Air conditioner parameter regulation and control method, device and equipment, storage medium and product

Abstract

The invention discloses an air conditioner parameter regulation and control method, device and equipment, a storage medium and a product, and relates to the technical field of parameter regulation and control. The air conditioner parameter regulation and control method comprises the steps that when it is monitored that the thermal self-adaption condition of a user is abnormal, target temperature data collected for different collection points of a preset position is obtained; inputting the target temperature data into a preset parameter prediction model for parameter prediction to obtain a parameter prediction result; and based on the parameter prediction result, air conditioner parameters are regulated and controlled. Through the preset parameter prediction model, parameter prediction is carried out on the obtained temperature data collected at different collection points of the preset position, the air conditioner parameters do not need to be adjusted after user feedback, then the air conditioner parameters are regulated and controlled based on the predicted parameter prediction result, and the situation that after user feedback, the air conditioner parameters are adjusted and controlled can be avoided. And air conditioner parameters are adjusted, and regulation and control cannot be conducted according to the real-time heat requirements of users.

Description

Technical Field

[0001] The present application relates to the field of parameter control technology, and in particular to an air conditioning parameter control method, device, equipment, storage medium and product. Background Art

[0002] In the traditional indoor air-conditioning control process, in order to keep the indoor temperature and wind speed within a comfortable range, the indoor users usually set the steady-state set temperature and wind speed level. The air-conditioning controller detects the difference between the set value and the actual value, and then adjusts the end effector. In the steady-state air-conditioning conditions in summer, the thermal sensation of indoor users is constantly changing. The steady-state conditions cannot fully meet the thermal comfort of users. Allowing the environment to change moderately and allowing users to exert their body temperature regulation ability is more conducive to user comfort and health.

[0003] In the related art, a hierarchical model is constructed through user personalized data, and the environmental parameter adjustment decision is calculated based on the user evaluation weight coefficient and the user's feedback on environmental comfort, so that the environment of different spaces or workstations in the public office area can be personalized and reasonably adjusted. However, this method can only adjust the air-conditioning parameters after user feedback, and cannot be adjusted according to the user's real-time thermal needs. Summary of the invention

[0004] The main purpose of the present application is to provide an air conditioning parameter control method, which aims to solve the technical problem that the air conditioning parameters can only be adjusted after user feedback and cannot be adjusted according to the user's real-time thermal demand.

[0005] To achieve the above purpose, the present application proposes an air conditioning parameter control method, the air conditioning parameter control method comprising:

[0006] When the user's thermal adaptation is abnormal, the target temperature data collected at different collection points at the preset position is obtained;

[0007] Inputting the target temperature data into a preset parameter prediction model to perform parameter prediction to obtain a parameter prediction result;

[0008] Based on the parameter prediction results, the air conditioning parameters are adjusted.

[0009] In one embodiment, when the user's thermal adaptation is detected to be abnormal, the step of obtaining target temperature data collected at different collection points at a preset position includes:

[0010] Acquire sample data and standard parameter data selected by a user, wherein the sample data is a historical temperature data set of a preset location associated with the user;

[0011] Using the standard parameter data as a sample label of the sample data;

[0012] An initial parameter prediction model is obtained, and a preset number of first sample data and the sample labels in the sample data are input into the initial parameter prediction model for model training to obtain a preset parameter prediction model that meets the accuracy requirements.

[0013] In one embodiment, the step of inputting a preset number of first sample data and the sample labels in the sample data into the initial parameter prediction model for model training to obtain a preset parameter prediction model that meets the accuracy requirements includes:

[0014] Inputting a preset number of first sample data from the sample data into the initial parameter prediction model, and performing parameter prediction on each individual of a preset initial population to obtain initial parameter prediction results corresponding to each individual, wherein the initial population is randomly generated, and each individual in the initial population represents a hyperparameter combination;

[0015] Determine the fitness corresponding to each individual based on the sample label and the initial parameter prediction result;

[0016] Based on the fitness, generating a target population;

[0017] Based on the target population, a preset parameter prediction model is obtained;

[0018] Based on the second sample data in the sample data, a weighting coefficient of the decision tree in the preset parameter prediction model is determined, and based on the weighting coefficient, a preset parameter prediction model that meets the accuracy requirement is determined.

[0019] In one embodiment, the step of generating a target population based on the fitness includes:

[0020] Based on the fitness of each individual, determine the target probability of each individual being selected as a parent;

[0021] Based on the target probability, determining a target individual representing the parent generation;

[0022] Crossover any two of the target individuals to obtain a generated first population;

[0023] Randomly mutating the first newly generated population to obtain a second population containing mutated individuals;

[0024] The target individuals are partially replaced by the first individual population to obtain a replaced target population.

[0025] In one embodiment, the step of determining a weight coefficient of a decision tree in the preset parameter prediction model based on the second sample data in the sample data, and determining a preset parameter prediction model that meets the accuracy requirement based on the weight coefficient includes:

[0026] Inputting the second sample data in the sample data into the preset parameter prediction model to perform parameter prediction, and obtaining the prediction result of each decision tree;

[0027] Calculating the consistency between the sample label corresponding to the second sample data and the prediction result corresponding to each decision tree to obtain a weighting coefficient corresponding to each decision tree;

[0028] Based on the weighting coefficients, a preset parameter prediction model that meets the accuracy requirements is determined.

