Temperature control method and temperature controller equipment

Abstract

The invention provides a temperature control method and temperature controller equipment, and the method comprises the steps: obtaining the temperature adjustment data of a user for a target temperature control mode in a historical period, and the initial mode data of the target temperature control mode in the historical period; in the current period, performing iterative adjustment on the initial mode data through a preset clustering learning algorithm according to the temperature adjustment data to obtain target mode data of the target temperature control mode in the current period; and controlling the environment temperature of the current period based on the target mode data. According to the method, the mode data of the target temperature control mode can be adjusted according to the temperature adjustment data of the user for the target temperature control mode in the historical period, so that the behavior rule of the user is better identified, the temperature control process better fits the actual preference of the user, the satisfaction degree and the comfort degree of the user are improved, and the user experience is improved. And moreover, the energy consumption is reduced, and the energy-saving effect is improved.

Description

Technical Field

[0001] This application relates to the field of smart living technology, and more specifically, to a temperature control method and a temperature controller device. Background Technology

[0002] With increasing awareness of living comfort and energy conservation, air conditioning systems, as crucial energy-consuming devices in homes and offices, have seen their temperature control strategies optimized, becoming a research hotspot. Traditional air conditioning thermostats typically employ fixed temperature settings, such as 24℃ in summer and 20℃ in winter, to maintain a constant indoor temperature. Therefore, achieving energy-saving and consumption-reducing intelligent temperature control strategies while ensuring user comfort has become a vital direction in the design of current air conditioning control systems.

[0003] Existing intelligent temperature control systems mainly rely on preset mode switching. Specifically, users configure usage modes to achieve temperature control at different times.

[0004] However, existing technologies typically use fixed temperature range divisions in different modes, which cannot dynamically adjust the time-temperature setting rules according to the user's actual behavior, resulting in a poor user experience. Summary of the Invention

[0005] The purpose of this application is to provide a temperature control method and a temperature controller device to address the shortcomings of the prior art and solve the problem of poor user experience in the prior art.

[0006] To achieve the above objectives, the technical solutions adopted in the embodiments of this application are as follows: In a first aspect, one embodiment of this application provides a temperature control method, the method comprising: The system acquires temperature adjustment data for a target temperature control mode from a user's perspective during a historical period, as well as initial mode data for the target temperature control mode during that historical period. The initial mode data is used to indicate the correspondence between temperature and time. The temperature adjustment data includes at least one set of adjustment information, which includes adjustment time and adjustment temperature. In the current cycle, based on the temperature adjustment data, the initial mode data is iteratively adjusted using a preset clustering learning algorithm to obtain the target mode data for the target temperature control mode in the current cycle. Based on the target pattern data, the ambient temperature of the current cycle is controlled.

[0007] In one possible implementation, the step of iteratively adjusting the initial pattern data based on the temperature adjustment data using a preset clustering learning algorithm to obtain the target pattern data of the target temperature control mode in the current cycle includes: Initialize clustering parameters, which include at least: multiple cluster centers and a membership matrix; In the current iteration, the clustering parameters of the previous iteration are updated based on the temperature adjustment data to obtain the clustering parameters of the current iteration. Based on the clustering parameters of the current iteration and the preset iteration termination condition, it is determined whether to end the iteration. If so, then based on the clusters at the end of the iteration, determine the target mode data for the target temperature control mode in the current cycle.

[0008] In one possible implementation, updating the clustering parameters of the previous iteration based on the temperature adjustment data to obtain the clustering parameters of the current iteration includes: Based on the temperature adjustment data, the cluster centers of the previous iteration, and the adaptive parameters corresponding to each cluster center in the previous iteration, the membership matrix of the current iteration is calculated. The membership matrix is ​​used to indicate the membership degree of each group of adjustment information relative to each cluster center of the previous iteration. Based on the temperature adjustment data and the membership matrix of the current iteration, the cluster centers of the previous iteration are updated to obtain the cluster centers of the current iteration. Based on the temperature adjustment data and the cluster centers from the previous iteration, the adaptive parameters corresponding to each cluster center in the previous iteration are updated to obtain the adaptive parameters corresponding to each cluster center in the current iteration.

[0009] In one possible implementation, calculating the membership matrix for the current iteration based on the temperature adjustment data, the cluster centers from the previous iteration, and the adaptive parameters corresponding to each cluster center in the previous iteration includes: The adjustment information in the temperature adjustment data is traversed. For the current adjustment information, the membership degree of the current adjustment information relative to each cluster is calculated based on the current adjustment information, the cluster centers of the previous iteration, and the adaptive parameters corresponding to each cluster center in the previous iteration. After traversing each group of adjustment information, the membership degree of each group of adjustment information is replaced with the corresponding position in the membership degree matrix of the previous iteration round to obtain the membership degree matrix of the current iteration round.

[0010] In one possible implementation, calculating the membership degree of the current adjustment information relative to each cluster based on the current adjustment information, the cluster centers of the previous iteration, and the adaptive parameters corresponding to each cluster center in the previous iteration includes: Calculate the difference between the current adjustment information and the cluster center of the target cluster in the previous iteration round to obtain the difference result, and perform a modulo operation on the difference result to obtain the first modulus value; Calculate the ratio of the first modulus value to the adaptive parameter corresponding to the target cluster center in the previous iteration round to obtain the first ratio; Based on the first ratio, the fuzzy universe parameter, and the distance adjustment parameter, the membership degree of the current adjusted information relative to the target cluster is calculated.

[0011] In one possible implementation, updating the cluster centers of the previous iteration based on the temperature adjustment data and the membership matrix of the current iteration to obtain the cluster centers of the current iteration includes: Based on the membership degree of each set of adjustment information relative to the target cluster, a weighted average operation is performed on each set of adjustment information in the temperature adjustment data to calculate the cluster center of the target cluster in the current iteration round.

[0012] In one possible implementation, updating the adaptive parameters of each cluster center in the previous iteration based on the temperature adjustment data and the cluster centers from the previous iteration to obtain the adaptive parameters of each cluster center in the current iteration includes: Iterate through each group of adjustment information in the temperature adjustment data, and for the current adjustment information that has been traversed, calculate the difference between the current adjustment information and the cluster center of the target cluster in the previous iteration round to obtain the difference result corresponding to the current adjustment information. After the traversal is completed, the adaptive parameters corresponding to the target clustering of the current iteration are calculated based on the difference results corresponding to the adjustment information of each group.

