Temperature control method, device, equipment and storage medium based on smart bracelet cluster

Abstract

The present invention provides a temperature control method, device, equipment and storage medium based on a smart bracelet cluster. The method includes: collecting physiological data and preference data of users, as well as real-time environmental data through multiple smart bracelets. Calculating the user's initial comfort score using a fuzzy logic control algorithm and establishing a comfort model. Analyzing user preferences through a collaborative filtering algorithm, identifying user groups with similar preferences, and then calculating an accurate comfort score. In combination with a multi-objective optimization algorithm, an optimal temperature control scheme is generated based on the user's comfort score and the energy efficiency parameters of the temperature control device. Furthermore, the indoor environmental comfort at future moments is predicted through a fitness prediction model, and a continuous temperature control scheme is formulated accordingly. Finally, the temperature control device is controlled to automatically adjust the indoor temperature according to the target temperature control scheme, thereby realizing personalized and intelligent indoor temperature control management.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence, and in particular to a temperature control method, device, equipment and storage medium based on a smart bracelet cluster. Background Art

[0002] With the development of science and technology and the improvement of people's living standards, the comfort of indoor environment has become an issue of increasing concern. In traditional temperature control systems, temperature adjustment is often based on fixed temperature setting values. This approach ignores the individual differences of different users and real-time environmental changes, resulting in energy waste and inconsistent user experience.

[0003] Although existing intelligent temperature control devices can adjust according to the ambient temperature, most of them still lack in-depth understanding and adaptation to the personalized needs of users. For example, they may not accurately capture changes in the user's physiological state, such as body temperature, heart rate, etc., nor fully consider the user's personal preferences, such as sensitivity to temperature, habitual work and rest time, etc. In addition, when dealing with the situation where multiple users coexist in the same indoor environment, these devices often cannot effectively coordinate the needs of each user to achieve the optimization of overall comfort and energy efficiency. Summary of the invention

[0004] The main purpose of the present invention is to solve the technical problem that the existing indoor temperature control method cannot effectively coordinate the needs of various users.

[0005] A first aspect of the present invention provides a temperature control method based on a smart bracelet cluster, wherein the smart bracelet cluster includes multiple smart bracelets in the same indoor environment; the temperature control method based on the smart bracelet cluster includes:

[0006] Collecting user wristband data of corresponding users in an indoor environment and real-time environmental data of each location in the indoor environment through multiple smart wristbands in the smart wristband cluster, wherein the user wristband data includes user physiological data and user preference data;

[0007] Using a preset fuzzy logic control algorithm to calculate the initial comfort score corresponding to each user according to the user physiological data and the real-time environmental data, and establishing a user comfort model according to the initial comfort score corresponding to each user;

[0008] Analyzing the user preference data through a preset collaborative filtering algorithm, identifying a user group with similar preferences in the same indoor environment, obtaining a user group model, and calculating an accurate comfort score corresponding to each user based on the user group model and the user comfort model;

[0009] The fitness function in the preset multi-objective optimization algorithm is used to score and calculate the optimal fitness value according to the precise comfort level corresponding to each user and the energy efficiency parameters of each temperature control device in the indoor environment, and a first temperature control scheme for each temperature control device in the indoor environment at the current moment is generated according to the optimal fitness value;

[0010] Inputting the temperature control parameters of the first temperature control scheme and the user's wristband data into a preset fitness prediction model to obtain a predicted comfort value of the indoor environment at the target time under the first temperature control scheme;

[0011] generating a second temperature control scheme between the current moment and the target moment according to the predicted comfort value, and generating a target temperature control scheme according to the first temperature control scheme and the second temperature control scheme;

[0012] Control each temperature control device in the indoor environment to adjust the temperature according to the target temperature control scheme.

[0013] Optionally, in a first implementation of the first aspect of the present invention, the using a preset fuzzy logic control algorithm to calculate the initial comfort score corresponding to each user according to the user physiological data and the real-time environmental data, and establishing a user comfort model according to the initial comfort score corresponding to each user includes:

[0014] Performing data preprocessing on the user physiological data and real-time environmental data, wherein the data preprocessing includes standardization processing and outlier removal processing;

[0015] The user's physiological data and real-time environmental data after data preprocessing are fuzzified by a preset membership function to obtain fuzzy data corresponding to each data point in the user's physiological data and real-time environmental data;

[0016] Performing reasoning processing on the fuzzified data according to a preset fuzzy logic rule set to obtain fuzzy outputs corresponding to the fuzzified data under each fuzzy rule in the fuzzy logic rule set;

[0017] Aggregating the fuzzy outputs corresponding to the fuzzified data under each fuzzy rule to obtain a comprehensive fuzzy output set, and defuzzifying the comprehensive fuzzy output set to obtain an initial comfort score of the corresponding user;

[0018] A user comfort model is established according to the initial comfort score corresponding to each user.

[0019] Optionally, in a second implementation of the first aspect of the present invention, analyzing the user preference data by a preset collaborative filtering algorithm, identifying a user group with similar preferences in the same indoor environment, obtaining a user group model, and calculating the precise comfort score corresponding to each user according to the user group model and the user comfort model includes:

[0020] Calculating similarity values ​​between preference items in the user preference data by using a preset collaborative filtering algorithm, and constructing a user similarity matrix based on the similarity values;

[0021] The users corresponding to multiple smart bracelets in the same indoor environment are grouped according to the user similarity matrix through a preset clustering algorithm to obtain a user group model;

[0022] Perform aggregate analysis on the user preference data of each user group in the user group model, and calculate the representative preference characteristics of the corresponding user group;

[0023] According to the representative preference features and the user comfort model, a precise comfort score corresponding to each user is calculated in a weighted manner.

[0024] Optionally, in a third implementation of the first aspect of the present invention, the multi-objective optimization algorithm is a genetic optimization algorithm;

[0025] The method of calculating the optimal fitness value by scoring according to the precise comfort level corresponding to each user and the energy efficiency parameters of each temperature control device in the indoor environment through the fitness function in the preset multi-objective optimization algorithm, and generating the first temperature control scheme for each temperature control device in the indoor environment at the current moment according to the optimal fitness value includes:

[0026] Initializing an initial population of the genetic optimization algorithm and using the initial population as a target population, wherein each individual in the initial population represents a first temperature control scheme;

[0027] Calculating the fitness value of each individual in the target population according to the precise comfort score by using the genetic optimization algorithm;

[0028] Performing a selection operation on each individual in the target population according to the fitness value to obtain an optimized population, and performing crossover and mutation operations on the optimized population;

[0029] Updating the optimized population after performing the crossover and mutation operations as the target population, and returning to the step of calculating the fitness value of each individual in the target population according to the precise comfort score by the genetic optimization algorithm until the iteration termination condition is met;

[0030] When the iteration termination condition is met, the individual with the highest total fitness value in the target population is decoded to obtain the optimal fitness value to generate the first temperature control plan.

