Control method and device of air conditioner and electronic equipment

Abstract

The invention provides a control method and device of an air conditioner, a computer readable storage medium and electronic equipment. The method comprises the following steps: acquiring user interaction data, wherein the user interaction data at least comprises voice data; the user interaction data are analyzed through a first language model to obtain expected data, the expected data are data representing adjustment expectation of a user and at least comprise the target temperature, the first language model is obtained through training of multiple sets of first data, and each set of first data comprises historical user interaction data and historical expected data; generating an initial control program according to the expected data, simulating the operation of the initial control program, obtaining a simulation operation result, adjusting the initial control program under the condition that the simulation operation result represents that the air conditioner is abnormal until the simulation operation result represents that the air conditioner is normal, obtaining a target control program, and executing the target control program to control the operation of the air conditioner. According to the invention, the problem of poor user experience in the prior art is solved.

Description

Technical Field

[0001] The present application relates to the technical field of air conditioner control, and in particular to a method, device, computer-readable storage medium, and electronic device for controlling an air conditioner. Background Art

[0002] In the current heating, ventilation and air conditioning (HVAC) field, especially in central air conditioning systems, the improvement of the level of intelligence mostly relies on traditional control algorithms and basic machine learning models. Although these technologies have optimized energy use and improved equipment operating efficiency to a certain extent, they mainly focus on processing structured sensor data, such as environmental parameters such as temperature and humidity. That is, they only operate according to the user's current or pre-set parameters, while ignoring the potential value of unstructured data. At the same time, the air conditioner is difficult to handle in the event of a malfunction, resulting in a poor user experience with traditional control methods. Summary of the Invention

[0003] The main purpose of this application is to provide a control method, device, computer-readable storage medium and electronic device for an air conditioner, so as to at least solve the problem of poor user experience in the prior art.

[0004] In order to achieve the above-mentioned purpose, according to one aspect of the present application, a method for controlling an air conditioner is provided, comprising: obtaining user interaction data, wherein the user interaction data at least includes voice data; analyzing the user interaction data through a first language model to obtain expected data, wherein the expected data is data representing the user's adjustment expectations and at least includes a target temperature, and the first language model is obtained by training multiple groups of first data, each group of first data including: historical user interaction data and historical expected data; generating an initial control program according to the expected data, simulating the operation of the initial control program to obtain a simulation operation result, and when the simulation operation result represents that the air conditioner is abnormal, adjusting the initial control program until the simulation operation result represents that the air conditioner is normal, obtaining a target control program, and executing the target control program to control the operation of the air conditioner.

[0005] Optionally, simulating the running of the initial control program includes: obtaining structural parameters of a predetermined space and position parameters of the air conditioner, wherein the predetermined space represents the space where the air conditioner is located, and the structural parameters include at least the area; constructing a virtual operation model based on at least the structural parameters and the position parameters, and simulating the running of the initial control program on the virtual operation model, wherein the virtual operation model is used to simulate the operation of the air conditioner in the predetermined space.

[0006] Optionally, a virtual operation model is constructed at least based on the structural parameters and the position parameters, including: constructing a physical model of the predetermined space based on the structural parameters and the position parameters of the predetermined space; determining a space conversion matrix, and converting the physical model into a virtual platform through the space conversion matrix, wherein the space conversion matrix represents the position conversion relationship between the physical model and the virtual platform, and the virtual platform includes a data transmission interface; and inputting at least the expected data into the virtual platform through the data transmission interface to obtain the virtual operation model.

[0007] Optionally, an initial control program is generated based on the expected data, including: obtaining the current temperature, and when the current temperature is different from the target temperature, calculating the absolute value of the difference between the current temperature and the target temperature; generating an initial control strategy based on at least the absolute value of the difference, and generating the initial control program based on the initial control strategy, wherein the initial control strategy includes at least a strategy for adjusting from the current temperature to the target temperature.

[0008] Optionally, after executing the target control program to control the operation of the air conditioner, the method further includes: obtaining user feedback data, wherein the user feedback data represents the user's feedback on the adjustment result of the air conditioner; analyzing the user feedback data through a second language model to obtain fine-tuning parameters, wherein the fine-tuning parameters represent parameters for adjusting the operation of the air conditioner, and the second language model is obtained by training multiple groups of second data, each group of second data includes: historical user feedback data and historical fine-tuning parameters; and controlling the operation of the air conditioner according to the fine-tuning parameters to meet the needs of the user.

[0009] Optionally, the method further includes: obtaining operating data and device status data of the air conditioner, wherein the operating data includes at least the historical operating frequency of the air conditioner, and the device status data represents the operating status of components in the air conditioner; analyzing the operating data and the device status data through a first neural network model to obtain reliability parameters, wherein the reliability parameters represent the reliability of components in the air conditioner, and the first neural network model is obtained by training multiple groups of third data, and each group of the third data includes: historical operating data, historical device status data and corresponding historical reliability parameters; when the reliability parameter is less than a preset threshold, generating an alternative control program, and executing the alternative control program to improve the reliability of the air conditioner.

[0010] Optionally, generating an alternative control program includes: outputting multiple recommended options so that the user selects one of the recommended options, wherein the recommended options include at least a replacement option and a retention option, the replacement option indicates replacing the air conditioner component whose reliability parameter is less than the preset threshold, and the retention option indicates retaining the air conditioner component whose reliability parameter is less than the preset threshold; in case the user selects the retention option, generating the alternative control program.

[0011] Optionally, the method includes: analyzing the operating data and the equipment status data through a second neural network model to obtain a predicted energy consumption value, wherein the second neural network model is obtained by training multiple groups of fourth data, and each group of the fourth data includes: historical operating data, historical equipment status data and corresponding historical predicted energy consumption values; when the predicted energy consumption value is greater than a preset energy consumption value, generating energy consumption warning information to warn the air conditioner of high energy consumption.

[0012] According to another aspect of the present application, a control device for an air conditioner is provided, comprising: a first acquisition unit for acquiring user interaction data, wherein the user interaction data includes at least voice data; a first analysis unit for analyzing the user interaction data through a first language model to obtain expected data, wherein the expected data is data representing the user's adjustment expectations and includes at least a target temperature, and the first language model is obtained by training multiple groups of first data, each group of first data includes: historical user interaction data and historical expected data; an execution unit for generating an initial control program according to the expected data, simulating the operation of the initial control program to obtain a simulation operation result, and when the simulation operation result represents an abnormality of the air conditioner, adjusting the initial control program until the simulation operation result represents that the air conditioner is normal, obtaining a target control program, and executing the target control program to control the operation of the air conditioner.

[0013] According to another aspect of the present application, a computer-readable storage medium is provided, which includes a stored program, wherein when the program is run, the device where the computer-readable storage medium is located is controlled to execute any one of the air conditioner control methods.

[0014] According to another aspect of the present application, an electronic device is provided, comprising: one or more processors, a memory, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, and the one or more programs include a method for executing any one of the control methods of the air conditioner.

[0015] By applying the technical solution of the present application, user interaction data is obtained, the user interaction data is analyzed using a first language model to obtain expected data, and an initial control program is generated based on the expected data. The initial control program is simulated to obtain a simulated operation result. If the simulated operation result indicates that the air conditioner is abnormal, the initial control program is adjusted until the simulated operation result indicates that the air conditioner is normal, thereby obtaining a target control program, and executing the target control program to control the operation of the air conditioner. Compared with the prior art, in which the air conditioner is directly adjusted based on the parameters manually set by the user, resulting in a poor user experience, the air conditioner control method of the present application can be controlled based on the user interaction data, and the operation results are also simulated to verify whether the initial control program generated by the expected data will cause the air conditioner to be abnormal, thereby avoiding the air conditioner abnormality that causes a bad user experience during the adjustment process based on the user interaction data, and no manual adjustment is required by the user, thereby improving the user experience. Therefore, it can solve the problem of poor user experience in the prior art and achieve the effect of improving the user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] The drawings that constitute part of this application are used to provide a further understanding of this application. The illustrative embodiments of this application and their descriptions are used to explain this application and do not constitute an improper limitation on this application. In the drawings:

[0017] Figure 1 A schematic flow chart of a method for controlling an air conditioner according to an embodiment of the present application is shown;

[0018] Figure 2 A control architecture diagram of a specific air conditioner provided in an embodiment of the present application is shown;

[0019] Figure 3 A multimodal alignment training flow chart provided in an embodiment of the present application is shown;

[0020] Figure 4 A structural block diagram of a control device for an air conditioner provided in an embodiment of the present application is shown. DETAILED DESCRIPTION

[0021] It should be noted that, in the absence of conflict, the embodiments and features of the embodiments in this application can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0022] In order to enable those skilled in the art to better understand the present invention, the following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments in the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts should fall within the scope of protection of this application.

