Large-model-based intelligent energy-saving control method and system for large building

Abstract

The invention provides an intelligent energy-saving control method and system for a large building based on a large model. The intelligent energy-saving control method for the large-scale building based on the large model comprises the following steps: controlling a sensor group to collect environment information data and energy consumption parameters of the large-scale building in real time; according to the environment information data and the energy consumption parameters of the large-scale building, obtaining a predicted value of the energy consumption load of the building; according to the predicted value of the building energy consumption load and an expected target parameter input by a user, obtaining an operation parameter of current energy consumption equipment, and according to the operation parameter of the current energy consumption equipment, adjusting an actual parameter of the energy consumption equipment to obtain an adjusted real-time operation parameter of the energy consumption equipment; and a control demand included in a natural language input by a user is converted into data information meeting input of the deep neural network module and the intelligent optimization module. The system comprises modules corresponding to the steps of the method.

Description

Technical Field

[0001] The invention proposes a large-scale building intelligent energy-saving control method and system based on a large model, belonging to the technical field of building intelligent energy-saving control. Background Art

[0002] At present, energy-saving control of large buildings is often based on maintenance personnel manually adjusting the operating parameters of key energy-consuming equipment, such as central air conditioners and electromechanical systems, during daily maintenance, thereby optimizing energy saving. However, the following technical problems still exist:

[0003] Complicated control: Large buildings require different energy-consuming equipment operating parameters in different areas according to different external conditions such as different seasons, changes in use, changes in traffic flow, and the influence of weather. For example, different areas of a building require different room temperatures and light intensities depending on external conditions. If optimization is achieved through manual adjustment, the complexity will be unacceptable.

[0004] Manual control is imprecise: Maintenance personnel need to adjust the air conditioning system, lighting system, etc. based on their personal experience, which makes it difficult to achieve efficient and optimized adjustment.

[0005] Professional knowledge is required: The control of large equipment systems such as central air conditioning and lighting systems requires the management personnel to have professional knowledge of the system. If the maintenance personnel do not have enough professional knowledge reserves, they will not be able to effectively optimize the system parameters. Summary of the invention

[0006] The present invention provides a large-scale building intelligent energy-saving control method and system based on a large model to solve the above-mentioned technical problems existing in the prior art. The technical solutions adopted are as follows:

[0007] A large-scale building intelligent energy-saving control method based on a large model, the large-scale building intelligent energy-saving control method based on a large model comprises:

[0008] Control sensor groups to collect environmental information data and energy consumption parameters of large buildings in real time;

[0009] Obtaining a predicted value of the building's energy consumption load based on the environmental information data and energy consumption parameters of the large building;

[0010] Acquire the operating parameters of the current energy-consuming equipment according to the predicted value of the energy consumption load of the building and the expected target parameters input by the user, and adjust the actual parameters of the energy-consuming equipment according to the operating parameters of the current energy-consuming equipment to obtain the adjusted real-time operating parameters of the energy-consuming equipment;

[0011] The control requirements contained in the natural language input by the user are converted into data information that conforms to the input of the deep neural network module and the intelligent optimization module.

[0012] Furthermore, the control sensor group collects environmental information data and energy consumption parameters of large buildings in real time, including:

[0013] Extracting the data collection frequency corresponding to the environmental sensor group in the large building; wherein the environmental sensor group includes a temperature sensor and a humidity sensor;

[0014] Performing data collection control on the environmental sensor group according to the data collection frequency corresponding to the environmental sensor group;

[0015] Extracting the data collection frequency corresponding to the energy consumption sensor group in the large building; wherein the energy consumption sensor group includes an electricity consumption collection sensor and a water consumption collection sensor, and the electricity consumption collection sensor includes but is not limited to an electricity monitoring sensor and / or an electricity meter, and the water consumption collection sensor includes but is not limited to a water flow sensor and / or a water meter;

[0016] Data collection is controlled for the energy consumption sensor group according to the data collection frequency corresponding to the energy consumption sensor group.

[0017] Furthermore, obtaining a predicted value of the building energy consumption load according to the environmental information data and energy consumption parameters of the large building includes:

[0018] Users input current environment data into the deep neural network model through natural language;

[0019] The deep neural network model obtains a predicted value of the building energy consumption load according to the current environmental data.

[0020] Furthermore, the operating parameters of the current energy-consuming equipment are obtained according to the predicted value of the energy consumption load of the building and the expected target parameters input by the user, and the actual parameters of the energy-consuming equipment are adjusted according to the operating parameters of the current energy-consuming equipment to obtain the adjusted real-time operating parameters of the energy-consuming equipment, including:

[0021] Extracting the predicted value of the building energy consumption load and the expected target parameters input by the user; wherein the expected target parameters input by the user include a target temperature parameter and a target humidity parameter;

[0022] Obtaining an energy consumption load value of the building energy consumption load according to the expected target parameter input by the user;

[0023] The energy consumption load value is obtained by the following formula:

[0024]

[0025] Among them, E f Indicates the energy consumption load value; E0 indicates the preset energy consumption load value benchmark value; T c Indicates the temperature difference between the target temperature parameter input by the user and the current indoor temperature value; H c Indicates the humidity difference between the target humidity parameter input by the user and the current indoor humidity value; T d Indicates the current indoor temperature value; T k represents a preset temperature reference value; δ represents an adjustment coefficient, and the range of the adjustment coefficient is 0.23-0.41; w 01 、w 02 and w 03 Respectively represent the preset first weight value, second weight value and third weight value;

