Iteration method and device for mechanism model and storage medium

Abstract

The invention relates to the technical field of model iteration, and discloses an iteration method for a mechanism model. The method comprises the steps of obtaining an initial mechanism model; training the initial mechanism model to obtain a mechanism pre-model; determining a target loss function according to the service life of the air conditioning system; and performing model iteration according to the mechanism pre-model, update task information input by the user and the target loss function to obtain a mechanism new model after iteration. According to the method, the target loss function can be more accurately determined in combination with the service life of the air conditioning system, and the model training precision is improved and the calculation resource occupation is reduced through an incremental training mode. The invention further discloses an iteration device for the mechanism model and a storage medium.

Description

Technical Field

[0001] The present application relates to the field of model iteration technology, for example, to an iteration method, device and storage medium for a mechanism model. Background Art

[0002] At present, with the popularization of big data and artificial intelligence, more and more companies are using global optimization algorithms based on big data to empower air conditioning system group control. This type of optimization algorithm needs to combine the mechanism to model some key monitored parameters. After generating this type of mechanism model, it needs to be updated in a specific way to keep the optimization algorithm effect optimal.

[0003] At present, it is usually necessary to set up scheduled tasks, update cycles, and error standards. When a task is triggered, a predetermined mechanism framework model is used, and the model is retrained with the full amount of data. When the error reaches the set error standard, the updated model is output. Although this training method ensures the real-time performance of the model, it ignores the problem that the server's computing resources are extremely large when training with the full amount of data. In addition, under this model training method, the older data in the full amount of data may have side effects on the establishment of an accurate mechanism model. Therefore, how to iterate the mechanism model more accurately has become a technical problem that needs to be solved urgently.

[0004] It should be noted that the information disclosed in the above background technology section is only used to enhance the understanding of the background of the present application, and therefore may include information that does not constitute the prior art known to ordinary technicians in the field. Summary of the invention

[0005] In order to provide a basic understanding of some aspects of the disclosed embodiments, a brief summary is given below. The summary is not an extensive review, nor is it intended to identify key / critical components or delineate the scope of protection of these embodiments, but rather serves as a prelude to the detailed description that follows.

[0006] The embodiments of the present disclosure provide an iterative method, device and storage medium for a mechanism model, which can iterate the mechanism model more accurately.

[0007] In some embodiments, the iterative method for the mechanism model includes: obtaining an initial mechanism model; training the initial mechanism model to obtain a mechanism pre-model; determining a target loss function based on the service life of the air-conditioning system; and iterating the model based on the mechanism pre-model, the update task information input by the user, and the target loss function to obtain an iterated new mechanism model.

[0008] In some embodiments, the iterative method for the mechanism model includes: determining the weight ratio of the incremental data and the weight ratio of the original model according to the service life of the air-conditioning system; determining the target loss function according to the weight ratio of the incremental data and the weight ratio of the original model.

[0009] In some embodiments, the iterative method for the mechanism model includes: when the service life of the air-conditioning system is not higher than a first threshold, determining the weight ratio of the incremental data to be a first ratio; when the service life of the air-conditioning system is higher than the first threshold and not higher than the second threshold, determining the weight ratio of the incremental data to be a second ratio; when the service life of the air-conditioning system is higher than the second threshold and not higher than the third threshold, determining the weight ratio of the incremental data to be a third ratio; when the service life of the air-conditioning system is higher than the third threshold, determining the weight ratio of the incremental data to be a fourth ratio; wherein, the first ratio < the second ratio < the third ratio < the fourth ratio.

[0010] In some embodiments, the iterative method for the mechanism model includes: when the service life of the air-conditioning system is not higher than a first threshold, determining the weight ratio of the original model to be the fifth ratio; when the service life of the air-conditioning system is higher than the first threshold and not higher than the second threshold, determining the weight ratio of the original model to be the sixth ratio; when the service life of the air-conditioning system is higher than the second threshold and not higher than the third threshold, determining the weight ratio of the original model to be the seventh ratio; when the service life of the air-conditioning system is higher than the third threshold, determining the weight ratio of the original model to be the eighth ratio; wherein, the eighth ratio < the seventh ratio < the sixth ratio < the fifth ratio.

[0011] In some embodiments, the iterative method for the mechanism model includes: obtaining the full amount of sample data required for model training; training the initial mechanism model based on the full amount of sample data to obtain a mechanism pre-model.

