Air conditioner starting time estimation model construction method and device, equipment and medium

Abstract

The invention provides an air conditioner starting duration estimation model construction method and device, equipment and a medium. The method comprises the steps that historical data of target parameters are obtained; the target parameters comprise the air conditioner number, the space temperature, the air conditioner horsepower, the target closed area, the air conditioner set temperature and the air conditioner air speed of the target closed area; based on the historical data of the target parameter, training a duration estimation model to obtain a training error; if the training error meets a preset error requirement, adjusting parameters of the duration estimation model according to an optimization function to obtain a duration estimation model with updated parameters; and if the training error does not meet the preset error demand, repeating the step of training the duration estimation model based on the historical data of the target parameter to obtain the training error until the training error meets the preset error demand. The starting time of the air conditioner can be accurately calculated, the automation degree is high, and manpower resources are saved.

Description

Technical Field

[0001] This application relates to the technical field of temperature regulation in production workshops. Specifically, it relates to a method, device, equipment, and medium for constructing an estimation model for the air conditioner startup duration. Background Art

[0002] Cut tobacco is the product of the technological processing and fermentation of tobacco leaves. As an important raw material for cigarette production, it is extremely sensitive to the temperature of the environment during various processes such as transportation, storage, production, and packaging. The temperature of the environment has an important impact on the passing rate and premium rate of cigarette products.

[0003] Currently, air conditioners are used to control the temperature in production workshops. Since the temperature is mostly different in different seasons, it is usually necessary to turn on the air conditioner in advance for a period of time and wait until the temperature reaches the required production temperature standard before starting production. For example, in summer, in order to avoid the workshop temperature not meeting the standard, the air conditioner is generally turned on three hours in advance, resulting in serious energy consumption losses, and it is all managed manually at the same time, consuming human resources. Summary of the Invention

[0004] In view of this, the embodiments of this application provide a method, device, computer equipment, and storage medium for constructing an estimation model for the air conditioner startup duration, which can accurately calculate the startup time of the air conditioner, with a high degree of automation and saving human resources.

[0005] In a first aspect, the embodiments of this application provide a method for constructing an estimation model for the air conditioner startup duration, including the following steps:

[0006] Obtain historical data of target parameters; the target parameters include the number of air conditioners, space temperature, air conditioner horsepower, area of the target enclosed area, set temperature of the air conditioner, and air conditioner wind speed in the target enclosed area;

[0007] Train the duration estimation model based on the historical data of the target parameters to obtain a training error;

[0008] If the training error meets the preset error requirement, adjust the coefficients of the duration estimation model according to the optimization function to obtain a duration estimation model with updated coefficients; if the training error does not meet the preset error requirement, repeat the step of training the duration estimation model based on the historical data of the target parameters to obtain a training error until the training error meets the preset error requirement.

[0009] In a possible implementation manner, the training of the duration estimation model based on the historical data of the target parameters to obtain a training error includes:

[0010] Import any set of training data in the historical data of the target parameters into the duration estimation model to obtain a duration estimation value;

[0011] Import the duration estimation value and the obtained actual duration value into an error function to obtain a training error.

[0012] In a possible implementation, the step of importing the duration estimation value and the obtained actual duration value into an error function to obtain a training error includes:

[0013] Import the duration estimation value and the obtained actual duration value into a mean squared error function to obtain

[0014]

[0015] where represents the duration estimation value, represents the actual duration value, represents the training error of the current training.

[0016] In a possible implementation, the step of if the training error meets a preset error requirement, adjusting the coefficients of the duration estimation model according to an optimization function to obtain a duration estimation model with updated coefficients includes:

[0017] Use the stochastic gradient descent method to process the training error and the coefficients of the duration estimation model to obtain new coefficients of the duration estimation model;

[0018] Based on the new coefficients of the duration estimation model, obtain the duration estimation model with updated coefficients.

[0019] In a possible implementation, before the step of training a duration estimation model based on historical data of the target parameter to obtain a training error, the method further includes:

[0020] Initialize each coefficient in the duration estimation model by using random numbers respectively.