[0023] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequential order. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present application described here. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0024] As introduced in the background technology, in the prior art, the air conditioner is directly adjusted only according to the parameters manually set by the user, resulting in a poor user experience. To solve the problem of poor user experience, the embodiments of the present application provide a control method, device, computer-readable storage medium and electronic device for an air conditioner.

[0025] The technical solutions in the embodiments of the present invention will be described clearly and completely below with reference to the accompanying drawings in the embodiments of the present invention.

[0026] In this embodiment, a method for controlling an air conditioner running on a mobile terminal, a computer terminal or a similar computing device is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0027] Figure 1 FIG. 1 is a flow chart of a method for controlling an air conditioner according to an embodiment of the present application. Figure 1 As shown, the method includes the following steps:

[0028] Step S201: acquiring user interaction data, wherein the user interaction data at least includes voice data;

[0029] Specifically, this embodiment no longer relies on manual user settings to control the air conditioner. Instead, it achieves accurate control by combining it with a language model, such as a multimodal large language model. Therefore, it is necessary to first obtain user interaction data, including but not limited to voice data and text data. For example, a user may issue a voice command: "I have an important meeting this afternoon. Please turn down the temperature early but keep quiet." Besides acquiring user interaction data on-site at the air conditioner itself, this data can also be acquired remotely through furniture devices that are connected to the Internet of Things (IoT) as well as the air conditioner. For example, a user in a different room from the air conditioner can directly say to their phone: "I have an important meeting this afternoon. Please turn down the temperature early but keep quiet." Other connected devices can also be used to obtain this data.

[0030] The input layer of the perception network, which is composed of a large multimodal language model, can input a variety of data, such as text data, voice data, and sensor data. Sensor data is generally structured data, including: a circular microphone array that supports 360-degree voice command capture, a thermal imaging sensor for human position and core body temperature detection, a UWB (Ultra Wide Band, abbreviated as UWB) positioning base station for personnel positioning accuracy, an environmental sensor box for obtaining temperature, humidity, CO2, etc., and support for 0.1-degree angle adjustment of air vents. Unstructured data includes user voice commands (converted to text via ASR), operation and maintenance work order text (fault descriptions, maintenance records), and building BIM (Building Information Modeling, abbreviated as BIM) models (spatial topology and thermal parameters). Input interfaces for multiple data formats are provided. Conduct multimodal alignment training. Multimodal data alignment refers to establishing and discovering corresponding relationships between different data modalities to achieve effective integration and utilization of information. Design a cross-modal comparative learning loss function to align text descriptions with sensor data. For example, if the text is "insufficient cooling", the corresponding sensor data may be reduced evaporator pressure and reduced current.

[0031] Step S202: Analyzing the user interaction data using a first language model to obtain desired data, wherein the desired data is data representing the user's desired adjustment and includes at least a target temperature. The first language model is trained using multiple sets of first data, each set of first data including historical user interaction data and historical desired data.

[0032] Specifically, the language model can be a large multimodal language model that integrates multiple functions. This large multimodal language model includes a first language model component that analyzes user interaction data. After analyzing the user interaction data using the first language model, the user's desired data can be obtained. For example, analyzing the user's voice command "I have an important meeting this afternoon. Cool down the room early but keep quiet" yields the following desired data: a target temperature of 24°C, a target time period of 2:00 PM to 4:00 PM, and a target operating mode of silent mode. The first language model is trained through machine learning based on a large amount of historical data. This data includes past user interaction records (such as user voice commands) and corresponding desired data (such as the specific temperature or operating mode the user desires). This training dataset enables the model to understand and learn the correspondence between various user commands and desired results. This allows the model to accurately interpret user intent and convert it into actionable control parameters when receiving new user data in the future. This in-depth understanding of the user's natural language allows the system to respond to user needs in a more humane and intuitive manner, without requiring the user to understand specific technical details or control parameters.

[0033] Step S203, generate an initial control program based on the expected data, simulate the operation of the initial control program, and obtain a simulation operation result. If the simulation operation result indicates that the air conditioner is abnormal, adjust the initial control program until the simulation operation result indicates that the air conditioner is normal, obtain a target control program, and execute the target control program to control the operation of the air conditioner.

[0034] Specifically, after parsing the expected data, it is converted into an initial control program. The energy efficiency and reliability of the initial control program's control strategy are then simulated to determine its feasibility and whether it will damage the air conditioner during operation. If the simulation results indicate an air conditioner anomaly, the initial control program is adjusted. For example, a user issues a command: "Next Wednesday at 2:00 PM, a key client will be meeting. Cool down conference room 1 in advance, but don't make the air conditioner hum." The system first searches the calendar to find that there's an important meeting in conference room next Wednesday. It then searches the weather and finds that the forecast for that day is 35°C and sunny. Based on peak and off-peak electricity prices, the system automatically selects pre-cooling at midnight, when electricity prices are lower. The initial control program is then simulated. If the simulation results indicate that "pre-cooling will cause pipe freezing," indicating an air conditioner anomaly, the strategy is immediately adjusted. This continues until a solution is found that both saves energy and prevents damage, resulting in the target control program. On the day of the meeting, the conference room temperature is automatically lowered to 24°C, and the fan speed is quietly lowered before the meeting to ensure quiet.

[0035] Through this embodiment, user interaction data is obtained, the user interaction data is analyzed using a first language model to obtain expected data, and an initial control program is generated based on the expected data. The initial control program is simulated to obtain a simulated operation result. If the simulated operation result indicates that the air conditioner is abnormal, the initial control program is adjusted until the simulated operation result indicates that the air conditioner is normal, and a target control program is obtained. The target control program is executed to control the operation of the air conditioner. Compared with the prior art, in which the air conditioner is directly adjusted based on the parameters manually set by the user, resulting in a poor user experience, the air conditioner control method of the present application can control based on user interaction data and also simulate the operation results to verify whether the initial control program generated by the expected data will cause the air conditioner to be abnormal, thereby avoiding the air conditioner abnormality caused by the adjustment process based on the user interaction data, which brings a bad experience to the user, and does not require the user to manually adjust, thereby improving the user experience. Therefore, it can solve the problem of poor user experience in the prior art and achieve the effect of improving user experience.

[0036] In a specific implementation, step S203 of simulating the initial control program can be accomplished by the following steps: Step S2031: Obtaining structural parameters of a predetermined space and location parameters of the air conditioner, wherein the predetermined space represents the space where the air conditioner is located, and the structural parameters include at least the area; Step S2032: Constructing a virtual operation model based on at least the structural parameters and the location parameters, and simulating the initial control program on the virtual operation model, wherein the virtual operation model is used to simulate the operation of the air conditioner in the predetermined space. By constructing an accurate virtual operation model and performing a simulated operation on it, this method can pre-evaluate the performance of the control program in a real-world environment, ensuring that it meets user needs while not causing damage to the air conditioning equipment.