[0026] Comparing the energy load value with a predicted value of the building energy load;

[0027] When the energy consumption load value does not exceed the predicted value of the building energy consumption load, the operating parameters of the current energy consumption equipment are automatically set according to the expected target parameters input by the user, wherein the former energy consumption equipment includes but is not limited to air conditioners, ventilation coefficients, humidifiers and other equipment that can adjust temperature and humidity parameters;

[0028] When the energy consumption load value exceeds the predicted value of the building energy consumption load, and the load value of the energy consumption load value exceeding the building energy consumption load is lower than the preset load threshold, the operating parameters of the current energy consuming equipment are automatically set according to the expected target parameters input by the user;

[0029] The preset load threshold is obtained by the following formula:

[0030]

[0031] Among them, E t Indicates the preset load threshold; E y0 Indicates the preset initial value of the load threshold; E f Indicates the energy consumption load value; E0 indicates the preset energy consumption load value benchmark value; T c Indicates the temperature difference between the target temperature parameter input by the user and the current indoor temperature value; H c Indicates the humidity difference between the target humidity parameter input by the user and the current indoor humidity value; T max Indicates the maximum value of the current indoor temperature change; H max Indicates the current maximum indoor humidity change; k 01 Indicates the preset environmental parameter impact weight value; k 02Indicates the preset energy consumption impact weight value;

[0032] When the energy consumption load value exceeds the predicted value of the building energy consumption load, and the energy consumption load value exceeds the load value of the building energy consumption load by not less than the preset load threshold, the operating parameters of the current energy-consuming equipment are automatically set according to the temperature parameters and humidity parameters corresponding to the predicted value of the building energy consumption load.

[0033] Furthermore, the control requirements contained in the natural language input by the user are converted into data information that conforms to the input of the deep neural network module and the intelligent optimization module, including:

[0034] Receive natural language input from a user terminal in real time;

[0035] The agent model is used to parse the natural language input by the user terminal to obtain the control demand information contained in the natural language, and the control demand information is converted into legal parameters that meet the input of the deep neural network module and the intelligent optimization module;

[0036] Input the legal parameters that meet the requirements of the deep neural network module and the intelligent optimization module into the deep neural network module and the intelligent optimization module respectively;

[0037] The real-time data collection sensor group collects environmental information data and energy consumption parameters of large buildings in real time, and converts the environmental information data and energy consumption parameters of the large buildings into natural language to feed back to the user terminal.

[0038] A large-scale building intelligent energy-saving control system based on a large model, the large-scale building intelligent energy-saving control system based on a large model comprises:

[0039] Data acquisition control module, used to control the sensor group to collect environmental information data and energy consumption parameters of large buildings in real time;

[0040] A deep neural network module, used for obtaining a predicted value of the building energy consumption load based on the environmental information data and energy consumption parameters of the large building;

[0041] An intelligent optimization module, used to obtain the operating parameters of the current energy-consuming equipment according to the predicted value of the energy consumption load of the building and the expected target parameters input by the user, and adjust the actual parameters of the energy-consuming equipment according to the operating parameters of the current energy-consuming equipment to obtain the adjusted real-time operating parameters of the energy-consuming equipment;

[0042] The large model Agent module is used to convert the control requirements contained in the natural language input by the user into data information that conforms to the input of the deep neural network module and the intelligent optimization module.

[0043] Furthermore, the data acquisition control module includes:

[0044] A first data acquisition frequency extraction module is used to extract the data acquisition frequency corresponding to the environmental sensor group in the large building; wherein the environmental sensor group includes a temperature sensor and a humidity sensor;

[0045] A first data acquisition control module, used for performing data acquisition control on the environmental sensor group according to the data acquisition frequency corresponding to the environmental sensor group;

[0046] A second data acquisition frequency extraction module is used to extract the data acquisition frequency corresponding to the energy consumption sensor group in the large building; wherein the energy consumption sensor group includes an electricity consumption acquisition sensor and a water consumption acquisition sensor, and the electricity consumption acquisition sensor includes but is not limited to an electricity monitoring sensor and / or an electricity meter, and the water consumption acquisition sensor includes but is not limited to a water flow sensor and / or a water meter;

[0047] The second data acquisition control module is used to control the data acquisition of the energy consumption sensor group according to the data acquisition frequency corresponding to the energy consumption sensor group.

[0048] Furthermore, the deep neural network module comprises:

[0049] A data input module is used for users to input current environment data into the deep neural network model through natural language;

[0050] A prediction value acquisition module is used for the deep neural network model to obtain a prediction value of the building energy consumption load according to the current environmental data.

[0051] Furthermore, the intelligent optimization module includes:

[0052] An expected target parameter extraction module is used to extract the predicted value of the building energy consumption load and the expected target parameters input by the user; wherein the expected target parameters input by the user include a target temperature parameter and a target humidity parameter;

[0053] An energy consumption load value acquisition module is used to acquire the energy consumption load value of the building energy consumption load according to the expected target parameters input by the user;

[0054] The energy consumption load value is obtained by the following formula:

[0055]

[0056] Among them, E f Indicates the energy consumption load value; E0 indicates the preset energy consumption load value benchmark value; T cIndicates the temperature difference between the target temperature parameter input by the user and the current indoor temperature value; H c Indicates the humidity difference between the target humidity parameter input by the user and the current indoor humidity value; T d Indicates the current indoor temperature value; T k represents a preset temperature reference value; δ represents an adjustment coefficient, and the range of the adjustment coefficient is 0.23-0.41; w 01 、w 02 and w 03 Respectively represent the preset first weight value, second weight value and third weight value;