[0021] In a possible implementation, the method further includes:

[0022] If the training error meets a preset error requirement and the number of training times reaches a preset number requirement, adjust the coefficients of the duration estimation model according to an optimization function to obtain a duration estimation model with updated coefficients.

[0023] In a second aspect, an embodiment of the present application provides an air conditioner startup duration estimation method, including:

[0024] Input the current data of the target parameter obtained into the duration estimation model obtained by the duration estimation model construction method according to any item in the first aspect to obtain a duration estimation result.

[0025] In a third aspect, an embodiment of the present application provides a device for constructing an air conditioner operation duration estimation model, including:

[0026] An acquisition module, configured to acquire historical data of target parameters; the target parameters include the number of air conditioners in a target enclosed area, the space temperature, the air conditioner horsepower, the area of the target enclosed area, the set temperature of the air conditioner, and the air conditioner wind speed;

[0027] A training module, configured to train a duration estimation model based on the historical data of the target parameters to obtain a training error;

[0028] A processing module, configured to, if the training error meets a preset error requirement, adjust the coefficients of the duration estimation model according to an optimization function to obtain a duration estimation model with updated coefficients; if the training error does not meet the preset error requirement, repeat the step of training the duration estimation model based on the historical data of the target parameters to obtain a training error until the training error meets the preset error requirement.

[0029] In a fourth aspect, an embodiment of the present application provides a computer device, including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the computer program, the steps of the air conditioner operation duration estimation model construction method described in any item of the first aspect and / or the steps of the air conditioner operation duration estimation method described in the second aspect are implemented.

[0030] In a fifth aspect, an embodiment of the present application provides a computer-readable storage medium, on which a computer program is stored. When the computer program is run by a processor, the steps of the air conditioner operation duration estimation model construction method described in any item of the first aspect and / or the steps of the air conditioner operation duration estimation method described in the second aspect are executed.

[0031] The technical solution provided by the embodiment of the present application has the following beneficial effects:

[0032] In order to train the air conditioner operation duration estimation model in the present application, it is necessary to first obtain the historical data of target parameters. The target parameters include the number of air conditioners in the target enclosed area, the space temperature, the air conditioner horsepower, the area of the target enclosed area, the set temperature of the air conditioner, and the air conditioner wind speed. Then, based on the historical data of the target parameters, the duration estimation model is trained to obtain a training error. For the obtained training error, if the training error meets the preset error requirement, the coefficients of the duration estimation model are adjusted according to the optimization function to obtain the duration estimation model with updated coefficients. If the training error does not meet the preset error requirement, then again, based on any other set of data in the historical data of the target parameters, the duration estimation model is trained to obtain a training error until the training error meets the preset error requirement, at which point the training ends. Then, again according to the optimization function, the coefficients of the duration estimation model are adjusted to obtain the duration estimation model with updated coefficients. This method can use the historical data of multiple target parameters to train the duration estimation model, making the estimated error meet the preset error requirement, thereby enabling the model to accurately calculate the operation time of the air conditioner, with a high degree of automation, no need for manual supervision and management, and saving human resources.

[0033] To make the above objects, features, and advantages of the present application more obvious and understandable, the following specific preferred embodiments are given in conjunction with the accompanying drawings and described in detail as follows. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following will briefly introduce the drawings required for the embodiments. It should be understood that the following drawings only show some embodiments of the present application and should not be regarded as limiting the scope. For those of ordinary skill in the art, without creative efforts, other related drawings can be obtained based on these drawings.

[0035] Figure 1 It is a flowchart of a method for constructing an air conditioner operation duration estimation model provided by an embodiment of the present application;

[0036] Figure 2 It is a flowchart of a method for model training provided by an embodiment of the present application;

[0037] Figure 3 It is a structural diagram of an air conditioner operation duration estimation model construction device provided by an embodiment of the present application;

[0038] Figure 4 It is a structural diagram of a computer device provided by an embodiment of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0039] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions in the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of this application. Apparently, the described embodiments are only some, but not all, of the embodiments of this application. Components of the embodiments of this application usually described and illustrated in the accompanying drawings here can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of this application provided in the accompanying drawings is not intended to limit the scope of the claimed application, but merely represents selected embodiments of this application. All other embodiments obtained by those skilled in the art based on the embodiments of this application without creative efforts fall within the scope of protection of this application.

