Air conditioner pre-setting method, electronic device, readable storage device and control system

Abstract

The application discloses a pre-setting method of an air conditioner. The method comprises the following steps: acquiring characteristic parameters; wherein the characteristic parameters comprise use data, environment data and time data, the use data represents the control parameter setting condition of the historical operation of the air conditioner, the environment data comprises the indoor and outdoor environment state where the air conditioner is located, and the time data comprises the time when the air conditioner operates; using a regression algorithm to predict preset control parameters after future starting based on the characteristic parameters, so as to set the air conditioner according to the preset control parameters. The application also discloses an electronic device, a computer readable storage device and a household appliance control system. Through the above method, the application can solve the problem that the air conditioner needs to be set and adjusted every time it starts to meet the user's needs under different conditions.

Description

Technical Field

[0001] This application relates to the field of control, and in particular to a method for presetting an air conditioner, electronic equipment, computer-readable storage device, and control system for household appliances. Background Technology

[0002] With the improvement of living standards, more and more families are choosing air conditioning as their primary cooling and heating equipment. However, during the cooling and heating process, users need to set various functions and control parameters to work together to achieve a suitable temperature environment and improve air comfort. The comfort experienced by users is also related to the current temperature, weather, and seasonal external environmental information. Users need to further adjust the air conditioning settings according to the current environmental conditions and their own needs to achieve the best experience. Currently, air conditioning settings are usually set to the parameters selected after the last shutdown, or fixed default settings. This often does not meet the needs of users at different times and in different environments. Therefore, users need to adjust the air conditioning parameters to some extent every time they turn on the air conditioner to achieve optimal air comfort. This operation is time-consuming and laborious, and also increases power consumption to some extent. How to ensure that the parameter settings after startup meet the current user needs, achieve the best experience, and minimize user adjustments has become a problem that technicians need to solve. Summary of the Invention

[0003] The main purpose of this application is to provide a method for presetting an air conditioner, an electronic device, a computer-readable storage device, and a control system for a household appliance, which can solve the problem that the air conditioner needs to be adjusted in terms of parameter settings every time it is turned on to meet the needs of users under different circumstances.

[0004] To address the aforementioned technical problems, the first technical solution adopted in this application is: to provide a pre-setting method for an air conditioner. This method includes: acquiring characteristic parameters; wherein the characteristic parameters include usage data, environmental data, and time data, the usage data representing the historical control parameter settings during air conditioner operation, the environmental data including the indoor and outdoor environmental conditions where the air conditioner is located, and the time data including the time the air conditioner has been running; using a regression algorithm on the characteristic parameters to predict the preset control parameters after future startup, so as to set the air conditioner according to the preset control parameters.

[0005] Among them, the preset control parameters include preset temperature data;

[0006] A regression algorithm is used to predict the preset control parameters after startup using the characteristic parameters, so that the air conditioner can be set according to the preset control parameters, including:

[0007] The effective feature parameters are obtained by inputting the feature parameters into the effective feature extraction model.

[0008] Use a regression algorithm to predict the preset temperature data after startup based on the effective feature parameters;

[0009] Among them, the preset control parameters include preset windshield data;

[0010] Using a regression algorithm on the characteristic parameters to predict the preset control parameters after future startup, so as to set the air conditioner according to the preset control parameters, further includes:

[0011] Based on preset temperature data and characteristic parameters, a one-to-many logistic regression algorithm is used to predict the preset wind speed data after startup.

[0012] The sigmoid function is used to obtain the preset windshield data with the highest probability based on the preset windshield data.

[0013] Among them, the preset control parameters include preset wind feel data or preset fresh air data;

[0014] Using a regression algorithm on the characteristic parameters to predict the preset control parameters after future startup, so as to set the air conditioner according to the preset control parameters, further includes:

[0015] Based on preset temperature data, preset wind speed data, and characteristic parameters, a logistic regression classification algorithm is used to predict the preset wind speed data or preset fresh air data to be set after startup.

