Operation control method and apparatus for air conditioner, device, and storage medium

Abstract

The present application discloses an operation control method and apparatus for an air conditioner, a device, and a storage medium. According to the present application, the method comprises: acquiring operation data of an air conditioner during operation; carrying out comfort evaluation by means of a trained comfort evaluation model on the basis of the operation data of the air conditioner to obtain the initial comfort and initial comfort curve of the air conditioner at the current moment; predicting the operation data of the air conditioner at the next moment on the basis of the initial comfort curve and a target comfort curve corresponding to the initial comfort; and finally, controlling the operation state of the air conditioner at the next moment on the basis of the predicted operation data.

Description

Air conditioner operation control method, device, equipment and storage medium

[0001] This application claims priority to Chinese patent application No. 202311086731.8 filed on August 25, 2023, the entire contents of which are incorporated by reference into this application. Technical Field

[0002] The present application relates to the technical field of air conditioners, and in particular to an operation control method, device, equipment and storage medium for an air conditioner. Background Art

[0003] In traditional technologies, comfort control technology during air conditioner operation has two major defects: biased control and rigid control. The main reasons for the above two defects are the lack of quantitative standards for comfort control and the air conditioner control logic is obtained from expert experience and experimental simulation without considering the user's usage habits. As a result, when controlling the operation of the air conditioner, the comfort level is low and cannot meet the user's usage needs.

[0004] The above content is only used to assist in understanding the technical solution of this application and does not constitute an admission that the above content is prior art. Technical issues

[0005] The main purpose of this application is to provide an air conditioner operation control method, device, equipment and storage medium, aiming to solve the technical problem of low comfort during the air conditioner operation control process in the prior art. Technical Solutions

[0006] To achieve the above object, the present application provides an operation control method for an air conditioner, the method comprising the following steps:

[0007] When the air conditioner is running, obtaining operating data of the air conditioner;

[0008] Determining the initial comfort level and initial comfort curve of the air conditioner through a trained comfort evaluation model based on the operating data;

[0009] Performing prediction based on the initial comfort curve and a set of target comfort curves corresponding to the initial comfort level to obtain predicted operating data of the air conditioner;

[0010] The operating state of the air conditioner at the next moment is controlled according to the predicted operating data.

[0011] In one embodiment, before determining the initial comfort level and initial comfort curve of the air conditioner using a trained comfort evaluation model based on the operating data, the method further includes:

[0012] generating a training sample set based on the operating data samples of the air conditioner and the comfort data samples of the comfort equipment;

[0013] Model training is performed based on the training sample set using an initial comfort prediction model to obtain a trained comfort evaluation model.

[0014] In one embodiment, the performing model training based on the training sample set using the initial comfort prediction model to obtain a trained comfort assessment model includes:

[0015] Performing model training using an initial regression model based on the training sample set to obtain a first prediction model;

[0016] Predicting a comfort level prediction value corresponding to the operating data sample according to the first prediction model;

[0017] Calculating an error value between the comfort level prediction value and the actual comfort level value in the comfort data sample;

[0018] Model training is performed using an initial comfort prediction model according to the operating data samples and the error value to obtain a trained comfort evaluation model.

[0019] In one embodiment, before performing prediction based on the initial comfort curve and the target comfort curve set corresponding to the initial comfort level to obtain predicted operating data of the air conditioner, the method further includes:

[0020] Obtaining historical reported data of the air conditioner;

[0021] Performing comfort evaluation based on the historical reported data using a trained comfort evaluation model to obtain a historical initial comfort and a corresponding historical comfort curve;

[0022] The historical comfort curves are classified to obtain a comfort curve set.

[0023] In one embodiment, performing comfort evaluation based on the historical reported data using a trained comfort evaluation model to obtain a historical initial comfort and a corresponding historical comfort curve includes:

[0024] Cleaning and sampling the historical reported data to obtain target historical reported data;

[0025] The comfort level is evaluated based on the historical target data using a trained comfort level evaluation model to obtain a historical initial comfort level and a corresponding historical comfort level curve.