[0013] In one possible implementation, determining the target pattern data of the target temperature control pattern in the current cycle based on the clusters at the end of the iteration includes: Based on the clusters at the end of the iteration, the initial pattern data is adjusted to obtain the target pattern data of the target temperature control mode in the current cycle.

[0014] In one possible implementation, adjusting the initial pattern data based on the clusters at the end of the iteration to obtain the target pattern data of the target temperature control mode in the current cycle includes: Project each cluster at the end of the iteration onto the horizontal axis to obtain at least one target time interval; Project each cluster at the end of the iteration onto the vertical axis to obtain at least one target temperature range; Based on each target time interval and each target temperature interval, the initial mode data is adjusted to obtain the target mode data of the target temperature control mode in the current cycle.

[0015] Secondly, another embodiment of this application provides a temperature control device, the device comprising: The acquisition module is used to acquire temperature adjustment data of the user for the target temperature control mode in a historical period and the initial mode data of the target temperature control mode in the historical period. The initial mode data is used to indicate the correspondence between temperature and time. The temperature adjustment data includes at least one set of adjustment information, which includes adjustment time and adjustment temperature. The adjustment module is used to iteratively adjust the initial mode data according to the temperature adjustment data in the current cycle through a preset clustering learning algorithm to obtain the target mode data of the target temperature control mode in the current cycle. The control module is used to control the ambient temperature of the current cycle based on the target mode data.

[0016] Thirdly, another embodiment of this application provides a temperature controller device, including: a processing module, a storage module, an RF module, a PCB board module, a KNX module, a step-down module, a screen module, a touch screen module, a measurement module, and a wake-up module. The storage module stores machine-readable instructions executable by the processing module. When the temperature controller device is running, the processing module executes the machine-readable instructions to perform the steps of any of the methods described in the first aspect above.

[0017] The beneficial effects of this application are as follows: By acquiring user temperature adjustment data for the target temperature control mode in historical cycles and the initial mode data of the target temperature control mode in those historical cycles, and then iteratively adjusting the initial mode data based on the temperature adjustment data in the current cycle using a preset clustering learning algorithm, the target mode data for the target temperature control mode in the current cycle is obtained. Based on this target mode data, the ambient temperature in the current cycle is controlled. This allows for adjustments to the target temperature control mode's mode data based on user temperature adjustment data in historical cycles, thereby better identifying user behavior patterns and making the temperature control process more aligned with user preferences, improving user satisfaction and comfort, and ultimately enhancing the user experience. Furthermore, by learning from the temperature adjustment data using the preset clustering learning algorithm, dynamic learning and adaptive control of the temperature control process can be achieved, balancing comfort and energy-saving goals, which helps reduce energy consumption and improve energy efficiency. Attached Figure Description

[0018] To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of this application and should not be regarded as a limitation of the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0019] Figure 1 This is a schematic diagram illustrating an application scenario of the temperature control method provided in the embodiments of this application; Figure 2 A schematic diagram of the structure of a temperature controller device provided in an embodiment of this application; Figure 3 This is a schematic diagram of an application process for the temperature control method provided in an embodiment of this application; Figure 4 A schematic flowchart of a temperature control method provided in an embodiment of this application; Figure 5 A schematic flowchart illustrating the process of obtaining target mode data of the target temperature control mode in the current cycle in the temperature control method provided in the embodiments of this application; Figure 6 This is a schematic flowchart illustrating the process of obtaining clustering parameters for the current iteration in the temperature control method provided in this application embodiment. Figure 7 A flowchart illustrating the calculation of the membership matrix for the current iteration in the temperature control method provided in this application embodiment; Figure 8 A schematic diagram illustrating the process of calculating the membership degree of the current adjustment information relative to each cluster in the temperature control method provided in the embodiments of this application; Figure 9 A schematic diagram of a process for obtaining the adaptive parameters of each cluster center in the current iteration round in the temperature control method provided in the embodiments of this application; Figure 10 Another flowchart illustrating the process of obtaining target temperature control mode data in the current cycle in the temperature control method provided in the embodiments of this application; Figure 11 This is a schematic diagram of a temperature control device provided in an embodiment of this application. Detailed Implementation

[0020] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. It should be understood that the accompanying drawings in this application are for illustrative and descriptive purposes only and are not intended to limit the scope of protection of this application. Furthermore, it should be understood that the schematic drawings are not drawn to scale. The flowcharts used in this application illustrate operations implemented according to some embodiments of this application. It should be understood that the operations in the flowcharts may not be implemented in sequence, and steps without logical contextual relationships may be reversed or implemented simultaneously. In addition, those skilled in the art, guided by the content of this application, may add one or more other operations to the flowcharts, or remove one or more operations from the flowcharts.

[0021] Furthermore, the described embodiments are merely some, not all, of the embodiments of this application. The components of the embodiments of this application described and illustrated herein can typically be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of this application provided in the accompanying drawings is not intended to limit the scope of the claimed application, but merely to illustrate selected embodiments of the application. All other embodiments obtained by those skilled in the art based on the embodiments of this application without inventive effort are within the scope of protection of this application.

[0022] It should be noted that the term "comprising" will be used in the embodiments of this application to indicate the presence of the features declared thereafter, but does not exclude the addition of other features.

[0023] Existing intelligent temperature control systems mainly rely on preset mode switching. Specifically, users configure usage modes to achieve temperature control at different times.

[0024] However, existing technologies typically use fixed temperature range divisions in different modes, which cannot dynamically adjust the time-temperature setting rules according to the user's actual behavior, resulting in a poor user experience.

[0025] This application proposes a temperature control method to address the aforementioned problems. It acquires user temperature adjustment data for a target temperature control mode over historical periods, along with the initial mode data of that mode during those periods. In the current period, based on the temperature adjustment data, a preset clustering learning algorithm iteratively adjusts the initial mode data to obtain the target mode data for the current period. Based on this target mode data, the ambient temperature for the current period is controlled. This method adjusts the target temperature control mode's mode data according to the user's temperature adjustment data over historical periods, making the temperature control process more aligned with user preferences, improving user satisfaction and comfort, and ultimately enhancing the user experience. Furthermore, the preset clustering learning algorithm enables dynamic learning and adaptive control of the temperature control process, thereby reducing energy consumption and improving energy efficiency.

[0026] First, the application scenarios involved in the temperature control method provided in the embodiments of this application will be described.

[0027] Figure 1 This is a schematic diagram illustrating an application scenario of the temperature control method provided in this application embodiment, with reference to... Figure 1 As shown, the temperature control method provided in this application embodiment is applied to a smart living scenario. A smart living scenario refers to a scenario that improves the comfort, safety, energy efficiency, and convenience of the human living environment through intelligent means.