[0057] A load value comparison module, used to compare the energy consumption load value with the predicted value of the building energy consumption load;

[0058] A first operating parameter setting module, used for automatically setting the operating parameters of the current energy-consuming equipment according to the expected target parameters input by the user when the energy consumption load value does not exceed the predicted value of the building energy consumption load, wherein the front energy-consuming equipment includes but is not limited to air conditioners, ventilation coefficients, humidifiers and other equipment capable of adjusting temperature and humidity parameters;

[0059] A second operating parameter setting module is used to automatically set the operating parameters of the current energy-consuming equipment according to the expected target parameters input by the user when the energy consumption load value exceeds the predicted value of the building energy consumption load and the load value of the energy consumption load value exceeding the building energy consumption load is lower than a preset load threshold;

[0060] The preset load threshold is obtained by the following formula:

[0061]

[0062] Among them, E t Indicates the preset load threshold; E y0 Indicates the preset initial value of the load threshold; E f Indicates the energy consumption load value; E0 indicates the preset energy consumption load value benchmark value; T c Indicates the temperature difference between the target temperature parameter input by the user and the current indoor temperature value; H c Indicates the humidity difference between the target humidity parameter input by the user and the current indoor humidity value; T max Indicates the maximum value of the current indoor temperature change; H max Indicates the current maximum indoor humidity change; k 01 Indicates the preset environmental parameter impact weight value; k 02 Indicates the preset energy consumption impact weight value;

[0063] The third operating parameter setting module is used to automatically set the operating parameters of the current energy-consuming equipment according to the temperature parameters and humidity parameters corresponding to the predicted value of the energy consumption load of the building when the energy consumption load value exceeds the predicted value of the energy consumption load of the building and the load value of the energy consumption load exceeding the building energy consumption load is not lower than a preset load threshold.

[0064] Furthermore, the large model Agent module includes:

[0065] A natural language receiving module, used to receive the natural language input by the user terminal in real time;

[0066] An information conversion module, used to parse the natural language input by the user terminal using the Agent model to obtain the control demand information contained in the natural language, and convert the control demand information into legal parameters that meet the input of the deep neural network module and the intelligent optimization module;

[0067] A legal parameter input module, used to input the legal parameters that meet the requirements of the deep neural network module and the intelligent optimization module into the deep neural network module and the intelligent optimization module respectively;

[0068] The information feedback module is used to collect environmental information data and energy consumption parameters of large buildings in real time using a real-time collection sensor group, and convert the environmental information data and energy consumption parameters of the large buildings into natural language to feed back to the user terminal.

[0069] Beneficial effects of the present invention:

[0070] The large-scale building intelligent energy-saving control method and system based on a large model proposed in the embodiment of the present invention have the following beneficial effects:

[0071] Simple control: Users only need to put forward certain specific requirements to achieve the lowest overall energy consumption of the building while meeting the user's requirements.

[0072] Precise control: Based on deep learning algorithms and intelligent optimization algorithms, the optimization parameters with the lowest overall energy consumption are obtained, with a higher degree of accuracy than the parameters adjusted based on experience.

[0073] Friendly to non-professionals: The control process can use natural language, which is convenient for managers who do not have professional equipment knowledge to use. BRIEF DESCRIPTION OF THE DRAWINGS

[0074] Figure 1 The principle of the method of the present invention Figure 1 ;

[0075] Figure 2 The principle of the method of the present invention Figure 2 ;

[0076] Figure 3 The principle of the method of the present invention Figure 3 ;

[0077] Figure 4 Schematic diagram of system functions of the system of the present invention. DETAILED DESCRIPTION

[0078] The preferred embodiments of the present invention are described below in conjunction with the accompanying drawings. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present invention, and are not used to limit the present invention.

[0079] The embodiment of the present invention proposes an intelligent energy-saving control method for large buildings based on a large model, such as Figures 1 to 3 As shown, the large-scale building intelligent energy-saving control method based on the large model includes:

[0080] S1, control the sensor group to collect environmental information data and energy consumption parameters of large buildings in real time;

[0081] S2. Obtaining a predicted value of the building's energy consumption load according to the environmental information data and energy consumption parameters of the large building;

[0082] S3, obtaining the operating parameters of the current energy-consuming equipment according to the predicted value of the building energy consumption load and the expected target parameters input by the user, and adjusting the actual parameters of the energy-consuming equipment according to the operating parameters of the current energy-consuming equipment to obtain the adjusted real-time operating parameters of the energy-consuming equipment;

[0083] S4. Convert the control requirements contained in the natural language input by the user into data information that conforms to the input of the deep neural network module and the intelligent optimization module.

[0084] The working principle of the above technical solution is: through the sensor group deployed in the large building, the environmental information data (such as temperature, humidity, light intensity, etc.) and energy consumption parameters (such as the consumption of electricity, water, gas, etc.) of the building are collected in real time. The collected environmental information data and energy consumption parameters are analyzed by a large model (which may be a machine learning model or a deep learning model) to predict the future energy consumption load of the building. This prediction value is based on a comprehensive analysis of historical data and current real-time data. According to the predicted energy consumption load and the expected target parameters input by the user (such as energy saving goals, comfort requirements, etc.), the optimal operating parameters of the current energy-consuming equipment (such as air conditioning, lighting, elevators, etc.) are calculated. Then, according to these calculated operating parameters, the actual parameters of the energy-consuming equipment are adjusted to achieve the dual goals of energy saving and meeting user needs. After adjustment, the system will continue to monitor the real-time operating parameters of the energy-consuming equipment to ensure that they meet expectations. Users can input control requirements through natural language, such as "let the temperature of the conference room drop to 24 degrees." The system will convert these natural language inputs into data information that conforms to the input of the deep neural network module and the intelligent optimization module. This usually involves natural language processing (NLP) techniques such as semantic parsing and entity recognition. The converted data will be used for further analysis and optimization to achieve the user's control needs.