[0031] Optionally, in a fourth implementation of the first aspect of the present invention, the multi-objective optimization algorithm is a Harris Eagle algorithm;

[0032] The step of calculating the optimal fitness value by scoring according to the precise comfort level corresponding to each user and the energy efficiency parameters of each temperature control device in the indoor environment through the fitness function in the preset multi-objective optimization algorithm, and generating the first temperature control scheme for each temperature control device in the indoor environment at the current moment according to the optimal fitness value also includes:

[0033] Calculating the fitness value of the temperature control scheme represented by each Harris Hawk individual according to the accurate comfort score by using the fitness function corresponding to the Harris Hawk algorithm, and selecting the position of the Harris Hawk individual with the highest fitness value as the current prey position;

[0034] Calculating the prey escape energy and jump intensity according to a preset prey escape energy and jump intensity calculation formula, and selecting a corresponding predation strategy according to the prey escape energy and the jump intensity;

[0035] updating the position of each Harris hawk individual according to the predation strategy, recalculating the fitness value of the power dispatching strategy represented by each Harris hawk individual after the position update, and reselecting the position of the Harris hawk individual with the highest fitness value as the current prey position;

[0036] Determine whether the preset stop condition is met;

[0037] If satisfied, the current prey position is output as the optimal solution;

[0038] If not, return to the step of calculating the prey escape energy and jump intensity according to the preset prey escape energy and jump intensity calculation formula until the preset stop condition is met;

[0039] When a preset stop condition is met, a first temperature control scheme is generated according to the optimal solution.

[0040] Optionally, in a fifth implementation manner of the first aspect of the present invention, inputting the temperature control parameters of the first temperature control scheme and the user bracelet data into a preset fitness prediction model to obtain a predicted comfort value of the indoor environment at the target time under the first temperature control scheme includes:

[0041] Inputting the temperature control parameters of the first temperature control solution and the user bracelet data into a preset fitness prediction model, wherein the fitness prediction model includes an input layer, an attention mechanism layer, a feature fusion layer, a multi-task detection layer and an output layer;

[0042] The temperature control parameters of the first temperature control solution and the user's wristband data are feature-encoded through the output layer to obtain temperature control data features and wristband data features;

[0043] The temperature control data features and the bracelet data features are subjected to feature fusion through the attention mechanism layer and the feature fusion layer to obtain fusion vector features;

[0044] The multi-task detection layer performs multi-task detection according to the fusion vector feature to obtain a multi-task detection result, and the multi-task detection result is integrated to obtain a predicted comfort value of the indoor environment at the target time under the first temperature control scheme, and the predicted comfort value is output through the output layer.

[0045] Optionally, in a fifth implementation of the first aspect of the present invention, the temperature control data features and the bracelet data features are subjected to feature fusion by the attention mechanism layer and the feature fusion layer to obtain a fusion vector feature, including:

[0046] Calculate the relationship score between each feature of the temperature control data feature and the bracelet data feature through the self-attention mechanism in the attention mechanism layer;

[0047] According to the relationship score of each feature in the temperature control data feature and the bracelet data feature, a weight is dynamically assigned to obtain a weight vector of each feature in the temperature control data feature and the bracelet data feature;

[0048] The temperature control data features and the bracelet data features are deeply fused according to the weights through the feature fusion layer to obtain a fusion vector feature.

[0049] A second aspect of the present invention provides a temperature control device based on a smart bracelet cluster, the temperature control device based on the smart bracelet cluster comprising:

[0050] A data collection module, used to collect user bracelet data of corresponding users in an indoor environment and real-time environmental data of each position in the indoor environment through multiple smart bracelets in the smart bracelet cluster, wherein the user bracelet data includes user physiological data and user preference data;

[0051] An initial scoring module, used to calculate the initial comfort score corresponding to each user according to the user's physiological data and real-time environmental data using a preset fuzzy logic control algorithm, and establish a user comfort model according to the initial comfort score corresponding to each user;

[0052] An accurate scoring module is used to analyze the user preference data through a preset collaborative filtering algorithm, identify user groups with similar preferences in the same indoor environment, obtain a user group model, and calculate an accurate comfort score corresponding to each user based on the user group model and the user comfort model;

[0053] An initial temperature control module is used to score and calculate an optimal fitness value according to the precise comfort level corresponding to each user and the energy efficiency parameters of each temperature control device in the indoor environment through a fitness function in a preset multi-objective optimization algorithm, and generate a first temperature control scheme for each temperature control device in the indoor environment at the current moment according to the optimal fitness value;

[0054] A comfort prediction module, used to input the temperature control parameters of the first temperature control scheme and the user's wristband data into a preset fitness prediction model to obtain a predicted comfort value of the indoor environment at a target time under the first temperature control scheme;

[0055] a target temperature control module, configured to generate a second temperature control scheme between the current moment and the target moment according to the predicted comfort value, and to generate a target temperature control scheme according to the first temperature control scheme and the second temperature control scheme;

[0056] The temperature control module is used to control each temperature control device in the indoor environment to adjust the temperature according to the target temperature control scheme.

[0057] The third aspect of the present invention provides a temperature control device based on a smart bracelet cluster, comprising: a memory and at least one processor, the memory storing instructions, the memory and the at least one processor being interconnected through a line; the at least one processor calls the instructions in the memory so that the temperature control device based on the smart bracelet cluster executes the steps of the above-mentioned temperature control method based on the smart bracelet cluster.

[0058] A fourth aspect of the present invention provides a computer-readable storage medium, which stores instructions. When the computer-readable storage medium is run on a computer, the computer executes the steps of the above-mentioned temperature control method based on a smart bracelet cluster.