[0012] In some embodiments, the iterative method for the mechanism model includes: determining the target device type to which the initial mechanism model belongs; obtaining a historical database, which stores sample data corresponding to different device types; extracting sample data corresponding to the target device type from the historical database, and determining it as the full amount of sample data required for model training.

[0013] In some embodiments, the iterative method for the mechanism model includes: determining the convergence criterion of the model; inputting the full amount of sample data into the initial mechanism model for model training until a mechanism pre-model that meets the convergence criterion is obtained.

[0014] In some embodiments, the iterative device for the mechanism model includes: an acquisition module configured to acquire an initial mechanism model; a training module configured to train the initial mechanism model to obtain a mechanism pre-model; a determination module configured to determine a target loss function based on the service life of the air-conditioning system; and an iteration module configured to perform model iteration based on the mechanism pre-model, update task information input by the user, and the target loss function to obtain an iterated new mechanism model.

[0015] In some embodiments, the iteration device for the mechanism model includes: a processor and a memory storing program instructions, wherein the processor executes the above-mentioned iteration method for the mechanism model when running the program instructions.

[0016] In some embodiments, the storage medium stores program instructions, and when the program instructions are run, they execute the above-mentioned iterative method for the mechanism model.

[0017] The iterative method, device and storage medium for the mechanism model provided by the embodiments of the present disclosure can achieve the following technical effects: by obtaining an initial mechanism model; and training the initial mechanism model to obtain a mechanism pre-model; thereby determining the target loss function according to the service life of the air-conditioning system; and then iterating the model according to the mechanism pre-model, the update task information input by the user and the target loss function to obtain an iterated new mechanism model. In this way, the target loss function can be determined more accurately in combination with the service life of the air-conditioning system, and through incremental training, the accuracy of model training can be improved while reducing computing resource usage.

[0018] The above general description and the following description are exemplary and explanatory only and are not intended to limit the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] One or more embodiments are exemplarily described by corresponding drawings, which do not limit the embodiments. Elements with the same reference numerals in the drawings are shown as similar elements, and the drawings do not constitute a scale limitation, and wherein:

[0020] Figure 1 is a schematic diagram of an iterative method for a mechanism model provided by an embodiment of the present disclosure;

[0021] Figure 2 is a schematic diagram of a method for determining a target loss function provided by an embodiment of the present disclosure;

[0022] Figure 3 is a schematic diagram of a method for obtaining a mechanism pre-model provided by an embodiment of the present disclosure;

[0023] Figure 4is a schematic diagram of a method for obtaining full sample data provided by an embodiment of the present disclosure;

[0024] Figure 5 is a schematic diagram of a method for obtaining a mechanism pre-model provided by an embodiment of the present disclosure;

[0025] Figure 6 is a schematic diagram of an iterative device for a mechanism model provided by an embodiment of the present disclosure;

[0026] Figure 7 It is a schematic diagram of another iterative device for a mechanism model provided by an embodiment of the present disclosure. DETAILED DESCRIPTION

[0027] In order to be able to understand the features and technical contents of the embodiments of the present disclosure in more detail, the implementation of the embodiments of the present disclosure is described in detail below in conjunction with the accompanying drawings. The attached drawings are for reference only and are not used to limit the embodiments of the present disclosure. In the following technical description, for the convenience of explanation, a full understanding of the disclosed embodiments is provided through multiple details. However, one or more embodiments can still be implemented without these details. In other cases, to simplify the drawings, well-known structures and devices can be simplified for display.

[0028] The terms "first", "second", etc. in the specification and claims of the embodiments of the present disclosure and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the terms used in this way can be interchanged where appropriate, so that the embodiments of the embodiments of the present disclosure described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions.

[0029] Unless otherwise stated, the term "plurality" means two or more.

[0030] In the embodiment of the present disclosure, the character " / " indicates that the preceding and following objects are in an "or" relationship. For example, A / B indicates: A or B.

[0031] The term "and / or" is a description of the association relationship between objects, indicating that three relationships can exist. For example, A and / or B means: A or B, or, A and B.

[0032] The term "correspondence" may refer to an association relationship or a binding relationship. The correspondence between A and B means that there is an association relationship or a binding relationship between A and B.