[0085] The effect of the above technical solution is: by predicting energy consumption load and optimizing the operating parameters of energy-consuming equipment, the energy consumption of buildings can be significantly reduced and energy utilization efficiency can be improved. The system can adjust the operation of energy-consuming equipment according to the expected target parameters input by the user, so as to meet the user's comfort requirements while ensuring energy saving. Through natural language processing and deep learning technology, the system can understand and respond to the user's natural language control needs and realize intelligent building management. Real-time data collection and analysis ensure that the system can accurately predict energy consumption load and adjust the operating parameters of energy-consuming equipment in time to adapt to changing environmental conditions and user needs. The application of large models enables the system to have powerful data processing and analysis capabilities, and is easy to expand to adapt to larger-scale buildings and more complex control needs. At the same time, the system also supports users to make customized settings and adjustments according to actual needs.

[0086] In summary, the large-scale building intelligent energy-saving control method based on large models realizes the intelligent management and optimization of energy consumption of large buildings by comprehensively using sensor technology, big data processing, machine learning, natural language processing and other technologies, and has significant energy-saving effects and improved user experience.

[0087] In one embodiment of the present invention, a sensor group is controlled to collect environmental information data and energy consumption parameters of a large building in real time, including:

[0088] S101, extracting the data collection frequency corresponding to the environmental sensor group in the large building; wherein the environmental sensor group includes a temperature sensor and a humidity sensor;

[0089] S102, performing data collection control on the environmental sensor group according to the data collection frequency corresponding to the environmental sensor group;

[0090] S103, extracting the data collection frequency corresponding to the energy consumption sensor group in the large building; wherein the energy consumption sensor group includes an electricity consumption collection sensor and a water consumption collection sensor, and the electricity consumption collection sensor includes but is not limited to an electricity monitoring sensor and / or an electricity meter, and the water consumption collection sensor includes but is not limited to a water flow sensor and / or a water meter;

[0091] S104: Controlling data collection of the energy consumption sensor group according to the data collection frequency corresponding to the energy consumption sensor group.

[0092] The working principle of the above technical solution is as follows: First, the system needs to know the data collection frequency of each sensor. For the environmental sensor group (such as temperature sensor and humidity sensor), the system extracts the corresponding data collection frequency. Similarly, for the energy consumption sensor group (such as power consumption collection sensor and water consumption collection sensor), the system also extracts the corresponding data collection frequency. These frequencies are set according to the type of sensor, accuracy requirements and actual needs of the building. After extracting the data collection frequency, the system controls the data collection of the sensor group according to these frequencies. For the environmental sensor group, the system will regularly collect environmental information data such as temperature and humidity according to the set frequency. For the energy consumption sensor group, the system will also collect energy consumption parameters such as power consumption and water consumption according to the set frequency. During the data collection process, the system may use various communication technologies (such as wireless or wired communication) to transmit data and ensure the accuracy and integrity of the data. In addition, the system may also need to pre-process the data, such as denoising, smoothing, missing value filling and outlier detection, to improve the reliability of the data and the accuracy of subsequent analysis.

[0093] The effect of the above technical solution is: by collecting environmental information data and energy consumption parameters of large buildings in real time, the system can monitor the operation status of the building in real time. This helps to promptly discover and solve potential problems such as energy waste and equipment failure. The system can analyze the energy consumption trend and energy-saving potential of the building based on the data collected in real time. By optimizing equipment operating parameters and adjusting energy distribution, the system can achieve the goal of energy saving and consumption reduction and reduce the operating costs of the building. The automated data collection and control process reduces the need for manual intervention and improves the efficiency of building management. Managers can intuitively understand the operating status of the building through the system interface and remotely control and adjust it as needed. The real-time collected data provides rich information support for the operation and management of the building. These data can be used in decision-making processes such as formulating energy management plans and optimizing equipment operation strategies to help buildings achieve more efficient and sustainable operations.

[0094] In summary, this technical solution realizes real-time monitoring and optimization control of building operation status by collecting environmental information data and energy consumption parameters of large buildings in real time. This not only helps to save energy and reduce consumption and improve management efficiency, but also provides strong decision-making support for building operation and management.

[0095] In one embodiment of the present invention, obtaining a predicted value of a building's energy consumption load according to the environmental information data and energy consumption parameters of the large building includes:

[0096] S201, the user inputs current environment data into the deep neural network model through natural language;

[0097] S202. The deep neural network model obtains a predicted value of the building energy consumption load according to the current environmental data.