[0029] In one embodiment, when the user's thermal adaptation is abnormal, the step of acquiring target temperature data collected at different collection points at a preset position further includes:

[0030] Acquire a preset number of first temperature data at a preset position, and a sample label for characterizing a user's thermal expectation;

[0031] Determine the correlation between the first temperature data and the sample label, and determine the second temperature data whose correlation is greater than a preset threshold value according to the correlation determination result;

[0032] The second temperature data is screened to obtain target temperature data for parameter prediction.

[0033] In addition, to achieve the above purpose, the present application also proposes an air conditioning parameter control device, the air conditioning parameter control device comprising:

[0034] An acquisition module is used to acquire target temperature data collected at different collection points at a preset position when the user's thermal adaptation is abnormal;

[0035] A prediction module, used for inputting the target temperature data into a preset parameter prediction model to perform parameter prediction and obtain parameter prediction results;

[0036] The control module is used to control the air-conditioning parameters based on the parameter prediction results.

[0037] In addition, to achieve the above-mentioned purpose, the present application also proposes an air-conditioning parameter control device, which includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, and the computer program is configured to implement the steps of the air-conditioning parameter control method described above.

[0038] In addition, to achieve the above-mentioned purpose, the present application also proposes a storage medium, which is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by the processor, the steps of the air conditioning parameter control method described above are implemented.

[0039] In addition, to achieve the above-mentioned purpose, the present application also provides a computer program product, which includes a computer program, and when the computer program is executed by a processor, the steps of the air conditioning parameter control method described above are implemented.

[0040] One or more technical solutions proposed in this application have at least the following technical effects:

[0041] Compared with the related art, a hierarchical model is constructed through user personalized data, and the environmental parameter adjustment decision is calculated based on the user evaluation weight coefficient and the user's feedback on environmental comfort, so that the environment of different spaces or workstations in the public office area can be personalized and reasonably adjusted. However, this method can only adjust the air-conditioning parameters after the user feedback, and cannot adjust the real-time thermal demand of the user. Compared with this, when the user's thermal adaptation is abnormal, the present application obtains the target temperature data collected at different collection points at the preset position; inputs the target temperature data into the preset parameter prediction model for parameter prediction to obtain the parameter prediction result; and adjusts the air-conditioning parameters based on the parameter prediction result. It can be understood that the present application uses the preset parameter prediction model to perform parameter prediction on the temperature data collected at different collection points at the preset position, and there is no need to adjust the air-conditioning parameters after the user feedback. Then, the air-conditioning parameters are adjusted based on the predicted parameter prediction results, which can avoid the problem that the air-conditioning parameters cannot be adjusted according to the user's real-time thermal demand after the user feedback. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0043] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0044] Figure 1 A flow chart of the first embodiment of the air conditioning parameter control method of the present application;

[0045] Figure 2A comparison chart of correlation coefficients between characteristic factors of the air conditioning parameter control method of this application;

[0046] Figure 3 A flow chart of the second embodiment of the air conditioning parameter control method of the present application;

[0047] Figure 4 A schematic diagram of building an initial parameter prediction model for the air conditioning parameter control method of this application;

[0048] Figure 5 The SHAP value of the input feature of each prediction label of the air conditioning parameter control method of this application;

[0049] Figure 6 This is a flow chart of optimizing hyperparameters of the air conditioning parameter control method of this application;

[0050] Figure 7 This is a schematic diagram of the module structure of the air conditioning parameter control device according to an embodiment of the present application;

[0051] Figure 8 Schematic diagram of the equipment structure of the hardware operating environment involved in the air conditioning parameter control method in the embodiment of the present application.

[0052] The purpose, features and advantages of this application will be further described in conjunction with the embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0053] It should be understood that the specific embodiments described herein are only used to explain the technical solutions of the present application and are not used to limit the present application.

[0054] In order to better understand the technical solution of the present application, a detailed description will be given below in conjunction with the accompanying drawings and specific implementation methods.

[0055] The main solution of the embodiment of the present application is: when monitoring shows that the user's thermal adaptation is abnormal, obtain the target temperature data collected at different collection points at the preset position; input the target temperature data into a preset parameter prediction model for parameter prediction to obtain parameter prediction results; and adjust the air-conditioning parameters based on the parameter prediction results.

[0056] In the related art, a hierarchical model is constructed through user personalized data, and the environmental parameter adjustment decision is calculated based on the user evaluation weight coefficient and the user's feedback on environmental comfort, so that the environment of different spaces or workstations in the public office area can be personalized and reasonably adjusted. However, this method can only adjust the air-conditioning parameters after user feedback, and cannot be adjusted according to the user's real-time thermal needs.

[0057] The present application uses a preset parameter prediction model to perform parameter prediction on the temperature data collected at different collection points at preset locations. There is no need to adjust the air-conditioning parameters after user feedback. Furthermore, the air-conditioning parameters are regulated based on the predicted parameter prediction results. This can avoid the problem that the air-conditioning parameters cannot be adjusted according to the user's real-time thermal needs when being adjusted after user feedback.