[0033] In the embodiments of the present disclosure, smart home appliances refer to home appliances that are formed by introducing microprocessors, sensor technology, and network communication technology into home appliances. They have the characteristics of intelligent control, intelligent perception, and intelligent application. The operation process of smart home appliances often relies on the application and processing of modern technologies such as the Internet of Things, the Internet, and electronic chips. For example, smart home appliances can be connected to electronic devices to enable users to remotely control and manage the smart home appliances.

[0034] In the embodiments of the present disclosure, the terminal device refers to an electronic device with a wireless connection function. The terminal device can communicate with the above-mentioned smart home appliances by connecting to the Internet, or can directly communicate with the above-mentioned smart home appliances through Bluetooth, WiFi, etc. In some embodiments, the terminal device is, for example, a mobile device, a computer, or a vehicle-mounted device built into a hover car, or any combination thereof. Mobile devices may include, for example, mobile phones, smart home devices, wearable devices, smart mobile devices, virtual reality devices, etc., or any combination thereof, wherein wearable devices include, for example: smart watches, smart bracelets, pedometers, etc.

[0035] Figure 1 is a schematic diagram of an iterative method for a mechanism model provided by an embodiment of the present disclosure; Figure 1 As shown, optionally, the embodiment of the present disclosure provides an iterative method for a mechanism model, comprising:

[0036] S11, the server obtains the initial mechanism model.

[0037] S12, the server trains the initial mechanism model to obtain a mechanism pre-model.

[0038] S13, the server determines the target loss function according to the service life of the air conditioning system.

[0039] S14, the server performs model iteration based on the mechanism pre-model, the updated task information input by the user and the target loss function to obtain a new mechanism model after iteration.

[0040] In this solution, the server can obtain the initial mechanism model to be trained. Here, the initial mechanism model refers to the mechanism framework model to be trained. Generally, the initial mechanism model can be obtained in combination with the model training requirements. Among them, the model training requirements can be model type, error convergence conditions, etc. In this way, the initial mechanism model can be accurately obtained.

[0041] Furthermore, after obtaining the initial mechanism model, the server can train the initial mechanism model. Specifically, the server trains the initial mechanism model to obtain a mechanism pre-model, including: the server obtains the full amount of sample data required for model training; the initial mechanism model is trained according to the full amount of sample data to obtain a mechanism pre-model. As an example, the training of the initial mechanism model can refer to some industry manuals, mechanism derivation formulas, simulation software principles, and combine with machine learning or deep learning models. In this way, during the first model training process, the model can be trained with the full amount of data to ensure that a more accurate mechanism pre-model is obtained.

[0042] Furthermore, the server can determine the target loss function in combination with the service life of the air-conditioning system. Here, the service life of the air-conditioning system can be determined in combination with the actual use of the air-conditioning. Specifically, the server determines the target loss function according to the service life of the air-conditioning system, including: the server determines the weight ratio of the incremental data and the weight ratio of the original model according to the service life of the air-conditioning system. The server determines the target loss function according to the weight ratio of the incremental data and the weight ratio of the original model. In this way, the weight ratio of each type of data in the mechanism model training process can be determined in combination with the service life of the air-conditioning system, so as to accurately determine the target loss function required for the mechanism model training according to the determined weight ratio of each type of data.

[0043] In this solution, the update task information input by the user includes incremental data for mechanism model iteration, update cycle, update task trigger time, mechanism model error standard, etc. The mechanism model error standard can be R2, MSE, RMSE, MAPE, etc. In this way, the server can perform model iteration according to the mechanism pre-model, the update task information input by the user, and the target loss function. Specifically, after the server performs model training according to the mechanism pre-model, the update task information input by the user, and the target loss function, the trained new mechanism model can be obtained; the server uses the trained new mechanism model as the mechanism pre-model to participate in model iteration. That is, after the server obtains the update task information input by the user again and determines the new target loss function, the model can be iterated according to the trained new mechanism model, the update task information input by the user again, and the new target loss function to obtain the iterated new mechanism model.

[0044] The iterative method of the mechanism model provided by the embodiment of the present disclosure is adopted, by obtaining the initial mechanism model; and training the initial mechanism model to obtain the mechanism pre-model; thereby determining the target loss function according to the service life of the air-conditioning system; and then iterating the model according to the mechanism pre-model, the update task information input by the user and the target loss function to obtain the iterated new mechanism model. In this way, the target loss function can be determined more accurately in combination with the service life of the air-conditioning system, and the model training accuracy can be improved while reducing the computing resource usage through incremental training.