[0016] The sigmoid function is used to obtain the preset wind feel data or preset fresh air data with the highest probability based on the preset wind feel data or preset fresh air data.

[0017] This includes, after obtaining the preset fresh air data with the highest probability using the sigmoid function based on the preset fresh air data, further including:

[0018] Determine if environmental data is abnormal;

[0019] If so, the preset fresh air data will be set to off or the preset fresh air data will be re-predicted;

[0020] An anomaly is determined by at least one of the following: the degree of outdoor pollution where the air conditioner is located, and the temperature difference between indoors and outdoors.

[0021] The method of using a regression algorithm to predict the preset control parameters after startup further includes inputting the previously set control parameters into the regression algorithm as reference data for calculating the preset control parameters.

[0022] This includes using a regression algorithm to predict preset control parameters after future startup of the feature parameters, so that the air conditioner can be set according to the preset control parameters, and further including:

[0023] Determine whether environmental data has changed to a preset change threshold or whether the time for setting control parameters has exceeded a preset time threshold.

[0024] If so, then re-execute the regression algorithm to predict the preset control parameters for the feature parameters, and

[0025] The control parameters set in the previous step are input into the regression algorithm as reference data for calculating the preset control parameters.

[0026] To address the aforementioned technical problems, the second technical solution adopted in this application is to provide an electronic device. This electronic device includes a memory and a processor. The memory stores program data, which can be executed by the processor to implement the method described in the first technical solution.

[0027] To address the aforementioned technical problems, the third technical solution adopted in this application is to provide a computer-readable storage device. This computer-readable storage device stores program data and can be executed by a processor to implement the method described in the first technical solution.

[0028] To solve the aforementioned technical problems, the fourth technical solution adopted in this application is: to provide a household appliance control system. This household appliance control system includes at least one household appliance and an electronic device as described in the second technical solution, which is capable of implementing the method described in the first technical solution to set the household appliance according to obtained control parameters.

[0029] The beneficial effects of this application are as follows: Unlike existing technologies, this application records the overall usage status of the air conditioner by acquiring data on air conditioner usage, environmental data, and time data. It then extracts more relevant feature parameters from the data to calculate control parameters based on user habits. Through the extracted feature parameters and corresponding logistic regression algorithms, control parameters that conform to user setting habits to a certain extent are obtained. This allows the air conditioner to be set according to these control parameters so that the settings after the air conditioner is turned on meet the user's needs, ensuring a comfortable user experience. Attached Figure Description

[0030] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0031] Figure 1 This is a percentage diagram illustrating the proportion of times when the user sets up the air conditioner.

[0032] Figure 2 This is a proportional diagram illustrating how the user's perception of temperature during cooling and heating corresponds to the settings and adjustments of the air conditioner.

[0033] Figure 3 This is a flowchart illustrating the first embodiment of the pre-setting method for the air conditioner in this application;

[0034] Figure 4 This is a flowchart illustrating the second embodiment of the air conditioner pre-setting method of this application;

[0035] Figure 5 This is a flowchart illustrating the third embodiment of the air conditioner pre-setting method of this application;

[0036] Figure 6 This is a flowchart illustrating the fourth embodiment of the air conditioner pre-setting method of this application;

[0037] Figure 7 This is a flowchart illustrating the fifth embodiment of the air conditioner pre-setting method of this application;

[0038] Figure 8 This is a flowchart illustrating the sixth embodiment of the air conditioner pre-setting method of this application;

[0039] Figure 9 This is a flowchart illustrating the seventh embodiment of the air conditioner pre-setting method of this application;

[0040] Figure 10 This is a schematic diagram of the structure of an embodiment of the electronic device of this application;

[0041] Figure 11 This is a schematic diagram of the structure of an embodiment of the computer-readable storage device of this application;

[0042] Figure 12 This is a schematic diagram of the structure of an embodiment of the household appliance control system of this application. Detailed Implementation

[0043] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of the embodiments. Based on the embodiments of this application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of this application.