[0037] Specifically, before simulation, detailed information about the air conditioner's environment must be collected. Structural parameters encompass fundamental spatial properties, such as room area, volume, ceiling height, and window location and size. This information is crucial for understanding the space's thermodynamic properties. Positional parameters accurately record the specific layout of the air conditioner within the space, including its location, orientation, and relative distances to walls, doors, and windows. This detailed data ensures that the virtual model accurately reflects the physical characteristics of the real environment, thereby enhancing the credibility of the simulation results. Based on the collected structural and positional parameters, a virtual operating model is constructed. This "virtual operating model" is essentially a component of a building digital twin that simulates the operating conditions of the air conditioner in a specific environment, including temperature distribution, humidity fluctuations, airflow patterns, and energy consumption. Once the model is constructed, the initial control program, generated from user instructions, can be simulated and executed on it. This allows the effectiveness of the control program to be predicted without interfering with actual equipment operation, assessing whether it will lead to equipment anomalies or poor performance.

[0038] In some optional implementations, step S2032 can be implemented by the following steps: step S2033: constructing a physical model of the predetermined space based on the structural parameters and the position parameters of the predetermined space; step S2034: determining a space conversion matrix, and converting the physical model into a virtual platform through the space conversion matrix, wherein the space conversion matrix represents the position conversion relationship between the physical model and the virtual platform, and the virtual platform includes a data transmission interface; step S2035: inputting at least the expected data into the virtual platform through the data transmission interface to obtain the virtual operation model. The method constructs a virtual operation model in the digital twin environment through the above steps, and maps the user's expected data to this model to achieve accurate simulation and strategy verification.

[0039] Specifically, the system needs to build a physical model that accurately reflects the actual thermodynamic properties of the intended space (i.e., the area served by the air conditioner, such as an office or conference room) based on the structural parameters (including but not limited to area, volume, wall location, window size, etc.) and the specific location information of the air conditioner (referring to the exact layout of the air conditioner in the space, including but not limited to the relative distance from the walls and windows, and the orientation of the air conditioner). Determine the spatial transformation matrix: Next, to use this physical model in the virtual platform (digital twin environment), a spatial transformation matrix must be determined. The specific steps for mathematical modeling of the spatial transformation matrix are as follows: Step 1: Define the coordinate system. The UWB coordinate system: This is typically a three-dimensional rectangular coordinate system (x, y, z) with the center of the UWB base station network as the origin; the BIM coordinate system: This is based on the global origin of the building BIM model (e.g., the southwest corner of the building). Step 2: Collect calibration points. Select at least four non-coplanar calibration points within the building (preferably equipment installation locations, such as air conditioner units and fan coil units). Record the coordinates of these points in both the UWB and BIM coordinate systems. Step 3: Calculate the rotation matrix R and translation vector T. The optimal rigid body transformation can be solved using the least squares method: First, coordinates are centered and the centroids of the calibration points in the UWB and BIM coordinate systems are calculated. Then, the covariance matrix is constructed and subjected to singular value decomposition. The translation vector and the transformation matrix are calculated, ultimately yielding the mapping formula from any UWB coordinate point (x, y, z) to BIM coordinates (X, Y, Z). This matrix defines the positional transformation relationship between the physical model and the virtual platform, ensuring that every point in the physical model (including the location of the air conditioner and other spatial features) is accurately mapped to the virtual platform. Establishing the spatial transformation matrix is a key technical step in achieving data synchronization and policy rehearsal between the digital twin model and the real environment. Inputting desired data using the data transmission interface: Once the virtual platform is ready, the system imports user desired data (such as target temperature, noise requirements, energy saving targets, etc.) into the virtual operating model through the data transmission interface within the virtual platform. This allows user requirements to be accurately simulated and rehearsed within the digital twin environment, thereby verifying the effectiveness and rationality of the control strategy.

[0040] In other optional embodiments, step S203 generates an initial control program based on the expected data, which can be achieved by the following steps: step S2036: obtaining the current temperature, and when the current temperature is different from the target temperature, calculating the absolute value of the difference between the current temperature and the target temperature; step S2037: generating an initial control strategy based on at least the absolute value of the difference, and generating the initial control program based on the initial control strategy, wherein the initial control strategy includes at least a strategy for adjusting from the current temperature to the target temperature. Through the above steps, this method achieves end-to-end mapping from user natural language instructions to specific air conditioning control programs, increases the diversity of air conditioning control, eliminates the need for manual settings by the user, and also improves the user experience.

[0041] During implementation, sensors acquire the current ambient temperature in real time, providing the system with the necessary data to respond to user temperature adjustment requests. The system then calculates the difference between the user's desired target temperature and the current temperature, taking its absolute value. This step quantifies the temperature difference and provides a numerical basis for subsequent policy generation. Based on the absolute value of this temperature difference, the system generates an initial control strategy, defining how to gradually adjust from the current temperature to the target temperature. This strategy may take into account the air conditioner's heating or cooling capacity to ensure both rapid and smooth temperature adjustment. Typically, there is more than one strategy to ensure the ability to switch to another if one option proves unsuccessful. Finally, based on this initial control strategy, the system translates it into a series of specific instructions executable by the air conditioner, forming the initial control program. These instructions may include adjusting air conditioner settings, such as changing cooling or heating power, fan speed, or operating mode, to achieve precise temperature control. For example, a user instruction, "I have an important meeting this afternoon. I need to cool down the room early but keep it quiet," could be translated into the following control instructions:

[0042] set_temp(22);

[0043] if time.between("14:00","16:00");

[0044] fan_mode("silent");

[0045] compressor_freq(40Hz).

[0046] In some optional embodiments, the method further includes step S204: after executing the target control program to control the operation of the air conditioner, obtaining user feedback data, wherein the user feedback data represents user feedback on the adjustment results of the air conditioner; step S205: analyzing the user feedback data using a second language model to obtain fine-tuning parameters, wherein the fine-tuning parameters represent parameters for adjusting the operation of the air conditioner, and the second language model is trained using multiple sets of second data, each set of second data including historical user feedback data and historical fine-tuning parameters; and step S206: controlling the operation of the air conditioner based on the fine-tuning parameters to meet the user's needs. This method, through a closed-loop feedback mechanism, can dynamically adjust the air conditioning control strategy based on real-time user feedback, making the user experience more personalized and comfortable.

[0047] Specifically, during the operation of the air conditioner, the user may provide real-time feedback on their current feelings. For example: (1) Taking the fault diagnosis and self-repair scenario as an example, if the user reports "there is a sour smell on the east side of the office" through voice, the visual sensor will be called to scan the east side air vents; the knowledge graph will be searched to find that "sour smell + condensed water pH < 5" matches the corrosion of the condenser copper tube, and fine-tuning parameters will be generated. The corresponding repair code will be generated: increase the pH of the chilled water to 8.5. Finally, a work order can be issued to remind the user to check the corrosion inhibitor. (2) Taking the user's real-time feedback as an example, the user said: "The air conditioner always blows towards my head." Through the automatic learning of the second language model in the multimodal large language model, the user's workstation location is analyzed. It will also find out whether the air vent is crooked by looking up the maintenance record and issue a warning to notify the maintenance personnel to come with tools to repair it the next day. The second language model is trained based on a large amount of historical user feedback data and corresponding fine-tuning parameters. It can understand the user's natural language feedback and convert it into specific technical parameter adjustments, namely fine-tuning parameters. These parameters may include temperature settings, fan speed, operation mode, etc. In addition to the data provided by users through voice feedback, historical user feedback data can also include fault repair work orders, fault repair records, etc., so that the second language model can learn solutions to historical problems, so as to more accurately parse user feedback data and generate corresponding fine-tuning parameters.

[0048] In other optional embodiments, the method further includes step S207: obtaining operating data and device status data of the air conditioner, wherein the operating data includes at least the historical operating frequency of the air conditioner, and the device status data represents the operating status of components in the air conditioner; step S208: analyzing the operating data and the device status data using a first neural network model to obtain a reliability parameter, wherein the reliability parameter represents the reliability of the components in the air conditioner, and the first neural network model is trained using multiple sets of third data, each set of third data including: historical operating data, historical device status data, and corresponding historical reliability parameters; step S209: generating an alternative control program if the reliability parameter is less than a preset threshold, and executing the alternative control program to improve the reliability of the air conditioner. Through the above steps, the method predicts the reliability of the device by real-time analysis of the device status, ensuring stable operation of the air conditioner.