[0058] It should be noted that the execution subject of this embodiment can be a computing service device with data processing, network communication and program running functions, such as a tablet computer, a personal computer, a mobile phone, etc., or an electronic device capable of realizing the above functions, etc. The following takes an air conditioning parameter control device as an example to illustrate this embodiment and the following embodiments.

[0059] Based on this, the present application embodiment provides an air conditioning parameter control method, referring to Figure 1 , Figure 1 This is a flow chart of the first embodiment of the air conditioning parameter control method of the present application.

[0060] In this embodiment, the air conditioning parameter control method includes steps S100 to S300:

[0061] Step S100, when it is monitored that the thermal adaptation of the user is abnormal, the target temperature data collected at different collection points at the preset position are obtained;

[0062] It should be noted that the executor of this embodiment is an air conditioning parameter control device. The air conditioning parameter control device is provided with an infrared module and a HOBO temperature and humidity recorder. The collection points include the workstation, forehead and back of the hand. Since the air conditioner is turned on, the indoor temperature and wind speed will cause changes in the workstation temperature, forehead skin temperature and back of the hand skin temperature, so it is necessary to collect temperature at these three collection points.

[0063] It is understandable that the air conditioning parameter control equipment is also equipped with multiple sensors such as video, image, audio and sensor information, and multimodal technology is used through the above sensors to record the thermal adaptive behavior of personnel within a certain period of time (similar to 10s).

[0064] Specifically, after acquiring video, image, audio and sensor information through multimodal technology, the air conditioning parameter control device inputs the above information into the thermal adaptation recognition model to obtain recognition results under different thermal environments.

[0065] Furthermore, the thermal adaptive behavior of personnel can be collected by recording the thermal adaptive behavior of personnel in a certain period of time (such as 10 seconds) in the form of video, image, etc. The recognition can be performed from one perspective or from multiple perspectives.

[0066] Taking office buildings as an example, when people feel cold, common thermal adaptive behaviors include adding clothes, blowing on hands, shaking shoulders, rubbing hands, crossing legs, stamping feet, holding hands in front of chest, etc.; when people feel hot, common thermal adaptive behaviors include taking off clothes, rolling up sleeves, fanning with hands, wiping sweat, etc.; at the same time, some thermal adaptive behaviors that are not caused by thermal discomfort should also be identified, such as standing, sitting, yawning, stretching, turning wrists, turning the body left and right, typing, moving the mouse, writing copy, etc. Further, a thermal adaptive behavior recognition model for personnel is built. Currently, there are several relatively mature personnel behavior recognition model algorithms. For example, deep learning models such as dual-stream I3D and SlowFast Networks are used to identify the thermal adaptive behavior of personnel, and a personnel thermal adaptation recognition model based on neural networks is constructed to provide recognition results under different thermal environments.

[0067] Furthermore, the differences between different thermal adaptive behavior identification results and the results of thermal sensation surveys conducted on site are compared to verify the accuracy of the model and continuously optimize the identification model.

[0068] It should be noted that when the air conditioning parameter control device detects that the thermal adaptation of personnel in the office scene is abnormal, the infrared module is used to detect the temperature of various parts of the personnel's body in real time, including but not limited to cochlear temperature, forehead skin temperature, back of hand skin temperature, back skin temperature, chest skin temperature, abdominal skin temperature, upper arm skin temperature, forearm skin temperature, thigh skin temperature, calf skin temperature, instep skin temperature and vertical temperature difference. The systolic blood pressure, diastolic blood pressure and heart rate data can also be obtained through the bracelet monitoring to form a multi-dimensional data set of personnel physiological parameters, and measured in real time through the HOBO temperature and humidity recorder The air temperature at the heights of 0.1m, 0.6m, 1.1m and 1.7m in the room. According to people's sitting height and comfort requirements, the temperature felt by people at the heights of 0.1m, 0.6m and 1.1m has a greater impact on comfort. Therefore, when integrating the air measurement values ​​at different heights, higher weights are given to the temperature measurement values ​​at the heights of 0.1m, 0.6m and 1.1m, and lower weights are given to the temperature measurement values ​​at the height of 1.7m. The weighted average temperature is calculated, and then the temperature after the weighted average calculation is obtained as the workstation temperature value.

[0069] Step S200, inputting the target temperature data into a preset parameter prediction model to perform parameter prediction to obtain a parameter prediction result;

[0070] It should be noted that the parameter prediction results include the set temperature and wind speed. The air conditioning parameter control device inputs the collected temperature data into the preset parameter prediction model, predicts the specific parameters that need to be adjusted for the air conditioning temperature and wind speed at the current temperature, and obtains the predicted parameter prediction results including the set temperature and wind speed.

[0071] Step S300: adjusting the air conditioning parameters based on the parameter prediction results.

[0072] It is understandable that the air conditioning parameter control device automatically controls the air conditioning parameters according to the predicted set temperature and wind speed.