[0044] The terms "first," "second," etc., used in this application are used to distinguish different objects, not to describe a specific order. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or apparatus that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to these processes, methods, products, or apparatuses.

[0045] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0046] This application, through extensive data accumulation, reveals that air conditioner settings primarily manifest in four aspects: temperature setting, fan speed setting, airflow sensitivity setting, and fresh air adjustment. Temperature setting refers to the threshold temperature set to the desired room temperature. Fan speed setting refers to the strength of the airflow delivered by the air conditioner when cooling or heating. Airflow sensitivity setting determines whether the user can perceive the airflow. The principle behind "no airflow" is not the absence of airflow, but rather the dispersion and slowing of airflow through numerous micro-vents, making it imperceptible to the user. Fresh air adjustment refers to whether outdoor air is drawn into the room. Prolonged stays in air-conditioned rooms often create a feeling of confinement, as air is in a closed environment, air circulation is limited, air turbidity increases, and oxygen content decreases. Therefore, it is necessary to improve indoor air quality by drawing in outdoor air.

[0047] like Figure 1 As shown, Figure 1 This diagram illustrates the proportion of times users adjust their air conditioner settings. It shows that users primarily adjust settings within the first ten minutes and one hour before turning on the air conditioner, with less likelihood of adjustments made afterward. Furthermore, taking temperature setting as an example... Figure 2 As shown. Figure 2 This diagram illustrates the proportion of users' perceived temperature changes in relation to air conditioner settings during cooling and heating. The upper shaded section represents the percentage of users with settings set too high, the lighter shaded section represents the percentage with settings that remain relatively constant, and the lower shaded section represents the percentage of users with settings set too low. For example, it can be seen that when cooling, the percentage of users with lower settings increases slightly when they feel the room temperature is colder than usual. Many similar influencing factors exist, which will not be elaborated upon here.

[0048] By analyzing user behavior data regarding various control parameter settings, feature data is obtained. Further, an algorithm predicts the current power-on control parameters based on the current environmental conditions, ensuring that the preset control parameters maximally meet user needs. This can be achieved through the methods described in the following embodiments.

[0049] like Figure 3 As shown, Figure 3 This is a flowchart illustrating the first embodiment of the pre-setting method for the air conditioner according to this application. It includes the following steps:

[0050] S11: Obtain feature parameters.

[0051] This system retrieves the settings of various control parameters for the air conditioner during use, along with usage time and relevant environmental information. Characteristic parameters include usage data, environmental data, and time data. Usage data represents the historical control parameter settings during air conditioner operation; environmental data includes the indoor and outdoor environmental conditions; and time data includes the duration of air conditioner operation. Further information may include the air conditioner's device identifier, related performance characteristics, and geographical location. Examples include the current province and city information, the indoor and outdoor temperatures at startup, and the longest-used set temperature since startup.

[0052] S12: Use a regression algorithm to predict the preset control parameters after startup based on the feature parameters, so as to set the air conditioner according to the preset control parameters.

[0053] Feature parameters, to a certain extent, represent user habits. Based on a large amount of data accumulation, regression algorithms are used to predict the control parameters that the user may need to set after powering on, based on information such as the current environmental conditions and the control parameters set by the user when the device was last powered off.

[0054] like Figure 4 As shown, Figure 4 This is a flowchart illustrating a second embodiment of the pre-setting method for the air conditioner according to this application. This method is a further extension of step S12. It includes the following steps:

[0055] S21: Input the feature parameters into the effective feature extraction model to obtain effective feature parameters.

[0056] The acquired feature parameters are further extracted and constructed to obtain feature parameters that are effective for usage habits. For example, the extraction of relevant parameters can be shown in the table below.