[0040] In the following description, reference is made to "some embodiments", which describe subsets of all possible embodiments. However, it can be understood that "some embodiments" can be the same subset or different subsets of all possible embodiments, and can be combined with each other without conflict.

[0041] In the prior art, when adjusting the temperature of a production workshop, the following problems may exist:

[0042] Currently, in a production workshop, air conditioners are used to control the temperature. Since the temperature is mostly different in different seasons, it is usually necessary to turn on the air conditioner in advance for a period of time and wait until the temperature reaches the temperature standard required for production before starting production. For example, in summer, in order to avoid the workshop temperature not meeting the standard, the air conditioner is generally turned on three hours in advance, resulting in serious energy consumption losses, and it is all managed manually at the same time, consuming human resources.

[0043] Based on the above defects, the embodiments of this application provide a method for constructing an air conditioner opening duration estimation model, as Figure 1 shown, including the following steps:

[0044] S101, obtaining historical data of target parameters; the target parameters include the number of air conditioners, space temperature, air conditioner horsepower, area of the target enclosed area, air conditioner set temperature, and air conditioner wind speed in the target enclosed area;

[0045] S102, training the duration estimation model based on the historical data of the target parameters to obtain a training error;

[0046] S103, if the training error meets the preset error requirement, adjusting the coefficients of the duration estimation model according to the optimization function to obtain a duration estimation model with updated coefficients; if the training error does not meet the preset error requirement, repeat the step of training the duration estimation model based on the historical data of the target parameters to obtain a training error until the training error meets the preset error requirement.

[0047] The above exemplary steps of the embodiments of the present application will be described separately below.

[0048] In step S101, historical data of target parameters is obtained; the target parameters include the number of air conditioners in the target enclosed area, space temperature, air conditioner horsepower, area of the target enclosed area, set temperature of the air conditioner, and air conditioner wind speed.

[0049] In some embodiments, in order to obtain a duration estimation model, parameters related to the change in space temperature need to be obtained, that is, data of relevant parameters that affect the estimation result of the duration estimation model. This method collects and processes data of six relevant parameters: the number of air conditioners in the target enclosed area, space temperature, air conditioner horsepower, area of the target enclosed area, set temperature of the air conditioner, and air conditioner wind speed.

[0050] In step S102, based on the historical data of the target parameters, the duration estimation model is trained to obtain a training error.

[0051] Specifically, in order to train the duration estimation model, the historical data of the target parameters needs to be imported into the duration estimation model, and the training error is obtained according to the ratio of the estimation result to the actual result until the training error meets the preset error requirement.

[0052] In step S103, if the training error meets the preset error requirement, according to the optimization function, the coefficients of the duration estimation model are adjusted to obtain a duration estimation model with updated coefficients; if the training error does not meet the preset error requirement, repeat the step of training the duration estimation model based on the historical data of the target parameters to obtain a training error until the training error meets the preset error requirement.

[0053] Specifically, when the training error does not meet the preset error requirement, the duration estimation model needs to be trained again, and another set of data in the historical data of the target parameters is used, that is, each time the historical data used for training is a new set of data. The duration estimation model is trained again according to a new set of historical data of the six parameters: the number of air conditioners in the target enclosed area, space temperature, air conditioner horsepower, area of the target enclosed area, set temperature of the air conditioner, and air conditioner wind speed, to obtain a training error until the training error meets the preset error requirement, and the training ends. Based on the training error, according to the optimization function, the coefficients of the duration estimation model are adjusted again to obtain a duration estimation model with updated coefficients.

[0054] By training the duration estimation model multiple times in the above manner, the estimation error of the duration estimation model meets the requirements, and the estimation accuracy of the duration estimation model is improved.