[0073] In a feasible implementation manner, the following steps are also included before step S100:

[0074] Acquire a preset number of first temperature data at a preset position, and a sample label for characterizing a user's thermal expectation;

[0075] It should be noted that the first temperature data consists of multiple samples, each of which contains 18 input features, including systolic blood pressure, diastolic blood pressure, heart rate, cochlear temperature, workstation temperature, workstation humidity, workstation wind speed, forehead skin temperature, back of hand skin temperature, back skin temperature, chest skin temperature, abdomen skin temperature, upper arm skin temperature, forearm skin temperature, thigh skin temperature, calf skin temperature, instep skin temperature and vertical temperature difference. The sample label is a subjective hot vote for the feature vector corresponding to each sample, which can better reflect the temperature expectation and wind speed expectation of the direction in which the subjects hope the environmental parameters will change under different temperature and wind speed environments.

[0076] It is understandable that the air conditioning parameter control device obtains the first temperature data consisting of multiple samples, and the expected temperature and wind speed corresponding to each sample feature vector.

[0077] Determine the correlation between the first temperature data and the sample label, and determine the second temperature data whose correlation is greater than a preset threshold value according to the correlation determination result;

[0078] It should be noted that the second temperature data includes characteristic factors that have a greater impact on the label, including workstation temperature, forehead temperature, back of hand skin temperature, upper arm skin temperature, thigh skin temperature, calf skin temperature and instep skin temperature. The air conditioning parameter control device obtains the characteristic factors that have a greater impact on the output label by analyzing the correlation between the characteristic factors themselves and between the characteristic factors and the label expectations, that is, the second temperature data with a correlation greater than the preset threshold, please refer to Figure 2 , Figure 2 A comparison chart of the correlation coefficients between characteristic factors is provided.

[0079] The second temperature data is screened to obtain target temperature data for parameter prediction.

[0080] It is understandable that considering the convenience and practicality of collecting data, infrared will be used to measure the local skin temperature of the human body. Therefore, when simplifying the input features, the local skin temperature exposed to the environment is given priority. Therefore, the air-conditioning parameter control device screens the second temperature data to obtain the target temperature data for parameter prediction.

[0081] In this embodiment, the air-conditioning parameter control device simplifies the collection features and collects temperature data of different collection points at preset locations in real time, predicts the air-conditioning parameters through a preset parameter prediction model, and controls the air-conditioning parameters based on the predicted results, thereby improving the real-time performance of the air-conditioning parameter control.

[0082] The present application provides a method for controlling air conditioning parameters. Figure 3 , Figure 3 This is a flowchart of the second embodiment of the business processing method of the present application.

[0083] In this embodiment, the step S100 includes steps A100 to A300:

[0084] Step A100, acquiring sample data and standard parameter data selected by the user, wherein the sample data is a historical temperature data set of a preset location associated with the user;

[0085] It should be noted that the sample data is a historical temperature data set including workstation temperature, forehead skin temperature and hand back skin temperature. The standard parameter data is the expected temperature and wind speed. The air conditioning parameter control device obtains the historical temperature data set of the historical user workstation and the expected temperature and wind speed selected by the user.

[0086] Step A200, using the standard parameter data as a sample label of the sample data;

[0087] It is understandable that the air conditioning parameter control device uses the desired temperature and desired wind speed selected by the user as sample labels of the sample data.

[0088] Step A300, obtaining an initial parameter prediction model, and inputting a preset number of first sample data and the sample labels in the sample data into the initial parameter prediction model for model training to obtain a preset parameter prediction model that meets the accuracy requirements.

[0089] It should be noted that the initial parameter prediction model is established based on random forest. The initial parameter prediction model is based on the characteristics of workstation temperature, forehead skin temperature, back of hand skin temperature, upper arm skin temperature, thigh skin temperature, calf skin temperature and instep skin temperature. Among them, random forest is an evaluation based on three performance indicators: classification accuracy, confusion matrix and ROC curve. The optimal algorithm is selected from multiple classification algorithms such as logistic regression, decision tree, random forest, K nearest neighbor, Gaussian naive Bayes, multi-layer perceptron, support vector machine, gradient boosting tree and adaptive boosting. Please refer to Figure 4 , Figure 4 A schematic diagram of building an initial parameter prediction model is provided.

[0090] Furthermore, after obtaining the initial parameter prediction model, the air conditioning parameter control device needs to simplify the number of features of the input model. Among the physiological parameters of the input features, there are many local skin temperatures, such as calf skin temperature, instep skin temperature and forehead skin temperature, which have strong correlations. In order to reduce the difficulty of measuring data, only one of them can be retained.

[0091] Furthermore, the air conditioning parameter control device calculates the SHAP value to quantify the contribution of the input features to the model, thereby simplifying the input features. The SHAP value is a method for explaining the prediction results of machine learning models, which is based on the concept of Shapley value in cooperative game theory. The core idea of ​​the SHAP value is to decompose the model prediction results into the contribution of each input feature, so as to understand the influence of each feature on the prediction results.