[0057] Feature parameters constructed using conventional methods:

[0058]

[0059] Characteristic parameters of weather environment structure:

[0060]

[0061] Feature parameters constructed from time and geographic location:

[0062]

[0063] The control parameters set last time:

[0064]

[0065] After the aforementioned feature extraction process, the resulting features are input into an effective feature extraction model for further filtering. This effective feature extraction model is constructed using a series of algorithms, including offline feature processing, feature cross-combination derivation, L1 feature filtering, and feature recursive elimination. The resulting effective feature parameters are then used to predict preset control parameters using a regression algorithm.

[0066] When the preset control parameters include preset temperature data, after extracting the effective feature parameters through the feature parameters obtained above, a regression algorithm is used to predict the predicted temperature data.

[0067] S22: Use a regression algorithm to predict the preset temperature data after startup using the effective feature parameters.

[0068] Taking a regression algorithm as an example, in one embodiment, let:

[0069]

[0070] in, For setting the preset temperature, Factors affecting the preset temperature To determine the weights of each factor, the regression algorithm generates a cost function, which describes the difference between the prior regression model and the actual data. When the cost function is minimized, the regression model is considered optimal, and the parameters can then be calculated. The preset temperature data is obtained based on the parameters and independent variables.

[0071] The process of obtaining weight parameters by gradient descent is described below using a single variable as an example.

[0072] Set up a regression algorithm model for a single variable:

[0073]

[0074] Its cost function is:

[0075]

[0076] in, , Let x be the parameter and x be the independent variable.

[0077] Substitute h(x) into the J function, and then calculate J with respect to... , The partial derivatives of x are calculated, and the resulting cost equation is substituted into the gradient descent algorithm. By transforming the dimension of x, the dimension of x is increased so that the obtained formula can be used for matrix operations. Finally, the cost function with the partial derivatives is substituted into the matrix form of the h(x) function to obtain the final result. This calculation process is not unique; it is only an example here.

[0078] The corresponding parameters are obtained using the gradient descent algorithm. Then, the preset temperature can be calculated based on the current independent variable x.

[0079] In one embodiment, the preset temperature data needs to be limited to a certain temperature range, such as between 16 and 30 degrees Celsius, and values ​​exceeding this limit are treated as limit values.

[0080] In another embodiment, considering the connectivity requirements of users, the control parameters set in the previous step are incorporated into the algorithm and assigned certain weights. This approach will be described in more detail in the following embodiments.

[0081] like Figure 5 As shown, Figure 5 This is a flowchart illustrating a third embodiment of the pre-setting method for the air conditioner according to this application. This method is a further extension of step S12 based on the second embodiment. It includes the following steps:

[0082] S31: Based on preset temperature data and characteristic parameters, use a one-to-many logistic regression algorithm to predict the preset wind speed data after startup.

[0083] Because there is a certain correlation between windshield data and preset temperature data, after obtaining the preset temperature data, a one-to-many logistic regression classification algorithm is used to make predictions by combining the feature parameters related to the windshield data. The logistic regression classification algorithm differs from the traditional linear regression algorithm in that it uses the sigmoid function. The sigmoid function, also called the Logistic function, has a value range of (0,1). It maps a real number to the interval (0,1) and can be used for binary classification. It is an S-shaped curve with values ​​between 0 and 1.

[0084] S32: Use the sigmoid function to obtain the preset windshield data with the highest probability based on the preset windshield data.

[0085] The preset windshield data obtained by the logistic regression algorithm is converted into a probability representing the corresponding windshield data by the sigmoid function, and the windshield data with the highest probability in the results is selected as the preset windshield data.

[0086] like Figure 6 As shown, Figure 6 This is a flowchart illustrating the fourth embodiment of the pre-setting method for the air conditioner according to this application. This method is a further extension of step S12 based on the third embodiment. It includes the following steps:

[0087] S41: Based on preset temperature data, preset wind speed data, and characteristic parameters, use a logistic regression classification algorithm to predict the preset wind speed data or preset fresh air data after startup.