[0026] In one embodiment, classifying the historical comfort curves to obtain a set of comfort curves includes:

[0027] Obtaining the extreme value, initial comfort and curve similarity of the historical comfort curve;

[0028] classifying the historical comfort curves based on the extreme values, the initial comfort levels, and the curve similarities to obtain a set of comfort curves;

[0029] The comfort curve set is preprocessed so that each comfort curve in the comfort curve set corresponds to a different initial comfort value.

[0030] In one embodiment, the performing prediction based on the initial comfort curve and the target comfort curve set corresponding to the initial comfort level to obtain the predicted operating data of the air conditioner includes:

[0031] Calculating the similarity between the initial comfort curve and the target comfort curve set;

[0032] determining a target predicted comfort curve in the target comfort curve set according to the similarity;

[0033] The predicted comfort level at the next moment and the predicted operating data of the air conditioner corresponding to the predicted comfort level are determined based on the target predicted comfort curve.

[0034] In addition, to achieve the above-mentioned purpose, the present application also proposes an operation control device for an air conditioner, the operation control device for the air conditioner comprising:

[0035] An acquisition module, configured to acquire operation data of the air conditioner when the air conditioner is in operation;

[0036] a calculation module, configured to determine an initial comfort level and an initial comfort curve of the air conditioner based on the operating data using a trained comfort evaluation model;

[0037] a prediction module, configured to make a prediction based on the initial comfort curve and a target comfort curve set corresponding to the initial comfort level, to obtain predicted operating data of the air conditioner;

[0038] A control module is used to control the operating state of the air conditioner at a next moment according to the predicted operating data.

[0039] In addition, to achieve the above-mentioned purpose, the present application also proposes an operation control device for an air conditioner, which includes: a memory, a processor, and an operation control program for an air conditioner stored on the memory and executable on the processor, wherein the operation control program for the air conditioner is configured to implement the steps of the operation control method for the air conditioner as described above.

[0040] In addition, to achieve the above-mentioned purpose, the present application also proposes a storage medium, on which an operation control program of an air conditioner is stored. When the operation control program of the air conditioner is executed by a processor, the steps of the operation control method of the air conditioner as described above are implemented. Beneficial effects

[0041] The present application discloses an operation control method for an air conditioner, the operation control method for the air conditioner comprising: obtaining operation data of the air conditioner when the air conditioner is operating; determining the initial comfort and initial comfort curve of the air conditioner through a trained comfort evaluation model based on the operation data; making predictions based on the initial comfort curve and a set of target comfort curves corresponding to the initial comfort to obtain predicted operation data of the air conditioner; and controlling the operation state of the air conditioner based on the predicted operation data of the air conditioner. Compared with the prior art, the present application obtains the operation data of the air conditioner when it is operating, and performs comfort evaluation based on the operation data of the air conditioner through a trained comfort evaluation model to obtain the initial comfort and initial comfort curve of the air conditioner at the current moment, and then predicts the operation data of the air conditioner at the next moment based on the initial comfort curve and the target comfort curve corresponding to the initial comfort, and finally controls the operation state of the air conditioner at the next moment based on the predicted operation data, thereby avoiding the technical problem of low comfort in the operation control process of the air conditioner in the prior art and improving the user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] FIG1 is a schematic diagram of the structure of an air conditioner operation control device in a hardware operation environment according to an embodiment of the present application;

[0043] FIG2 is a flow chart of a first embodiment of an operation control method for an air conditioner according to the present application;

[0044] FIG3 is a flow chart of a second embodiment of the operation control method of the air conditioner of the present application;

[0045] FIG4 is a flow chart of a third embodiment of the operation control method of the air conditioner of the present application;

[0046] FIG5 is a structural block diagram of a first embodiment of an operation control device for an air conditioner according to the present application.

[0047] The realization of the objectives, functional features and advantages of this application will be further explained in conjunction with embodiments and with reference to the accompanying drawings. Modes for Carrying Out the Invention

[0048] It should be understood that the specific embodiments described herein are only used to explain the present application and are not intended to limit the present application.