[0092] Specifically, the SHAP value evaluates the importance of each feature by randomly arranging different values ​​of the feature and calculating its impact on the prediction result. A positive value indicates that the feature has a positive impact on increasing the prediction value, and a negative value indicates that it has a negative impact on reducing the prediction value. The magnitude of the value indicates the degree of impact on the prediction result. By analyzing the SHAP value of each feature, we can gain a deep understanding of how the model makes prediction decisions. This explanatory method is very helpful for verifying the fairness and robustness of the model and improving the credibility of the model. The application of the SHAP value can provide important insights for model interpretation and help to better understand and explain the prediction results of machine learning models in practical applications. The SHAP formula is:

[0093]

[0094] It is understandable that, where θ i (x) is the SHAP value of feature i, indicating the contribution of feature i to the prediction result; f(x) is the predicted output of the model for input x; S is the subset of feature i that does not contain feature i; x s represents the input containing only the features in S; x S∪{i} represents the input containing feature i, where the value of feature i is determined by the input x, and the values ​​of other features are determined by the subset S; |S| represents the number of features in the subset S; p is the total number of features.

[0095] Specifically, the SHAP value not only reflects the importance of the feature, but also quantifies the contribution of each feature to the model prediction, revealing the impact of each variable on the model prediction. Figure 5 , Figure 5is the SHAP value of the input feature of each prediction label; Figure (a), (b), (c) are the SHAP values ​​of each input feature for temperature expectation (reduction, unchanged, increase). Based on these three figures, the contribution of workstation temperature, forehead skin temperature, and back of hand skin temperature to the prediction of temperature expectation reduction, unchanged, and increase is at the top. Figure (d), (e), (f) are the SHAP values ​​of each input feature for wind speed expectation (reduction, unchanged, and increase). Based on these three figures, the contribution of workstation temperature, forehead skin temperature, and back of hand skin temperature to the prediction of temperature expectation reduction, unchanged, and increase is also at the top. According to the feature contribution ranking, it is concluded that the simplified input features for predicting temperature expectation and wind speed expectation are all workstation temperature, forehead skin temperature, and back of hand skin temperature, among which Feature0: workstation temperature; Feature1: forehead skin temperature; Feature2: back of hand skin temperature; Feature3: upper arm skin temperature; Feature4: thigh skin temperature; Feature5: calf skin temperature; Feature6: back of foot skin temperature.

[0096] It should be noted that the sample data is divided into a training set and a validation set at a ratio of 7:3, repeated 50 times, and 20% of the training data set is randomly separated as the second sample data, and the remaining training data set is used as the first sample data. The air conditioning parameter control device puts the remaining training set into the random forest for training, and obtains a preset parameter prediction model that meets the accuracy requirements after training.

[0097] In a feasible implementation manner, the step of inputting a preset number of first sample data and the sample labels in the sample data into the initial parameter prediction model for model training to obtain a preset parameter prediction model that meets the accuracy requirements includes the following steps:

[0098] Inputting a preset number of first sample data from the sample data into the initial parameter prediction model, and performing parameter prediction on each individual of a preset initial population to obtain initial parameter prediction results corresponding to each individual, wherein the initial population is randomly generated, and each individual in the initial population represents a hyperparameter combination;

[0099] It is understandable that the preset initial population is randomly generated, including N individuals, each of which represents a hyperparameter combination. The air conditioning parameter control device inputs a preset number of first sample data in the sample data into the initial parameter prediction model, and predicts the air conditioning parameters based on the hyperparameters corresponding to each individual to obtain an initial prediction result.

[0100] Determine the fitness corresponding to each individual based on the sample label and the initial parameter prediction result;

[0101] It should be noted that the air conditioning parameter control device first defines a fitness function f(x) of the optimization problem, where x represents the hyperparameter combination, and calculates the fitness of each individual based on the sample label and the initial parameter prediction result, that is, f(x i ) to evaluate its performance in the problem space.

[0102] Based on the fitness, generating a target population;

[0103] It is understandable that the target population is the target population after individual replacement, and based on the target population, the model performs better. The air conditioning parameter control device generates a target population with better performance based on the fitness of each individual.

[0104] Based on the target population, a preset parameter prediction model is obtained;

[0105] It should be noted that the air-conditioning parameter control device obtains a preset parameter prediction model that meets the accuracy requirements based on a set of hyperparameters with better performance.

[0106] Based on the second sample data in the sample data, a weighting coefficient of the decision tree in the preset parameter prediction model is determined, and based on the weighting coefficient, a preset parameter prediction model that meets the accuracy requirement is determined.

[0107] It is understandable that in order to improve the shortcomings of the traditional random forest algorithm, a weighted voting strategy is introduced into the model so that the random forest algorithm can further improve its accuracy. After each decision tree in the preset parameter prediction model has completed its own training, the air conditioning parameter control device tests all decision trees through the second sample data, calculates the weight of each decision tree, and determines the preset parameter prediction model based on the weight.

[0108] In a feasible implementation, based on the fitness, the step of generating a target population includes the following steps:

[0109] Based on the fitness of each individual, determine the target probability of each individual being selected as a parent;

[0110] It should be noted that the air conditioning parameter control device determines the probability of each individual being selected as the parent according to the fitness of the individual, usually using methods such as roulette selection or tournament selection. Assume that P(x i ) Individual x i The probability of being selected as a parent is:

[0111]

[0112] Based on the target probability, determining a target individual representing the parent generation;

[0113] It is understandable that the air conditioning parameter control device determines the individual whose target probability exceeds the threshold as the target individual representing the parent generation.