[0088] Similarly, since there is a certain correlation between the wind perception data and the preset data obtained above, the wind perception data is predicted using a logistic regression algorithm based on the preset temperature data, preset wind speed data, and feature parameters related to the wind perception data. Likewise, the preset fresh air data is predicted using a logistic regression algorithm based on the preset temperature data, preset wind speed data, and feature parameters related to the fresh air data.

[0089] S42: Use the sigmoid function to obtain the preset wind feel data or preset fresh air data with the highest probability based on the preset wind feel data or preset fresh air data.

[0090] The preset wind sensation data obtained through logistic regression is converted into probabilities representing the corresponding wind sensation data using a sigmoid function. Based on these probabilities, the preset wind sensation data is selected as either windy or windless. Similarly, the preset fresh air data is set to on or off based on the final obtained probabilities.

[0091] like Figure 7 As shown, Figure 7 This is a flowchart illustrating the fifth embodiment of the pre-setting method for the air conditioner according to this application. This method is a further extension of step S42 based on the third embodiment. It includes the following steps:

[0092] S51: Determine if the environmental data is abnormal.

[0093] After the fresh air data prediction is completed, since indoor air needs to interact with outdoor air after the fresh air system is turned on, it will inevitably be affected by the outdoor air conditions. The drawn-in fresh air will cause changes in indoor temperature or air quality, etc. Therefore, after predicting that the fresh air system will be turned on, it is necessary to judge the current environmental conditions before starting the intake. The criteria for judging whether the current environmental conditions are abnormal may include the degree of outdoor air pollution and outdoor air temperature conditions. If the outdoor air quality is good and the temperature difference between indoors and outdoors does not exceed a certain threshold, the fresh air intake operation will continue. If the current environmental data is judged to be abnormal, step S52 will be executed.

[0094] S52: Set the preset fresh air data to off or re-predict the preset fresh air data.

[0095] When the current outdoor environment is determined to be abnormal, the operation of setting the preset fresh air data to be on is stopped, the fresh air data setting is changed to off, or the prediction is re-executed and the probability value of the fresh air data is recalculated.

[0096] like Figure 8 As shown, Figure 8 This is a flowchart illustrating the sixth embodiment of the pre-setting method for the air conditioner according to this application. This method is a further extension of step S12. It includes the following steps:

[0097] S61: Input the control parameters set in the previous step into the effective feature extraction model as reference data for calculating the preset control parameters.

[0098] Because user settings for air conditioning control parameters are interconnected, the control parameters set last time before startup are used as reference data in the regression algorithm to calculate the final prediction result. Furthermore, the weight of the previously set control parameters is appropriately reduced to avoid excessive influence on the prediction result.

[0099] In one embodiment, when solving for the preset temperature data, the previously set temperature data is added to the process of solving for the predicted temperature data, and an appropriately reduced weighting coefficient is assigned to it to avoid excessive influence on the final result. Furthermore, since the control parameter settings of the air conditioner involve multi-dimensional and mutually influential changes, other corresponding data, such as fresh air data, will also affect the preset temperature data. Therefore, fresh air data can also be considered as a limiting parameter in the solution process.

[0100] like Figure 9 As shown, Figure 9 This is a flowchart illustrating the seventh embodiment of the pre-setting method for the air conditioner according to this application. This method is a further extension of step S12. It includes the following steps:

[0101] S71: Determine whether environmental data has changed to the preset change threshold or whether the time for setting control parameters has exceeded the preset time threshold.

[0102] For a period of time after the air conditioner is turned on, if the control parameters remain unchanged for an extended period, it is necessary to recalculate the preset control parameters based on the characteristic parameters to reduce the possibility of system errors. Alternatively, in the event of a sudden situation where a significant change in the indoor or outdoor environment is detected, the set control parameters need to be adjusted to adapt to the new environmental conditions.