[0028] Specifically, smart living scenarios involve smart living systems, terminal control devices, and controlled devices.

[0029] Among them, the smart living system is a closed-loop system that comprehensively perceives and intelligently controls the living environment. Through the smart living system, environmental parameters (temperature, humidity, air quality, light, etc.), equipment (air conditioning, lighting, curtains, security, etc.), and user behaviors (work and rest, preferences, health status) in the living space can be perceived, analyzed, predicted, and controlled to achieve a personalized, energy-saving, and automated living experience.

[0030] Among them, the controlled devices are those that are controlled in the smart living scenario, such as air conditioning equipment, lighting equipment, curtain equipment, security equipment, etc.

[0031] Among them, the terminal control device is the control device used to control the controlled device.

[0032] For example, taking a smart living scenario specifically as a smart temperature living scenario, a smart living scenario involves a smart living system, thermostat equipment, and air conditioning equipment.

[0033] in, Figure 2This is a schematic diagram of a temperature controller device provided in an embodiment of this application, with reference to... Figure 2 As shown, the temperature controller device is a temperature terminal control device, including: a processing module, a storage module, a radio frequency module (RF module), a printed circuit board module (PCB module), a KNX communication module (KNX module), a step-down module, a screen module, a touch screen module, a measurement module, and a wake-up module. The storage module stores machine-readable instructions that the processing module can execute. When the temperature controller device is running, the processing module executes the machine-readable instructions to perform the steps of the temperature control method provided in the embodiments of this application.

[0034] For example, Figure 3 This is a schematic diagram of an application process for the temperature control method provided in an embodiment of this application, referring to... Figure 3 As shown, after the thermostat is powered by mains electricity, it first performs voltage reduction and wake-up processing through a step-down module and a wake-up module, and then collects the user-set air conditioner temperature / fan speed, time, and temperature and humidity sensor information at different times through a measurement module, thereby realizing temperature updates.

[0035] Based on this, the thermostat device stores the user-set temperature and time through the storage module, and executes the steps of the temperature control method provided in this application embodiment through the calculation module to obtain target mode data. This allows for settings changes through the smart living system and control of the air conditioning equipment through the KNX module to achieve temperature control.

[0036] The temperature control method provided in this application will be described in detail below with reference to several embodiments.

[0037] Figure 4 This is a schematic flowchart of a temperature control method provided in an embodiment of this application, referring to... Figure 3 As shown, the executing entity of this method can be any electronic device with processing capabilities, such as the aforementioned thermostat device. The method includes: S401. Obtain the temperature adjustment data of the target temperature control mode for the user in the historical period and the initial mode data of the target temperature control mode in the historical period.

[0038] It is understandable that users can set the temperature control mode of the air conditioner and adjust the temperature or fan speed through the thermostat when using the air conditioner.

[0039] Optionally, the user can obtain temperature adjustment data for the target temperature control mode in the historical period and the initial mode data of the target temperature control mode in the historical period.

[0040] The historical period can be the previous period or several previous periods, and the length of the period can be one week, one day, or one month; this application does not impose any restrictions on this. The target temperature control mode can be any temperature control mode.

[0041] The initial mode data is used to indicate the correspondence between temperature and time. The temperature adjustment data includes at least one set of adjustment information, which includes the adjustment time and the adjustment temperature.

[0042] For example, depending on the season, there can be multiple temperature control modes. For instance, in summer, there can be a first low-carbon energy-saving mode, a first healthy comfort mode, a second low-carbon energy-saving mode, and a second healthy comfort mode. The first low-carbon energy-saving mode and the first healthy comfort mode can be used when the user is not asleep, while the second low-carbon energy-saving mode and the second healthy comfort mode can be used when the user is asleep with a blanket.

[0043] For example, taking the target temperature control mode as the first health and comfort mode and the historical period as the past week, the initial mode data of the target temperature control mode in the historical period can be the correspondence between temperature and time when the user selected the first health and comfort mode in the past week, as shown below:

[0044] Where time represents hours and T2 represents temperature.

[0045] For example, continuing with the target temperature control mode as the first health and comfort mode, and the historical period as the past week, the user's temperature adjustment data for the target temperature control mode during the historical period is the adjustment time and temperature adjusted by the user in the first health and comfort mode over the past week. For example, if the user adjusts the temperature to 25 degrees at 9:00 AM, then the adjustment information would be: 9:00 AM, 25 degrees.

[0046] S402. In the current cycle, based on the temperature adjustment data, the initial pattern data is iteratively adjusted using a preset clustering learning algorithm to obtain the target pattern data of the target temperature control mode in the current cycle.

[0047] Optionally, within the current cycle, based on temperature adjustment data, a preset clustering learning algorithm is used to learn the user's temperature adjustment habits, thereby iteratively adjusting the initial mode data to obtain the target mode data for the current cycle. The target mode data indicates the correspondence between temperature and time in the current cycle.

[0048] The preset clustering learning algorithms may include: K-means clustering algorithm, hierarchical clustering algorithm, density clustering algorithm, grid clustering algorithm and fuzzy clustering algorithm, etc.

[0049] For example, continuing with the target temperature control mode as the primary health and comfort mode, and using the past week as an example, assuming the user frequently adjusts the temperature at 9 AM, and the adjusted temperature is consistently around 25°C, then multiple sets of adjustment information can be obtained: 9 AM, 25 degrees. By using a preset clustering algorithm to learn from the user's temperature adjustment data and iteratively adjusting the initial mode data, the target mode data is obtained as shown below:

[0050] in, For temperature, time represents time. The target mode data is used to indicate the temperature corresponding to each time interval within multiple time intervals.

[0051] S403. Based on the target pattern data, control the ambient temperature for the current cycle.

[0052] Optionally, after obtaining the target mode data, the ambient temperature of the current cycle can be controlled according to the time and temperature indicated by the target mode data.

[0053] For example, if we continue to use the target temperature control mode as the first health and comfort mode and the historical period is the past week, we can set the temperature of the air conditioner to 22°C every day from 8 pm to 10 pm in the current period.

[0054] In this embodiment, by acquiring user temperature adjustment data for the target temperature control mode in historical cycles and the initial mode data of the target temperature control mode in those historical cycles, and then iteratively adjusting the initial mode data based on the temperature adjustment data in the current cycle using a preset clustering learning algorithm, the target mode data for the target temperature control mode in the current cycle is obtained. Based on this target mode data, the ambient temperature in the current cycle is controlled. This allows for adjustments to the target temperature control mode's mode data according to the user's temperature adjustment data in historical cycles, thereby better identifying user behavior patterns and making the temperature control process more aligned with the user's actual preferences, improving user satisfaction and comfort, and ultimately enhancing the user experience. Furthermore, by learning from the temperature adjustment data through the preset clustering learning algorithm, dynamic learning and adaptive control of the temperature control process can be achieved, balancing comfort and energy-saving goals, which helps reduce energy consumption and improve energy efficiency.