[0049] Refer to Figure 1, which is a schematic diagram of the structure of an air conditioner operation control device in the hardware operation environment involved in the embodiment of the present application.

[0050] As shown in Figure 1, the air conditioner operation control device may include: a processor 1001, such as a central processing unit (CPU), a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. The communication bus 1002 is used to enable communication between these components. The user interface 1003 may include a display and an input unit, such as a keyboard. The user interface 1003 may also include a standard wired interface or a wireless interface. The network interface 1004 may include a standard wired interface or a wireless interface (such as a Wireless Fidelity (Wi-Fi) interface). The memory 1005 may be a high-speed random access memory (RAM) or a stable non-volatile memory (NVM), such as a disk drive. The memory 1005 may also be a storage device independent of the processor 1001.

[0051] Those skilled in the art will appreciate that the structure shown in FIG1 does not limit the operation control device of the air conditioner, and may include more or fewer components than shown, or a combination of certain components, or a different arrangement of components.

[0052] As shown in FIG1 , the memory 1005 as a storage medium may include an operating system, a network communication module, a user interface module, and an operation control program of the air conditioner.

[0053] In the operation control device of the air conditioner shown in Figure 1, the network interface 1004 is mainly used for data communication with the network server; the user interface 1003 is mainly used for data interaction with the user; the processor 1001 and the memory 1005 in the operation control device of the air conditioner of this application can be set in the operation control device of the air conditioner, and the operation control device of the air conditioner calls the operation control program of the air conditioner stored in the memory 1005 through the processor 1001, and executes the operation control method of the air conditioner provided in this application.

[0054] The present application provides an operation control method for an air conditioner. Referring to FIG. 2 , FIG. 2 is a flow chart of a first embodiment of the operation control method for an air conditioner of the present application.

[0055] In one embodiment, the operation control method of the air conditioner includes the following steps:

[0056] Step S10: When the air conditioner is running, obtaining the operating data of the air conditioner.

[0057] It should be noted that the method provided in this application can be performed by the air conditioner device, which has functions such as data processing, data communication, and program execution. It can also be other devices with the same or similar functions, and this implementation condition does not impose any restrictions on this. For ease of explanation, this embodiment uses the air conditioner controller as an example.

[0058] In conventional technology, air conditioner comfort control is generally achieved through temperature control technology, humidity control technology, air flow rate control technology, and air quality control technology, etc., to achieve the effect of improving user comfort. Among them, temperature control technology refers to controlling the cooling or heating capacity of the air conditioner so that the indoor temperature reaches the user-set temperature value within the user's desired time range and maintains the temperature stable without overcooling or overheating. Humidity control technology refers to controlling the humidification or dehumidification capacity of the air conditioner so that the indoor humidity is maintained within the user-set comfort range. Currently, in actual air conditioner control, humidity control is generally coupled with temperature control to reduce humidity by cooling. Air flow rate control technology refers to adjusting the indoor air flow rate by controlling parameters such as the opening and closing degree of the air supply vents and the air supply direction to achieve the user's desired comfort level, such as windless technology. Air quality control technology refers to improving indoor air quality and reducing harmful substances in the air through technical means such as air filtration, negative ion generation, or UV sterilization, such as natural wind or air conditioning purification functions, etc. This application does not impose specific restrictions on these.

[0059] Regardless of the control technology of the above-mentioned air conditioners, they all face two major defects: biased control and control solidification. Among them, in biased control: temperature control technology mainly affects the comfortable temperature level, humidity control technology mainly affects the comfortable humidity level, and as for wind control technology and air quality control, they also act on comfortable wind and health dimensions respectively. Even if some combination technologies combine the centralized control technologies to perform multi-dimensional joint control, there is still a problem of control priority, and it cannot truly perform comprehensive control according to complete comfort standards; control solidification means that regardless of equipment, location, user, or time, the air conditioners all use the same set of control logic.

[0060] The main reasons for the above two defects are the lack of practical quantitative standards for air conditioning comfort measurement (for example, traditional comfort measurement indicators such as PMV or SET require expensive experimental equipment or professional instruments to implement); or because the current air conditioning control logic is mostly derived from expert experience + experimental simulation, proprietary information such as the behavioral habits of air conditioning users, the environmental conditions of air conditioning operation, and the reported data during air conditioning operation is not fully utilized.