[0049] Specifically, the above steps aim to analyze the reliability of the air conditioner through operation data and equipment status data, which can also be understood as the remaining life. Historical equipment status data may include: (1) Control parameters: set temperature, fan speed, valve opening; the data source may be the historical log of the air conditioning control system. (2) Environmental parameters: indoor and outdoor temperature and humidity, occupant density, solar radiation; the data source may be the building BIM model and meteorological database. (3) Equipment status: compressor frequency, refrigerant pressure, current; the data source may be real-time monitoring by sensors. Historical operation data may include: Time series characteristics: energy consumption trend and load fluctuation in the past hour; the data source may be the time series database. Corresponding historical reliability parameters: (1) Direct observation values: real-time energy consumption (kW), outlet air temperature (℃), used for supervised learning of data fitting items; (2) Physical field distribution: evaporator surface temperature field, air duct velocity field, used for physical residual term constraint. (3) Equipment health indicators: compressor bearing wear (0-1), refrigerant charge, used for reliability prediction and life modeling. In the case where the reliability parameter is less than a preset threshold, an alternative control program is generated and executed to improve the reliability of the air conditioner. For example, when the predicted life of a component is lower than a safety threshold, the control strategy needs to be automatically adjusted, that is, the predicted equipment life loss is greater than the threshold, and the following alternatives are automatically generated: 1. Alternatives for dynamic adjustment of operating parameters: that is, by reducing the component load or switching the operating mode, its remaining life is extended. For example, the alternative to compressor life warning (remaining life <30 days) is to reduce the number of compressor starts and stops during peak loads during the day, which is expected to extend the life by 50%. For example, the alternative to fan bearing wear (vibration value > 5mm / s) is to reduce the fan speed from 1200rpm to 900rpm and to link the fans in adjacent areas to increase the speed to compensate for the air volume. 2. Human-machine collaboration solution: convert the technical solution into natural language suggestions and implement it in consultation with the user. For example, if the filter life is exhausted (usage time > 500 hours), the system will automatically reduce the fresh air ratio from 30% to 15% (to reduce dust entry), and then push a message to the user: "It is detected that the filter in the east area has expired, and it is recommended to replace it immediately. Temporary solution: Reduce the amount of fresh air, and the indoor CO2 concentration will rise to 800ppm (still in line with national standards). Do you agree? Let the user actively choose [Replace immediately] or [Delay until 18:00]"; if the user chooses to delay, start the backup fan and record the liability exemption clause. 3. Load transfer and redundant switching solution: This is to use the system redundancy design to transfer the load of the faulty component; for example, a multi-split refrigerant leak; the alternative is to isolate the leaking branch, redistribute the refrigerant to the normal branch, start the VRF system in the adjacent area for cross-cooling, and send an early warning: "R32 leakage has been detected, and the A3 pipeline valve has been closed."

[0050] In other optional implementations, step S209 can be implemented by the following steps: Step S2091: Outputting multiple suggested options so that the user selects one of the suggested options, wherein the suggested options include at least a replacement option and a retention option, wherein the replacement option represents replacing the air conditioner component whose reliability parameter is less than the preset threshold, and the retention option represents retaining the air conditioner component whose reliability parameter is less than the preset threshold; Step S2092: If the user selects the retention option, generating the alternative control program. Through the above steps, the method generates the alternative control program through user participation in decision-making, thereby balancing equipment maintenance and user experience.

[0051] Specifically, multiple recommended options are output for users to choose from: when the first neural network model analyzes that the reliability parameters of one or some components are lower than the preset threshold, the system will generate and display multiple recommended options to the user. These options usually include replacement options and retention options, which allow users to make decisions based on current circumstances and preferences. Users are advised to replace components with low reliability to ensure the stability of the system and extend the service life of the equipment. Alternative control strategies are provided in the event that components are not replaced immediately, which may include reducing the load on the component, adjusting the operating mode to reduce component wear, or enabling spare components. Generate an alternative control program when the user chooses the retention option: If the user chooses the retention option, an alternative control program will be generated based on this decision, aiming to reduce the risk of component failure by changing the control strategy, while minimizing impact on user comfort and system performance.

[0052] In some optional embodiments, the method further includes step S210: analyzing the operating data and the device status data using a second neural network model to obtain a predicted energy consumption value, wherein the second neural network model is trained using multiple sets of fourth data, each set of fourth data including historical operating data, historical device status data, and corresponding historical predicted energy consumption values; and step S211: generating an energy consumption warning message to warn the air conditioner of excessive energy consumption when the predicted energy consumption value is greater than a preset energy consumption value. By predicting energy consumption values, this method can balance energy consumption with user comfort.

[0053] Specifically, the aforementioned historical operating data and historical device status data can be used to predict energy consumption through a second neural network model. For example, this model can output a one-hour energy consumption forecast, recommend optimal energy efficiency control parameters (such as chilled water temperature setpoints), and generate energy consumption warnings to alert users of high energy consumption. Furthermore, a causal model can be constructed to analyze factors that significantly impact energy consumption, such as the impact of "filter cleaning" on energy consumption, which is Δ = 0.35.

[0054] In order to enable those skilled in the art to more clearly understand the technical solution of the present application, the implementation process of the air conditioner control method of the present application will be described in detail below with reference to specific embodiments.

[0055] This embodiment relates to a specific control architecture diagram of an air conditioner, such as Figure 2 As shown, the following steps are included:

[0056] Step S1: Input voice, sensor, text, positioning, BIM, and image data through the multimodal input layer; sensor data is stored as Kafka data and transmitted to the edge computing layer through real-time data streaming;

[0057] Step S2: Perform local speech recognition, sensor data alignment, and lightweight model inference at the edge computing layer to obtain a draft control instruction (initial control program);

[0058] Step S3: Further multimodal alignment training, strategy generation and optimization, and causal reasoning through the causal reasoning engine are performed in the cloud-based large model inference layer;

[0059] Step S4: Perform digital twin verification through the digital twin verification layer, virtual air conditioning system simulation, energy efficiency / lifespan prediction, and strategy safety verification;

[0060] Step S5: The instructions are finally executed through the physical execution layer to achieve air outlet control, compressor frequency adjustment and energy storage system management.

[0061] This embodiment relates to a multimodal alignment training flow chart, such as Figure 3 As shown, the following steps are included:

[0062] Step S6: Encode the text data using a text encoder, extract voice features from the voice data, and encode the sensor data using a sensor encoder;

[0063] Step S7: cross-modal contrastive learning;

[0064] Step S8: joint optimization;

[0065] Step S9: comparative evaluation;

[0066] Step S10: Model output.

[0067] The embodiments of the present application also provide a control device for an air conditioner. It should be noted that the control device for the air conditioner in the embodiments of the present application can be used to execute the control method for an air conditioner provided in the embodiments of the present application. The device is used to implement the above-mentioned embodiments and preferred implementation modes, and the details that have been described will not be repeated here. As used below, the term "module" can be a combination of software and / or hardware that implements a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceivable.

[0068] The following is an introduction to the control device of the air conditioner provided in the embodiment of the present application.

[0069] Figure 4 Schematic diagram of the control device of the air conditioner according to the embodiment of the present application. Figure 4 The device comprises:

[0070] A first acquiring unit 10 is configured to acquire user interaction data, wherein the user interaction data at least includes voice data;

[0071] Specifically, this embodiment no longer relies on manual user settings to control the air conditioner. Instead, it achieves accurate control by combining it with a language model, such as a multimodal large language model. Therefore, it is necessary to first obtain user interaction data, including but not limited to voice data and text data. For example, a user may issue a voice command: "I have an important meeting this afternoon. Please turn down the temperature early but keep quiet." Besides acquiring user interaction data on-site at the air conditioner itself, this data can also be acquired remotely through furniture devices that are connected to the Internet of Things (IoT) as well as the air conditioner. For example, a user in a different room from the air conditioner can directly say to their phone: "I have an important meeting this afternoon. Please turn down the temperature early but keep quiet." Other connected devices can also be used to obtain this data.