[0045] Figure 2 is a schematic diagram of a method for determining a target loss function provided by an embodiment of the present disclosure; Figure 2 As shown, optionally, in S13, the server determines a target loss function according to the service life of the air conditioning system, including:

[0046] S21, the server determines the weight ratio of the incremental data and the weight ratio of the original model according to the service life of the air-conditioning system.

[0047] S22, the server determines the target loss function according to the weight ratio of the incremental data and the weight ratio of the original model.

[0048] In this solution, the server can determine the weight ratio of each type of data in the mechanism model training process in combination with the service life of the air-conditioning system. Understandably, for air-conditioning systems that have been in use for a long time, the influence ratio of the incremental data items can be larger, and for air-conditioning systems that have just been put into use, the influence ratio of the original model can be increased. In this way, the weight ratio of the incremental data and the weight ratio of the original model can be accurately determined in combination with the service life of the air-conditioning system, and the attenuation problem can be considered more reasonably.

[0049] Furthermore, after determining the weight proportion of the incremental data and the weight proportion of the original model, the server can determine the target loss function according to the weight proportion of the incremental data and the weight proportion of the original model. Specifically, take the basic error as MSPE as an example.

[0050]

[0051] In this way, the server determines the target loss function based on the weight ratio of the incremental data and the weight ratio of the original model, including:

[0052]

[0053] Among them, y i =f pre (X i ) is the original model, y i =f new (Xi ) is the new model, is the weight ratio of the incremental data, and ω is the weight ratio of the original model. In this way, the original loss function can be introduced into the incremental term to provide a more optimized and more accurate target loss function.

[0054] Optionally, at S21, the server determines a weight ratio of the incremental data according to the service life of the air conditioning system, including:

[0055] When the service life of the air-conditioning system is not higher than the first threshold, the server determines the weight ratio of the incremental data to be the first ratio.

[0056] When the service life of the air-conditioning system is higher than the first threshold and not higher than the second threshold, the server determines the weight ratio of the incremental data to be the second ratio.

[0057] When the service life of the air-conditioning system is higher than the second threshold and not higher than the third threshold, the server determines the weight ratio of the incremental data to be the third ratio.

[0058] When the service life of the air-conditioning system is higher than the third threshold, the server determines the weight ratio of the incremental data to be the fourth ratio.

[0059] In this solution, the first threshold is 1 year, the second threshold is 3 years, and the third threshold is 5 years, and the first proportion is less than the second proportion and less than the third proportion and less than the fourth proportion. It can be understood that the longer the air-conditioning system is used, the higher the weight proportion of the incremental data is. As an example, the first proportion is 0.3, the second proportion is 0.55, the third proportion is 0.65, and the fourth proportion is 0.85. In this way, when the service life of the air-conditioning system is not more than 1 year, the server determines that the weight proportion of the incremental data is 0.3; when the service life of the air-conditioning system is more than 1 year and not more than 3 years, the server determines that the weight proportion of the incremental data is 0.55; when the service life of the air-conditioning system is more than 3 years and not more than 5 years, the server determines that the weight proportion of the incremental data is 0.65; when the service life of the air-conditioning system is more than 5 years, the server determines that the weight proportion of the incremental data is 0.85. In this way, the weight proportion of the incremental data can be accurately determined in combination with the service life of the air-conditioning system.

[0060] Optionally, at S21, the server determines a weight ratio of the original model according to the service life of the air conditioning system, including:

[0061] When the service life of the air-conditioning system is not higher than the first threshold, the server determines that the weight ratio of the original model is the fifth ratio.

[0062] When the service life of the air-conditioning system is higher than the first threshold value and not higher than the second threshold value, the server determines that the weight ratio of the original model is the sixth ratio.

[0063] When the service life of the air-conditioning system is higher than the second threshold value and lower than the third threshold value, the server determines that the weight ratio of the original model is the seventh ratio.

[0064] When the service life of the air-conditioning system is higher than the third threshold, the server determines that the weight ratio of the original model is the eighth ratio.