[0055] The above method for constructing an air conditioner opening duration estimation model To train the duration estimation model, it is necessary to first obtain historical data of target parameters. The target parameters include the number of air conditioners in the target enclosed area, the space temperature, the air conditioner horsepower, the area of the target enclosed area, the set temperature of the air conditioner, and the air conditioner wind speed. Then, based on the historical data of the target parameters, the duration estimation model is trained to obtain a training error. For the obtained training error, if the training error meets the preset error requirement, the coefficients of the duration estimation model are adjusted according to the optimization function to obtain a duration estimation model with updated coefficients. If the training error does not meet the preset error requirement, the duration estimation model is trained again according to any other set of data in the historical data of the target parameters to obtain a training error until the training error meets the preset error requirement, and the training ends. Then, the coefficients of the duration estimation model are adjusted again according to the optimization function to obtain a duration estimation model with updated coefficients. This method can train the duration estimation model using the historical data of multiple target parameters, making the estimated error meet the preset error requirement, so that the model can accurately calculate the opening time of the air conditioner, with high automation, no need for manual supervision and management, and saving human resources.

[0056] In some embodiments, when training the duration estimation model according to the historical data of the target parameters, in order to obtain the training error of the duration estimation model, specifically, as Figure 2 shown, step S102 includes the following steps:

[0057] S201, import any set of training data in the historical data of the target parameters into the duration estimation model to obtain a duration estimation value;

[0058] In the embodiments of the present application, the duration estimation model adopts a maximum likelihood estimation model, and its formula is expressed as follows:

[0059] (1)

[0060] Where, represents the feature vector, represents the weight vector, represents the linear regression intercept. This formula is equivalent to:

[0061] (2)

[0062] Where, represents each target parameter. Therefore, in the present application, the above formula is equivalent to:

[0063] (3)

[0064] Where, , , , , , respectively represent six parameters: the number of air conditioners, the space temperature, the air conditioner horsepower, the area of the target enclosed area, the set temperature of the air conditioner, and the air conditioner wind speed in the target enclosed area. , , , , , respectively represent the weight coefficients of the above six parameters. represents the vertical intercept in the linear regression, that is, the ordinate of the intersection point of the straight line and the Y-axis.

[0065] After determining the duration estimation model, any set of training data in the historical data of the target parameters is imported into the duration estimation model, specifically as follows:

[0066] Take any set of training data in the historical data of the target parameters, denoted as , , , , , and , where is the true value of the duration corresponding to this set of historical data. Substitute the historical data of the above six parameters into formula (3) to obtain:

[0067] (4)

[0068] where represents the duration estimation value calculated using the above parameters.

[0069] S202, import the duration estimation value and the obtained true value of the duration into the error function to obtain the training error;

[0070] In the embodiment of the present application, the error function adopts the L2 loss function, that is, the mean squared error function, which is expressed as follows:

[0071] (5)

[0072] where represents the duration estimation value, represents the true value of the duration, represents the training error of this training.

[0073] The step of importing the duration estimation value and the obtained true value of the duration into the error function to obtain the training error includes:

[0074] Import the duration estimation value and the obtained true duration value into the mean squared error function to obtain

[0075] (6)

[0076] where represents the duration estimation value of the current training, represents the true duration value corresponding to the historical data of this group, represents the training error of the current training; since a group of historical data is used in each training, so is equal to 1.

[0077] In some embodiments, if the training error meets the preset error requirement, according to the optimization function, adjust the coefficients of the duration estimation model to obtain the duration estimation model with updated coefficients, including:[[]]

[0078] Use the stochastic gradient descent method to process the training error and the coefficients of the duration estimation model to obtain the new coefficients of the duration estimation model;

[0079] Based on the new coefficients of the duration estimation model, obtain the duration estimation model with updated parameters.

[0080] Specifically, according to the training error obtained above, judge whether the training error meets the preset error requirement. If the training error meets the preset error requirement, then adjust the coefficients of the duration estimation model according to the optimization function. The optimization function in the embodiments of the present application can use the stochastic gradient descent method, and its formula is as follows:[[]]

[0081] (7)

[0082] (8)

[0083] where represents the gradient in this round of training, is the Hamiltonian operator, in this round of training, using the current coefficient calculated by formula (6), the obtained loss value, that is, the training error, is the coefficient value in the maximum likelihood estimation model in the next round of training, is the coefficient values in this round of training, is the learning rate, which is set before training according to requirements.