[0059] The temperature control method, device, equipment and storage medium based on the smart bracelet cluster collect the user's physiological data and preference data, as well as real-time environmental data through multiple smart bracelets. The fuzzy logic control algorithm is used to calculate the user's initial comfort score and establish a comfort model. The collaborative filtering algorithm is used to analyze user preferences, identify user groups with similar preferences, and then calculate the accurate comfort score. Combined with the multi-objective optimization algorithm, the optimal temperature control plan is generated according to the user's comfort score and the energy efficiency parameters of the temperature control device. Furthermore, the indoor environmental comfort at future moments is predicted by the fitness prediction model, and a continuous temperature control plan is formulated accordingly. Finally, the temperature control device is controlled to automatically adjust the indoor temperature according to the target temperature control plan to achieve personalized and intelligent indoor temperature control management.

[0060] Other features and advantages of the present invention will be described in the following description, and partly become apparent from the description, or understood by practicing the present invention. The purpose and other advantages of the present invention are realized and obtained by the structures particularly pointed out in the description, claims and drawings.

[0061] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, preferred embodiments are given below and described in detail with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0062] Figure 1 It is a schematic diagram of an embodiment of a temperature control method based on a smart bracelet cluster in an embodiment of the present invention;

[0063] Figure 2 It is a schematic diagram of an embodiment of a temperature control device based on a smart bracelet cluster in an embodiment of the present invention;

[0064] Figure 3 The figure is a schematic diagram of an embodiment of a temperature control device based on a smart bracelet cluster in an embodiment of the present invention. DETAILED DESCRIPTION

[0065] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0066] The terms "including" and "having" and any variations thereof mentioned in the embodiments of the present invention are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device end including a series of steps or units is not limited to the listed steps or units, but may optionally include other steps or units that are not listed, or may optionally include other steps or units that are inherent to these processes, methods, products or device ends.

[0067] To facilitate understanding of this embodiment, a temperature control method based on a smart bracelet cluster disclosed in an embodiment of the present invention is first described in detail, wherein the smart bracelet cluster includes multiple smart bracelets in the same indoor environment. Figure 1 As shown, the method comprises the following steps:

[0068] 101. Collecting user wristband data of corresponding users in an indoor environment and real-time environmental data of various locations in the indoor environment through multiple smart wristbands in a smart wristband cluster, wherein the user wristband data includes user physiological data and user preference data;

[0069] In one embodiment of the present invention, each wristband in the smart wristband cluster acts as a data node, responsible for collecting physiological data of a specific user and real-time environmental data of the user's current environment. The user's wristband data mainly includes two parts: the user's physiological data, such as heart rate, body temperature, etc., and the user's preference data, including but not limited to preferences for environmental factors such as temperature and humidity. Each smart wristband needs to be equipped with a variety of sensors, such as temperature sensors, humidity sensors, heart rate sensors, etc., and an interface that allows users to input their preference settings. In this way, the smart wristband can not only monitor the user's physiological state, but also record the user's specific preferences for the indoor environment. In order to collect these data in real time, the smart wristband is connected to the central data processing system via a wireless network, which requires each wristband to have a stable wireless communication function. Whenever the sensor of the smart wristband detects physiological data or the user updates its preference settings through the interface, the data will be instantly encoded and sent to the central processing system via the wireless network. The key calculation formulas involved here include data weighting and standardization processing formulas, which are used to ensure the consistency and comparability of data during transmission and analysis. Users input their preferences for indoor temperature, humidity, etc. through the interface of the smart bracelet, and these preference data are then encoded and transmitted to the central processing system. The processing of preference data involves algorithms similar to collaborative filtering, which can help identify groups of users with similar preferences, but at this stage, the main task is to ensure that all collected data is accurately recorded and stored.

[0070] 102. Calculate the initial comfort score corresponding to each user according to the user's physiological data and the real-time environmental data using a preset fuzzy logic control algorithm, and establish a user comfort model according to the initial comfort score corresponding to each user;

[0071] In one embodiment of the present invention, the use of a preset fuzzy logic control algorithm to calculate the initial comfort score corresponding to each user based on the user physiological data and real-time environmental data, and establishing a user comfort model based on the initial comfort score corresponding to each user includes: performing data preprocessing on the user physiological data and real-time environmental data, wherein the data preprocessing includes standardization processing and outlier removal processing; fuzzifying the user physiological data and real-time environmental data after data preprocessing through a preset membership function to obtain fuzzified data corresponding to each data point in the user physiological data and real-time environmental data; performing inference processing on the fuzzy data according to a preset fuzzy logic rule set to obtain fuzzy outputs corresponding to the fuzzy data under each fuzzy rule in the fuzzy logic rule set; performing aggregation processing on the fuzzy outputs corresponding to the fuzzy data under each fuzzy rule to obtain a comprehensive fuzzy output set, and defuzzifying the comprehensive fuzzy output set to obtain the initial comfort score of the corresponding user; and establishing a user comfort model based on the initial comfort score corresponding to each user.

[0072] Specifically, in the data preprocessing stage, the user's physiological data and real-time environmental data are first standardized to eliminate the impact of different dimensions and magnitudes. The standardization process can be achieved through the following formula:

[0073] ;

[0074] in, Represents the original data, and Represent the minimum and maximum values ​​in the data set, respectively. Represents the standardized data. In this way, all data will be converted to the [0,1] interval for subsequent processing. Next, outlier removal is performed to ensure the quality and accuracy of the data. Outliers can be identified using statistical methods such as standard deviation or box plots. For example, if the value of a data point exceeds the range of plus or minus three standard deviations from the mean of the data set, then this data point can be marked as an outlier and removed.

[0075] After completing the data preprocessing, the data is fuzzified by the membership function. The membership function is used to convert the crisp value (i.e., non-fuzzy, precise value) into the membership value in the fuzzy set. A common membership function is the Gaussian membership function, which has the following formula:

[0076] ;

[0077] in, Represents data points For fuzzy sets The membership degree of is the mean of the Gaussian distribution, is the standard deviation, is the base of the natural logarithm. By adjusting and The value of can control the shape of the membership function to adapt to different data distributions. After the data is fuzzified, the preset fuzzy logic rule set is used to perform reasoning on the fuzzified data. A fuzzy logic rule set usually consists of a series of "if-then" rules, such as: "If the temperature is high and the humidity is high, the discomfort level is high". Each rule can be represented by a fuzzy matrix, where the rows of the matrix represent the fuzzy sets of premises and the columns represent the fuzzy sets of conclusions. In the reasoning process, the premises are combined using fuzzy logic AND, OR, and NOT operations, and the aggregation operation of fuzzy logic is used to merge the conclusions of all rules. For example, if there are two rules: "If the temperature is high, the discomfort level is high" and "If the humidity is high, the discomfort level is high", then in the aggregation operation, the fuzzy sets of the two conclusions can be merged through the fuzzy OR operation:

[0078] ;

[0079] in, represents the fuzzy set indicating the degree of discomfort, and represent the fuzzy sets of high temperature and high humidity respectively, Represents a fuzzy AND operation, Represents a fuzzy OR operation. Finally, the aggregated fuzzy output set is defuzzified to obtain a crisp initial comfort score. Defuzzification can be achieved by the centroid method, and its formula is as follows:

[0080] ;

[0081] in, represents the initial comfort score after defuzzification, is the aggregated fuzzy output set, is the score value. Through integral calculation, a representative score value can be obtained, namely the initial comfort score.