[0065] In this solution, the eighth proportion < the seventh proportion < the sixth proportion < the fifth proportion. It can be understood that the longer the air-conditioning system is used, the lower the weight proportion of the original model. As an example, the fifth proportion is 0.7, the sixth proportion is 0.45, the seventh proportion is 0.35, and the eighth proportion is 0.15. When the service life of the air-conditioning system is not more than 1 year, the server determines that the weight proportion of the original model is 0.7; when the service life of the air-conditioning system is more than 1 year and not more than 3 years, the server determines that the weight proportion of the original model is 0.45; when the service life of the air-conditioning system is more than 3 years and not more than 5 years, the server determines that the weight proportion of the original model is 0.35; when the service life of the air-conditioning system is more than 5 years, the server determines that the weight proportion of the original model is 0.15. In this way, the weight proportion of the original model can be accurately determined in combination with the service life of the air-conditioning system.

[0066] Figure 3 is a schematic diagram of a method for obtaining a mechanism pre-model provided by an embodiment of the present disclosure; Figure 3 As shown, optionally, in S12, the server trains the initial mechanism model to obtain a mechanism pre-model, including:

[0067] S31: The server obtains the full amount of sample data required for model training.

[0068] S32, the server trains the initial mechanism model based on the full sample data to obtain a mechanism pre-model.

[0069] In this solution, the server can obtain the full amount of sample data required for model training. Specifically, the server obtains the full amount of sample data required for model training, including: the server determines the target device type to which the initial mechanism model belongs. The server obtains a historical database, which stores sample data corresponding to different device types. The server extracts the sample data corresponding to the target device type from the historical database and determines it as the full amount of sample data required for model training. In this way, accurate acquisition of the full amount of sample data can be achieved.

[0070] Furthermore, after the server has obtained the full sample data, it can train the initial mechanism model based on the full sample data to obtain the mechanism pre-model. In this way, during the first model training process, the model can be trained with the full data to ensure that a more accurate mechanism pre-model is obtained.

[0071] Figure 4 is a schematic diagram of a method for obtaining full sample data provided by an embodiment of the present disclosure; Figure 4 As shown, optionally, in S31, the server obtains the full amount of sample data required for model training, including:

[0072] S41, the server determines the target device type to which the initial mechanism model belongs.

[0073] S42, the server obtains a historical database, which stores sample data corresponding to different device types.

[0074] S43, the server extracts sample data corresponding to the target device type from the historical database, and determines it as the full amount of sample data required for model training.

[0075] In this solution, the server can determine the target device type to which the initial mechanism model belongs. Here, the target device type includes information such as device brand, device model, and key parameters of the device. Furthermore, the server can obtain a historical database, which stores sample data corresponding to different device types. It should be noted that the sample data stored in the historical database are factory test data of different devices in historical projects. Furthermore, the server can extract sample data corresponding to the target device type from the historical database and determine it as the full sample data required for model training. With this solution, accurate acquisition of full sample data can be achieved.

[0076] Figure 5 is a schematic diagram of a method for obtaining a mechanism pre-model provided by an embodiment of the present disclosure; Figure 5 As shown, optionally, in S32, the server trains the initial mechanism model according to the full sample data to obtain a mechanism pre-model, including:

[0077] S51, the server determines the convergence standard of the model.

[0078] S52, the server inputs the full amount of sample data into the initial mechanism model for model training until a mechanism pre-model that meets the convergence standard is obtained.

[0079] In this solution, the server obtains the convergence criteria of the model. Here, the convergence criteria of the model is determined in combination with the training requirements of the model. Furthermore, the server inputs the full amount of sample data into the initial mechanism model for standardized training until a mechanism pre-model that meets the convergence criteria is obtained. With this solution, a mechanism pre-model that meets the convergence criteria can be accurately obtained.

[0080] Figure 6 is a schematic diagram of an iterative device for a mechanism model provided by an embodiment of the present disclosure; Figure 6 As shown, an embodiment of the present disclosure provides an iterative device for a mechanism model, including an acquisition module 61, a training module 62, a determination module 63 and an iteration module 64; the acquisition module 61 is configured to acquire an initial mechanism model; the training module 62 is configured to train the initial mechanism model to obtain a mechanism pre-model; the determination module 63 is configured to determine a target loss function according to the service life of the air-conditioning system; the iteration module 64 is configured to perform model iteration according to the mechanism pre-model, the update task information input by the user and the target loss function to obtain an iterated new mechanism model.

[0081] By adopting the iteration device for the mechanism model provided by the embodiment of the present disclosure, the initial mechanism model is obtained; and the initial mechanism model is trained to obtain the mechanism pre-model; thereby determining the target loss function according to the service life of the air-conditioning system; and then performing model iteration according to the mechanism pre-model, the update task information input by the user and the target loss function, to obtain the iterated new mechanism model. In this way, the target loss function can be determined more accurately in combination with the service life of the air-conditioning system, and the model training accuracy can be improved while reducing the computing resource usage through incremental training.