[0061] In one embodiment, the operating data of the air conditioner includes but is not limited to: environmental information, operating condition information and user setting information, wherein the environmental information includes indoor ambient temperature, indoor ambient humidity and outdoor thermal environment information, the operating condition information includes fan speed, throttling element opening and windshield opening, etc., and the user setting information includes user-set temperature and air conditioner operating mode, etc. This application does not impose specific restrictions on this.

[0062] In a specific implementation, when the air conditioner is running, the operating data of the air conditioner can be collected at preset periods, and periodic features in the operating data can be extracted: including but not limited to environmental information, operating condition information, and user setting information, etc. The preset period can be 30s or 1min, and can also be set by the user. In this embodiment and the following embodiments, 30s is used as an example for explanation.

[0063] Step S20: determining the initial comfort level and initial comfort curve of the air conditioner through a trained comfort level evaluation model based on the operating data.

[0064] It should be noted that the trained comfort evaluation model is used to calculate the comfort corresponding to the operating data uploaded by the air conditioner. In one embodiment, the trained comfort evaluation model can be based on an improved human comfort intelligent control model (Predicted Mean Vote, PMV), which is mainly composed of a Lasso model and an integrated learning model (eXtreme Gradient Boosting, XGB) to jointly achieve the purpose of calculating the comfort corresponding to the operating data uploaded by the air conditioner.

[0065] In a specific implementation, the initial comfort level is calculated by reporting the operating data of the air conditioner every 30 seconds. The initial comfort level of the air conditioner in a second consecutive preset period is counted, and an initial comfort curve is generated based on the initial comfort level in the second period. The second preset period is greater than the preset period. For example, if the preset period is 30 seconds, the second preset period can be 5 minutes. This application does not impose any specific restrictions on this.

[0066] The initial comfort level corresponds to the operating data of the air conditioner at the current moment, and the initial comfort curve corresponds to the operating data of the air conditioner 5 minutes before the current moment.

[0067] Step S30: performing prediction based on the initial comfort curve and a target comfort curve set corresponding to the initial comfort level to obtain predicted operating data of the air conditioner.

[0068] It should be noted that the predicted operation data refers to the operation data that will achieve the best comfort level during the operation of the air conditioner at the next moment.

[0069] The step of performing prediction based on the initial comfort curve and a target comfort curve set corresponding to the initial comfort level to obtain predicted operating data of the air conditioner includes:

[0070] Calculating the similarity between the initial comfort curve and the target comfort curve set;

[0071] determining a target predicted comfort curve in the target comfort curve set according to the similarity;

[0072] The predicted comfort level at the next moment and the predicted operating data of the air conditioner corresponding to the predicted comfort level are determined based on the target predicted comfort curve.

[0073] In a specific implementation, due to changes in the operating parameters of the air conditioner, the corresponding comfort level will also change, and there will be differences in the comfort curve over a period of time. In one embodiment, the comfort curve corresponding to the initial comfort level can be extracted from the database first as the basis for the air conditioner operating parameters at the next moment.

[0074] This application is based on the initial comfort value and the comfort curve of the previous five minutes. By performing similarity calculation in a set of comfort curves with the same initial comfort value, the curve with the highest similarity is taken as the expected comfort curve (i.e., the target predicted comfort curve); similarity is calculated based on the current operating parameters of the air conditioner and a set of feasible parameters, and the feasible parameters with the highest similarity are taken as the operating parameters of the air conditioner at the next moment; similarity is calculated based on the current operating parameters of the air conditioner and a set of feasible parameters, and the feasible parameters with the highest similarity are taken as the operating parameters of the air conditioner at the next moment.

[0075] Step S40: controlling the operating state of the air conditioner at the next moment according to the predicted operating data.