[0098] The working principle of the above technical solution is as follows: the user describes the current environmental data, such as temperature, humidity, etc., in natural language, and inputs this information into the deep neural network model. The deep neural network model receives the natural language data input by the user and first parses and understands the data. This usually involves natural language processing (NLP) technology, such as text classification, entity recognition, etc., to ensure that the model can accurately capture the user's intentions and the environmental information described. Once the input data is understood, the model will use the previously learned relationship between the building energy load and environmental data to further process and analyze the data. This may involve steps such as data normalization and feature extraction to convert the raw data into a format that the model can understand. Finally, based on the processed data, the model uses a deep learning algorithm (such as a multi-layer perceptron MLP, a recurrent neural network RNN, a long short-term memory network LSTM, etc.) to make predictions and output the predicted value of the building energy load.

[0099] The effect of the above technical solution is: by using a deep neural network model, the technical solution can capture the complex relationship between the building energy load and environmental data, thereby improving the accuracy of the prediction. Users can interact with the model through natural language without having professional technical background or knowledge. This greatly reduces the threshold for use and enhances the user experience. The technical solution can receive environmental data input by the user in real time and quickly output the predicted value of the energy load. This provides strong support for the intelligent management of buildings and helps to achieve efficient use and conservation of energy. The deep neural network model has strong learning ability and adaptability, and can be continuously optimized and improved as new data is continuously added. This means that the technical solution has good scalability and flexibility, and can adapt to the actual needs of different buildings and environments.

[0100] In summary, this technical solution achieves accurate prediction of building energy load by using a deep neural network model to understand and analyze the current environmental data in natural language input by users. This not only improves the accuracy of prediction and user experience, but also provides strong support for intelligent management of buildings and efficient use of energy.

[0101] In one embodiment of the present invention, the operating parameters of the current energy-consuming equipment are obtained according to the predicted value of the energy consumption load of the building and the expected target parameters input by the user, and the actual parameters of the energy-consuming equipment are adjusted according to the operating parameters of the current energy-consuming equipment to obtain the adjusted real-time operating parameters of the energy-consuming equipment, including:

[0102] S301, extracting the predicted value of the building energy consumption load and the expected target parameters input by the user; wherein the expected target parameters input by the user include a target temperature parameter and a target humidity parameter;

[0103] S302, obtaining the energy consumption load value of the building energy consumption load according to the expected target parameter input by the user;

[0104] The energy consumption load value is obtained by the following formula:

[0105]

[0106] Among them, E f Indicates the energy consumption load value; E0 indicates the preset energy consumption load value benchmark value; T c Indicates the temperature difference between the target temperature parameter input by the user and the current indoor temperature value; H c Indicates the humidity difference between the target humidity parameter input by the user and the current indoor humidity value; T d Indicates the current indoor temperature value; T krepresents a preset temperature reference value; δ represents an adjustment coefficient, and the range of the adjustment coefficient is 0.23-0.41; w 01 、w 02 and w 03 Respectively represent the preset first weight value, second weight value and third weight value;

[0107] S303, comparing the energy consumption load value with the predicted value of the building energy consumption load;

[0108] S304: When the energy consumption load value does not exceed the predicted value of the building energy consumption load, the operating parameters of the current energy consumption equipment are automatically set according to the expected target parameters input by the user, wherein the former energy consumption equipment includes but is not limited to air conditioners, ventilation coefficients, humidifiers and other equipment capable of adjusting temperature and humidity parameters;

[0109] S305, when the energy consumption load value exceeds the predicted value of the building energy consumption load, and the load value of the energy consumption load value exceeding the building energy consumption load is lower than the preset load threshold, the operating parameters of the current energy consuming equipment are automatically set according to the expected target parameters input by the user;

[0110] The preset load threshold is obtained by the following formula:

[0111]

[0112] Among them, E t Indicates the preset load threshold; E y0 Indicates the preset initial value of the load threshold; E f Indicates the energy consumption load value; E0 indicates the preset energy consumption load value benchmark value; T c Indicates the temperature difference between the target temperature parameter input by the user and the current indoor temperature value; H c Indicates the humidity difference between the target humidity parameter input by the user and the current indoor humidity value; T max Indicates the maximum value of the current indoor temperature change; H max Indicates the current maximum indoor humidity change; k 01 Indicates the preset environmental parameter impact weight value; k 02 Indicates the preset energy consumption impact weight value;

[0113] S306. When the energy consumption load value exceeds the predicted value of the energy consumption load of the building, and the load value of the energy consumption load exceeding the building energy consumption load is not lower than the preset load threshold, the operating parameters of the current energy-consuming equipment are automatically set according to the temperature parameters and humidity parameters corresponding to the predicted value of the energy consumption load of the building.

[0114] The working principle of the above technical solution is as follows: the system first extracts the predicted value of the building's energy load, which is obtained through deep learning or other prediction models based on the previous environmental information data and energy consumption parameters. At the same time, the system also extracts the expected target parameters entered by the user, such as target temperature parameters and target humidity parameters. Based on the target temperature parameters and target humidity parameters entered by the user, as well as the actual values ​​of the current indoor temperature and humidity, the system calculates an energy load value (Ef). This calculation process involves a formula that takes into account the temperature difference (Tc), the humidity difference (Hc), the preset energy load value reference value (E0), the adjustment coefficient (δ), and the first, second and third weight values ​​(w01, w02, w03).

[0115] The system compares the calculated energy load value with the predicted value of the building's energy load. If the energy load value does not exceed the predicted value, or if it exceeds but the excess load value is lower than the preset load threshold (Et), the system automatically sets the operating parameters of the current energy-consuming equipment according to the expected target parameters entered by the user, such as adjusting the temperature and humidity parameters of equipment such as air conditioners, ventilation coefficients, and humidifiers. If the energy load value exceeds the predicted value and the excess load value is not lower than the preset load threshold, the system automatically sets the operating parameters of the current energy-consuming equipment according to the temperature parameters and humidity parameters corresponding to the predicted value of the building's energy load to ensure that the building's energy consumption is not too high.