[0055] In one possible implementation, Figure 5A flowchart illustrating the process of obtaining target temperature control mode data in the current cycle in the temperature control method provided in this application embodiment, referring to... Figure 5 As shown, in step S402 above, based on the temperature adjustment data, the initial model data is iteratively adjusted using a preset clustering learning algorithm to obtain the target model data for the target temperature control model in the current cycle, including: S501. Initialize clustering parameters.

[0056] It is understandable that before iteratively adjusting the initial pattern data through a preset clustering learning algorithm, the data space of the clustering algorithm and the clustering parameters can be initialized first.

[0057] Optionally, the data space of the clustering algorithm is divided into several uniform grid cells, each grid cell is numbered, and the grid set is initialized as an empty set.

[0058] Optionally, clustering parameters are initialized, wherein the clustering parameters include at least: multiple cluster centers and a membership matrix, and the clustering parameters also include: the number of clusters, the membership matrix, an adaptive rate of change parameter, a distance adjustment parameter, and the number of fuzzy universes.

[0059] The cluster number refers to the number of clusters into which the input data is divided, i.e., the number of clusters. The cluster number is used to indicate the number of time periods or patterns of different temperature regulation habits in temperature regulation data.

[0060] The membership matrix indicates the degree of membership of each data point to each cluster, that is, the degree to which each data point belongs to each cluster. Specifically, each data point represents an adjustment information.

[0061] Here, the cluster center refers to the center of each cluster, corresponding to a type of adjustment information.

[0062] Among them, the adaptive rate of change parameter is used to control the update speed of the adaptive parameters of each cluster. Specifically, user behavior may change with seasons, work and rest, health status, etc., and the adaptive rate of change parameter is used to adjust the sensitivity to these changes during the learning process.

[0063] The distance adjustment parameter controls the weight of the distance between data points and cluster centers in the calculation of the membership matrix. A larger distance adjustment parameter indicates a greater influence of distance, meaning that clustering is more dependent on distance. A smaller distance adjustment parameter indicates that clustering focuses more on data density.

[0064] The number of fuzzy universes can be a fuzzy index, a parameter used to control the degree of fuzziness in membership. The larger the number of fuzzy universes, the more fuzzy the membership, and the higher the degree to which a data point can belong to multiple clusters. The smaller the number of fuzzy universes, the more explicit the membership, and the more inclined to classify the data point into one cluster.

[0065] For example, the number of clusters can be initialized to half the number of grid cells, and each cluster center can be randomly initialized. Based on the initialized cluster centers, the membership matrix can be initially calculated.

[0066] For example, the adaptive rate of change parameter, distance adjustment parameter, and number of fuzzy universes can also be initialized to preset constants.

[0067] S502. In the current iteration, the clustering parameters of the previous iteration are updated based on the temperature adjustment data to obtain the clustering parameters of the current iteration. Based on the clustering parameters of the current iteration and the preset iteration termination condition, it is determined whether to end the iteration.

[0068] Optionally, in each iteration, the clustering parameters of the previous iteration can be calculated based on the temperature adjustment data and the clustering parameters of the previous iteration to update the clustering parameters of the current iteration. Then, based on the clustering parameters of the current iteration and the preset iteration termination condition, it can be determined whether to end the iteration.

[0069] Updating the clustering parameters of the previous iteration can be achieved by updating the cluster centers and membership matrix of the previous iteration to obtain the cluster centers and membership matrix of the current iteration.

[0070] For example, updating the clustering parameters of the previous iteration can be done by updating the cluster centers of the previous iteration to obtain the cluster centers of the current iteration. This allows the temperature and time when the ambient temperature is controlled in the current cycle to be represented by the cluster centers after the iteration ends.

[0071] Optionally, the membership parameter can be calculated based on the membership matrix of the current iteration and the membership matrix of the previous iteration. If the membership parameter is less than a preset membership error threshold, the iteration ends; if the membership parameter is greater than the preset membership error threshold, the next iteration continues.

[0072] Optionally, adaptive parameter data can be calculated based on the adaptive parameters of the current iteration and the adaptive parameters of the previous iteration. If the adaptive parameter data is less than the preset adaptive parameter error threshold, the iteration is terminated. If the adaptive parameter data is greater than the preset adaptive parameter error threshold, the next iteration continues.

[0073] By iteratively updating the clustering parameters based on temperature adjustment data, it is possible to identify users' specific preferences at different times, thereby dynamically adjusting the target pattern data. At the same time, it can also filter out users' occasional misoperations or atypical behaviors, making the obtained target pattern data more stable.

[0074] S503. If so, then determine the target mode data of the target temperature control mode in the current cycle based on each cluster at the end of the iteration.

[0075] It is understandable that when the iteration ends, the clustering learning is completed, and multiple clusters can be obtained. Each cluster includes: cluster center, set of cluster members belonging to the cluster, membership matrix and adaptive parameters.

[0076] Optionally, if it is determined to end the iteration, the target pattern data of the target temperature control pattern in the current cycle is determined based on the clusters at the end of the iteration.

[0077] Optionally, calculations can be performed based on the clustering parameters at the end of the iteration to obtain the calculation results, and the initial model data can be adjusted based on the calculation results to obtain the target model data of the target temperature control model in the current cycle.

[0078] For example, each cluster center at the end of the iteration can be used as a new time-temperature setpoint to obtain multiple time-temperature setpoints. Based on each time-temperature setpoint, the corresponding data can be found from the initial pattern data and replaced to obtain the target pattern data of the target temperature control mode in the current cycle.

[0079] In one possible implementation, Figure 6 This is a schematic flowchart illustrating the process of obtaining clustering parameters for the current iteration in the temperature control method provided in this application embodiment, with reference to... Figure 6 As shown, in step S502 above, the clustering parameters of the previous iteration are updated based on the temperature adjustment data to obtain the clustering parameters of the current iteration, including: S601. Based on the temperature adjustment data, the cluster centers of the previous iteration, and the adaptive parameters corresponding to each cluster center in the previous iteration, calculate the membership matrix of the current iteration.