[0114] Crossover any two of the target individuals to obtain a generated first population;

[0115] It should be noted that the air conditioning parameter control device selects the selected parent individuals for crossover in the crossover operation to generate new individuals. Common crossover operations include single-point crossover and multi-point crossover. Assume that the two selected parent individuals are x a and x b , then a new individual x can be generated by the following formula c , and form a new population based on the newly generated individuals:

[0116] x c =α·x a +(1-α)·x b

[0117] Among them, α is the position of the intersection point, which can be randomly selected.

[0118] Randomly mutating the first newly generated population to obtain a second population containing mutated individuals;

[0119] It is understandable that the air conditioning parameter control device randomly mutates the newly generated individuals during the mutation operation to increase the diversity of the population. Common mutation operations include randomly selecting certain hyperparameters for slight changes, or randomly generating new hyperparameter values, and generating a second population based on the mutated individuals.

[0120] The target individuals are partially replaced by the first individual population to obtain a replaced target population.

[0121] It should be noted that the air conditioning parameter control device replaces part of the individuals in the original population with the newly generated individuals in the replacement operation to form the next generation population, and repeats the above steps until the stop condition is met. Figure 6 , Figure 6 A flowchart for optimizing hyperparameters is provided.

[0122] In a feasible implementation manner, based on the second sample data in the sample data, determining the weight coefficient of the decision tree in the preset parameter prediction model, and based on the weight coefficient, determining the preset parameter prediction model that meets the accuracy requirement includes the following steps:

[0123] Inputting the second sample data in the sample data into the preset parameter prediction model to perform parameter prediction, and obtaining the prediction result of each decision tree;

[0124] It is understandable that the second sample data is validation set data. The air conditioning parameter control device inputs the validation set data into the preset parameter prediction model after hyperparameter optimization for model verification, and obtains the prediction results output by each decision tree in the model.

[0125] Calculating the consistency between the sample label corresponding to the second sample data and the prediction result corresponding to each decision tree to obtain a weighting coefficient corresponding to each decision tree;

[0126] It should be noted that the air conditioning parameter control device calculates the corresponding Kappa coefficient through the sample label and the prediction results of each decision tree. The Kappa coefficient eliminates the influence of chance. Compared with the recall rate and precision rate, it does not need to be calculated separately for each category, so the amount of calculation can be reduced. The Kappa coefficient expression formula is as follows:

[0127]

[0128] Among them, p o is the observed classification accuracy, p e is the expected classification accuracy.

[0129] The air conditioning parameter control device uses the kappa coefficient as the weight of each decision tree in the preset parameter prediction model, and each tree needs to be multiplied by the corresponding coefficient when voting.

[0130] Based on the weighting coefficients, a preset parameter prediction model that meets the accuracy requirements is determined.

[0131] It is understandable that the air conditioning parameter control device determines the preset parameter prediction model based on the weighting coefficient. When the model predicts the parameters, it performs weighted voting based on the prediction results and weighting coefficients of each decision tree to obtain the final parameter prediction results. The output formula of the preset parameter prediction model after weighting is as follows:

[0132]

[0133] Among them, v(v1,v2,…,v m ) is the prediction sample; k is the category of thermal expectation level; K is the total number of categories of thermal expectation level; The thermal expected category output by the qth decision tree is the kth category; kappa is the weight of the qth decision tree.

[0134] It should be noted that the above examples are only used to understand the present application and do not constitute a limitation on the air conditioning parameter control method of the present application. More simple transformations based on this technical concept are all within the protection scope of the present application.

[0135] This application also provides an air conditioning parameter control device, please refer to Figure 7 , the air conditioning parameter control device comprises:

[0136] The acquisition module 10 is used to acquire target temperature data collected at different collection points at a preset position when the user's thermal adaptation is abnormal;

[0137] The prediction module 20 is used to input the target temperature data into a preset parameter prediction model to perform parameter prediction and obtain a parameter prediction result;

[0138] The control module 30 is used to control the air-conditioning parameters based on the parameter prediction results.

[0139] Optionally, the acquisition module includes:

[0140] The model training submodule is used to obtain sample data and standard parameter data selected by the user, wherein the sample data is a historical temperature data set of a preset location associated with the user; the standard parameter data is used as the sample label of the sample data; an initial parameter prediction model is obtained, and a preset number of first sample data and the sample label in the sample data are input into the initial parameter prediction model for model training to obtain a preset parameter prediction model that meets the accuracy requirements. The screening submodule is used to obtain a preset number of first temperature data of a preset location, and a sample label used to characterize the user's thermal expectations; the correlation between the first temperature data and the sample label is judged, and based on the correlation judgment result, the second temperature data whose correlation is greater than a preset threshold is determined; the second temperature data is screened to obtain the target temperature data for parameter prediction.