[0116] The effect of the above technical solution is: the technical solution can intelligently adjust the operating parameters of energy-consuming equipment according to the predicted value of the building's energy consumption load and the expected target parameters input by the user, thereby improving energy utilization efficiency. By comparing the energy consumption load value and the predicted value, and considering the load threshold, the system can avoid excessive energy consumption and achieve energy saving effects. The system can adjust the operation of energy-consuming equipment according to the target temperature and humidity parameters input by the user to meet the user's comfort requirements. The formulas and weight values ​​in the technical solution can be adjusted and optimized according to actual conditions to meet the needs of different buildings and environments. At the same time, the system also supports the addition of more sensors and devices to expand its functions and application scope. The automated and intelligent adjustment process reduces the need for manual intervention and improves the efficiency of building management.

[0117] In summary, this technical solution has achieved both energy-saving effects and user comfort by intelligently adjusting the operating parameters of energy-consuming equipment. At the same time, its flexibility and scalability also provide possibilities for future optimization and expansion.

[0118] In one embodiment of the present invention, the control requirements contained in the natural language input by the user are converted into data information that meets the input of the deep neural network module and the intelligent optimization module, including:

[0119] S401, receiving natural language input from a user terminal in real time;

[0120] S402, using the Agent model to parse the natural language input by the user terminal to obtain the control requirement information contained in the natural language, and convert the control requirement information into legal parameters that meet the input of the deep neural network module and the intelligent optimization module;

[0121] S403, inputting the legal parameters that meet the requirements of the deep neural network module and the intelligent optimization module into the deep neural network module and the intelligent optimization module respectively;

[0122] S404: The real-time data collection sensor group collects environmental information data and energy consumption parameters of large buildings in real time, and converts the environmental information data and energy consumption parameters of the large buildings into natural language to feed back to the user terminal.

[0123] The working principle of the above technical solution is as follows: the system receives natural language instructions input by users in real time through user terminals (such as mobile phones, computers, voice assistants, etc.). These instructions may include control requirements for building environment (such as temperature, humidity), or optimization requirements for energy consumption parameters. The natural language input by users is parsed using an Agent model (an intelligent agent that can interact on behalf of users or other entities). The Agent model understands user intentions through natural language processing (NLP) technology and extracts control requirement information contained in natural language. Subsequently, the Agent model converts these control requirement information into legal parameters that meet the input requirements of the deep neural network module and the intelligent optimization module. These parameters may include temperature set values, humidity set values, energy consumption optimization targets, etc. The converted legal parameters are input into the deep neural network module and the intelligent optimization module respectively. The deep neural network module may be used to predict the energy consumption load of the building, evaluate the environmental comfort, etc.; while the intelligent optimization module may be used to optimize energy consumption allocation and adjust equipment operation strategies according to the prediction results and user needs. The system collects environmental information data and energy consumption parameters of large buildings provided by the sensor group in real time. These data include temperature, humidity, light intensity, power consumption, water consumption, etc. After being processed, the collected data is converted into natural language form and fed back to the user through the user terminal. In this way, the user can intuitively understand the current environmental conditions and energy consumption of the building, as well as whether the control requirements previously entered are effectively executed.

[0124] The effect of the above technical solution is: this technical solution realizes the intelligent interaction between users and building environment and energy consumption management system through natural language processing and Agent model. Users can easily control the building environment and optimize energy consumption through natural language instructions without professional knowledge. The system can accurately extract the control requirements according to the natural language instructions input by the user, and convert them into legal parameters to input into the deep neural network module and intelligent optimization module. This ensures that the system can accurately execute the user's control requirements and improve the comfort and energy efficiency of the building. The system can collect environmental information data and energy consumption parameters of the building in real time, and convert them into natural language form to feedback to the user. This helps users to understand the operating status of the building in a timely manner and make adjustments as needed. Through the collaborative work of the deep neural network module and the intelligent optimization module, the system can achieve efficient optimization of the building's energy consumption. This helps to reduce the operating costs of the building and improve energy efficiency. The technical solution has good scalability. With the continuous development of technology, more sensors, smart devices and optimization algorithms can be further introduced to expand the functions and application scope of the system.

[0125] In summary, this technical solution provides users with a more convenient, efficient and comfortable building environment and energy management experience through the advantages of intelligent interaction, precise control, real-time feedback, efficient optimization and scalability.

[0126] The embodiment of the present invention proposes a large-scale building intelligent energy-saving control system based on a large model, such as Figure 4 As shown, the large-scale building intelligent energy-saving control system based on the large model includes:

[0127] Data acquisition control module, used to control the sensor group to collect environmental information data and energy consumption parameters of large buildings in real time;

[0128] A deep neural network module, used for obtaining a predicted value of the building energy consumption load based on the environmental information data and energy consumption parameters of the large building;

[0129] An intelligent optimization module, used to obtain the operating parameters of the current energy-consuming equipment according to the predicted value of the energy consumption load of the building and the expected target parameters input by the user, and adjust the actual parameters of the energy-consuming equipment according to the operating parameters of the current energy-consuming equipment to obtain the adjusted real-time operating parameters of the energy-consuming equipment;

[0130] The large model Agent module is used to convert the control requirements contained in the natural language input by the user into data information that conforms to the input of the deep neural network module and the intelligent optimization module.