[0080] Optionally, the membership matrix of the current iteration can be calculated based on the temperature adjustment data, the cluster centers of the previous iteration, and the adaptive parameters corresponding to each cluster center in the previous iteration.

[0081] The adaptive parameter corresponding to each cluster center in the previous iteration is used to control the sensitivity of the membership degree of the data point to the cluster as the distance changes. The adaptive parameter corresponding to each cluster center in the previous iteration can be calculated by combining the average distance from all points in the cluster to the center with the adaptive rate of change parameter.

[0082] For example, the adaptive parameters corresponding to each cluster center in the previous iteration can be calculated by the local density of each cluster, the data distribution, or the distance between adjacent clusters.

[0083] The membership matrix indicates the membership degree of each group of adjustment information relative to the cluster centers of the previous iteration.

[0084] S602. Based on the temperature adjustment data and the membership matrix of the current iteration, update the cluster centers of the previous iteration to obtain the cluster centers of the current iteration.

[0085] Optionally, after obtaining the membership matrix of the current iteration, the cluster centers of the current iteration can be calculated based on the membership matrix of the current iteration and the temperature adjustment data.

[0086] For example, the cluster centers for the current iteration can be obtained by using the gradient descent method based on the membership matrix of the current iteration and the temperature adjustment data.

[0087] S603. Based on the temperature adjustment data and the cluster centers of the previous iteration, update the adaptive parameters of each cluster center in the previous iteration to obtain the adaptive parameters of each cluster center in the current iteration.

[0088] Optionally, based on the temperature adjustment data and the cluster centers of the previous iteration, the data distribution of each cluster is determined, and the adaptive parameters corresponding to each cluster center in the previous iteration are updated based on the data distribution of each cluster, so as to obtain the adaptive parameters corresponding to each cluster center in the current iteration.

[0089] In the current iteration, the membership matrix of the current iteration is updated first. Then, based on the temperature adjustment data and the membership matrix of the current iteration, the cluster centers of the previous iteration are updated to obtain the cluster centers of the current iteration. Next, based on the temperature adjustment data and the cluster centers of the previous iteration, the adaptive parameters corresponding to each cluster center in the previous iteration are updated to obtain the adaptive parameters corresponding to each cluster center in the current iteration. This ensures that the updates of cluster centers and adaptive parameters are based on the latest membership matrix, thereby more accurately capturing changes in users' temperature preferences over different time periods. Furthermore, since each iteration updates the membership, centers, and parameters based on the latest data distribution and user behavior, the interpretability of the clustering results is improved, enabling automatic optimization of personalized temperature adjustment strategies and enhancing the user experience.

[0090] In one possible implementation, Figure 7 A flowchart illustrating the calculation of the membership matrix for the current iteration in the temperature control method provided in this application embodiment is shown below. Figure 7 As shown, in step S601 above, the membership matrix for the current iteration is calculated based on temperature adjustment data, the cluster centers from the previous iteration, and the adaptive parameters corresponding to each cluster center in the previous iteration. This matrix includes: S701. Traverse each group of adjustment information in the temperature adjustment data. For the current adjustment information that has been traversed, calculate the membership degree of the current adjustment information relative to each cluster based on the current adjustment information, the cluster centers of the previous iteration, and the adaptive parameters corresponding to each cluster center in the previous iteration.

[0091] Optionally, the adjustment information of each group in the temperature adjustment data can be traversed. For the current adjustment information that has been traversed, the membership degree of the current adjustment information relative to each cluster can be calculated based on the current adjustment information, the cluster centers of the previous iteration, and the adaptive parameters corresponding to each cluster center in the previous iteration.

[0092] For example, the membership degree of the current adjustment information relative to each cluster can be calculated based on the current adjustment information, the cluster centers of the previous iteration, the adaptive parameters of each cluster center in the previous iteration, and a preset membership degree calculation formula.

[0093] S702. After traversing each group of adjustment information, replace the membership degree of each group of adjustment information with the corresponding position in the membership degree matrix of the previous iteration round to obtain the membership degree matrix of the current iteration round.

[0094] Optionally, after all the adjustment information has been traversed, the membership degree of each group of adjustment information is replaced with the corresponding position in the membership degree matrix of the previous iteration to obtain the membership degree matrix of the current iteration. Thus, the membership degree of each group of adjustment information in the current iteration can be characterized by the membership degree of each group of adjustment information in each cluster in the current iteration through the membership degree matrix of the current iteration.

[0095] For example, after all the adjustment information has been traversed, the membership degree of each group of adjustment information is inserted into the corresponding position in the membership degree matrix of the previous iteration according to the index of each group of adjustment information, so as to obtain the membership degree matrix of the current iteration.

[0096] In one possible implementation, Figure 8 A flowchart illustrating the calculation of the membership degree of the current adjustment information relative to each cluster in the temperature control method provided in this application embodiment, referring to... Figure 8 As shown, in S701 above, based on the current adjustment information, the cluster centers of the previous iteration, and the adaptive parameters corresponding to each cluster center in the previous iteration, the membership degree of the current adjustment information relative to each cluster is calculated, including: S801. Calculate the difference between the current adjustment information and the cluster center of the target cluster in the previous iteration, obtain the difference result, and perform a modulo operation on the difference result to obtain the first modulus value.

[0097] Optionally, taking the membership degree of the current adjustment information relative to the target cluster as an example, the target cluster can be any cluster. The difference between the cluster centers of the current adjustment information and the target cluster in the previous iteration is calculated to obtain the difference result. The difference result is then moduloed to obtain the first modulus value.

[0098] For example, the current adjustment information can be calculated. Compared with the previous iteration round Target clustering Cluster center The difference is obtained by finding the difference result. Then, perform a modulo operation on the difference result to obtain the first modulus value. .

[0099] S802. Calculate the ratio of the first modulus value to the adaptive parameter corresponding to the target cluster center in the previous iteration round to obtain the first ratio.

[0100] Optionally, the first modulus can be calculated. Adaptive parameters corresponding to the target cluster centers in the previous iteration round The ratio of the two values ​​is used to obtain the first ratio. .

[0101] S803. Based on the first ratio, the fuzzy universe parameter, and the distance adjustment parameter, calculate the membership degree of the current adjusted information relative to the target cluster.

[0102] Alternatively, it can be based on the first ratio Fuzzy universe parameters and distance adjustment parameters The current adjustment information is calculated. Compared to target clustering membership degree .

[0103] For example, the current adjustment information can be calculated using the following formula. Compared to target clustering membership degree :

[0104] in, For the first Group adjustment information, For the previous iteration round Mid-target clustering Cluster centers These are the adaptive parameters corresponding to the previous iteration round. For fuzzy universe parameters, Adjust the distance parameters.