[0076] This application obtains the operating data of the air conditioner during operation, and performs comfort evaluation by training a comfort evaluation model based on the operating data of the air conditioner, thereby obtaining the initial comfort and initial comfort curve of the air conditioner at the current moment, and then predicts the operating data of the air conditioner at the next moment based on the initial comfort curve and the target comfort curve corresponding to the initial comfort. Finally, the operating state of the air conditioner at the next moment is controlled according to the predicted operating data, thereby avoiding the technical problem of low comfort in the air conditioner operation control process in the prior art and improving the user experience.

[0077] Refer to FIG3 , which is a flow chart of a second embodiment of the operation control method of the air conditioner of the present application.

[0078] Based on the first embodiment above, in one embodiment, before step S20, the method further includes:

[0079] Step S110: generating a training sample set according to the operating data samples of the air conditioner and the comfort data samples of the comfort equipment.

[0080] It should be noted that the comfort data samples of comfort equipment include but are not limited to six indicators: air temperature, radiant temperature, air speed, relative humidity, metabolic rate and clothing resistance.

[0081] Step S120: performing model training based on the training sample set using the initial comfort prediction model to obtain a trained comfort assessment model.

[0082] It should be noted that the initial comfort prediction model in this embodiment can be a model established based on the Lasso+XGB hybrid regression algorithm, which uses Lasso to learn the basic characteristics of the data, uses XGB to learn the residuals, and constructs the final prediction model by integrating the model training results.

[0083] The model training is performed based on the training sample set using the initial comfort prediction model to obtain a trained comfort assessment model, including:

[0084] Performing model training using an initial regression model based on the training sample set to obtain a first prediction model;

[0085] Predicting a comfort level prediction value corresponding to the operating data sample according to the first prediction model;

[0086] Calculating an error value between the comfort level prediction value and the actual comfort level value in the comfort data sample;

[0087] Model training is performed using an initial comfort prediction model according to the operating data samples and the error value to obtain a trained comfort evaluation model.

[0088] In the specific implementation, the air conditioner and the PMV comfort measurement device are connected to collect real-time data reported by the air conditioner operation and comfort data reported by the comfort device. The air conditioner operating information, environmental conditions, and user operation data are used as feature variables, and the PMV data reported by the comfort device at the corresponding moment is used as the dependent variable. Through multiple sets of experimental operations, a corresponding training dataset is constructed. Based on the constructed training dataset, Lasso regression is used to fit the feature variables and PMV in the training dataset to obtain the corresponding Lasso model. The Lasso model is used to predict the PMV predicted value of the training data, lasso_pmv_pred, and the predicted value is subtracted from the actual PMV value to obtain the PMV prediction error, lasso_pmv_error = pmv – lasso_pmv_pred; build an XGB model to learn the model representation between the feature variables in the training data set and the lasso prediction error, and obtain the corresponding XGB model; predict the training data set based on the XGB model to obtain the prediction xgb_pred; add up the XGB prediction and the Lasso prediction value to obtain the final PMV prediction value pmv_pred=lasso_pmv_pred+xgb_pred, and obtain new prediction values ​​through continuous iteration until the trained model loss value is less than a certain threshold, then the trained comfort assessment model can be output.

[0089] This application trains the model established by the Lasso+XGB hybrid regression algorithm, continuously iterating the Lasso prediction value and the XGB prediction value, so as to train a model that can accurately adjust the operating status of the air conditioner and improve the user's air conditioner comfort.

[0090] Refer to FIG4 , which is a flow chart of a third embodiment of the air conditioner operation control method of the present application.

[0091] Based on the above second embodiment, in one embodiment, before step S30, the method further includes:

[0092] Step S210: Acquire historical reported data of the air conditioner.

[0093] It should be noted that the historical reported data of the air conditioner includes but is not limited to historical environmental information, historical operating condition information, and historical user setting information within a historical period of time.

[0094] Step S220: performing comfort evaluation based on the historical reported data using a trained comfort evaluation model to obtain a historical initial comfort and a corresponding historical comfort curve.