[0082] 103. Analyze user preference data through a preset collaborative filtering algorithm, identify user groups with similar preferences in the same indoor environment, obtain a user group model, and calculate the precise comfort score corresponding to each user based on the user group model and the user comfort model;

[0083] In one embodiment of the present invention, the user preference data is analyzed by a preset collaborative filtering algorithm, user groups with similar preferences in the same indoor environment are identified, a user group model is obtained, and a precise comfort score corresponding to each user is calculated based on the user group model and the user comfort model, including: calculating the similarity values ​​between the preference items in the user preference data by a preset collaborative filtering algorithm, and constructing a user similarity matrix based on the similarity values; grouping users corresponding to multiple smart bracelets in the same indoor environment according to the user similarity matrix by a preset clustering algorithm to obtain a user group model; performing aggregation analysis on the user preference data in each user group in the user group model, and calculating the representative preference features of the corresponding user group; and calculating the precise comfort score corresponding to each user in a weighted manner based on the representative preference features and the user comfort model.

[0084] Specifically, first of all, the core of the collaborative filtering algorithm is to calculate the similarity between the preference items in the user preference data. This can be achieved through the cosine similarity formula, which is used to measure the angle between two user preference vectors to determine their similarity:

[0085] Sim ;

[0086] in, and Represent the preference vectors of two users respectively, is a collection of preference items, Indicates user For preferred items Rating, Sim Indicates user and The cosine similarity value range is between [-1,1], and the closer the value is to 1, the more similar the two users are.

[0087] Through the cosine similarity formula, the similarity can be calculated for each pair of users and a user similarity matrix can be constructed. , where each element of the matrix Indicates user and Next, the clustering algorithm is used to group users. K-means clustering algorithm is a commonly used user grouping method, and its goal is to divide users into groups, so that the similarity of users in the same group is as high as possible, and the similarity of users between different groups is as low as possible.

[0088] Through the K-means clustering algorithm, a user group model can be obtained, in which each group represents a collection of users with similar preference characteristics. After obtaining the user group model, it is necessary to aggregate and analyze the user preference data in each group to calculate the representative preference characteristics. This can be achieved through the weighted average formula:

[0089] ;

[0090] in, Indicates user groups, Indicates user For preferred items Rating, It is a weight factor that can be assigned based on user activity or other indicators. Representing a group For preferred items Representative ratings.

[0091] Finally, the representative preference features are combined with the user comfort model to calculate the precise comfort score of each user in a weighted manner. This can be achieved by the following formula:

[0092] ;

[0093] in, Indicates user Accurate comfort rating for Indicates user With their group The cluster center The similarity between Representing a group The representative preference characteristics of are model parameters, which can be obtained through regression analysis. is the error term.

[0094] 104. Using a fitness function in a preset multi-objective optimization algorithm, score and calculate an optimal fitness value according to the precise comfort level corresponding to each user and the energy efficiency parameters of each temperature control device in the indoor environment, and generate a first temperature control scheme for each temperature control device in the indoor environment at the current moment according to the optimal fitness value;

[0095] In one embodiment of the present invention, the multi-objective optimization algorithm is a genetic optimization algorithm; the fitness function in the preset multi-objective optimization algorithm is used to score and calculate the optimal fitness value according to the precise comfort corresponding to each user and the energy efficiency parameters of each temperature control device in the indoor environment, and the first temperature control scheme of each temperature control device in the indoor environment at the current moment is generated according to the optimal fitness value, including: initializing the initial population of the genetic optimization algorithm, and using the initial population as the target population, wherein each individual in the initial population represents a first temperature control scheme; using the genetic optimization algorithm to generate the first temperature control scheme according to the precise comfort corresponding to each user and the energy efficiency parameters of each temperature control device in the indoor environment; The method comprises the following steps: calculating the fitness value of each individual in the target population according to the fitness value; performing a selection operation on each individual in the target population according to the fitness value to obtain an optimized population, and performing crossover and mutation operations on the optimized population; updating the optimized population after the crossover and mutation operations as the target population, and returning to the step of calculating the fitness value of each individual in the target population according to the precise comfort score through the genetic optimization algorithm until an iteration termination condition is met; when the iteration termination condition is met, decoding the individual with the highest total fitness value in the target population to obtain the optimal fitness value to generate a first temperature control scheme.

[0096] Specifically, first, initialize the initial population of the genetic optimization algorithm. This population is composed of a group of randomly generated individuals, each of which represents a possible temperature control solution. These solutions can be a combination of multiple control parameters such as temperature setting, humidity control, ventilation strategy, etc. The size of the initial population depends on the complexity of the problem and the computing resources, but it usually needs to be large enough to ensure diversity and diversity of solutions. Next, the initial population is used as the target population and the genetic optimization process begins.

[0097] In this process, we first need to calculate the fitness value of each individual in the target population. The fitness function is a function that evaluates the quality of an individual. It measures the quality of an individual based on its precise comfort score. The fitness value can be calculated using the following formula:

[0098] ;

[0099] in, Represents an individual The fitness value of is the number of evaluation metrics, It is indivual

[0100] The weight of the evaluation indicator, Is an individual In the The scores on the evaluation indicators. The weights can be adjusted according to different temperature control requirements to reflect the relative importance of different indicators. After the fitness values ​​are calculated, the individuals in the target population are selected according to these values. The purpose of the selection operation is to retain individuals with high fitness and eliminate individuals with low fitness. A common selection method is roulette selection, in which the probability of each individual being selected is proportional to its fitness value. In this way, an optimized population can be obtained in which individuals have higher average fitness values. Then, crossover and mutation operations are performed on the optimized population. The crossover operation simulates the mating process in biological genetics to generate new individuals by exchanging certain parts of two individuals. A simple crossover operation is a single-point crossover, and its formula can be expressed as:

[0101] offspring ;

[0102] in, and There are two parent individuals, is the crossover point, which randomly selects and decides which part of the two parent individuals will be exchanged. The mutation operation is a process that simulates gene mutation, which increases the diversity of the population by randomly changing some parts of the individuals. After performing the crossover and mutation operations, a new optimized population is obtained and updated as the target population. Then, the fitness value of each individual in the target population is calculated again, and the selection, crossover and mutation operations are repeated until the iteration termination condition is met. The iteration termination condition can be reaching the preset number of iterations, the fitness value is no longer significantly improved, or other custom conditions.