[0105] By using the current adjustment information, the cluster centers from the previous iteration, the adaptive parameters of each cluster center in the previous iteration, the fuzzy universe of discourse parameter, and the distance adjustment parameter, the membership degree of the current adjustment information relative to each cluster can be calculated. This allows for more accurate identification of user behavior patterns and improves the clustering algorithm's accuracy in recognizing user temperature adjustment behavior. Furthermore, by introducing the fuzzy universe of discourse parameter, the membership degree distribution can be adjusted to prevent misclassification. Introducing the distance adjustment parameter controls the cluster compactness to prevent overfitting. Introducing the adaptive parameters corresponding to each cluster center in the previous iteration adapts to user schedules and seasonal changes, thus dynamically adapting to changes in user behavior. This avoids misjudging user preferences due to short-term behavioral fluctuations and also improves the stability and convergence speed of the clustering algorithm, reducing misjudgments and oscillations.

[0106] In one possible implementation, in step S602 above, the cluster centers of the previous iteration are updated based on the temperature adjustment data and the membership matrix of the current iteration, resulting in the cluster centers of the current iteration, including: Based on the membership degree of each group of adjustment information relative to the target cluster, a weighted average calculation is performed on each group of adjustment information in the temperature adjustment data to calculate the cluster center of the target cluster in the current iteration round.

[0107] Optionally, the membership degree of each group of adjustment information relative to the target cluster can be used as a weight to perform a weighted average operation on each group of adjustment information in the temperature adjustment data, and the cluster center of the target cluster in the current iteration round can be calculated.

[0108] For example, the target cluster can be any cluster, and the cluster centers of the target cluster in the current iteration round are calculated. For example, you can refer to the following formula for calculation:

[0109] in, For the current iteration round Mid-target clustering Cluster centers For the first Group adjustment information, To adjust the total number of messages, Information for current adjustments Compared to target clustering membership degree For fuzzy universe parameters.

[0110] By calculating the membership degree of each set of adjustment information relative to the target cluster, a weighted average is performed on the temperature adjustment data to obtain the cluster center of the target cluster in the current iteration. This method preserves the dominant role of high-membership samples in the cluster center and weakens the interference of low-membership samples. It also avoids drastic shifts in cluster centers due to outliers or noise, thereby improving the stability and convergence of the clustering results. Furthermore, it enhances the robustness of the clustering process.

[0111] In one possible implementation, Figure 9 This application provides a schematic flowchart illustrating the process of obtaining the adaptive parameters of each cluster center in the current iteration round within the temperature control method. (Refer to...) Figure 9 As shown, in step S603 above, based on the temperature adjustment data and the cluster centers from the previous iteration, the adaptive parameters corresponding to each cluster center in the previous iteration are updated to obtain the adaptive parameters corresponding to each cluster center in the current iteration, including: S901. Traverse each group of adjustment information in the temperature adjustment data. For the current adjustment information that has been traversed, calculate the difference between the current adjustment information and the cluster center of the target cluster in the previous iteration round to obtain the difference result corresponding to the current adjustment information.

[0112] Optionally, each set of adjustment information can be traversed, and for the current adjustment information that has been traversed, the difference between the current adjustment information and the cluster center of the target cluster in the previous iteration can be calculated to obtain the difference result corresponding to the current adjustment information.

[0113] For example, the current adjustment information can be calculated. Compared with the previous iteration round Target clustering Cluster center The difference is used to obtain the difference result corresponding to the current adjustment information. .

[0114] S902. After the traversal is completed, the adaptive parameters corresponding to the target clustering of the current iteration are calculated based on the difference results corresponding to the adjustment information of each group.

[0115] Optionally, after the traversal is completed, the adaptive parameters corresponding to the target cluster of the current iteration are calculated based on the difference results corresponding to the adjustment information of each group and the preset calculation formula.

[0116] For example, the target cluster can be any cluster to calculate the current iteration round. Target clustering Corresponding adaptive parameters For example, you can refer to the following formula for calculation:

[0117] in, For adaptive rate of change parameters, Clustering for the target The total number of data points in the data. To adjust the total number of messages, For the first Group adjustment information, For the previous iteration round Mid-target clustering Cluster centers.

[0118] By adjusting the information in each group, the difference result corresponding to the current adjustment information is calculated. After the traversal is completed, the adaptive parameters corresponding to the target clustering of the current iteration are calculated based on the difference result corresponding to the adjustment information in each group. It can automatically identify high-density regions, thereby making more detailed divisions in time periods with dense user behavior. It can also reduce the membership degree in regions with low data point density, thereby reducing the impact of noise points on cluster centers, thus achieving dynamic balance and convergence control of the clustering process.

[0119] In one possible implementation, S503 above determines the target mode data for the current cycle based on the clusters at the end of the iteration, including: Based on the clusters at the end of the iteration, the initial pattern data is adjusted to obtain the target pattern data of the target temperature control mode in the current cycle.

[0120] Optionally, calculations can be performed on each cluster at the end of the iteration to obtain multiple calculation results. Based on each calculation result, the corresponding data can be found from the initial pattern data and replaced to obtain the target pattern data of the target temperature control mode in the current cycle.

[0121] For example, at the end of the iteration, the weights of each cluster are weighted and averaged over the cluster centers to obtain a temperature setpoint curve. Based on the temperature setpoint curve, the initial model data is adjusted to obtain the target model data for the target temperature control model in the current cycle. The weights of each cluster can be calculated using the membership matrix of each cluster or the amount of data in each cluster.

[0122] By adjusting the initial pattern data through the clusters at the end of the iteration, the target pattern data of the target temperature control mode in the current cycle is obtained. The target pattern data can be automatically updated according to the continuous changes in user behavior, eliminating the need for frequent manual settings by the user. At the same time, the target pattern data can also be dynamically adjusted to improve the user experience.

[0123] In one possible implementation, Figure 10 Another flowchart illustrating the process of obtaining target temperature control mode data in the current cycle in the temperature control method provided in this application embodiment is shown below. Figure 10 As shown, the initial model data is adjusted based on the clusters at the end of the iteration to obtain the target model data for the target temperature control model in the current cycle, including: S1001. Project each cluster at the end of the iteration onto the horizontal axis to obtain at least one target time interval.

[0124] Optionally, each cluster at the end of the iteration can be projected onto the horizontal axis, and at least one target time interval can be obtained based on the cluster center and the values ​​of the cluster members on the horizontal axis. Here, the horizontal axis is the time axis.

