such as user experience, temperature control safety, and device loss are eliminated, and a temperature control collaborative strategy optimization space that meets the conditions is generated. Then, the temperature control fitness optimization network is used to perform fitness scoring and maximization optimization on this strategy space, and considering the user experience weight, temperature control safety weight, and device loss weight, the strategy with the highest fitness is selected, and finally the device temperature control strategy optimization result is generated.

[0052] Further, in the method provided by the application embodiment, based on the device temperature control multi-layer optimization network, multi-level joint optimization is performed on the device temperature control collaborative strategy space to obtain the device temperature control strategy optimization result, and it further includes:

[0053] The device temperature control multi-layer optimization network includes a device temperature control prediction network, a temperature control expectation constraint optimization network, and a temperature control fitness optimization network; performing optimization analysis on the device temperature control collaborative strategy space based on the device temperature control prediction network and the temperature control expectation constraint optimization network to obtain a temperature control collaborative strategy optimization space; performing temperature control fitness maximization optimization on the temperature control collaborative strategy optimization space based on the temperature control fitness optimization network to generate the device temperature control strategy optimization result, where the temperature control fitness optimization network includes temperature control fitness weight conditions, and the temperature control fitness weight conditions include user experience weight, temperature control safety weight, and device loss weight.

[0054] In the embodiment of the present application, the device temperature control multi-layer optimization network includes a device temperature control prediction network, a temperature control expectation constraint optimization network, and a temperature control fitness optimization network.

[0055] First, the device temperature control prediction network is used to analyze each strategy in the temperature control collaborative strategy space one by one. The prediction network simulates its operation process according to the core parameters of the strategy, such as the heating rate, target temperature, and constant temperature time, and evaluates key features such as the time in the heating stage, the stability in the temperature control stage, and the rate in the cooling stage. For example, for the strategy "heating rate 2°C / second, target temperature 40°C, constant temperature time 3 minutes", the user experience prediction coefficient, temperature control safety prediction coefficient, and device loss prediction coefficient are calculated through the prediction network.

[0056] Then, the prediction results are screened through the temperature control expectation constraint optimization network, and strategies that do not meet the multi-dimensional constraint conditions are eliminated to generate a temperature control collaborative strategy optimization space.

[0057] Subsequently, a temperature control fitness optimization network is used to perform fitness analysis on the screened strategies, and calculate the temperature control fitness of each strategy. The fitness score is calculated based on the temperature control fitness weight conditions, which include the user experience weight, the temperature control safety weight, and the equipment loss weight. These weights are preset by technical experts. The corresponding prediction coefficients in each strategy are weighted according to these preset weights, and the strategy with the highest prediction coefficient is selected as the optimal strategy, and the output of this strategy is used as the optimization result of the equipment temperature control strategy.

[0058] Through the above steps, the multi-level optimization network for equipment temperature control realizes multi-level joint optimization from strategy analysis to fitness scoring, and finally generates the temperature control strategy that best suits the application scenario, generating the optimization result of the equipment temperature control strategy.

[0059] Further, in the method provided in the application embodiment, based on the equipment temperature control prediction network and the temperature control expectation constraint optimization network, the equipment temperature control collaborative strategy space is optimized and analyzed to obtain the temperature control collaborative strategy optimization space, and it further includes:

[0060] According to the equipment temperature control collaborative strategy space, the first equipment temperature control collaborative strategy is extracted; based on the equipment application scenario, the temperature control characteristics of the first equipment temperature control collaborative strategy are predicted according to the equipment temperature control prediction network, and the first equipment temperature control prediction result is obtained; the first equipment temperature control prediction result is input into the temperature control expectation constraint optimization network to determine whether the first equipment temperature control prediction result meets the multi-dimensional temperature control expectation constraints in the temperature control expectation constraint optimization network, where the multi-dimensional temperature control expectation constraints include user experience constraints, temperature control safety constraints, and equipment loss constraints; if the first equipment temperature control prediction result meets the multi-dimensional temperature control expectation constraints, the first equipment temperature control collaborative strategy is added to the temperature control collaborative strategy optimization space; according to the equipment temperature control prediction network and the temperature control expectation constraint optimization network, the equipment temperature control collaborative strategy space is continuously optimized and analyzed to generate the temperature control collaborative strategy optimization space.

[0061] In the embodiment of the present application, first, the equipment temperature control collaborative strategy space is randomly extracted to obtain the first equipment temperature control collaborative strategy.