[0103] Furthermore, the multi-objective optimization algorithm is a Harris Hawk algorithm; the fitness function in the preset multi-objective optimization algorithm is used to score and calculate the optimal fitness value according to the precise comfort corresponding to each user and the energy efficiency parameters of each temperature control device in the indoor environment, and the first temperature control scheme for each temperature control device in the indoor environment at the current moment is generated according to the optimal fitness value. It also includes: calculating the fitness value of the temperature control scheme represented by each Harris Hawk individual according to the precise comfort score through the fitness function corresponding to the Harris Hawk algorithm, and selecting the position of the Harris Hawk individual with the highest fitness value as the current prey position; calculating the prey escape energy and jump strength according to the preset prey escape energy and jump strength calculation formula. degree, and select a corresponding predation strategy according to the prey escape energy and the jump intensity; update the position of each Harris hawk individual according to the predation strategy, recalculate the fitness value of the power dispatching strategy represented by each Harris hawk individual after the position update, and reselect the Harris hawk individual position with the highest fitness value as the current prey position; determine whether the preset stop condition is met; if so, output the current prey position as the optimal solution; if not, return to the step of calculating the prey escape energy and jump intensity according to the preset prey escape energy and jump intensity calculation formula until the preset stop condition is met; when the preset stop condition is met, generate a first temperature control plan according to the optimal solution.

[0104] Specifically, first, initialize the population of the Harris Hawk algorithm, that is, a group of Harris Hawk individuals, each of which represents a possible temperature control solution. These solutions can be a combination of multiple control parameters such as temperature setting, humidity control, ventilation strategy, etc. The position of the initial population is randomly generated, representing the solution space of the problem.

[0105] Then, the fitness value of each Harris Hawk individual is calculated based on the accurate comfort score. The fitness function is a function that evaluates the quality of an individual, which can be expressed as:

[0106] ;

[0107] in, Represents an individual The fitness value of is the number of evaluation metrics, It is The weight of the evaluation index, Is an individual In the The scores on the evaluation indicators are is the expected score. The weights can be adjusted according to different temperature control requirements to reflect the relative importance of different indicators. The fitness function is designed to minimize the difference between the actual score and the expected score.

[0108] After calculating the fitness value, the position of the Harris hawk individual with the highest fitness value is selected as the current prey position. This position represents the best temperature control solution currently found. Then, the escape behavior of the prey and the Harris hawk's hunting strategy are determined according to the preset prey escape energy and jump intensity calculation formula. Escape Energy and jump intensity It can be expressed as:

[0109] ;

[0110] in, and are the maximum values ​​of escape energy and jump intensity, and is the initial value, and iter is the current iteration number. These formulas simulate the process in which the escape energy of the prey decreases gradually over time, while the predation intensity of Harris's hawk increases gradually.

[0111] According to the escape energy and jump intensity , select the corresponding predation strategy. The predation strategy can be a position update rule based on the following formula:

[0112] ;

[0113] in, is the new location of the Harris Hawk, is the current location of the prey, is the best position currently found. This formula simulates the Harris Hawk adjusting its hunting direction and intensity according to the location and escape energy of the prey.

[0114] After executing the predation strategy, the position of the Harris hawk individual is updated, and the fitness value of the temperature control scheme represented by each individual is recalculated. Then, the position of the individual with the highest fitness value is selected again as the current prey position.

[0115] This process will continue until the preset stop condition is met, such as reaching the maximum number of iterations or the fitness value converges. When the stop condition is met, the current prey position is output as the optimal solution, which represents the best temperature control solution found.

[0116] 105. Input the temperature control parameters of the first temperature control scheme and the user's wristband data into a preset fitness prediction model to obtain a predicted comfort value of the indoor environment at the target time under the first temperature control scheme;

[0117] In one embodiment of the present invention, the step of inputting the temperature control parameters of the first temperature control scheme and the user's wristband data into a preset fitness prediction model to obtain a predicted comfort value of the indoor environment at the target time under the first temperature control scheme includes: inputting the temperature control parameters of the first temperature control scheme and the user's wristband data into a preset fitness prediction model, wherein the fitness prediction model includes an input layer, an attention mechanism layer, a feature fusion layer, a multi-task detection layer and an output layer; performing feature encoding on the temperature control parameters of the first temperature control scheme and the user's wristband data through the output layer to obtain temperature control data features and wristband data features; performing feature fusion on the temperature control data features and the wristband data features through the attention mechanism layer and the feature fusion layer to obtain fusion vector features; performing multi-task detection according to the fusion vector features through the multi-task detection layer to obtain multi-task detection results, integrating the multi-task detection results to obtain the predicted comfort value of the indoor environment at the target time under the first temperature control scheme, and outputting the predicted comfort value through the output layer.

[0118] Furthermore, the feature fusion of the temperature control data features and the bracelet data features through the attention mechanism layer and the feature fusion layer to obtain the fusion vector features includes: calculating the relationship score between each feature of the temperature control data features and the bracelet data features through the self-attention mechanism in the attention mechanism layer; dynamically allocating weights according to the relationship scores of each feature of the temperature control data features and the bracelet data features to obtain the weight vector of each feature of the temperature control data features and the bracelet data features; deeply fusing the temperature control data features and the bracelet data features according to the weight vector through the feature fusion layer to obtain the fusion vector features.