[0095] Since the air conditioner does not consider which data is effective for improving comfort when reporting data, a large amount of invalid data exists when reporting data. In order to reduce the amount of erroneous data and improve the efficiency of air conditioner control, the comfort evaluation model trained based on the historical reported data is used to perform comfort evaluation to obtain the historical initial comfort and the corresponding historical comfort curve, including:

[0096] Cleaning and sampling the historical reported data to obtain target historical reported data;

[0097] The comfort level is evaluated based on the historical target data using a trained comfort level evaluation model to obtain a historical initial comfort level and a corresponding historical comfort level curve.

[0098] Data cleaning includes but is not limited to missing value processing, outlier processing, data deduplication, data format conversion, dedimensionalization, data unification and error correction, etc. This application does not impose specific restrictions on this.

[0099] In the specific implementation, the historical reported data of the air conditioners is cleaned to obtain neat and clean air conditioning data. Then, based on random sampling, 2,000 sets of equipment are randomly selected as the construction set for comfort curve generation. Then, based on the trained comfort evaluation model, the comfort curve of each set of equipment in each operating range (i.e., the historical comfort curve) is obtained.

[0100] Step S230: classify the historical comfort curves to obtain a comfort curve set.

[0101] It should be noted that the basis for classification of historical comfort curves can be different heating and cooling demands, different environmental working conditions and different comfort change demands. In specific performance, the extreme value range (peak or valley) of the comfort curve can be used to represent the heating and cooling demands, the initial comfort of the curve can be used to represent the environmental working conditions, and the similarity of the curve can be used to represent the comfort change demands. This application does not impose any specific restrictions on this.

[0102] The historical comfort curves are classified to obtain a comfort curve set, including:

[0103] Obtaining the extreme value, initial comfort and curve similarity of the historical comfort curve;

[0104] classifying the historical comfort curves based on the extreme values, the initial comfort levels, and the curve similarities to obtain a set of comfort curves;

[0105] The comfort curve set is preprocessed so that each comfort curve in the comfort curve set corresponds to a different initial comfort value.

[0106] In the specific implementation, based on three criteria, namely, the peak or valley value of the comfort curve, the initial comfort of the curve, and the similarity of the curve, the historical comfort curves are classified into different clusters, and the curves in each cluster are smoothed and truncated to obtain a set of comfort curves corresponding to different initial comfort values.

[0107] This application evaluates the air conditioner's historical reported data through a trained comfort evaluation model to obtain multiple historical comfort curves, and then classifies the historical comfort curves into different clusters based on three criteria: comfort curve peak or valley value, curve initial comfort, and curve similarity, to obtain a set of comfort curves corresponding to different initial comfort values, which facilitates subsequent curve similarity calculation and improves the accuracy of air conditioner control at the next moment.

[0108] In addition, the present application also proposes a storage medium on which an operation control program for an air conditioner is stored. When the operation control program for the air conditioner is executed by a processor, the steps of the operation control method for the air conditioner as described above are implemented.

[0109] Since the storage medium adopts all the technical solutions of all the above embodiments, it has at least all the beneficial effects brought by the technical solutions of the above embodiments, which will not be described one by one here.

[0110] 5 , which is a structural block diagram of a first embodiment of an operation control device for an air conditioner according to the present application.

[0111] As shown in FIG5 , the operation control device of the air conditioner proposed in this application includes:

[0112] The acquisition module 10 is used to acquire the operating data of the air conditioner when the air conditioner is running.

[0113] The calculation module 20 is configured to determine the initial comfort level and initial comfort curve of the air conditioner based on the operating data using a trained comfort evaluation model.

[0114] The prediction module 30 is configured to perform prediction based on the initial comfort curve and a target comfort curve set corresponding to the initial comfort level to obtain predicted operating data of the air conditioner.

[0115] The control module 40 is configured to control the operating state of the air conditioner at a next moment according to the predicted operating data.

[0116] In one embodiment, the calculation module 20 is further used to generate a training sample set based on the operating data samples of the air conditioner and the comfort data samples of the comfort equipment; and perform model training based on the training sample set through the initial comfort prediction model to obtain a trained comfort evaluation model.