[0082] Figure 7 is a schematic diagram of another iterative device for a mechanism model provided by an embodiment of the present disclosure; Figure 7 As shown, the embodiment of the present disclosure provides an iterative device 200 for a mechanism model, including a processor 201 and a memory 202. Optionally, the device may also include a communication interface 203 and a bus 204. The processor 201, the communication interface 203, and the memory 202 may communicate with each other through the bus 204. The communication interface 203 may be used for information transmission. The processor 201 may call the logic instructions in the memory 202 to execute the iterative method for the mechanism model of the above embodiment.

[0083] In addition, the logic instructions in the memory 202 described above may be implemented in the form of software functional units and when sold or used as independent products, may be stored in a computer-readable storage medium.

[0084] The memory 202 is a computer-readable storage medium that can be used to store software programs and computer executable programs, such as program instructions / modules corresponding to the methods in the embodiments of the present disclosure. The processor 201 executes the functional application and data processing by running the program instructions / modules stored in the memory 202, that is, the iterative method for the mechanism model in the above-mentioned embodiment is implemented.

[0085] The memory 202 may include a program storage area and a data storage area, wherein the program storage area may store an operating system and an application required for at least one function; the data storage area may store data created according to the use of the terminal device, etc. In addition, the memory 202 may include a high-speed random access memory and may also include a non-volatile memory.

[0086] An embodiment of the present disclosure provides a computer-readable storage medium storing computer-executable instructions, wherein the computer-executable instructions are configured to execute the above-mentioned iterative method for the mechanism model.

[0087] The computer-readable storage medium mentioned above may be a transient computer-readable storage medium or a non-transitory computer-readable storage medium.

[0088] The technical solution of the embodiment of the present disclosure can be embodied in the form of a software product, which is stored in a storage medium and includes one or more instructions for enabling a computer device (which may be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in the embodiment of the present disclosure. The aforementioned storage medium may be a non-transient storage medium, including: a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and other media that can store program codes, or a transient storage medium.

[0089] The above description and the accompanying drawings fully illustrate the embodiments of the present disclosure so that those skilled in the art can practice them. Other embodiments may include structural, logical, electrical, process and other changes. The embodiments represent only possible changes. Unless explicitly required, separate components and functions are optional, and the order of operation may vary. The parts and features of some embodiments may be included in or replace the parts and features of other embodiments. Moreover, the words used in this application are only used to describe the embodiments and are not used to limit the claims. As used in the description of the embodiments and the claims, unless the context clearly indicates, the singular forms of "a", "an" and "the" are intended to include plural forms as well. Similarly, the term "and / or" as used in this application refers to any and all possible combinations of listings containing one or more associated ones. In addition, when used in the present application, the term "comprise" and its variants "comprises" and / or comprising refer to the presence of stated features, wholes, steps, operations, elements, and / or components, but do not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or groups thereof. In the absence of further restrictions, the elements defined by the sentence "comprising a ..." do not exclude the presence of other identical elements in the process, method or device comprising the elements. In this article, each embodiment may focus on the differences from other embodiments, and the same and similar parts between the various embodiments may refer to each other. For the methods, products, etc. disclosed in the embodiments, if they correspond to the method part disclosed in the embodiments, then the relevant parts can refer to the description of the method part.

[0090] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software may depend on the specific application and design constraints of the technical solution. The technicians may use different methods for each specific application to implement the described functions, but such implementations should not be considered to exceed the scope of the embodiments of the present disclosure. The technicians may clearly understand that, for the convenience and simplicity of description, the specific working processes of the systems, devices and units described above may refer to the corresponding processes in the aforementioned method embodiments, and will not be repeated here.

[0091] In the embodiments disclosed herein, the disclosed methods and products (including but not limited to devices, equipment, etc.) can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units can be only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between each other shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms. 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 may be located in one place, or they may be distributed on multiple network units. Some or all of the units may be selected according to actual needs to implement this embodiment. In addition, each functional unit in the embodiment of the present disclosure may be integrated in a processing unit, or each unit may exist physically alone, or two or more units may be integrated in one unit.