[0084] By optimizing the use of functions, in the training process of the duration estimation model, this method gives a new proposed value for the coefficients of the maximum likelihood estimation model by comparing the errors obtained from the error function, so that the maximum likelihood estimation model can better fit the data.

[0085] In some embodiments, before the step of training the duration estimation model based on the historical data of the target parameter to obtain the training error, the method further includes:

[0086] Initializing each coefficient in the duration estimation model with random numbers.

[0087] Specifically, in the embodiments of the present application, random numbers are used to initialize the weights and intercepts. If these values deviate greatly from the ideal values, they will be quickly optimized to be close to the ideal values in the previous iterative training. Therefore, using random numbers to initialize the weights and intercepts will not have too much impact on the training speed.

[0088] In some embodiments, the method further includes:

[0089] If the training error meets the preset error requirement and the number of training times reaches the preset number requirement, then according to the optimization function, adjust the coefficients of the duration estimation model to obtain a duration estimation model with updated coefficients.

[0090] Specifically, in order to ensure the estimation accuracy of the duration estimation model, on the basis that the training error meets the preset error requirement, this embodiment also makes a requirement on the number of training times. For example, the training ends after 100,000 iterations, that is, it is necessary to end the training after the training error meets the preset error requirement and at the same time the number of training times also reaches the preset number requirement. Then, according to the optimization function, adjust the coefficients of the duration estimation model to obtain a duration estimation model with updated coefficients.

[0091] In summary, the embodiments of the present application have the following beneficial effects:

[0092] In order to train the duration estimation model, the method of this application needs to first obtain the historical data of the target parameters. The target parameters include the number of air conditioners, the space temperature, the air conditioner horsepower, the area of the target enclosed area, the set temperature of the air conditioner, and the air conditioner wind speed in the target enclosed area. Then, based on the historical data of the target parameters, the duration estimation model is trained to obtain a training error. For the obtained training error, if the training error meets the preset error requirement, the coefficients of the duration estimation model are adjusted according to the optimization function to obtain a duration estimation model with updated coefficients. If the training error does not meet the preset error requirement, the duration estimation model is trained again according to any other set of data in the historical data of the target parameters to obtain a training error until the training error meets the preset error requirement, and the training ends. Then, the coefficients of the duration estimation model are adjusted again according to the optimization function to obtain a duration estimation model with updated coefficients. This method can train the duration estimation model using the historical data of multiple target parameters, making the estimated error meet the preset error requirement, so that the model can accurately calculate the opening time of the air conditioner, with a high degree of automation, no need for manual supervision and management, and saving human resources.

[0093] Corresponding to Figure 1 the method for constructing the air conditioner opening duration estimation model in

[0094] Input the current data of the obtained target parameters into the duration estimation model obtained by the above-mentioned method for constructing the duration estimation model to obtain a duration estimation result.

[0095] Specifically, since in formula (3) represents the time required for the temperature to change by one degree, the duration estimation result obtained by inputting the current data of the target parameters into the duration estimation model is the estimated duration required for the temperature to change by one degree. Then, for the temperature that needs to be adjusted, the total duration that the air conditioner needs to be turned on in advance is calculated, and the air conditioner is turned on in advance according to this total duration.

[0096] For example, in some embodiments, when it is found that there is a production plan on the same day, the target parameters of the workshop are obtained in real time, and the opening time of the air conditioner is calculated according to the duration estimation model. Taking the opening time of the air conditioner from October 5th to October 9th as an example, combined with other actual data, it is summarized in the following table:

[0097]

[0098] As can be seen from the above table, the error time for the temperature to reach the standard is within ±5. Previously, the air conditioner was turned on at 3:40. Now, the air conditioner is turned on much later, shortening the working time of the air conditioner and saving energy and human resource costs.