[0131] The working principle of the above technical solution is: through the sensor group deployed in the large building, the environmental information data (such as temperature, humidity, light intensity, etc.) and energy consumption parameters (such as the consumption of electricity, water, gas, etc.) of the building are collected in real time. The collected environmental information data and energy consumption parameters are analyzed by a large model (which may be a machine learning model or a deep learning model) to predict the future energy consumption load of the building. This prediction value is based on a comprehensive analysis of historical data and current real-time data. According to the predicted energy consumption load and the expected target parameters input by the user (such as energy saving goals, comfort requirements, etc.), the optimal operating parameters of the current energy-consuming equipment (such as air conditioning, lighting, elevators, etc.) are calculated. Then, according to these calculated operating parameters, the actual parameters of the energy-consuming equipment are adjusted to achieve the dual goals of energy saving and meeting user needs. After adjustment, the system will continue to monitor the real-time operating parameters of the energy-consuming equipment to ensure that they meet expectations. Users can input control requirements through natural language, such as "let the temperature of the conference room drop to 24 degrees." The system will convert these natural language inputs into data information that conforms to the input of the deep neural network module and the intelligent optimization module. This usually involves natural language processing (NLP) techniques such as semantic parsing and entity recognition. The converted data will be used for further analysis and optimization to achieve the user's control needs.

[0132] The effect of the above technical solution is: by predicting energy consumption load and optimizing the operating parameters of energy-consuming equipment, the energy consumption of buildings can be significantly reduced and energy utilization efficiency can be improved. The system can adjust the operation of energy-consuming equipment according to the expected target parameters input by the user, so as to meet the user's comfort requirements while ensuring energy saving. Through natural language processing and deep learning technology, the system can understand and respond to the user's natural language control needs and realize intelligent building management. Real-time data collection and analysis ensure that the system can accurately predict energy consumption load and adjust the operating parameters of energy-consuming equipment in time to adapt to changing environmental conditions and user needs. The application of large models enables the system to have powerful data processing and analysis capabilities, and is easy to expand to adapt to larger-scale buildings and more complex control needs. At the same time, the system also supports users to make customized settings and adjustments according to actual needs.

[0133] In summary, the large-scale building intelligent energy-saving control method based on large models realizes the intelligent management and optimization of energy consumption of large buildings by comprehensively using sensor technology, big data processing, machine learning, natural language processing and other technologies, and has significant energy-saving effects and improved user experience.

[0134] In one embodiment of the present invention, the data acquisition control module includes:

[0135] A first data acquisition frequency extraction module is used to extract the data acquisition frequency corresponding to the environmental sensor group in the large building; wherein the environmental sensor group includes a temperature sensor and a humidity sensor;

[0136] A first data acquisition control module, used for performing data acquisition control on the environmental sensor group according to the data acquisition frequency corresponding to the environmental sensor group;

[0137] A second data acquisition frequency extraction module is used to extract the data acquisition frequency corresponding to the energy consumption sensor group in the large building; wherein the energy consumption sensor group includes an electricity consumption acquisition sensor and a water consumption acquisition sensor, and the electricity consumption acquisition sensor includes but is not limited to an electricity monitoring sensor and / or an electricity meter, and the water consumption acquisition sensor includes but is not limited to a water flow sensor and / or a water meter;

[0138] The second data acquisition control module is used to control the data acquisition of the energy consumption sensor group according to the data acquisition frequency corresponding to the energy consumption sensor group.

[0139] The working principle of the above technical solution is as follows: First, the system needs to know the data collection frequency of each sensor. For the environmental sensor group (such as temperature sensor and humidity sensor), the system extracts the corresponding data collection frequency. Similarly, for the energy consumption sensor group (such as power consumption collection sensor and water consumption collection sensor), the system also extracts the corresponding data collection frequency. These frequencies are set according to the type of sensor, accuracy requirements and actual needs of the building. After extracting the data collection frequency, the system controls the data collection of the sensor group according to these frequencies. For the environmental sensor group, the system will regularly collect environmental information data such as temperature and humidity according to the set frequency. For the energy consumption sensor group, the system will also collect energy consumption parameters such as power consumption and water consumption according to the set frequency. During the data collection process, the system may use various communication technologies (such as wireless or wired communication) to transmit data and ensure the accuracy and integrity of the data. In addition, the system may also need to pre-process the data, such as denoising, smoothing, missing value filling and outlier detection, to improve the reliability of the data and the accuracy of subsequent analysis.

[0140] The effect of the above technical solution is: by collecting environmental information data and energy consumption parameters of large buildings in real time, the system can monitor the operation status of the building in real time. This helps to promptly discover and solve potential problems such as energy waste and equipment failure. The system can analyze the energy consumption trend and energy-saving potential of the building based on the data collected in real time. By optimizing equipment operating parameters and adjusting energy distribution, the system can achieve the goal of energy saving and consumption reduction and reduce the operating costs of the building. The automated data collection and control process reduces the need for manual intervention and improves the efficiency of building management. Managers can intuitively understand the operating status of the building through the system interface and remotely control and adjust it as needed. The real-time collected data provides rich information support for the operation and management of the building. These data can be used in decision-making processes such as formulating energy management plans and optimizing equipment operation strategies to help buildings achieve more efficient and sustainable operations.