[0117] In one embodiment, the calculation module 20 is further used to perform model training through an initial regression model based on the training sample set to obtain a first prediction model; predict the comfort prediction value corresponding to the operating data sample according to the first prediction model; calculate the error value between the comfort prediction value and the actual comfort value in the comfort data sample; perform model training through the initial comfort prediction model according to the operating data sample and the error value to obtain a trained comfort evaluation model.

[0118] In one embodiment, the prediction module 30 is further used to obtain historical reported data of the air conditioner; perform comfort evaluation based on the historical reported data using a trained comfort evaluation model to obtain historical initial comfort and corresponding historical comfort curves; and classify the historical comfort curves to obtain a set of comfort curves.

[0119] In one embodiment, the prediction module 30 is further used to clean and sample the historical reported data to obtain target historical reported data; and perform comfort evaluation based on the target historical reported data using a trained comfort evaluation model to obtain historical initial comfort and a corresponding historical comfort curve.

[0120] In one embodiment, the prediction module 30 is further used to obtain the extreme value, initial comfort and curve similarity of the historical comfort curve; classify the historical comfort curve based on the extreme value, the initial comfort and the curve similarity to obtain a comfort curve set; and preprocess the comfort curve set so that each comfort curve in the comfort curve set corresponds to a different initial comfort value.

[0121] In one embodiment, the prediction module 30 is further used to calculate the similarity between the initial comfort curve and the target comfort curve set; determine the target predicted comfort curve in the target comfort curve set based on the similarity; and determine the predicted comfort at the next moment and the predicted operating data of the air conditioner corresponding to the predicted comfort based on the target predicted comfort curve.

[0122] This application obtains the operating data of the air conditioner during operation, and performs comfort evaluation by training a comfort evaluation model based on the operating data of the air conditioner, thereby obtaining the initial comfort and initial comfort curve of the air conditioner at the current moment, and then predicts the operating data of the air conditioner at the next moment based on the initial comfort curve and the target comfort curve corresponding to the initial comfort. Finally, the operating state of the air conditioner at the next moment is controlled according to the predicted operating data, thereby avoiding the technical problem of low comfort in the air conditioner operation control process in the prior art and improving the user experience.

[0123] Although the various steps in the flowchart in the embodiment of the present application are shown in sequence according to the indication of the arrows, these steps are not necessarily performed in sequence in the order indicated by the arrows. Unless clearly stated herein, the execution of these steps is not strictly limited in order and can be performed in other orders. Moreover, at least a portion of the steps in the figure may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily performed at the same time, but can be performed at different times, and their execution order is not necessarily performed in sequence, but can be performed in turn or alternately with at least a portion of other steps or sub-steps or stages of other steps.

[0124] The above is only an example and does not constitute any limitation to the technical solution of the present application. In specific applications, technicians in this field can make settings as needed, and the present application does not impose any restrictions on this.

[0125] It should be noted that the workflow described above is merely illustrative and does not limit the scope of protection of this application. In actual applications, technicians in this field can select part or all of it according to actual needs to achieve the purpose of this embodiment scheme, and no restrictions are imposed here.

[0126] In addition, for technical details not fully described in one embodiment, please refer to the operation control method of the air conditioner provided in any embodiment of the present application, and will not be repeated here.

[0127] In addition, it should be noted that, in this document, the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, article, or system comprising a series of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, method, article, or system. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of other identical elements in the process, method, article, or system comprising the element.

[0128] The serial numbers of the above embodiments of the present application are for description only and do not represent the advantages or disadvantages of the embodiments.

[0129] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus the necessary general hardware platform. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this application, or the part that contributes to the existing technology, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as read-only memory (ROM) / RAM, a magnetic disk, or an optical disk) and includes a number of instructions for enabling a terminal device (which can be a mobile phone, a computer, a server, or a network device, etc.) to execute the methods described in each embodiment of this application.

[0130] The above are merely optional embodiments of the present application and do not limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made using the contents of the present application specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present application.

Claims

1. A method for controlling the operation of an air conditioner, wherein: The operation control method of the air conditioner comprises: When the air conditioner is running, obtaining operation data of the air conditioner; Determine the initial comfort level and initial comfort curve of the air conditioner through a trained comfort level evaluation model based on the operating data; Perform prediction based on the initial comfort curve and a set of target comfort curves corresponding to the initial comfort level to obtain predicted operating data of the air conditioner; The operating state of the air conditioner at the next moment is controlled according to the predicted operating data.