[0141] Optionally, the model training submodule includes:

[0142] A model determination unit is used to input a preset number of first sample data in the sample data into the initial parameter prediction model, and perform parameter prediction based on each individual in the preset initial population to obtain initial parameter prediction results corresponding to each individual, wherein the initial population is randomly generated, and each individual in the initial population represents a hyperparameter combination; based on the sample label and the initial parameter prediction results, determine the fitness corresponding to each individual; based on the fitness, generate a target population; based on the target population, obtain a preset parameter prediction model; based on the second sample data in the sample data, determine the weight coefficient of the decision tree in the preset parameter prediction model, and based on the weight coefficient, determine the preset parameter prediction model that meets the accuracy requirements.

[0143] Optionally, the model determination unit includes:

[0144] A replacement subunit is used to determine the target probability of each individual being selected as a parent based on the fitness corresponding to each individual; determine the target individual representing the parent based on the target probability; cross any two of the target individuals to obtain a generated first population; perform random mutation on the newly generated first population to obtain a second population including mutated individuals; and partially replace the target individuals with the first individual population to obtain a replaced target population.

[0145] The weighting coefficient subunit is used to input the second sample data in the sample data into the preset parameter prediction model for parameter prediction to obtain the prediction result of each decision tree; calculate the consistency between the sample label corresponding to the second sample data and the prediction result corresponding to each decision tree to obtain the weighting coefficient corresponding to each decision tree; based on the weighting coefficient, determine the preset parameter prediction model that meets the accuracy requirements.

[0146] The air conditioning parameter control device provided by the present application adopts the air conditioning parameter control method in the above embodiment, which can solve the technical problem of air conditioning parameter control. Compared with the prior art, the beneficial effects of the air conditioning parameter control device provided by the present application are the same as the beneficial effects of the air conditioning parameter control method provided by the above embodiment, and other technical features in the air conditioning parameter control device are the same as the features disclosed in the above embodiment method, which will not be repeated here.

[0147] The present application provides an air conditioning parameter control device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the air conditioning parameter control method in the above-mentioned embodiment one.

[0148] Reference below Figure 8 , which shows a schematic diagram of the structure of an air conditioning parameter control device suitable for implementing the embodiment of the present application. The air conditioning parameter control device in the embodiment of the present application may include but is not limited to mobile terminals such as mobile phones, laptop computers, tablet computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PMPs (Portable Media Players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 8 The air conditioning parameter control device shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0149] like Figure 8As shown, the air conditioning parameter control device may include a processing device 1001 (such as a central processing unit, a graphics processor, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM: Read Only Memory) 1002 or a program loaded from a storage device 1003 to a random access memory (RAM: Random Access Memory) 1004. In RAM1004, various programs and data required for the operation of the air conditioning parameter control device are also stored. The processing device 1001, ROM1002 and RAM1004 are connected to each other through a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Generally, the following systems can be connected to the I / O interface 1006: an input device 1007 including, for example, a touch screen, a touchpad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; an output device 1008 including, for example, a liquid crystal display (LCD: Liquid Crystal Display), a speaker, a vibrator, etc.; a storage device 1003 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 1009. The communication device 1009 can allow the air conditioning parameter control device to communicate with other devices wirelessly or wired to exchange data. Although the figure shows an air conditioning parameter control device with various systems, it should be understood that it is not required to implement or have all the systems shown. More or fewer systems can be implemented or provided instead.

[0150] In particular, according to the embodiments disclosed in the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in the present application include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication device, or installed from a storage device 1003, or installed from a ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiment disclosed in the present application are executed.

[0151] The air conditioning parameter control device provided by the present application adopts the air conditioning parameter control method in the above embodiment, which can solve the technical problem of air conditioning parameter control. Compared with the prior art, the beneficial effects of the air conditioning parameter control device provided by the present application are the same as the beneficial effects of the air conditioning parameter control method provided by the above embodiment, and other technical features in the air conditioning parameter control device are the same as the features disclosed in the method of the previous embodiment, which will not be repeated here.

[0152] It should be understood that the various parts disclosed in this application can be implemented by hardware, software, firmware or a combination thereof. In the description of the above embodiments, specific features, structures, materials or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

[0153] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0154] The present application provides a computer-readable storage medium having computer-readable program instructions (ie, computer programs) stored thereon, and the computer-readable program instructions are used to execute the air conditioning parameter control method in the above-mentioned embodiment.

[0155] The computer-readable storage medium provided in the present application may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, systems or devices, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, system or device. The program code contained on the computer-readable storage medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination of the above.

[0156] The computer-readable storage medium may be included in the air-conditioning parameter control device; or may exist independently without being assembled into the air-conditioning parameter control device.

[0157] The above-mentioned computer-readable storage medium carries one or more programs. When the above-mentioned one or more programs are executed by the air-conditioning parameter control device, the air-conditioning parameter control device: when monitoring finds that the user's thermal adaptation situation is abnormal, obtains the target temperature data collected at different collection points at a preset position; inputs the target temperature data into a preset parameter prediction model for parameter prediction to obtain parameter prediction results; and regulates the air-conditioning parameters based on the parameter prediction results.

[0158] Computer program code for performing the operations of the present application may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0159] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present application. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0160] The modules involved in the embodiments described in this application may be implemented by software or hardware, wherein the name of the module does not constitute a limitation on the unit itself in some cases.