[0062] Next, based on the equipment application scenario, the temperature control characteristics of the first equipment temperature control collaborative strategy are predicted according to the equipment temperature control prediction network. Through the respective sub-networks in the equipment temperature control prediction network, corresponding calculation and processing are performed on the first equipment temperature control collaborative strategy to obtain the user experience prediction coefficient, the temperature control safety prediction coefficient, and the equipment loss prediction coefficient, and these prediction coefficients are integrated to obtain the first equipment temperature control prediction result.

[0063] Subsequently, the temperature control prediction result of the first device is input into the temperature control expectation constraint optimization network. According to the multi-dimensional temperature control expectation constraints set in the temperature control expectation constraint optimization network, it is judged whether the temperature control prediction result of the first device meets the multi-dimensional temperature control expectation constraints. The multi-dimensional temperature control expectation constraints include user experience degree constraint, temperature control safety constraint, and device loss constraint. These user experience degree constraint, temperature control safety constraint, and device loss constraint are all a preset coefficient. The user experience degree prediction coefficient, temperature control safety prediction coefficient, and device loss prediction coefficient are respectively compared with the preset coefficients in the multi-dimensional temperature control expectation constraints. If both the user experience degree prediction coefficient and the temperature control safety prediction coefficient are higher than the preset coefficients, and the device loss prediction coefficient is lower than the coefficient corresponding to the device loss constraint, it is considered that the temperature control prediction result of the first device meets the multi-dimensional temperature control expectation constraints, and the first device temperature control cooperation strategy is added to the temperature control cooperation strategy optimization space.

[0064] After that, continue to perform optimization analysis on the device temperature control cooperation strategy space according to the device temperature control prediction network and the temperature control expectation constraint optimization network, that is, randomly select strategies from the device temperature control cooperation strategy space and repeat the above steps until the traversal of the temperature control cooperation strategy space is completed to generate the temperature control cooperation strategy optimization space.

[0065] Further, in the method provided by the application embodiment, based on the device application scenario, according to the device temperature control prediction network, temperature control feature prediction is performed on the first device temperature control cooperation strategy to obtain the temperature control prediction result of the first device, and it further includes:

[0066] The device temperature control prediction network includes a user experience degree prediction sub-network, a temperature control safety prediction sub-network, and a device loss prediction sub-network; collect the basic parameters of the skin thermotherapy and itching relief device to obtain device basic data; input the device application scenario, the first device temperature control cooperation strategy, and the device basic data into the user experience degree prediction sub-network to obtain the first user experience degree prediction coefficient; input the device application scenario, the first device temperature control cooperation strategy, and the device basic data into the temperature control safety prediction sub-network to obtain the first temperature control safety prediction coefficient; input the device application scenario, the first device temperature control cooperation strategy, and the device basic data into the device loss prediction sub-network to obtain the first device loss prediction coefficient; add the first user experience degree prediction coefficient, the first temperature control safety prediction coefficient, and the first device loss prediction coefficient to the temperature control prediction result of the first device.

[0067] In the embodiment of the present application, the device temperature control prediction network includes a user experience degree prediction sub-network, a temperature control safety prediction sub-network, and a device loss prediction sub-network.

[0068] To obtain the temperature control prediction result of the first device, first collect the basic parameters of the skin thermotherapy and itching relief device to obtain the basic device data, including the power of the heating element, the sensitivity of the temperature sensor, the current operating state of the device (such as power output and temperature change rate), and environmental conditions (such as room temperature and humidity).

[0069] In the user experience prediction sub-network, the model is trained through a supervised learning method. The training data includes input and annotation coefficients. The input data is the historical temperature control strategy parameters (such as heating rate, target temperature, constant temperature time, etc.) and the corresponding basic device data. The annotation coefficient is the user experience coefficient, which is used to reflect the user's comfort score for the temperature control strategy. These scores are stored in the historical database through a questionnaire survey. In the training stage, by minimizing the error between the predicted output and the user experience coefficient (such as mean square error), the network weights are gradually optimized to establish the mapping relationship between the strategy parameters and the user comfort. In the prediction stage, this sub-network analyzes the impact of features such as heating rate and temperature control fluctuation on user comfort according to the input device application scenario and temperature control strategy, and outputs the first user experience prediction coefficient to quantify the performance of the strategy in terms of user experience.

[0070] Next, input the device application scenario (such as the user's skin type, current task requirements, environmental conditions, etc.), the first device temperature control cooperation strategy (including heating rate, target temperature, constant temperature time, etc.) and the collected basic device data into the user experience prediction sub-network. The user experience prediction sub-network is designed based on a convolutional neural network (CNN). This network extracts the feature patterns in the input data to predict the performance of the strategy in terms of user experience. In the training stage, the model uses historical strategy parameters (such as heating rate and target temperature) and basic device data as input, and the user's feedback score as the annotation label for supervised learning. By minimizing the error between the predicted value and the user experience score (such as mean square error), the model establishes the mapping relationship between the strategy parameters and the user comfort. In the prediction stage, based on the input strategy parameters and basic device data, this sub-network analyzes the impact of temperature control accuracy, heating rate, and temperature fluctuation on user comfort, and outputs the first user experience prediction coefficient to quantify the performance of the strategy in terms of user experience.