[0125] For example, the cluster center of each cluster can be mapped onto a time axis, and continuous time intervals can be divided according to the intervals between each time point, thereby obtaining at least one target time interval.

[0126] For example, the cluster boundaries of each cluster can also be mapped onto a time axis to obtain at least one target time interval.

[0127] S1002. Project each cluster at the end of the iteration onto the vertical axis to obtain at least one target temperature range.

[0128] Optionally, each cluster at the end of the iteration can be projected onto the vertical axis, and at least one target temperature range can be obtained based on the cluster center and the values ​​of the cluster members on the vertical axis. Here, the vertical axis is the temperature coordinate axis.

[0129] For example, the cluster center of each cluster can be mapped onto a temperature coordinate axis, and continuous temperature intervals can be divided according to the intervals between temperature points, thereby obtaining at least one target temperature interval.

[0130] For example, the cluster boundaries of each cluster can also be mapped onto a temperature coordinate axis to obtain at least one target temperature range.

[0131] S1003. Adjust the initial mode data according to each target time interval and each target temperature interval to obtain the target mode data of the target temperature control mode in the current cycle.

[0132] Optionally, the target time intervals generated by clustering are matched with the time periods in the initial pattern data. If the times are different, the time periods in the initial pattern data are replaced with the target time intervals generated by clustering.

[0133] Optionally, the matched target temperature range is assigned to the corresponding time period to obtain the target mode data of the target temperature control mode in the current cycle.

[0134] By projecting the clustering results onto the horizontal and vertical axes respectively, the target time interval and target temperature interval are obtained. Based on this, the initial model data is adjusted to obtain the target model data of the target temperature control mode in the current cycle. This allows for more precise control of temperature changes, avoiding discomfort or energy waste caused by coarse-grained settings, while also improving comfort and energy efficiency.

[0135] Based on the same inventive concept, this application also provides a temperature control device corresponding to the temperature control method. Since the principle of the device in this application is similar to the temperature control method described above in this application, the implementation of the device can refer to the implementation of the method, and the repeated parts will not be described again.

[0136] Reference Figure 11 As shown, Figure 11 This is a schematic diagram of a temperature control device provided in an embodiment of the present application. The device includes: an acquisition module 1101, an adjustment module 1102, and a control module 1103. The acquisition module 1101 is used to acquire the temperature adjustment data of the target temperature control mode by the user in the historical period and the initial mode data of the target temperature control mode in the historical period. The initial mode data is used to indicate the correspondence between temperature and time. The temperature adjustment data includes at least one set of adjustment information, which includes the adjustment time and the adjustment temperature. The adjustment module 1102 is used to adjust the temperature data according to the current cycle, and to iteratively adjust the initial pattern data through a preset clustering learning algorithm to obtain the target pattern data of the target temperature control mode in the current cycle. The control module 1103 is used to control the ambient temperature of the current cycle based on the target mode data.

[0137] In one possible implementation, adjustment module 1102 is specifically used for: Initialize the clustering parameters, which should include at least: multiple cluster centers and a membership matrix; In the current iteration, the clustering parameters of the previous iteration are updated based on the temperature adjustment data to obtain the clustering parameters of the current iteration. Based on the clustering parameters of the current iteration and the preset iteration termination condition, it is determined whether to end the iteration. If so, then based on the clusters at the end of the iteration, determine the target mode data for the target temperature control mode in the current cycle.

[0138] In one possible implementation, adjustment module 1102 is specifically used for: Based on the temperature adjustment data, the cluster centers of the previous iteration, and the adaptive parameters corresponding to each cluster center in the previous iteration, the membership matrix of the current iteration is calculated. The membership matrix is ​​used to indicate the membership degree of each group of adjustment information relative to each cluster center of the previous iteration. Based on the temperature adjustment data and the membership matrix of the current iteration, the cluster centers of the previous iteration are updated to obtain the cluster centers of the current iteration. Based on the temperature adjustment data and the cluster centers from the previous iteration, the adaptive parameters corresponding to each cluster center in the previous iteration are updated to obtain the adaptive parameters corresponding to each cluster center in the current iteration.

[0139] In one possible implementation, adjustment module 1102 is specifically used for: Traverse each set of adjustment information in the temperature adjustment data. For the current adjustment information that has been traversed, calculate the membership degree of the current adjustment information relative to each cluster based on the current adjustment information, the cluster centers of the previous iteration, and the adaptive parameters corresponding to each cluster center in the previous iteration. After traversing each group of adjustment information, the membership degree of each group of adjustment information is replaced with the corresponding position in the membership degree matrix of the previous iteration round to obtain the membership degree matrix of the current iteration round.

[0140] In one possible implementation, adjustment module 1102 is specifically used for: Calculate the difference between the current adjustment information and the cluster center of the target cluster in the previous iteration, obtain the difference result, and perform a modulo operation on the difference result to obtain the first modulus value; Calculate the ratio of the first modulus value to the adaptive parameter corresponding to the target cluster center in the previous iteration round to obtain the first ratio; Based on the first ratio, the fuzzy universe parameter, and the distance adjustment parameter, the membership degree of the current adjusted information relative to the target cluster is calculated.

[0141] In one possible implementation, adjustment module 1102 is specifically used for: Based on the membership degree of each group of adjustment information relative to the target cluster, a weighted average calculation is performed on each group of adjustment information in the temperature adjustment data to calculate the cluster center of the target cluster in the current iteration round.

[0142] In one possible implementation, adjustment module 1102 is specifically used for: Iterate through each set of adjustment information in the temperature adjustment data. For the current adjustment information that has been traversed, calculate the difference between the current adjustment information and the cluster center of the target cluster in the previous iteration round to obtain the difference result corresponding to the current adjustment information. After the traversal is completed, the adaptive parameters corresponding to the target clustering of the current iteration are calculated based on the difference results corresponding to the adjustment information of each group.

[0143] In one possible implementation, adjustment module 1102 is specifically used for: Based on the clusters at the end of the iteration, the initial pattern data is adjusted to obtain the target pattern data of the target temperature control mode in the current cycle.

[0144] In one possible implementation, adjustment module 1102 is specifically used for: Project each cluster at the end of the iteration onto the horizontal axis to obtain at least one target time interval; Project each cluster at the end of the iteration onto the vertical axis to obtain at least one target temperature range; Based on each target time interval and each target temperature interval, the initial model data is adjusted to obtain the target model data of the target temperature control mode in the current cycle.