2. The operation control method of the air conditioner according to claim 1, wherein: Before determining the initial comfort level and initial comfort curve of the air conditioner through the trained comfort level evaluation model based on the operating data, the method further includes: Generate a training sample set according to the operation data samples of the air conditioner and the comfort data samples of the comfort equipment; Model training is performed based on the training sample set using an initial comfort prediction model to obtain a trained comfort assessment model.

3. The operation control method of the air conditioner according to claim 2, wherein: The model training is performed based on the training sample set through the initial comfort prediction model to obtain a trained comfort evaluation model, including: Performing model training based on the training sample set through an initial regression model to obtain a first prediction model; Predicting a comfort level prediction value corresponding to the operation data sample according to the first prediction model; Calculating an error value between the comfort prediction value and the actual comfort value in the comfort data sample; Model training is performed using an initial comfort prediction model according to the operating data samples and the error value to obtain a trained comfort assessment model.

4. The operation control method of the air conditioner according to any one of claims 1 to 3, wherein: Before performing prediction according to the initial comfort curve and the target comfort curve set corresponding to the initial comfort level to obtain the predicted operation data of the air conditioner, the method further includes: Acquire historical reported data of the air conditioner; Performing comfort evaluation based on the historical reported data through a trained comfort evaluation model to obtain a historical initial comfort and a corresponding historical comfort curve; The historical comfort curves are classified to obtain a set of comfort curves.

5. The operation control method of the air conditioner according to claim 4, wherein: The comfort evaluation is performed according to the historical reported data through a trained comfort evaluation model to obtain a historical initial comfort and a corresponding historical comfort curve, including: Cleaning and sampling the historical reported data to obtain target historical reported data; The comfort level is evaluated by using a trained comfort level evaluation model according to the historical reported data of the target, and a historical initial comfort level and a corresponding historical comfort level curve are obtained.

6. The operation control method of the air conditioner according to claim 4, wherein: The classifying of the historical comfort curves to obtain a set of comfort curves includes: Obtaining the extreme value, initial comfort and curve similarity of the historical comfort curve; Classifying the historical comfort curves based on the extreme values, the initial comfort levels, and the curve similarities to obtain a set of comfort curves; The comfort curve set is preprocessed so that each comfort curve in the comfort curve set corresponds to a different initial comfort value.

7. The operation control method of the air conditioner according to claim 1, wherein: The step of performing prediction according to the initial comfort curve and a target comfort curve set corresponding to the initial comfort level to obtain predicted operation data of the air conditioner includes: Calculating the similarity between the initial comfort curve and the target comfort curve set; Determining a target predicted comfort curve in the target comfort curve set according to the similarity; The predicted comfort level at the next moment and the predicted operation data of the air conditioner corresponding to the predicted comfort level are determined based on the target predicted comfort curve.

8. An operation control device for an air conditioner, wherein: The operation control device of the air conditioner comprises: An acquisition module, used for acquiring operation data of the air conditioner when the air conditioner is running; A calculation module, used for determining the initial comfort and initial comfort curve of the air conditioner through a trained comfort evaluation model based on the operating data; A prediction module, used for making predictions based on the initial comfort curve and a target comfort curve set corresponding to the initial comfort level, to obtain predicted operation data of the air conditioner; A control module is used to control the operating state of the air conditioner at the next moment according to the predicted operating data.

9. An operation control device for an air conditioner, wherein: The operation control device of the air conditioner includes: a memory, a processor, and an operation control program of the air conditioner stored in the memory and executable on the processor, wherein the operation control program of the air conditioner is configured to implement the operation control method of the air conditioner as described in any one of claims 1 to 7.

10. A storage medium, wherein: The storage medium stores an operation control program of the air conditioner, and when the operation control program of the air conditioner is executed by the processor, the operation control method of the air conditioner according to any one of claims 1 to 7 is implemented.

Images