[0103] S72: Re-execute the regression algorithm to predict the preset control parameters for the feature parameters, and input the previously set control parameters into the regression algorithm as reference data for calculating the preset control parameters.

[0104] When a change in environmental data is detected that reaches a preset threshold, such as a sudden heavy rain that causes a drop in outdoor temperature, the preset control parameters will be recalculated based on the current environmental data when the temperature difference between the outdoor and indoor areas reaches the set threshold. The newly set control parameters will then be used as the previous control parameters in the calculation of the new preset control parameters.

[0105] If no change in control parameters is detected for an extended period, the system needs to determine whether this is due to an error or whether environmental factors have changed after a certain period but have not reached the threshold for change. In order to make the control parameter settings more in line with the user's needs, the control parameters are re-predicted, and the control parameters set at this time are used as reference data in the calculation process of the new preset control parameters.

[0106] like Figure 10 As shown, Figure 10 This is a schematic diagram of the structure of an embodiment of the electronic device of this application.

[0107] The electronic device includes a processor 110 and a memory 120.

[0108] Processor 110 controls the operation of electronic devices. Processor 110 may also be referred to as a CPU (Central Processing Unit). Processor 110 may be an integrated circuit chip with signal sequence processing capabilities. Processor 110 may also be a general-purpose processor, a digital signal sequence processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. A general-purpose processor may be a microprocessor or any conventional processor.

[0109] The memory 120 stores the instructions and program data required for the processor 110 to operate.

[0110] The processor 110 is used to execute instructions to implement the method provided by any embodiment and possible combination of the aforementioned air conditioning preset method of this application.

[0111] like Figure 11 As shown, Figure 11 This is a schematic diagram of the structure of an embodiment of the computer-readable storage device of this application.

[0112] One embodiment of the readable storage device of this application includes a memory 210 that stores program data, which, when executed, implements the method provided by any embodiment and possible combinations of the air conditioning preset method of this application.

[0113] The memory 210 may include a USB flash drive, a portable hard drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk, or other media that can store program instructions. Alternatively, it may be a server that stores the program instructions, which can send the stored program instructions to other devices for execution or execute the stored program instructions itself.

[0114] like Figure 12 As shown, Figure 12 This is a schematic diagram of the structure of an embodiment of the household appliance control system of this application.

[0115] The home appliance control system includes at least one home appliance 310 and an electronic device 320.

[0116] The household appliance 310 is capable of performing operations such as cooling, heating, and air circulation. This electronic device includes a processor and memory. The processor controls the operation of the electronic device; the processor can also be called a CPU (Central Processing Unit). The processor may be an integrated circuit chip with signal sequence processing capabilities. The processor 110 can also be a general-purpose processor, a digital signal processing unit (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. A general-purpose processor can be a microprocessor or any conventional processor. The memory stores the instructions and program data required for the processor's operation.

[0117] The electronic device 320 implements the method provided by any embodiment and possible combination of the above-described air conditioner preset method to set control parameters for the household appliance 310 according to the obtained preset control parameters.

[0118] In summary, the embodiments of this application record the overall usage status of the air conditioner by acquiring data on air conditioner usage, environmental data, and time data. Then, more relevant feature parameters are extracted from the data to calculate control parameters based on user habits. By using the extracted feature parameters and corresponding logistic regression algorithms, control parameters that conform to user settings to a certain extent are obtained. These control parameters allow the air conditioner to be set so that its settings after startup meet user needs, ensuring a comfortable user experience.

[0119] In the several embodiments provided in this application, it should be understood that the disclosed methods and devices can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For instance, the division of modules or units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed.

[0120] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment, depending on actual needs.

[0121] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0122] If the integrated units in the other embodiments described above are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) or processor to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0123] The above description is merely an embodiment of this application and does not limit the patent scope of this application. Any equivalent structural or procedural transformations made using the content of this application's specification and drawings, or direct or indirect applications in other related technical fields, are similarly included within the patent protection scope of this application.