[0071] Subsequently, the same input data is passed to the temperature control safety prediction sub-network. This sub-network is based on a support vector machine and combines historical policy parameters with the device's security event data (such as overheating, hardware failures) to learn the impact of temperature control policies on device security. During the training phase, the model uses historical temperature control policy parameters and device basic data as input, and security event records as labels. Through the classification cross-entropy loss function, the network weights are optimized to learn the security risk characteristics of the policy. During the prediction phase, the temperature control safety prediction sub-network evaluates whether the heating rate of the policy is too fast or whether the target temperature exceeds the safe range based on the input data, and outputs the first temperature control safety prediction coefficient to quantify the performance of the current policy in terms of device operation security.

[0072] Next, the data is input into the device loss prediction sub-network. This sub-network is based on a multi-layer perceptron (MLP) and is used to analyze the long-term impact of temperature control policies on device hardware, such as power consumption and hardware lifespan. During the training phase, the model uses historical temperature control policy parameters and device operation data (such as cumulative heating time and operating power) as input, and the device's energy consumption records and lifespan test data as labels. Through regression analysis, the error between the predicted value and the labeled value is minimized to establish a mapping between policy parameters and device losses. During the prediction phase, this sub-network analyzes the impact of the input policy on device energy efficiency and hardware lifespan, and outputs the first device loss prediction coefficient to quantify the energy efficiency level and hardware loss degree of the current policy.

[0073] Finally, the first user experience prediction coefficient, the first temperature control safety prediction coefficient, and the first device loss prediction coefficient are integrated to generate the first device temperature control prediction result.

[0074] Step S500: Based on the target user, control the skin heat therapy and itching relief device according to the device temperature control policy optimization result to obtain control and monitoring data.

[0075] In the embodiment of the present application, the control unit of the skin heat therapy and itching relief device loads the device temperature control policy optimization result into the heating element and the temperature control system, and drives the device to accurately execute each instruction in the policy. During the execution process, the operating state of the skin heat therapy and itching relief device is monitored in real time, and data including the current temperature, power consumption, and device operating conditions is collected. These monitoring data are integrated to obtain control and monitoring data.

[0076] Step S600: Optimize the control of the skin heat therapy and itching relief device based on the control and monitoring data.

[0077] In the embodiments of the present application, first, the control monitoring data is analyzed to identify the deviations existing in the operation process, such as insufficient heating rate or fluctuations in the constant temperature stage exceeding the range. Then, an adaptive adjustment algorithm is used to dynamically adjust the key parameters, such as heating rate, target temperature, and constant temperature time, to generate an optimized operation strategy. Subsequently, the new control strategy is loaded into the control system of the device, driving the heating element and the temperature control module to work according to the optimized parameters to ensure accurate and stable operation. Finally, the operation is completed under the optimized strategy to achieve optimized control.

[0078] In the embodiments of the present application, in summary, the embodiments of the present application at least have the following technical effects:

[0079] The present application activates the control interaction channel of the skin heat therapy itching relief device. Among them, the skin heat therapy itching relief device includes a power supply unit, a control unit, and a heating element. The control interaction channel includes a data interaction layer, multiple usage scenario factors, and multiple control stage factors. The multiple usage scenario factors include user characteristics, the environment where the user is located, and the heat therapy task. The multiple control stage factors include the initial heating stage, the constant temperature control stage, and the cooling ending stage; based on the data interaction layer, according to the multiple usage scenario factors, the heat therapy request characteristics of the target user are interacted to construct the device application scenario; the multi-stage temperature control decision computing power constraint network is activated, and the skin heat therapy itching relief device is subjected to multi-stage temperature control collaborative decision-making in combination with the device application scenario and the multiple control stage factors to establish the device temperature control collaborative strategy space; based on the device temperature control multi-level optimization network, the device temperature control collaborative strategy space is subjected to multi-level joint optimization to obtain the device temperature control strategy optimization result; based on the target user, the skin heat therapy itching relief device is controlled according to the device temperature control strategy optimization result to obtain the control monitoring data; the skin heat therapy itching relief device is optimized and controlled based on the control monitoring data. The present invention solves the technical problems of low temperature control accuracy, poor adaptability, and difficulty in dynamic optimization existing in the prior art when detecting and controlling the temperature of the skin heat therapy itching relief device. By activating the control interaction channel, constructing the device application scenario, combining the multi-stage temperature control decision computing power constraint network and the device temperature control multi-level optimization network, the accurate temperature control collaborative decision-making and optimization control of the skin heat therapy itching relief device are realized, ensuring the efficiency, safety, and stability of the temperature control process, and achieving the technical effect of improving the user experience.