[0092] The flowchart and block diagram in the accompanying drawings show the possible architecture, function and operation of the system, method and computer program product according to the embodiment of the present disclosure. In this regard, each box in the flowchart or block diagram can represent a module, a program segment or a part of the code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. In some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, which can depend on the functions involved. In the description corresponding to the flowchart and the block diagram in the accompanying drawings, the operations or steps corresponding to different boxes can also occur in a different order from the order disclosed in the description, and sometimes there is no specific order between different operations or steps. For example, two consecutive operations or steps can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, which can depend on the functions involved. Each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, may be implemented by a dedicated hardware-based system that performs the specified functions or actions, or may be implemented by a combination of dedicated hardware and computer instructions.

Claims

1. An iterative method for a mechanistic model, characterized in that Applied to an air conditioning system, the method comprises: Obtaining an initial mechanism model; Training the initial mechanism model to obtain a mechanism pre-model; Determine the target loss function based on the service life of the air conditioning system; Model iteration is performed according to the mechanism pre-model, the update task information input by the user and the target loss function to obtain an iterated new mechanism model.

2. The method according to claim 1, characterized in that According to the service life of the air conditioning system, determine the target loss function, including: According to the service life of the air-conditioning system, determine the weight ratio of the incremental data and the weight ratio of the original model; Determine the target loss function based on the weight ratio of the incremental data and the weight ratio of the original model.

3. The method according to claim 2, characterized in that According to the service life of the air conditioning system, determine the weight ratio of the incremental data, including: When the service life of the air-conditioning system is not higher than a first threshold, determining the weight ratio of the incremental data to be a first ratio; When the service life of the air-conditioning system is higher than the first threshold and not higher than the second threshold, determining the weight proportion of the incremental data to be the second proportion; When the service life of the air-conditioning system is higher than the second threshold value and lower than the third threshold value, determining the weight proportion of the incremental data to be the third proportion; When the service life of the air-conditioning system is higher than the third threshold, determining the weight proportion of the incremental data to be the fourth proportion; Among them, the first proportion is less than the second proportion, the third proportion is less than the fourth proportion.

4. The method according to claim 2, characterized in that: According to the service life of the air conditioning system, determine the weight ratio of the original model, including: When the service life of the air-conditioning system is not higher than the first threshold, determining the weight proportion of the original model to be the fifth proportion; When the service life of the air-conditioning system is higher than the first threshold value and lower than the second threshold value, the weight proportion of the original model is determined to be the sixth proportion; When the service life of the air-conditioning system is higher than the second threshold value and lower than the third threshold value, the weight proportion of the original model is determined to be the seventh proportion; When the service life of the air-conditioning system is higher than the third threshold, the weight proportion of the original model is determined to be the eighth proportion; Among them, the eighth proportion is less than the seventh proportion, less than the sixth proportion, and less than the fifth proportion.

5. The method according to claim 1, characterized in that The initial mechanism model is trained to obtain a mechanism pre-model, including: Obtain all sample data required for model training; The initial mechanism model is trained according to the full amount of sample data to obtain a mechanism pre-model.

6. The method according to claim 5, characterized in that Obtain the full amount of sample data required for model training, including: Determining the target device type to which the initial mechanism model belongs; Acquire a historical database, wherein the historical database stores sample data corresponding to different device types; Sample data corresponding to the target device type is extracted from the historical database and determined as the full amount of sample data required for model training.

7. The method according to claim 5, characterized in that The initial mechanism model is trained according to the full amount of sample data to obtain a mechanism pre-model, including: Determine the convergence criteria of the model; The full amount of sample data is input into the initial mechanism model for model training until a mechanism pre-model that meets the convergence criteria is obtained.

8. An iterative device for a mechanism model, characterized in that: Applied to an air conditioning system, the device comprises: an acquisition module, configured to acquire an initial mechanism model; A training module is configured to train the initial mechanism model to obtain a mechanism pre-model; a determination module configured to determine a target loss function according to the service life of the air conditioning system; The iteration module is configured to perform model iteration according to the mechanism pre-model, the update task information input by the user and the target loss function to obtain a new mechanism model after iteration.

9. An iterative device for a mechanism model, comprising a processor and a memory storing program instructions, characterized in that: The processor is configured to execute the iterative method for the mechanism model according to any one of claims 1 to 7 when running the program instructions.

10. A storage medium storing program instructions, characterized in that: When the program instructions are executed, the iterative method for the mechanism model according to any one of claims 1 to 7 is executed.

Images