[0099] Based on the same inventive concept, an apparatus for constructing an air conditioner startup duration estimation model corresponding to the method for constructing an air conditioner startup duration estimation model in the first embodiment is further provided in the embodiments of the present application. Since the principle of solving problems by the apparatus in the embodiments of the present application is similar to that of the above-mentioned method for constructing an air conditioner startup duration estimation model, the implementation of the apparatus can refer to the implementation of the method, and the repeated parts will not be elaborated.

[0100] As Figure 3 shown, Figure 3 is a schematic structural diagram of the apparatus for constructing an air conditioner startup duration estimation model provided by the present application. The apparatus for constructing an air conditioner startup duration estimation model includes:

[0101] An acquisition module 301, configured to acquire historical data of target parameters; the target parameters include the number of air conditioners, space temperature, air conditioner horsepower, area of the target enclosed area, air conditioner set temperature, and air conditioner wind speed in the target enclosed area;

[0102] A training module 302, configured to train a duration estimation model based on the historical data of the target parameters to obtain a training error;

[0103] A processing module 303, configured to, if the training error meets a preset error requirement, adjust the coefficients of the duration estimation model according to an optimization function to obtain a duration estimation model with updated coefficients; if the training error does not meet the preset error requirement, repeat the step of training the duration estimation model based on the historical data of the target parameters to obtain a training error until the training error meets the preset error requirement.

[0104] Those skilled in the art should understand that Figure 3 the implementation functions of the modules in the apparatus for constructing an air conditioner startup duration estimation model shown can be understood with reference to the relevant descriptions of the above-mentioned method for constructing an air conditioner startup duration estimation model. Figure 3 The functions of the units in the apparatus for constructing an air conditioner startup duration estimation model shown can be implemented by a program running on a processor or by specific logic circuits.

[0105] In a possible implementation manner, the training module 302 includes:

[0106] An input unit, configured to import any set of training data in the historical data of the target parameters into the duration estimation model to obtain a duration estimation value;

[0107] A calculation unit, configured to import the duration estimation value and the obtained true duration value into an error function to obtain a training error.

[0108] In a possible implementation manner, the training module 302 further includes:

[0109] Import the duration estimation value and the obtained true duration value into the mean squared error function to obtain

[0110]

[0111] wherein, represents the duration estimation value, represents the true duration value, represents the training error of this training.

[0112] In a possible implementation manner, the processing module 303 includes:

[0113] a processing unit, configured to process the training error and the coefficients of the duration estimation model by using the stochastic gradient descent method to obtain new coefficients of the duration estimation model;

[0114] a determination unit, configured to obtain the duration estimation model with updated coefficients based on the new coefficients of the duration estimation model.

[0115] In a possible implementation manner, before the training module 302 uses the historical data based on the target parameter to train the duration estimation model to obtain a training error, the apparatus further includes:

[0116] an initialization module, configured to initialize each coefficient in the duration estimation model by using random numbers.

[0117] In a possible implementation manner, the processing module 303 is further configured to:

[0118] If the training error meets the preset error requirement and the number of training times reaches the preset number requirement, adjust the coefficients of the duration estimation model according to the optimization function to obtain the duration estimation model with updated coefficients.

[0119] The above-mentioned air conditioner startup duration estimation model construction device needs to first obtain historical data of target parameters according to the acquisition module 301 for training the duration estimation model. The target parameters include the number of air conditioners in the target enclosed area, the space temperature, the air conditioner horsepower, the area of the target enclosed area, the set temperature of the air conditioner, and the air conditioner wind speed. Then, based on the historical data of the target parameters, the training module 302 trains the duration estimation model to obtain a training error. For the obtained training error, if the training error meets the preset error requirement, the processing module 303 performs processing, that is, according to the optimization function, adjusts the coefficients of the duration estimation model to obtain a duration estimation model with updated coefficients. If the training error does not meet the preset error requirement, the duration estimation model is trained again according to any other set of data in the historical data of the target parameters to obtain a training error until the training error meets the preset error requirement, and the training ends. Then, according to the optimization function again, the coefficients of the duration estimation model are adjusted to obtain a duration estimation model with updated coefficients. The usage method of this device can train the duration estimation model using historical data of multiple target parameters, making the estimated error meet the preset error requirement, so that the model can accurately calculate the startup time of the air conditioner, with a high degree of automation, no need for manual supervision and management, and saving human resources.