[0072] The input layer of the perception network, comprised of a multimodal large language model, can accept a variety of data, such as text, voice, and sensor data. Sensor data is generally structured and includes: a circular microphone array supporting 360-degree voice command capture, thermal imaging sensors for body position and core temperature detection, UWB positioning base stations for accurate positioning of personnel, environmental sensor boxes for acquiring temperature, humidity, and CO2, and air vents that support 0.1-degree angle adjustment. Unstructured data includes user voice commands (converted to text via ASR), maintenance work order text (fault descriptions, repair records), and building BIM models (spatial topology and thermal parameters). Input interfaces for various data formats are provided. Multimodal alignment training is performed. Multimodal data alignment involves establishing and discovering corresponding relationships between different data modalities to achieve effective information integration and utilization. A cross-modal comparative learning loss function is designed to align text descriptions with sensor data. For example, if the text reads "insufficient cooling," the corresponding sensor data may be decreased evaporator pressure or current.

[0073] a first analyzing unit 20 configured to analyze the user interaction data using a first language model to obtain desired data, wherein the desired data is data representing the user's desired adjustment and includes at least a target temperature, and the first language model is obtained by training multiple sets of first data, each set of first data including historical user interaction data and historical desired data;

[0074] Specifically, the language model can be a large multimodal language model that integrates multiple functions. This large multimodal language model includes a first language model component that analyzes user interaction data. After analyzing the user interaction data using the first language model, the user's desired data can be obtained. For example, analyzing the user's voice command "I have an important meeting this afternoon. Cool down the room early but keep quiet" yields the following desired data: a target temperature of 24°C, a target time period of 2:00 PM to 4:00 PM, and a target operating mode of silent mode. The first language model is trained through machine learning based on a large amount of historical data. This data includes past user interaction records (such as user voice commands) and corresponding desired data (such as the specific temperature or operating mode the user desires). This training dataset enables the model to understand and learn the correspondence between various user commands and desired results. This allows the model to accurately interpret user intent and convert it into actionable control parameters when receiving new user data in the future. This in-depth understanding of the user's natural language allows the system to respond to user needs in a more humane and intuitive manner, without requiring the user to understand specific technical details or control parameters.

[0075] The execution unit 30 is used to generate an initial control program based on the expected data, simulate the operation of the initial control program, and obtain a simulation operation result. When the simulation operation result indicates that the air conditioner is abnormal, the initial control program is adjusted until the simulation operation result indicates that the air conditioner is normal, thereby obtaining a target control program and executing the target control program to control the operation of the air conditioner.

[0076] Specifically, after parsing the expected data, it is converted into an initial control program. The energy efficiency and reliability of the initial control program's control strategy are then simulated to determine its feasibility and whether it will damage the air conditioner during operation. If the simulation results indicate an air conditioner anomaly, the initial control program is adjusted. For example, a user issues a command: "Next Wednesday at 2:00 PM, a key client will be meeting. Cool down conference room 1 in advance, but don't make the air conditioner hum." The system first searches the calendar to find out that there's an important meeting in conference room next Wednesday. It then searches the weather and finds that the forecast for that day is 35°C and sunny. Based on peak and off-peak electricity prices, the system automatically selects pre-cooling at midnight, when electricity prices are lower. The initial control program is then simulated. If the simulation results indicate that "pre-cooling will cause pipe freezing," indicating an air conditioner anomaly, the strategy is immediately adjusted. This continues until a solution that both saves energy and prevents damage is found, resulting in the target control program. On the day of the meeting, the conference room temperature is automatically lowered to 24°C, and the fan speed is quietly lowered before the meeting to ensure quiet.

[0077] Through this embodiment, user interaction data is obtained, the user interaction data is analyzed using a first language model to obtain expected data, and an initial control program is generated based on the expected data. The initial control program is simulated to obtain a simulated operation result. If the simulated operation result indicates that the air conditioner is abnormal, the initial control program is adjusted until the simulated operation result indicates that the air conditioner is normal, and a target control program is obtained. The target control program is executed to control the operation of the air conditioner. Compared with the prior art, in which the air conditioner is directly adjusted based on the parameters manually set by the user, resulting in a poor user experience, the air conditioner control device of the present application can control based on user interaction data and also simulate the operation results to verify whether the initial control program generated by the expected data will cause the air conditioner to be abnormal, thereby avoiding the air conditioner abnormality caused by the adjustment process based on the user interaction data, which brings a bad experience to the user, and does not require the user to make manual adjustments, thereby improving the user experience. Therefore, it can solve the problem of poor user experience in the prior art and achieve the effect of improving user experience.

[0078] In a specific implementation, the execution unit includes a first acquisition module and a first operation module. The first acquisition module is configured to acquire structural parameters of a predetermined space and location parameters of the air conditioner, wherein the predetermined space represents the space where the air conditioner is located, and the structural parameters include at least the area. The first operation module is configured to construct a virtual operation model based on at least the structural parameters and the location parameters, and simulate the initial control program on the virtual operation model. The virtual operation model is configured to simulate the operation of the air conditioner in the predetermined space. By constructing an accurate virtual operation model and performing a simulated operation on it, the device can pre-evaluate the performance of the control program in a real-world environment, ensuring that it meets user needs without causing damage to the air conditioning equipment.

[0079] Specifically, before simulation, detailed information about the air conditioner's environment must be collected. Structural parameters encompass fundamental spatial properties, such as room area, volume, ceiling height, and window location and size. This information is crucial for understanding the space's thermodynamic properties. Positional parameters accurately record the specific layout of the air conditioner within the space, including its location, orientation, and relative distances to walls, doors, and windows. This detailed data ensures that the virtual model accurately reflects the physical characteristics of the real environment, thereby enhancing the credibility of the simulation results. Based on the collected structural and positional parameters, a virtual operating model is constructed. This "virtual operating model" is essentially a component of a building digital twin that simulates the operating conditions of the air conditioner in a specific environment, including temperature distribution, humidity fluctuations, airflow patterns, and energy consumption. Once the model is constructed, the initial control program, generated from user instructions, can be simulated and executed on it. This allows the effectiveness of the control program to be predicted without interfering with actual equipment operation, assessing whether it will lead to equipment anomalies or poor performance.

[0080] In some optional embodiments, the first operation module includes a construction submodule, a conversion submodule, and an input submodule. The construction submodule is used to construct a physical model of the predetermined space based on the structural parameters and position parameters of the predetermined space. The conversion submodule is used to determine a spatial conversion matrix and convert the physical model into a virtual platform through the spatial conversion matrix, wherein the spatial conversion matrix represents the position conversion relationship between the physical model and the virtual platform, and the virtual platform includes a data transmission interface. The input submodule is used to input at least the expected data into the virtual platform through the data transmission interface to obtain the virtual operation model. The device constructs a virtual operation model in the digital twin environment through the above steps and maps the user's expected data to this model to achieve accurate simulation and strategy verification.