[0080] Embodiment 2, based on the temperature detection control method for the skin heat therapy itching relief device in the foregoing embodiment, with the same inventive concept, the present application also provides a computer-readable storage medium, on which a computer program is stored, and the computer program realizes the steps of any one of the methods in the foregoing Embodiment 1 when executed.

[0081] It should be noted that the above order of the embodiments of the present application is only for description and does not represent the superiority or inferiority of the embodiments. And the above description of specific embodiments of this specification has been made. The processes depicted in the drawings do not necessarily require the specific order and continuous order shown to achieve the desired result. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0082] The above are only the preferred embodiments of the present application and are not intended to limit the present application. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present application shall be included within the protection scope of the present application.

[0083] This specification and the drawings are only exemplary descriptions of the present application and are considered to have covered any and all modifications, variations, combinations, or equivalents within the scope of the present application. Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalent technologies, the present application is intended to include these changes and modifications.

Claims

1. Temperature detection and control method for skin heat therapy itching relief device, characterized in that, The method includes: Activating the control interaction channel of the skin thermotherapy itching relief device, where the skin thermotherapy itching relief device includes a power supply unit, a control unit, and a heating element, the control interaction channel includes a data interaction layer, multiple usage scenario factors, and multiple control stage factors, the multiple usage scenario factors include user characteristics, the environment where the user is located, and the thermotherapy task, and the multiple control stage factors include an initial temperature rise stage, a constant temperature control stage, and a cooling ending stage; Based on the data interaction layer, according to the multiple usage scenario factors, performing thermotherapy request feature interaction on the target user to construct a device application scenario; Activating the multi-stage temperature control decision computing power constraint network, and combining the device application scenario and the multiple control stage factors to perform multi-stage temperature control collaborative decision-making on the skin thermotherapy itching relief device to establish a device temperature control collaborative strategy space; Based on the device temperature control multi-level optimization network, performing multi-level joint optimization on the device temperature control collaborative strategy space to obtain the device temperature control strategy optimization result; Based on the target user, controlling the skin thermotherapy itching relief device according to the device temperature control strategy optimization result to obtain control monitoring data; Performing optimized control on the skin thermotherapy itching relief device based on the control monitoring data; Among them, activating the multi-stage temperature control decision computing power constraint network, and combining the device application scenario and the multiple control stage factors to perform multi-stage temperature control collaborative decision-making on the skin thermotherapy itching relief device to establish a device temperature control collaborative strategy space, includes: Based on the multi-stage temperature control decision computing power constraint network, performing decision constraint computing power analysis on the multiple control stage factors to obtain the initial stage decision constraint computing power, the constant temperature stage decision constraint computing power, and the cooling stage decision constraint computing power; Based on the initial stage decision constraint computing power, performing initial temperature rise stage control decision-making on the skin thermotherapy itching relief device according to the device application scenario to build an initial stage temperature control decision space; Based on the constant temperature stage decision constraint computing power, performing constant temperature stage control decision-making on the skin thermotherapy itching relief device according to the device application scenario to build a constant temperature stage temperature control decision space; Based on the cooling stage decision constraint computing power, performing cooling stage control decision-making on the skin thermotherapy itching relief device according to the device application scenario to build a cooling stage temperature control decision space; Based on the initial stage decision constraint computing power, the constant temperature stage decision constraint computing power, and the cooling stage decision constraint computing power, calculating the temperature control collaborative decision computing power; Based on the temperature control collaborative decision computing power, performing random decision combination on the initial stage temperature control decision space, the constant temperature stage temperature control decision space, and the cooling stage temperature control decision space to generate the device temperature control collaborative strategy space.