[0120] Corresponding to Figure 1 the air conditioner startup duration estimation model construction method in Figure 4 shown, this device includes a memory 401, a processor 402, and a computer program stored on the memory 401 and executable on the processor 402. Among them, when the above-mentioned processor 402 executes the above-mentioned computer program, it implements the above-mentioned air conditioner startup duration estimation model construction method.

[0121] Specifically, the above-mentioned memory 401 and processor 402 can be general memories and processors, which are not specifically limited here. When the processor 402 runs the computer program stored in the memory 401, it can execute the above-mentioned air conditioner startup duration estimation model construction method, solving the problems in the prior art that the air conditioner energy consumption loss is serious and it is all managed by humans at a unified time, consuming human resources.

[0122] Corresponding to Figure 1 the air conditioner startup duration estimation model construction method in

[0123] Specifically, the storage medium can be a general storage medium, such as a removable disk, a hard disk, etc. When the computer program on the storage medium runs, it can execute the above-mentioned method for constructing the air conditioner opening duration estimation model, solving the problems of serious air conditioner energy consumption loss and manual unified time management consuming human resources in the prior art.

[0124] For the above computer-readable storage medium, in order to train the duration estimation model, it is necessary to first obtain historical data of target parameters. The target parameters include the number of air conditioners in the target enclosed area, the space temperature, the air conditioner horsepower, the area of the target enclosed area, the set temperature of the air conditioner, and the air conditioner wind speed. Then, based on the historical data of the target parameters, the duration estimation model is trained to obtain a training error. For the obtained training error, if the training error meets the preset error requirement, the coefficients of the duration estimation model are adjusted according to the optimization function to obtain a duration estimation model with updated coefficients. If the training error does not meet the preset error requirement, the duration estimation model is trained again according to any other set of data in the historical data of the target parameters to obtain a training error until the training error meets the preset error requirement, and the training ends. Then, the coefficients of the duration estimation model are adjusted again according to the optimization function to obtain a duration estimation model with updated coefficients. The usage method provided by this storage medium can train the duration estimation model using the historical data of multiple target parameters, making the estimated error meet the preset error requirement, so that the model can accurately calculate the opening time of the air conditioner, with a high degree of automation, no need for manual supervision and management, and saving human resources.

[0125] In the embodiments provided in the present application, it should be understood that the disclosed methods and devices can be implemented in other ways. The device embodiments described above are only illustrative. For example, the division of the units is only a logical function division, and there may be other division methods in actual implementation. For another example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed mutual coupling or direct coupling or communication connection can be through some communication interfaces, and the indirect coupling or communication connection of the device or unit can be in an electrical, mechanical or other form.

[0126] The units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they can be located in one place or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0127] In addition, each functional unit in the embodiments provided in the present application may be integrated into a processing unit, may exist physically alone for each unit, or two or more units may be integrated into one unit.

[0128] If the above-mentioned function is implemented in the form of a software functional unit and sold or used as an independent product, it may be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art, or a part of this technical solution, may be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present application. The aforementioned storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memories (ROM, Read-Only Memory), random access memories (RAM, Random Access Memory), magnetic disks, or optical discs that can store program codes.

[0129] It should be noted that similar reference numerals and letters represent similar items in the following drawings. Therefore, once an item is defined in one drawing, it does not need to be further defined and explained in subsequent drawings. In addition, the terms "first", "second", "third", etc. are only used for distinguishing descriptions and cannot be understood as indicating or implying relative importance.

[0130] It should be noted that the term "including" used in the embodiments of the present application is used to indicate the existence of the features stated thereafter, but does not exclude adding other features.

[0131] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the technical field to which this application belongs. The terms used herein are for the purpose of describing the embodiments of the present application and do not limit the present application.