[0119] Specifically, first, the input layer receives the parameters of the first temperature control solution and the user's wristband data. These data may include temperature settings, humidity control, ventilation strategies, user's physiological data and preference data, etc. The role of the input layer is to convert these data into a format suitable for neural network processing. Then, the attention mechanism layer is used to enhance the model's attention to important features. The attention mechanism can be implemented by the following formula:

[0120] ;

[0121] in, , and They are query, key and value matrices respectively. is the dimension of the key, which is used to scale the dot product to make the gradient more stable. The softmax function converts the dot product into a probability distribution, so that the model can learn which features are more important. Then, the feature fusion layer combines the temperature control data features and the bracelet data features to form a fused vector feature. This can be achieved through a simple concatenation operation or more complex fusion techniques such as feature weighting and fusion neural networks. Next, the multi-task detection layer performs multi-task detection based on the fused vector features. This layer can be designed as multiple parallel sub-layers, each responsible for a specific task, such as temperature comfort prediction, humidity comfort prediction, etc. The softmax function converts the output into a probability distribution, representing the prediction results of different tasks. Finally, the output layer integrates the multi-task detection results to obtain the predicted comfort value of the indoor environment at the target time under the first temperature control scheme. This can be achieved through an integration layer. This layer combines the prediction results of different tasks to form a comprehensive comfort score. For example, the following formula can be used to calculate the final comfort score.

[0122] 106. Generate a second temperature control plan between the current time and the target time according to the predicted comfort value, and generate a target temperature control plan according to the first temperature control plan and the second temperature control plan;

[0123] In one embodiment of the present invention, based on the predicted comfort score generated by the above model, the temperature control parameters that need to be adjusted between the current and target time can be determined. These adjustments are intended to make the predicted comfort level as close as possible to the ideal comfort level. The adjustments can be made according to the following rules:

[0124] ;

[0125] in, is the adjusted temperature control parameter, is the current temperature control parameter, is the adjustment amount determined based on the comfort prediction. The adjustment amount can be calculated as follows:

[0126] =k(DesiredComfort- );

[0127] in, is the adjustment coefficient, which is used to control the amplitude of the adjustment. DesiredComfort is the desired comfort level. is the predicted comfort score. After completing the adjustment of the second temperature control plan, it needs to be integrated with the first temperature control plan to form the target temperature control plan. The integration can be achieved by a simple weighted average method, as shown below:

[0128] ;

[0129] in, is the parameter of the target temperature control scheme, is the parameter of the first temperature control scheme, is the adjusted parameter of the second temperature control scheme, It is the weight during integration and can be adjusted according to actual conditions.

[0130] 107. Control the temperature of each temperature control device in the indoor environment according to the target temperature control plan.

[0131] In one embodiment of the present invention, the temperature, humidity and other relevant environmental parameters in the room are monitored in real time by a smart bracelet. These data will be collected through a sensor network and transmitted to a central processing unit. The central processing unit compares these real-time data with the target temperature control scheme to determine the deviation between the current environmental state and the expected target. Subsequently, the control system will calculate the required adjustment amount based on the deviation and generate corresponding control signals. These signals will be sent to various temperature control devices, such as air conditioners, heaters, humidifiers, and ventilation systems. The control signal will guide these devices to perform necessary operations, such as adjusting the temperature set point, changing the wind speed or humidity level, to gradually adjust the indoor environment to the target state. In addition, in order to ensure the smoothness and efficiency of the adjustment process, the control system also needs to have a certain degree of adaptive ability. This means that the system can optimize the control strategy based on the response speed and historical performance of the device to reduce over-adjustment or under-adjustment. For example, if the cooling speed of an air conditioning unit is slow, the system will send a control signal in advance to ensure that the set temperature is reached before the target time arrives.

[0132] In this embodiment, the user's physiological data and preference data, as well as real-time environmental data, are collected through multiple smart bracelets. The fuzzy logic control algorithm is used to calculate the user's initial comfort score and establish a comfort model. The collaborative filtering algorithm is used to analyze user preferences, identify user groups with similar preferences, and then calculate the precise comfort score. Combined with the multi-objective optimization algorithm, the optimal temperature control plan is generated based on the user's comfort score and the energy efficiency parameters of the temperature control device. Furthermore, the indoor environmental comfort at future times is predicted by the fitness prediction model, and a continuous temperature control plan is formulated accordingly. Finally, the temperature control device is controlled to automatically adjust the indoor temperature according to the target temperature control plan to achieve personalized and intelligent indoor temperature control management.

[0133] The above describes the temperature control method based on the smart bracelet cluster in the embodiment of the present invention. The following describes the temperature control device based on the smart bracelet cluster in the embodiment of the present invention. The smart bracelet cluster includes multiple smart bracelets in the same indoor environment; please refer to Figure 2In one embodiment of the present invention, a temperature control device based on a smart bracelet cluster includes:

[0134] A data collection module, used to collect user bracelet data of corresponding users in an indoor environment and real-time environmental data of each position in the indoor environment through multiple smart bracelets in the smart bracelet cluster, wherein the user bracelet data includes user physiological data and user preference data;

[0135] An initial scoring module, used to calculate the initial comfort score corresponding to each user according to the user's physiological data and real-time environmental data using a preset fuzzy logic control algorithm, and establish a user comfort model according to the initial comfort score corresponding to each user;

[0136] An accurate scoring module is used to analyze the user preference data through a preset collaborative filtering algorithm, identify user groups with similar preferences in the same indoor environment, obtain a user group model, and calculate an accurate comfort score corresponding to each user based on the user group model and the user comfort model;

[0137] An initial temperature control module is used to score and calculate an optimal fitness value according to the precise comfort level corresponding to each user and the energy efficiency parameters of each temperature control device in the indoor environment through a fitness function in a preset multi-objective optimization algorithm, and generate a first temperature control scheme for each temperature control device in the indoor environment at the current moment according to the optimal fitness value;

[0138] A comfort prediction module, used to input the temperature control parameters of the first temperature control scheme and the user's wristband data into a preset fitness prediction model to obtain a predicted comfort value of the indoor environment at a target time under the first temperature control scheme;

[0139] a target temperature control module, configured to generate a second temperature control scheme between the current moment and the target moment according to the predicted comfort value, and to generate a target temperature control scheme according to the first temperature control scheme and the second temperature control scheme;

[0140] The temperature control module is used to control each temperature control device in the indoor environment to adjust the temperature according to the target temperature control scheme.