Claims

1. A method for pre-setting an air conditioner, characterized in that, The method includes: Acquire feature parameters; wherein, the feature parameters include usage data, environmental data and time data, the usage data represents the control parameter settings of the air conditioner during historical operation, the environmental data includes the indoor and outdoor environmental conditions of the air conditioner, and the time data includes the time during which the air conditioner was running; A regression algorithm is used to predict the preset control parameters after startup using the feature parameters, so that the air conditioner can be set according to the preset control parameters; the preset control parameters include preset temperature data and preset fresh air data; When solving for the preset temperature data, the previously set temperature data is added to the process of solving the predicted temperature data, and an appropriately reduced weighting coefficient is set for it to avoid excessive influence on the final result. In addition, the preset fresh air data is considered as a limiting parameter in the process of solving for the preset temperature data. After predicting that the preset fresh air data is enabled, before starting to draw in fresh air, it is determined whether the environmental data is abnormal. If so, the preset fresh air data is set to be turned off or the preset fresh air data is re-predicted; The anomaly is determined by at least one of the following: the degree of outdoor pollution where the air conditioner is located and the temperature difference between indoors and outdoors. When the outdoor air quality is good and the temperature difference between indoors and outdoors does not exceed a certain threshold, the operation of starting to draw in fresh air continues.

2. The method according to claim 1, characterized in that, The step of using a regression algorithm to predict preset control parameters after future startup using the feature parameters, so as to set the air conditioner according to the preset control parameters, includes: The feature parameters are input into the effective feature extraction model to obtain effective feature parameters; wherein, the effective feature extraction model includes an algorithm model constructed by feature recursive elimination; A regression algorithm is used to predict the preset temperature data after startup using the effective feature parameters.

3. The method according to claim 2, characterized in that, The preset control parameters include preset windshield data; The step of using a regression algorithm to predict preset control parameters after future startup using the feature parameters, so as to set the air conditioner according to the preset control parameters, further includes: Based on the preset temperature data and the feature parameters, a one-to-many logistic regression algorithm is used to predict the preset wind speed data after startup. The preset windshield data is used to obtain the preset windshield data with the highest probability using the sigmoid function.

4. The method according to claim 3, characterized in that, The preset control parameters include preset wind perception data; The step of using a regression algorithm to predict preset control parameters after future startup using the feature parameters, so as to set the air conditioner according to the preset control parameters, further includes: Based on the preset temperature data, the preset wind speed data, and the feature parameters, a logistic regression classification algorithm is used to predict the preset wind speed data to be set after startup in the future. The preset wind sense data is obtained by using the sigmoid function based on the preset wind sense data to obtain the preset wind sense data with the highest probability.

5. The method according to claim 2, characterized in that, The step of using a regression algorithm to predict the preset control parameters after future startup using the feature parameters further includes: The control parameters set in the previous step are input into the regression algorithm as reference data for calculating the preset control parameters.

6. The method according to claim 2, characterized in that, The step of using a regression algorithm to predict preset control parameters after future startup using the feature parameters, so as to set the air conditioner according to the preset control parameters, further includes: Determine whether the environmental data has changed to a preset change threshold or whether the time for setting the control parameter has exceeded a preset time threshold. If so, then re-execute the regression algorithm to predict the preset control parameters using the feature parameters, and The control parameters set in the previous step are input into the regression algorithm as reference data for calculating the preset control parameters.

7. An electronic device, characterized in that, It includes a memory and a processor, the memory being used to store program data, the program data being executable by the processor to implement the method as described in any one of claims 1-6.

8. A computer-readable storage device, characterized in that, It stores program data and can be executed by a processor to implement the method as described in any one of claims 1-6.

9. A household appliance control system, characterized in that, It includes at least one household appliance and an electronic device as described in claim 7, the electronic device being capable of implementing the method as described in any one of claims 1-6 to set the household appliance according to the obtained control parameters.

Images