[0081] Specifically, the system needs to build a physical model that accurately reflects the actual thermodynamic properties of the intended space (i.e., the area served by the air conditioner, such as an office or conference room) based on the structural parameters (including but not limited to area, volume, wall location, window size, etc.) and the specific location information of the air conditioner (referring to the exact layout of the air conditioner in the space, including but not limited to the relative distance from the walls and windows, and the orientation of the air conditioner). Determine the spatial transformation matrix: Next, to use this physical model in the virtual platform (digital twin environment), a spatial transformation matrix must be determined. The specific steps for mathematical modeling of the spatial transformation matrix are as follows: Step 1: Define the coordinate system. The UWB coordinate system: This is typically a three-dimensional rectangular coordinate system (x, y, z) with the center of the UWB base station network as the origin; the BIM coordinate system: This is based on the global origin of the building BIM model (e.g., the southwest corner of the building). Step 2: Collect calibration points. Select at least four non-coplanar calibration points within the building (preferably equipment installation locations, such as air conditioner units and fan coil units). Record the coordinates of these points in both the UWB and BIM coordinate systems. Step 3: Calculate the rotation matrix R and translation vector T. The optimal rigid body transformation can be solved using the least squares method: First, coordinates are centered and the centroids of the calibration points in the UWB and BIM coordinate systems are calculated. Then, the covariance matrix is constructed and subjected to singular value decomposition. The translation vector and the transformation matrix are calculated, ultimately yielding the mapping formula from any UWB coordinate point (x, y, z) to BIM coordinates (X, Y, Z). This matrix defines the positional transformation relationship between the physical model and the virtual platform, ensuring that every point in the physical model (including the location of the air conditioner and other spatial features) is accurately mapped to the virtual platform. Establishing the spatial transformation matrix is a key technical step in achieving data synchronization and policy rehearsal between the digital twin model and the real environment. Inputting desired data using the data transmission interface: Once the virtual platform is ready, the system imports user desired data (such as target temperature, noise requirements, energy saving targets, etc.) into the virtual operating model through the data transmission interface within the virtual platform. This allows user requirements to be accurately simulated and rehearsed within the digital twin environment, thereby verifying the effectiveness and rationality of the control strategy.

[0082] In other optional embodiments, the execution unit further includes a calculation module and a generation module. The calculation module is configured to obtain the current temperature and, if the current temperature differs from the target temperature, calculate the absolute value of the difference between the current temperature and the target temperature. The generation module is configured to generate an initial control strategy based at least on the absolute value of the difference, and to generate the initial control program based on the initial control strategy, wherein the initial control strategy includes at least a strategy for adjusting the temperature from the current temperature to the target temperature. Through the above steps, the device achieves end-to-end mapping from user natural language commands to specific air conditioner control programs, increasing the diversity of air conditioner control without requiring manual user settings and improving the user experience.

[0083] During implementation, sensors acquire the current ambient temperature in real time, providing the system with the necessary data to respond to user temperature adjustment requests. The system then calculates the difference between the user's desired target temperature and the current temperature, taking its absolute value. This step quantifies the temperature difference and provides a numerical basis for subsequent policy generation. Based on the absolute value of this temperature difference, the system generates an initial control strategy, defining how to gradually adjust from the current temperature to the target temperature. This strategy may take into account the air conditioner's heating or cooling capacity to ensure both rapid and smooth temperature adjustment. Typically, there is more than one strategy to ensure the ability to switch to another if one option proves unsuccessful. Finally, based on this initial control strategy, the system translates it into a series of specific instructions executable by the air conditioner, forming the initial control program. These instructions may include adjusting air conditioner settings, such as changing cooling or heating power, fan speed, or operating mode, to achieve precise temperature control. For example, a user instruction, "I have an important meeting this afternoon. I need to cool down the room early but keep it quiet," could be translated into the following control instructions:

[0084] set_temp(22);

[0085] if time.between("14:00","16:00");

[0086] fan_mode("silent");

[0087] compressor_freq(40Hz).

[0088] In some optional embodiments, the device further includes a second acquisition unit, a second analysis unit, and a first operation unit. The second acquisition unit is configured to acquire user feedback data after executing the target control program to control the operation of the air conditioner, wherein the user feedback data represents user feedback on the adjustment results of the air conditioner. The second analysis unit is configured to analyze the user feedback data using a second language model to obtain fine-tuning parameters, wherein the fine-tuning parameters represent parameters for adjusting the operation of the air conditioner. The second language model is trained using multiple sets of second data, each set of second data including historical user feedback data and historical fine-tuning parameters. The first operation unit is configured to control the operation of the air conditioner based on the fine-tuning parameters to meet the user's needs. Through a closed-loop feedback mechanism, the device can dynamically adjust the air conditioning control strategy based on real-time user feedback, making the user experience more personalized and comfortable.

[0089] Specifically, during the operation of the air conditioner, the user may provide real-time feedback on their current feelings. For example: (1) Taking the fault diagnosis and self-repair scenario as an example, if the user reports "there is a sour smell on the east side of the office" through voice, the visual sensor will be called to scan the east side air vents; the knowledge graph will be searched to find that "sour smell + condensed water pH < 5" matches the corrosion of the condenser copper tube, and fine-tuning parameters will be generated. The corresponding repair code will be generated: increase the pH of the chilled water to 8.5. Finally, a work order can be issued to remind the user to check the corrosion inhibitor. (2) Taking the user's real-time feedback as an example, the user said: "The air conditioner always blows towards my head." Through the automatic learning of the second language model in the multimodal large language model, the user's workstation location is analyzed. It will also find out whether the air vent is crooked by looking up the maintenance record and issue a warning to notify the maintenance personnel to come with tools to repair it the next day. The second language model is trained based on a large amount of historical user feedback data and corresponding fine-tuning parameters. It can understand the user's natural language feedback and convert it into specific technical parameter adjustments, namely fine-tuning parameters. These parameters may include temperature settings, fan speed, operation mode, etc. In addition to the data provided by users through voice feedback, historical user feedback data can also include fault repair work orders, fault repair records, etc., so that the second language model can learn the solution to historical problems, so as to more accurately parse the user feedback data and generate corresponding fine-tuning parameters.

[0090] In other optional embodiments, the device further includes a second acquisition unit, a third analysis unit, and a second operation unit. The second acquisition unit is configured to acquire operating data and device status data of the air conditioner, wherein the operating data includes at least the historical operating frequency of the air conditioner, and the device status data represents the operating status of components in the air conditioner. The third analysis unit is configured to analyze the operating data and device status data using a first neural network model to obtain reliability parameters, wherein the reliability parameters represent the reliability of components in the air conditioner. The first neural network model is trained using multiple sets of third data, each set of third data including historical operating data, historical device status data, and corresponding historical reliability parameters. The second operation unit is configured to generate an alternative control program if the reliability parameter is less than a preset threshold, and execute the alternative control program to improve the reliability of the air conditioner. Through the above steps, the device predicts device reliability by analyzing device status in real time, ensuring stable operation of the air conditioner.

[0091] Specifically, the above steps aim to analyze the reliability of the air conditioner through operation data and equipment status data, which can also be understood as the remaining life. Historical equipment status data may include: (1) Control parameters: set temperature, fan speed, valve opening; the data source may be the historical log of the air conditioning control system. (2) Environmental parameters: indoor and outdoor temperature and humidity, occupant density, solar radiation; the data source may be the building BIM model and meteorological database. (3) Equipment status: compressor frequency, refrigerant pressure, current; the data source may be real-time monitoring by sensors. Historical operation data may include: Time series characteristics: energy consumption trend and load fluctuation in the past hour; the data source may be the time series database. Corresponding historical reliability parameters: (1) Direct observation values: real-time energy consumption (kW), outlet air temperature (℃), used for supervised learning of data fitting items; (2) Physical field distribution: evaporator surface temperature field, air duct velocity field, used for physical residual term constraint. (3) Equipment health indicators: compressor bearing wear (0-1), refrigerant charge, used for reliability prediction and life modeling. In the case where the reliability parameter is less than a preset threshold, an alternative control program is generated and executed to improve the reliability of the air conditioner. For example, when the predicted life of a component is lower than a safety threshold, the control strategy needs to be automatically adjusted, that is, the predicted equipment life loss is greater than the threshold, and the following alternatives are automatically generated: 1. Alternatives for dynamic adjustment of operating parameters: that is, by reducing the component load or switching the operating mode, its remaining life is extended. For example, the alternative to compressor life warning (remaining life <30 days) is to reduce the number of compressor starts and stops during peak loads during the day, which is expected to extend the life by 50%. For example, the alternative to fan bearing wear (vibration value > 5mm / s) is to reduce the fan speed from 1200rpm to 900rpm and to link the fans in adjacent areas to increase the speed to compensate for the air volume. 2. Human-machine collaboration solution: convert the technical solution into natural language suggestions and implement it in consultation with the user. For example, if the filter life is exhausted (usage time > 500 hours), the system will automatically reduce the fresh air ratio from 30% to 15% (to reduce dust entry), and then push a message to the user: "It is detected that the filter in the east area has expired, and it is recommended to replace it immediately. Temporary solution: Reduce the amount of fresh air, and the indoor CO2 concentration will rise to 800ppm (still in line with national standards). Do you agree? Let the user actively choose [Replace immediately] or [Delay until 18:00]"; if the user chooses to delay, start the backup fan and record the liability exemption clause. 3. Load transfer and redundant switching solution: This is to use the system redundancy design to transfer the load of the faulty component; for example, a multi-split refrigerant leak; the alternative is to isolate the leaking branch, redistribute the refrigerant to the normal branch, start the VRF system in the adjacent area for cross-cooling, and send an early warning: "R32 leakage has been detected, and the A3 pipeline valve has been closed."