[0141] In an embodiment of the present invention, the temperature control device based on the smart bracelet cluster runs the above-mentioned temperature control method based on the smart bracelet cluster, and the temperature control device based on the smart bracelet cluster collects the user's physiological data and preference data, as well as real-time environmental data through multiple smart bracelets. The fuzzy logic control algorithm is used to calculate the user's initial comfort score and establish a comfort model. The user's preferences are analyzed by the collaborative filtering algorithm, and user groups with similar preferences are identified, and then the accurate comfort score is calculated. Combined with the multi-objective optimization algorithm, the optimal temperature control scheme is generated according to the user's comfort score and the energy efficiency parameters of the temperature control device. Furthermore, the indoor environmental comfort at future moments is predicted by the fitness prediction model, and a continuous temperature control scheme is formulated accordingly. Finally, the temperature control device is controlled to automatically adjust the indoor temperature according to the target temperature control scheme to achieve personalized and intelligent indoor temperature control management.

[0142] above Figure 2 From the perspective of modular functional entities, the temperature control device based on the smart bracelet cluster in the embodiment of the present invention is described in detail. The temperature control device based on the smart bracelet cluster in the embodiment of the present invention is described in detail from the perspective of hardware processing.

[0143] Figure 3 It is a structural schematic diagram of a temperature control device based on a smart bracelet cluster provided by an embodiment of the present invention. The temperature control device 300 based on the smart bracelet cluster may have relatively large differences due to different configurations or performances, and may include one or more processors (central processing units, CPU) 310 (for example, one or more processors) and a memory 320, and one or more storage media 330 (for example, one or more mass storage device terminals) storing application programs 333 or data 332. Among them, the memory 320 and the storage medium 330 can be short-term storage or persistent storage. The program stored in the storage medium 330 may include one or more modules (not shown in the figure), and each module may include a series of instruction operations in the temperature control device 300 based on the smart bracelet cluster. Furthermore, the processor 310 can be configured to communicate with the storage medium 330, and execute a series of instruction operations in the storage medium 330 on the temperature control device 300 based on the smart bracelet cluster to implement the steps of the temperature control method based on the smart bracelet cluster.

[0144] The temperature control device 300 based on the smart bracelet cluster may also include one or more power supplies 340, one or more wired or wireless network interfaces 350, one or more input and output interfaces 360, and / or one or more operating systems 331, such as Windows Serve, Mac OS X, Unix, Linux, FreeBSD, etc. Those skilled in the art will appreciate that Figure 3The structure of the temperature control device based on the smart bracelet cluster shown does not constitute a limitation on the temperature control device based on the smart bracelet cluster provided by the present invention, and may include more or fewer components than shown in the figure, or combine certain components, or arrange the components differently.

[0145] The present invention also provides a computer-readable storage medium, which may be a non-volatile computer-readable storage medium or a volatile computer-readable storage medium. Instructions are stored in the computer-readable storage medium. When the instructions are executed on a computer, the computer executes the steps of the temperature control method based on a smart bracelet cluster.

[0146] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the above-described system, device, or unit can refer to the corresponding process in the aforementioned method embodiment and will not be repeated here.

[0147] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art or the whole or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions to enable a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk and other media that can store program code.

[0148] As described above, the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features thereof may be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A temperature control method based on a smart bracelet cluster, characterized in that: The smart bracelet cluster includes multiple smart bracelets in the same indoor environment; the temperature control method includes: Collecting user wristband data of corresponding users in an indoor environment and real-time environmental data of each location in the indoor environment through multiple smart wristbands in the smart wristband cluster, wherein the user wristband data includes user physiological data and user preference data; Using a preset fuzzy logic control algorithm to calculate the initial comfort score corresponding to each user according to the user physiological data and the real-time environmental data, and establishing a user comfort model according to the initial comfort score corresponding to each user; Analyzing the user preference data through a preset collaborative filtering algorithm, identifying a user group with similar preferences in the same indoor environment, obtaining a user group model, and calculating an accurate comfort score corresponding to each user based on the user group model and the user comfort model; The fitness function in the preset multi-objective optimization algorithm is used to score and calculate the optimal fitness value according to the precise comfort level corresponding to each user and the energy efficiency parameters of each temperature control device in the indoor environment, and a first temperature control scheme for each temperature control device in the indoor environment at the current moment is generated according to the optimal fitness value; Inputting the temperature control parameters of the first temperature control scheme and the user's wristband data into a preset fitness prediction model to obtain a predicted comfort value of the indoor environment at the target time under the first temperature control scheme; generating a second temperature control scheme between the current moment and the target moment according to the predicted comfort value, and generating a target temperature control scheme according to the first temperature control scheme and the second temperature control scheme; Control each temperature control device in the indoor environment to adjust the temperature according to the target temperature control scheme.

2. The temperature control method according to claim 1, characterized in that: The method of using a preset fuzzy logic control algorithm to calculate the initial comfort score corresponding to each user according to the user physiological data and the real-time environmental data, and establishing a user comfort model according to the initial comfort score corresponding to each user includes: Performing data preprocessing on the user physiological data and real-time environmental data, wherein the data preprocessing includes standardization processing and outlier removal processing; The user's physiological data and real-time environmental data after data preprocessing are fuzzified by a preset membership function to obtain fuzzy data corresponding to each data point in the user's physiological data and real-time environmental data; Performing reasoning processing on the fuzzified data according to a preset fuzzy logic rule set to obtain fuzzy outputs corresponding to the fuzzified data under each fuzzy rule in the fuzzy logic rule set; Aggregating the fuzzy outputs corresponding to the fuzzified data under each fuzzy rule to obtain a comprehensive fuzzy output set, and defuzzifying the comprehensive fuzzy output set to obtain an initial comfort score of the corresponding user; A user comfort model is established according to the initial comfort score corresponding to each user.

3. The temperature control method according to claim 1, characterized in that: The analyzing the user preference data by a preset collaborative filtering algorithm, identifying a user group with similar preferences in the same indoor environment, obtaining a user group model, and calculating the precise comfort score corresponding to each user according to the user group model and the user comfort model includes: Calculating similarity values ​​between preference items in the user preference data by using a preset collaborative filtering algorithm, and constructing a user similarity matrix based on the similarity values; The users corresponding to multiple smart bracelets in the same indoor environment are grouped according to the user similarity matrix through a preset clustering algorithm to obtain a user group model; Perform aggregate analysis on the user preference data of each user group in the user group model, and calculate the representative preference characteristics of the corresponding user group; According to the representative preference features and the user comfort model, a precise comfort score corresponding to each user is calculated in a weighted manner.