2. The method according to claim 1, characterized in that, Based on the multi-stage temperature control decision computing power constraint network, performing decision constraint computing power analysis on the multiple control stage factors to obtain the initial stage decision constraint computing power, the constant temperature stage decision constraint computing power, and the cooling stage decision constraint computing power, includes: The target user performs importance scoring on the multi-stage control phase factors to obtain multi-stage factor importance scores, where the multi-stage factor importance scores include initial stage importance scores, constant temperature stage importance scores, and cooling stage importance scores; Load the multi-stage factor importance score sample set and the multi-stage temperature control decision constraint computing power sample set; Using the multi-stage factor importance score sample set as input data and the multi-stage temperature control decision constraint computing power sample set as output data, train a BP neural network to build the multi-stage temperature control decision computing power constraint network; Input the multi-stage factor importance scores into the multi-stage temperature control decision computing power constraint network to obtain multi-stage temperature control decision constraint computing power, where the multi-stage temperature control decision constraint computing power includes the initial stage decision constraint computing power, the constant temperature stage decision constraint computing power, and the cooling stage decision constraint computing power.

3. The method according to claim 1, characterized in that, Based on the initial stage decision constraint computing power, perform initial heating stage control decision on the skin heat therapy and itching relief device according to the device application scenario, and build an initial stage temperature control decision space, including: Retrieve the initial heating stage control decision records of the skin heat therapy and itching relief device according to the device application scenario to obtain the initial stage temperature control decision sample set; Perform discrete data cleaning on the initial stage temperature control decision sample set to obtain the initial stage temperature control decision sample domain; Perform temperature control interval feature recognition on the initial stage temperature control decision sample domain to establish the initial stage temperature control constraint domain; Based on the initial stage decision constraint computing power, perform initial stage temperature control decision on the device application scenario according to the initial stage temperature control constraint domain to build the initial stage temperature control decision space.

4. The method according to claim 1, characterized in that, Based on the device temperature control multi-layer optimization network, perform multi-level joint optimization on the device temperature control collaborative strategy space to obtain the device temperature control strategy optimization result, including: The device temperature control multi-layer optimization network includes a device temperature control prediction network, a temperature control expectation constraint optimization network, and a temperature control fitness optimization network; Based on the device temperature control prediction network and the temperature control expectation constraint optimization network, perform optimization analysis on the device temperature control collaborative strategy space to obtain the temperature control collaborative strategy optimization space; Based on the temperature control fitness optimization network, perform temperature control fitness maximization optimization on the temperature control collaborative strategy optimization space to generate the device temperature control strategy optimization result, where the temperature control fitness optimization network includes temperature control fitness weight conditions, and the temperature control fitness weight conditions include user experience degree weight, temperature control safety weight, and device loss weight.

5. The method according to claim 4, wherein Based on the device temperature control prediction network and the temperature control expectation constraint optimization network, perform optimization analysis on the device temperature control collaborative strategy space to obtain the temperature control collaborative strategy optimization space, including: Extract the first device temperature control collaborative strategy according to the device temperature control collaborative strategy space; Based on the device application scenario, perform temperature control feature prediction on the first device temperature control collaborative strategy according to the device temperature control prediction network to obtain the first device temperature control prediction result; Input the temperature control prediction result of the first device into the temperature control expectation constraint optimization network, and determine whether the temperature control prediction result of the first device satisfies the multi-dimensional temperature control expectation constraints within the temperature control expectation constraint optimization network, where the multi-dimensional temperature control expectation constraints include user experience degree constraints, temperature control safety constraints, and device loss constraints; If the temperature control prediction result of the first device satisfies the multi-dimensional temperature control expectation constraints, add the temperature control cooperation strategy of the first device to the temperature control cooperation strategy optimization space; Continue to perform optimization analysis on the device temperature control cooperation strategy space according to the device temperature control prediction network and the temperature control expectation constraint optimization network, and generate the temperature control cooperation strategy optimization space.

6. The method according to claim 5, characterized in that, Based on the device application scenario, perform temperature control feature prediction on the temperature control cooperation strategy of the first device according to the device temperature control prediction network to obtain the temperature control prediction result of the first device, including: The device temperature control prediction network includes a user experience degree prediction sub-network, a temperature control safety prediction sub-network, and a device loss prediction sub-network; Collect the basic parameters of the skin heat therapy and itching relief device to obtain device basic data; Input the device application scenario, the temperature control cooperation strategy of the first device, and the device basic data into the user experience degree prediction sub-network to obtain the first user experience degree prediction coefficient; Input the device application scenario, the temperature control cooperation strategy of the first device, and the device basic data into the temperature control safety prediction sub-network to obtain the first temperature control safety prediction coefficient; Input the device application scenario, the temperature control cooperation strategy of the first device, and the device basic data into the device loss prediction sub-network to obtain the first device loss prediction coefficient; Add the first user experience degree prediction coefficient, the first temperature control safety prediction coefficient, and the first device loss prediction coefficient to the temperature control prediction result of the first device.

7. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by a processor, it implements the temperature detection and control method for a skin heat therapy and itching relief device according to any one of claims 1-6.

Images