[0145] The processing flow of each module in the device and the interaction flow between each module can be referred to the relevant descriptions in the above method embodiments, and will not be detailed here.

[0146] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems and devices described above can be referred to the corresponding processes in the method embodiments, and will not be repeated here. In the several embodiments provided in this application, it should be understood that the disclosed systems, devices, and methods can be implemented in other ways. The device embodiments described above are merely illustrative. For example, the division of modules is only a logical functional division, and in actual implementation, there may be other division methods. Furthermore, multiple modules or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed mutual coupling or direct coupling or communication connection can be through some communication interfaces; the indirect coupling or communication connection of devices or modules can be electrical, mechanical, or other forms.

[0147] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. If the functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this invention. The aforementioned storage medium includes: USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, optical disks, and other media capable of storing program code.

[0148] The above are merely specific embodiments of this application, but the scope of protection of this application is not limited thereto. Any changes or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application.

Claims

1. A temperature control method, characterized in that, include: The system acquires temperature adjustment data for a target temperature control mode from a user's perspective during a historical period, as well as initial mode data for the target temperature control mode during that historical period. The initial mode data is used to indicate the correspondence between temperature and time. The temperature adjustment data includes at least one set of adjustment information, which includes adjustment time and adjustment temperature. In the current cycle, based on the temperature adjustment data, the initial mode data is iteratively adjusted using a preset clustering learning algorithm to obtain the target mode data for the target temperature control mode in the current cycle. Based on the target pattern data, the ambient temperature of the current cycle is controlled.

2. The temperature control method according to claim 1, characterized in that, The step of iteratively adjusting the initial pattern data based on the temperature adjustment data using a preset clustering learning algorithm to obtain the target pattern data of the target temperature control mode in the current cycle includes: Initialize clustering parameters, which include at least: multiple cluster centers and a membership matrix; In the current iteration, the clustering parameters of the previous iteration are updated based on the temperature adjustment data to obtain the clustering parameters of the current iteration. Based on the clustering parameters of the current iteration and the preset iteration termination condition, it is determined whether to end the iteration. If so, then based on the clusters at the end of the iteration, determine the target mode data for the target temperature control mode in the current cycle.

3. The temperature control method according to claim 2, characterized in that, The step of updating the clustering parameters of the previous iteration based on the temperature adjustment data to obtain the clustering parameters of the current iteration includes: Based on the temperature adjustment data, the cluster centers of the previous iteration, and the adaptive parameters corresponding to each cluster center in the previous iteration, the membership matrix of the current iteration is calculated. The membership matrix is ​​used to indicate the membership degree of each group of adjustment information relative to each cluster center of the previous iteration. Based on the temperature adjustment data and the membership matrix of the current iteration, the cluster centers of the previous iteration are updated to obtain the cluster centers of the current iteration. Based on the temperature adjustment data and the cluster centers from the previous iteration, the adaptive parameters corresponding to each cluster center in the previous iteration are updated to obtain the adaptive parameters corresponding to each cluster center in the current iteration.

4. The temperature control method according to claim 3, characterized in that, The step of calculating the membership matrix for the current iteration based on the temperature adjustment data, the cluster centers from the previous iteration, and the adaptive parameters corresponding to each cluster center in the previous iteration includes: The adjustment information in the temperature adjustment data is traversed. For the current adjustment information, the membership degree of the current adjustment information relative to each cluster is calculated based on the current adjustment information, the cluster centers of the previous iteration, and the adaptive parameters corresponding to each cluster center in the previous iteration. After traversing each group of adjustment information, the membership degree of each group of adjustment information is replaced with the corresponding position in the membership degree matrix of the previous iteration round to obtain the membership degree matrix of the current iteration round.

5. The temperature control method according to claim 4, characterized in that, The step of calculating the membership degree of the current adjustment information relative to each cluster based on the current adjustment information, the cluster centers of the previous iteration, and the adaptive parameters corresponding to each cluster center in the previous iteration includes: Calculate the difference between the current adjustment information and the cluster center of the target cluster in the previous iteration round to obtain the difference result, and perform a modulo operation on the difference result to obtain the first modulus value; Calculate the ratio of the first modulus value to the adaptive parameter corresponding to the target cluster center in the previous iteration round to obtain the first ratio; Based on the first ratio, the fuzzy universe parameter, and the distance adjustment parameter, the membership degree of the current adjusted information relative to the target cluster is calculated.

6. The temperature control method according to claim 3, characterized in that, The step of updating the cluster centers of the previous iteration based on the temperature adjustment data and the membership matrix of the current iteration to obtain the cluster centers of the current iteration includes: Based on the membership degree of each set of adjustment information relative to the target cluster, a weighted average operation is performed on each set of adjustment information in the temperature adjustment data to calculate the cluster center of the target cluster in the current iteration round.

7. The temperature control method according to claim 3, characterized in that, The step of updating the adaptive parameters of each cluster center in the previous iteration based on the temperature adjustment data and the cluster centers in the previous iteration to obtain the adaptive parameters of each cluster center in the current iteration includes: Iterate through each group of adjustment information in the temperature adjustment data, and for the current adjustment information that has been traversed, calculate the difference between the current adjustment information and the cluster center of the target cluster in the previous iteration round to obtain the difference result corresponding to the current adjustment information. After the traversal is completed, the adaptive parameters corresponding to the target clustering of the current iteration are calculated based on the difference results corresponding to the adjustment information of each group.

8. The temperature control method according to claim 2, characterized in that, The step of determining the target mode data for the target temperature control mode in the current cycle based on the clusters at the end of the iteration includes: Based on the clusters at the end of the iteration, the initial pattern data is adjusted to obtain the target pattern data of the target temperature control mode in the current cycle.

9. The temperature control method according to claim 8, characterized in that, The step of adjusting the initial pattern data based on the clusters at the end of the iteration to obtain the target pattern data of the target temperature control mode in the current cycle includes: Project each cluster at the end of the iteration onto the horizontal axis to obtain at least one target time interval; Project each cluster at the end of the iteration onto the vertical axis to obtain at least one target temperature range; Based on each target time interval and each target temperature interval, the initial mode data is adjusted to obtain the target mode data of the target temperature control mode in the current cycle.

10. A temperature controller device, characterized in that, include: The device includes a processing module, a storage module, an RF module, a PCB board module, a KNX module, a step-down module, a screen module, a touch screen module, a measurement module, and a wake-up module. The storage module stores machine-readable instructions that the processing module can execute. When the temperature controller device is running, the processing module executes the machine-readable instructions to perform the steps of the temperature control method as described in any one of claims 1 to 9.

Images