4. The temperature control method according to claim 1, characterized in that: The multi-objective optimization algorithm is a genetic optimization algorithm; The method of calculating the optimal fitness value by scoring according to the precise comfort level corresponding to each user and the energy efficiency parameters of each temperature control device in the indoor environment through the fitness function in the preset multi-objective optimization algorithm, and generating the first temperature control scheme for each temperature control device in the indoor environment at the current moment according to the optimal fitness value includes: Initializing an initial population of the genetic optimization algorithm and using the initial population as a target population, wherein each individual in the initial population represents a first temperature control scheme; Calculating the fitness value of each individual in the target population according to the precise comfort score by using the genetic optimization algorithm; Performing a selection operation on each individual in the target population according to the fitness value to obtain an optimized population, and performing crossover and mutation operations on the optimized population; Updating the optimized population after performing the crossover and mutation operations as the target population, and returning to the step of calculating the fitness value of each individual in the target population according to the precise comfort score by the genetic optimization algorithm until the iteration termination condition is met; When the iteration termination condition is met, the individual with the highest total fitness value in the target population is decoded to obtain the optimal fitness value to generate the first temperature control plan.

5. The temperature control method according to claim 1, characterized in that: The multi-objective optimization algorithm is the Harris Eagle algorithm; The step of calculating the optimal fitness value by scoring according to the precise comfort level corresponding to each user and the energy efficiency parameters of each temperature control device in the indoor environment through the fitness function in the preset multi-objective optimization algorithm, and generating the first temperature control scheme for each temperature control device in the indoor environment at the current moment according to the optimal fitness value also includes: Calculating the fitness value of the temperature control scheme represented by each Harris Hawk individual according to the accurate comfort score by using the fitness function corresponding to the Harris Hawk algorithm, and selecting the position of the Harris Hawk individual with the highest fitness value as the current prey position; Calculating the prey escape energy and jump intensity according to a preset prey escape energy and jump intensity calculation formula, and selecting a corresponding predation strategy according to the prey escape energy and the jump intensity; updating the position of each Harris hawk individual according to the predation strategy, recalculating the fitness value of the power dispatching strategy represented by each Harris hawk individual after the position update, and reselecting the position of the Harris hawk individual with the highest fitness value as the current prey position; Determine whether the preset stop condition is met; If satisfied, the current prey position is output as the optimal solution; If not, return to the step of calculating the prey escape energy and jump intensity according to the preset prey escape energy and jump intensity calculation formula until the preset stop condition is met; When a preset stop condition is met, a first temperature control scheme is generated according to the optimal solution.

6. The temperature control method according to claim 1, characterized in that: The step of inputting the temperature control parameters of the first temperature control scheme and the user's wristband data into a preset fitness prediction model to obtain a predicted comfort value of the indoor environment at a target time under the first temperature control scheme includes: Inputting the temperature control parameters of the first temperature control solution and the user bracelet data into a preset fitness prediction model, wherein the fitness prediction model includes an input layer, an attention mechanism layer, a feature fusion layer, a multi-task detection layer and an output layer; The temperature control parameters of the first temperature control solution and the user's wristband data are feature-encoded through the output layer to obtain temperature control data features and wristband data features; The temperature control data features and the bracelet data features are subjected to feature fusion through the attention mechanism layer and the feature fusion layer to obtain fusion vector features; The multi-task detection layer performs multi-task detection according to the fusion vector feature to obtain a multi-task detection result, and the multi-task detection result is integrated to obtain a predicted comfort value of the indoor environment at the target time under the first temperature control scheme, and the predicted comfort value is output through the output layer.

7. The temperature control method according to claim 6, characterized in that: The temperature control data features and the bracelet data features are fused by the attention mechanism layer and the feature fusion layer to obtain the fused vector features, which include: Calculate the relationship score between each feature of the temperature control data feature and the bracelet data feature through the self-attention mechanism in the attention mechanism layer; According to the relationship score of each feature in the temperature control data feature and the bracelet data feature, a weight is dynamically assigned to obtain a weight vector of each feature in the temperature control data feature and the bracelet data feature; The temperature control data features and the bracelet data features are deeply fused according to the weights through the feature fusion layer to obtain a fusion vector feature.

8. A temperature control device based on a smart bracelet cluster, characterized in that: The smart bracelet cluster includes multiple smart bracelets in the same indoor environment; The temperature control device based on the smart bracelet cluster includes: A data collection module, used to collect user bracelet data of corresponding users in an indoor environment and real-time environmental data of each position in the indoor environment through multiple smart bracelets in the smart bracelet cluster, wherein the user bracelet data includes user physiological data and user preference data; An initial scoring module, used to calculate the initial comfort score corresponding to each user according to the user's physiological data and real-time environmental data using a preset fuzzy logic control algorithm, and establish a user comfort model according to the initial comfort score corresponding to each user; An accurate scoring module is used to analyze the user preference data through a preset collaborative filtering algorithm, identify user groups with similar preferences in the same indoor environment, obtain a user group model, and calculate an accurate comfort score corresponding to each user based on the user group model and the user comfort model; An initial temperature control module is used to score and calculate an optimal fitness value according to the precise comfort level corresponding to each user and the energy efficiency parameters of each temperature control device in the indoor environment through a fitness function in a preset multi-objective optimization algorithm, and generate a first temperature control scheme for each temperature control device in the indoor environment at the current moment according to the optimal fitness value; A comfort prediction module, used to input the temperature control parameters of the first temperature control scheme and the user's wristband data into a preset fitness prediction model to obtain a predicted comfort value of the indoor environment at a target time under the first temperature control scheme; a target temperature control module, configured to generate a second temperature control scheme between the current moment and the target moment according to the predicted comfort value, and to generate a target temperature control scheme according to the first temperature control scheme and the second temperature control scheme; The temperature control module is used to control each temperature control device in the indoor environment to adjust the temperature according to the target temperature control scheme.

9. A temperature control device based on a smart bracelet cluster, characterized in that: The temperature control device based on the smart bracelet cluster includes: a memory and at least one processor, wherein instructions are stored in the memory; The at least one processor calls the instruction in the memory so that the temperature control device based on the smart bracelet cluster performs the steps of the temperature control method based on the smart bracelet cluster as described in any one of claims 1-7.

10. A computer-readable storage medium having instructions stored thereon, characterized in that: When the instruction is executed by the processor, the steps of the temperature control method based on the smart bracelet cluster as described in any one of claims 1 to 7 are implemented.

Images