[0092] In other optional embodiments, the second operating unit includes an output module and a generation module. The output module is configured to output multiple suggested options, enabling the user to select one of the suggested options, wherein the suggested options include at least a replacement option and a retention option. The replacement option represents replacing the air conditioner component whose reliability parameter is less than the preset threshold, and the retention option represents retaining the air conditioner component whose reliability parameter is less than the preset threshold. The generation module is configured to generate the alternative control program if the user selects the retention option. The device generates the alternative control program through the above steps, through user participation in decision-making, to balance equipment maintenance and user experience.

[0093] Specifically, multiple recommended options are output for users to choose from: when the first neural network model analyzes that the reliability parameters of one or some components are lower than the preset threshold, the system will generate and display multiple recommended options to the user. These options usually include replacement options and retention options, which allow users to make decisions based on current circumstances and preferences. Users are advised to replace components with low reliability to ensure the stability of the system and extend the service life of the equipment. Alternative control strategies are provided in the event that components are not replaced immediately, which may include reducing the load on the component, adjusting the operating mode to reduce component wear, or enabling spare components. Generate an alternative control program when the user chooses the retention option: If the user chooses the retention option, an alternative control program will be generated based on this decision, aiming to reduce the risk of component failure by changing the control strategy, while minimizing impact on user comfort and system performance.

[0094] In some optional embodiments, the device further includes a fourth analysis unit and a generation unit. The fourth analysis unit is configured to analyze the operating data and the device status data using a second neural network model to obtain a predicted energy consumption value, wherein the second neural network model is trained using multiple sets of fourth data, each set of fourth data including historical operating data, historical device status data, and corresponding historical predicted energy consumption values. The generation unit is configured to generate an energy consumption warning message to warn the air conditioner of excessive energy consumption when the predicted energy consumption value exceeds a preset energy consumption value. By predicting energy consumption values, the device can balance energy consumption with user comfort.

[0095] Specifically, the aforementioned historical operating data and historical device status data can be used to predict energy consumption through a second neural network model. For example, this model can output a one-hour energy consumption forecast, recommend optimal energy efficiency control parameters (such as chilled water temperature setpoints), and generate energy consumption warnings to alert users of high energy consumption. Furthermore, a causal model can be constructed to analyze factors that significantly impact energy consumption, such as the impact of "filter cleaning" on energy consumption, which is Δ = 0.35.

[0096] The air conditioner control device includes a processor and a memory. The first acquisition unit, the first analysis unit, and the execution unit are all stored as program units in the memory. The processor executes the program units stored in the memory to implement the corresponding functions. The above modules are all located in the same processor; alternatively, the above modules can be located in different processors in any combination.

[0097] The processor contains a kernel, which retrieves the corresponding program unit from the memory. You can set one or more kernels, and adjust the kernel parameters to improve the user experience.

[0098] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM, and the memory includes at least one memory chip.

[0099] An embodiment of the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium includes a stored program, wherein when the program is executed, the device where the computer-readable storage medium is located is controlled to execute the air conditioner control method.

[0100] Specifically, the control method of the air conditioner includes:

[0101] Step S201: acquiring user interaction data, wherein the user interaction data at least includes voice data;

[0102] Step S202: Analyzing the user interaction data using a first language model to obtain desired data, wherein the desired data is data representing the user's desired adjustment and includes at least a target temperature. The first language model is trained using multiple sets of first data, each set of first data including historical user interaction data and historical desired data.

[0103] Step S203, generate an initial control program based on the expected data, simulate the operation of the initial control program, and obtain a simulation operation result. If the simulation operation result indicates that the air conditioner is abnormal, adjust the initial control program until the simulation operation result indicates that the air conditioner is normal, obtain a target control program, and execute the target control program to control the operation of the air conditioner.

[0104] An embodiment of the present invention provides an electronic device, including a processor, a memory, and a program stored in the memory and executable on the processor. When the processor executes the program, at least the following steps are performed:

[0105] Step S201: acquiring user interaction data, wherein the user interaction data at least includes voice data;

[0106] Step S202: Analyzing the user interaction data using a first language model to obtain desired data, wherein the desired data is data representing the user's desired adjustment and includes at least a target temperature. The first language model is trained using multiple sets of first data, each set of first data including historical user interaction data and historical desired data.

[0107] Step S203, generate an initial control program based on the expected data, simulate the operation of the initial control program, and obtain a simulation operation result. If the simulation operation result indicates that the air conditioner is abnormal, adjust the initial control program until the simulation operation result indicates that the air conditioner is normal, obtain a target control program, and execute the target control program to control the operation of the air conditioner.

[0108] The devices in this article can be servers, PCs, PADs, mobile phones, etc.

[0109] The present application also provides a computer program product, including a computer program, which, when executed by a processor, implements the steps of the method described in each embodiment of the present application:

[0110] Step S201: acquiring user interaction data, wherein the user interaction data at least includes voice data;

[0111] Step S202: Analyzing the user interaction data using a first language model to obtain desired data, wherein the desired data is data representing the user's desired adjustment and includes at least a target temperature. The first language model is trained using multiple sets of first data, each set of first data including historical user interaction data and historical desired data.

[0112] Step S203, generate an initial control program based on the expected data, simulate the operation of the initial control program, and obtain a simulation operation result. If the simulation operation result indicates that the air conditioner is abnormal, adjust the initial control program until the simulation operation result indicates that the air conditioner is normal, obtain a target control program, and execute the target control program to control the operation of the air conditioner.

[0113] Obviously, those skilled in the art will appreciate that the various modules or steps of the present invention described above can be implemented using a general-purpose computing device, can be centralized on a single computing device, or can be distributed across a network of multiple computing devices. They can be implemented using program code executable by the computing device, and thus, can be stored in a storage device and executed by the computing device. In some cases, the steps shown or described herein can be performed in a different order than that shown, or can be fabricated as separate integrated circuit modules, or multiple modules or steps can be fabricated as a single integrated circuit module. Thus, the present invention is not limited to any particular combination of hardware and software.

[0114] Those skilled in the art will appreciate that the embodiments of the present application can be provided as methods, systems, or computer program products. Therefore, the present application can adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application can adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0115] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the steps in the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0116] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0117] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0118] In a typical configuration, a computing device includes one or more processors (CPUs), input / output interfaces, network interfaces, and memory.

[0119] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0120] Computer-readable media includes permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. The information can be computer-readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassettes, magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer-readable media does not include transitory computer-readable media (transitory media), such as modulated data signals and carrier waves.