[0161] The readable storage medium provided in the present application is a computer-readable storage medium, which stores computer-readable program instructions (i.e., computer programs) for executing the above-mentioned air conditioning parameter control method, and can solve the technical problem of air conditioning parameter control. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided in the present application are the same as the beneficial effects of the air conditioning parameter control method provided in the above-mentioned embodiment, and will not be repeated here.

[0162] The present application also provides a computer program product, including a computer program, which implements the steps of the above-mentioned air-conditioning parameter control method when executed by a processor.

[0163] The computer program product provided in this application can solve the technical problem of air conditioning parameter control. Compared with the prior art, the beneficial effects of the computer program product provided in this application are the same as the beneficial effects of the air conditioning parameter control method provided in the above embodiment, which will not be repeated here.

[0164] The above descriptions are only some embodiments of the present application, and are not intended to limit the patent scope of the present application. All equivalent structural changes made using the contents of the present application specification and drawings under the technical concept of the present application, or direct / indirect applications in other related technical fields are included in the patent protection scope of the present application.

Claims

1. A method for controlling air conditioning parameters, characterized in that: The air conditioning parameter control method comprises: When the user's thermal adaptation is abnormal, the target temperature data collected at different collection points at the preset position is obtained; Inputting the target temperature data into a preset parameter prediction model to perform parameter prediction to obtain a parameter prediction result; Based on the parameter prediction results, the air conditioning parameters are adjusted.

2. The air conditioning parameter control method according to claim 1, characterized in that: When the user's thermal adaptation is abnormal, the step of obtaining target temperature data collected at different collection points at a preset position includes: Acquire sample data and standard parameter data selected by a user, wherein the sample data is a historical temperature data set of a preset location associated with the user; Using the standard parameter data as a sample label of the sample data; An initial parameter prediction model is obtained, and a preset number of first sample data and the sample labels in the sample data are input into the initial parameter prediction model for model training to obtain a preset parameter prediction model that meets the accuracy requirements.

3. The air conditioning parameter control method according to claim 2, characterized in that: The step of inputting a preset number of first sample data and the sample labels in the sample data into the initial parameter prediction model for model training to obtain a preset parameter prediction model that meets the accuracy requirement includes: Inputting a preset number of first sample data from the sample data into the initial parameter prediction model, and performing parameter prediction on each individual of a preset initial population to obtain initial parameter prediction results corresponding to each individual, wherein the initial population is randomly generated, and each individual in the initial population represents a hyperparameter combination; Determine the fitness corresponding to each individual based on the sample label and the initial parameter prediction result; Based on the fitness, generating a target population; Based on the target population, a preset parameter prediction model is obtained; Based on the second sample data in the sample data, the weight coefficient of the decision tree in the preset parameter prediction model is determined, and based on the weight coefficient, the preset parameter prediction model that meets the accuracy requirement is determined.

4. The air conditioning parameter control method according to claim 3, characterized in that: The step of generating a target population based on the fitness comprises: Based on the fitness of each individual, determine the target probability of each individual being selected as a parent; Based on the target probability, determining a target individual representing the parent generation; Crossover any two of the target individuals to obtain a generated first population; Randomly mutating the first newly generated population to obtain a second population containing mutated individuals; The target individuals are partially replaced by the first individual population to obtain a replaced target population.

5. The air conditioning parameter control method according to claim 3, characterized in that: The steps of determining a weighting coefficient of a decision tree in the preset parameter prediction model based on second sample data in the sample data, and determining a preset parameter prediction model that meets the accuracy requirement based on the weighting coefficient include: Inputting the second sample data in the sample data into the preset parameter prediction model to perform parameter prediction, and obtaining the prediction result of each decision tree; Calculating the consistency between the sample label corresponding to the second sample data and the prediction result corresponding to each decision tree to obtain a weighting coefficient corresponding to each decision tree; Based on the weighting coefficients, a preset parameter prediction model that meets the accuracy requirements is determined.

6. The air conditioning parameter control method according to claim 1, characterized in that: When the user's thermal adaptation is abnormal, the step of acquiring target temperature data collected at different collection points at a preset position also includes: Acquire a preset number of first temperature data at a preset position, and a sample label for characterizing a user's thermal expectation; Determine the correlation between the first temperature data and the sample label, and determine the second temperature data whose correlation is greater than a preset threshold value according to the correlation determination result; The second temperature data is screened to obtain target temperature data for parameter prediction.

7. An air conditioning parameter control device, characterized in that: The device comprises: An acquisition module is used to acquire target temperature data collected at different collection points at a preset position when the user's thermal adaptation is abnormal; A prediction module, used for inputting the target temperature data into a preset parameter prediction model to perform parameter prediction and obtain parameter prediction results; The control module is used to control the air-conditioning parameters based on the parameter prediction results.

8. An air conditioning parameter control device, characterized in that: The device comprises: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the air conditioning parameter control method according to any one of claims 1 to 6.

9. A storage medium, characterized in that: The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, the steps of the air conditioning parameter control method according to any one of claims 1 to 6 are implemented.

10. A computer program product, characterized in that The computer program product comprises a computer program, and when the computer program is executed by a processor, the steps of the air conditioning parameter control method according to any one of claims 1 to 6 are implemented.

Images