[0132] Finally, it should be noted that the above-described embodiments are only specific implementation manners of the present application, used to illustrate the technical solutions of the present application, rather than limiting it. The protection scope of the present application is not limited thereto. Although the present application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that any person skilled in the art within the technical scope disclosed by the present application can still modify the technical solutions described in the foregoing embodiments, or can easily think of changes, or perform equivalent replacements on some of the technical features; and these modifications, changes or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application. All should be covered within the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A method for constructing an air conditioner on-time estimation model, characterized in that: The following steps are involved: Obtain historical data of target parameters; the target parameters include the number of air conditioners in the target enclosed area, space temperature, air conditioner horsepower, target enclosed area area, air conditioner set temperature and air conditioner wind speed; Based on the historical data of the target parameter, a duration estimation model is trained to obtain a training error; If the training error meets the preset error requirement, adjusting the coefficients of the duration estimation model according to the optimization function to obtain a duration estimation model with updated coefficients; If the training error does not meet the preset error requirement, repeat the step of training the duration estimation model based on the historical data of the target parameter to obtain the training error until the training error meets the preset error requirement.

2. The method for constructing an air conditioner on-time estimation model according to claim 1, characterized in that: The training of the duration estimation model based on the historical data of the target parameter to obtain the training error includes: Importing any set of training data from the historical data of the target parameter into the duration estimation model to obtain a duration estimation value; The estimated duration value and the acquired actual duration value are introduced into the error function to obtain the training error.

3. The method for constructing an air conditioner on-time estimation model according to claim 2, characterized in that: The step of importing the estimated duration value and the acquired actual duration value into an error function to obtain a training error includes: The estimated duration value and the acquired actual duration value are introduced into the square error function to obtain: , in, Represents the estimated duration. Indicates the actual value of duration, Represents the training error of this training.

4. The method for constructing an air conditioner on-time estimation model according to claim 1, characterized in that: If the training error meets the preset error requirement, adjusting the coefficient of the duration estimation model according to the optimization function to obtain the duration estimation model with updated coefficients, including: The training error and the coefficients of the duration estimation model are processed by using a stochastic gradient descent method to obtain new coefficients of the duration estimation model; Based on the new coefficients of the duration estimation model, the duration estimation model with updated coefficients is obtained.

5. The method for constructing an air conditioner on-time estimation model according to claim 1, characterized in that: Before the step of training the duration estimation model based on the historical data of the target parameter to obtain a training error, the method further includes: The coefficients in the duration estimation model are initialized respectively using random numbers.

6. The method for constructing an air conditioner on-time estimation model according to claim 1, characterized in that: The method further comprises: If the training error meets the preset error requirement and the number of training times reaches the preset number requirement, the coefficients of the duration estimation model are adjusted according to the optimization function to obtain the duration estimation model with updated coefficients.

7. A method for estimating the duration of air conditioning on, characterized in that: include: The acquired current data of the target parameter is input into the duration estimation model obtained by the air conditioner on-time estimation model construction method according to any one of claims 1 to 6 to obtain a duration estimation result.

8. A device for constructing an air conditioner on-time estimation model, characterized in that: include: An acquisition module, used to acquire historical data of target parameters; the target parameters include the number of air conditioners in the target enclosed area, space temperature, air conditioner horsepower, target enclosed area area, air conditioner set temperature and air conditioner wind speed; A training module, used for training the duration estimation model based on the historical data of the target parameter to obtain a training error; A processing module, configured to adjust the coefficients of the duration estimation model according to an optimization function if the training error meets a preset error requirement, so as to obtain a duration estimation model with updated coefficients; If the training error does not meet the preset error requirement, repeat the step of training the duration estimation model based on the historical data of the target parameter to obtain the training error until the training error meets the preset error requirement.

9. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the method for building an air-conditioning on-time estimation model described in any one of claims 1 to 6 and / or the steps of the method for estimating the air-conditioning on-time described in claim 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method for constructing an air conditioner on-time estimation model described in any one of claims 1 to 6 and / or the steps of the method for estimating the air conditioner on-time described in claim 7 are executed.

Images