[0121] It should also be noted that the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, commodity, or apparatus that includes a series of elements includes not only those elements but also other elements not explicitly listed, or includes elements inherent to such process, method, commodity, or apparatus. In the absence of further limitations, an element defined by the phrase "comprises a ..." does not exclude the presence of other identical elements in the process, method, commodity, or apparatus that includes the element.

[0122] From the above description, it can be seen that the above embodiments of the present application achieve the following technical effects:

[0123] 1) In the air conditioner control method of the present application, user interaction data is obtained, the user interaction data is analyzed through a first language model to obtain expected data, and an initial control program is generated based on the expected data. The initial control program is simulated to obtain a simulated operation result. In the case where the simulated operation result indicates that the air conditioner is abnormal, the initial control program is adjusted until the simulated operation result indicates that the air conditioner is normal, and a target control program is obtained. The target control program is executed to control the operation of the air conditioner. Compared with the prior art, in which the air conditioner is directly adjusted only according to the parameters manually set by the user, resulting in a poor user experience, the air conditioner control method of the present application can be controlled according to the user interaction data, and the operation results are also simulated to verify whether the initial control program generated by the expected data will cause the air conditioner to be abnormal, thereby avoiding the air conditioner abnormality in the process of adjustment according to the user interaction data, which brings a bad experience to the user, and no manual adjustment is required by the user, thereby improving the user experience. Therefore, it can solve the problem of poor user experience in the prior art and achieve the effect of improving user experience.

[0124] 2) In the control device of the air conditioner of the present application, user interaction data is obtained, the user interaction data is analyzed by a first language model to obtain expected data, and an initial control program is generated based on the expected data. The initial control program is simulated to obtain a simulated operation result. When the simulated operation result indicates that the air conditioner is abnormal, the initial control program is adjusted until the simulated operation result indicates that the air conditioner is normal, and a target control program is obtained. The target control program is executed to control the operation of the air conditioner. Compared with the prior art, in which the air conditioner is directly adjusted only according to the parameters manually set by the user, resulting in a poor user experience, the control device of the air conditioner of the present application can be controlled according to the user interaction data, and at the same time, the operation result is simulated to verify whether the initial control program generated by the expected data will cause the air conditioner to be abnormal, thereby avoiding the air conditioner abnormality in the process of adjustment according to the user interaction data, which brings a bad experience to the user, and no manual adjustment is required by the user, thereby improving the user experience. Therefore, it is possible to solve the problem of poor user experience in the prior art and achieve the effect of improving user experience.

[0125] The above description is merely a preferred embodiment of the present application and is not intended to limit the present application. Various modifications and variations are possible for those skilled in the art. Any modifications, equivalent substitutions, or improvements made within the spirit and principles of the present application shall be included within the scope of protection of the present application.

Claims

1. A method for controlling an air conditioner, characterized in that: include: Acquiring user interaction data, wherein the user interaction data at least includes voice data; Analyzing the user interaction data using a first language model to obtain desired data, wherein the desired data is data representing the user's desired adjustment and includes at least a target temperature, the first language model being trained by multiple sets of first data, each set of first data including: historical user interaction data and historical desired data; An initial control program is generated based on the expected data, and the initial control program is simulated and run to obtain a simulation result. When the simulation result indicates that the air conditioner is abnormal, the initial control program is adjusted until the simulation result indicates that the air conditioner is normal, and a target control program is obtained. The target control program is executed to control the operation of the air conditioner.

2. The air conditioner control method according to claim 1, characterized in that: The initial control program is simulated and run, including: Acquire structural parameters of a predetermined space and position parameters of the air conditioner, wherein the predetermined space represents a space where the air conditioner is located, and the structural parameters include at least area; A virtual operation model is constructed at least according to the structural parameters and the position parameters, and the initial control program is simulated and run on the virtual operation model, wherein the virtual operation model is used to simulate the operation of the air conditioner in the predetermined space.

3. The air conditioner control method according to claim 2, characterized in that: Constructing a virtual operation model at least according to the structural parameters and the position parameters, comprising: constructing a physical model of the predetermined space according to the structural parameters and the position parameters of the predetermined space; Determining a space conversion matrix, and converting the physical model into a virtual platform using the space conversion matrix, wherein the space conversion matrix represents a position conversion relationship between the physical model and the virtual platform, and the virtual platform includes a data transmission interface; At least the expected data is input into the virtual platform through the data transmission interface to obtain the virtual operation model.

4. The air conditioner control method according to claim 1, wherein: Generating an initial control program according to the expected data includes: Acquiring a current temperature, and if the current temperature is different from the target temperature, calculating an absolute value of a difference between the current temperature and the target temperature; An initial control strategy is generated at least according to the absolute value of the difference, and the initial control program is generated according to the initial control strategy, wherein the initial control strategy at least includes a strategy for adjusting from the current temperature to the target temperature.

5. The air conditioner control method according to claim 1, characterized in that: After executing the target control program to control the operation of the air conditioner, the method further includes: Acquiring user feedback data, wherein the user feedback data represents user feedback on adjustment results of the air conditioner; Analyzing the user feedback data using a second language model to obtain fine-tuning parameters, wherein the fine-tuning parameters represent parameters for adjusting the operation of the air conditioner, the second language model being trained using multiple sets of second data, each set of second data including: historical user feedback data and historical fine-tuning parameters; The operation of the air conditioner is controlled according to the fine-tuning parameters to meet the needs of the user.

6. The air conditioner control method according to claim 1, characterized in that: The method further comprises: Acquiring operating data and device status data of the air conditioner, wherein the operating data at least includes a historical operating frequency of the air conditioner, and the device status data indicates an operating status of a component in the air conditioner; Analyzing the operating data and the device status data using a first neural network model to obtain a reliability parameter, wherein the reliability parameter represents the reliability of a component in the air conditioner, the first neural network model being trained using multiple sets of third data, each set of the third data including: historical operating data, historical device status data, and a corresponding historical reliability parameter; When the reliability parameter is less than a preset threshold, an alternative control program is generated and executed to improve the reliability of the air conditioner.

7. The air conditioner control method according to claim 6, characterized in that: Generate alternative control procedures, including: Outputting a plurality of suggestion options so that the user selects one of the suggestion options, wherein the suggestion options include at least a replace option and a retain option, wherein the replace option indicates replacing the air conditioner component whose reliability parameter is less than the preset threshold, and the retain option indicates retaining the air conditioner component whose reliability parameter is less than the preset threshold; In case the user selects the retain option, the alternative control program is generated.

8. The air conditioner control method according to claim 6, characterized in that: The method further comprises: analyzing the operating data and the device status data using a second neural network model to obtain a predicted energy consumption value, wherein the second neural network model is trained using multiple sets of fourth data, each set of the fourth data including: historical operating data, historical device status data, and corresponding historical predicted energy consumption values; When the predicted energy consumption value is greater than the preset energy consumption value, energy consumption warning information is generated to warn the air conditioner of high energy consumption.

9. A control device for an air conditioner, characterized in that: include: a first acquiring unit, configured to acquire user interaction data, wherein the user interaction data at least includes voice data; a first analyzing unit, configured to analyze the user interaction data using a first language model to obtain expected data, wherein the expected data is data representing the user's adjustment expectation and includes at least a target temperature, and the first language model is obtained by training multiple sets of first data, each set of first data including historical user interaction data and historical expected data; An execution unit is used to generate an initial control program based on the expected data, simulate the operation of the initial control program, obtain a simulation operation result, and when the simulation operation result indicates that the air conditioner is abnormal, adjust the initial control program until the simulation operation result indicates that the air conditioner is normal, obtain a target control program, and execute the target control program to control the operation of the air conditioner.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium includes a stored program, wherein when the program is executed, the device where the computer-readable storage medium is located is controlled to execute the air conditioner control method according to any one of claims 1 to 8.

11. An electronic device, characterized in that: include: One or more processors, a memory, and one or more programs, wherein the one or more programs are stored in the memory and are configured to be executed by the one or more processors, and the one or more programs include a method for executing the control method of the air conditioner according to any one of claims 1 to 8.

Images