[0141] In summary, this technical solution realizes real-time monitoring and optimization control of building operation status by collecting environmental information data and energy consumption parameters of large buildings in real time. This not only helps to save energy and reduce consumption and improve management efficiency, but also provides strong decision-making support for building operation and management.

[0142] One embodiment of the present invention, based on the deep neural network module, includes:

[0143] A data input module is used for users to input current environment data into the deep neural network model through natural language;

[0144] A prediction value acquisition module is used for the deep neural network model to obtain a prediction value of the building energy consumption load according to the current environmental data.

[0145] The working principle of the above technical solution is as follows: the user describes the current environmental data, such as temperature, humidity, etc., in natural language, and inputs this information into the deep neural network model. The deep neural network model receives the natural language data input by the user and first parses and understands the data. This usually involves natural language processing (NLP) technology, such as text classification, entity recognition, etc., to ensure that the model can accurately capture the user's intentions and the environmental information described. Once the input data is understood, the model will use the previously learned relationship between the building energy load and environmental data to further process and analyze the data. This may involve steps such as data normalization and feature extraction to convert the raw data into a format that the model can understand. Finally, based on the processed data, the model uses a deep learning algorithm (such as a multi-layer perceptron MLP, a recurrent neural network RNN, a long short-term memory network LSTM, etc.) to make predictions and output the predicted value of the building energy load.

[0146] The effect of the above technical solution is: by using a deep neural network model, the technical solution can capture the complex relationship between the building energy load and environmental data, thereby improving the accuracy of the prediction. Users can interact with the model through natural language without having professional technical background or knowledge. This greatly reduces the threshold for use and enhances the user experience. The technical solution can receive environmental data input by the user in real time and quickly output the predicted value of the energy load. This provides strong support for the intelligent management of buildings and helps to achieve efficient use and conservation of energy. The deep neural network model has strong learning ability and adaptability, and can be continuously optimized and improved as new data is continuously added. This means that the technical solution has good scalability and flexibility, and can adapt to the actual needs of different buildings and environments.

[0147] In summary, this technical solution achieves accurate prediction of building energy load by using a deep neural network model to understand and analyze the current environmental data in natural language input by users. This not only improves the accuracy of prediction and user experience, but also provides strong support for intelligent management of buildings and efficient use of energy.

[0148] In one embodiment of the present invention, the intelligent optimization module includes:

[0149] An expected target parameter extraction module is used to extract the predicted value of the building energy consumption load and the expected target parameters input by the user; wherein the expected target parameters input by the user include a target temperature parameter and a target humidity parameter;

[0150] An energy consumption load value acquisition module is used to acquire the energy consumption load value of the building energy consumption load according to the expected target parameters input by the user;

[0151] The energy consumption load value is obtained by the following formula:

[0152]

[0153] Among them, E f Indicates the energy consumption load value; E0 indicates the preset energy consumption load value benchmark value; T c Indicates the temperature difference between the target temperature parameter input by the user and the current indoor temperature value; H c Indicates the humidity difference between the target humidity parameter input by the user and the current indoor humidity value; T d Indicates the current indoor temperature value; T k represents a preset temperature reference value; δ represents an adjustment coefficient, and the range of the adjustment coefficient is 0.23-0.41; w 01 、w 02 and w 03Respectively represent the preset first weight value, second weight value and third weight value;

[0154] A load value comparison module, used to compare the energy consumption load value with the predicted value of the building energy consumption load;

[0155] A first operating parameter setting module, used for automatically setting the operating parameters of the current energy-consuming equipment according to the expected target parameters input by the user when the energy consumption load value does not exceed the predicted value of the building energy consumption load, wherein the front energy-consuming equipment includes but is not limited to air conditioners, ventilation coefficients, humidifiers and other equipment capable of adjusting temperature and humidity parameters;

[0156] A second operating parameter setting module is used to automatically set the operating parameters of the current energy-consuming equipment according to the expected target parameters input by the user when the energy consumption load value exceeds the predicted value of the building energy consumption load and the load value of the energy consumption load value exceeding the building energy consumption load is lower than a preset load threshold;

[0157] The preset load threshold is obtained by the following formula:

[0158]

[0159] Among them, E t Indicates the preset load threshold; E y0 Indicates the preset initial value of the load threshold; E f Indicates the energy consumption load value; E0 indicates the preset energy consumption load value benchmark value; T c Indicates the temperature difference between the target temperature parameter input by the user and the current indoor temperature value; H c Indicates the humidity difference between the target humidity parameter input by the user and the current indoor humidity value; T max Indicates the maximum value of the current indoor temperature change; H max Indicates the current maximum indoor humidity change; k 01 Indicates the preset environmental parameter impact weight value; k 02 Indicates the preset energy consumption impact weight value;

[0160] The third operating parameter setting module is used to automatically set the operating parameters of the current energy-consuming equipment according to the temperature parameters and humidity parameters corresponding to the predicted value of the energy consumption load of the building when the energy consumption load value exceeds the predicted value of the energy consumption load of the building and the load value of the energy consumption load exceeding the building energy consumption load is not lower than a preset load threshold.

[0161] The working principle of the above technical solution is as follows: the system first extracts the predicted value of the building's energy load, which is obtained through deep learning or other prediction models based on the previous environmental information data and energy consumption parameters. At the same time, the system also extracts the expected target parameters entered by the user, such as target temperature parameters and target humidity parameters. Based on the target temperature parameters and target humidity parameters entered by the user, as well as the actual values ​​of the current indoor temperature and humidity, the system calculates an energy load value (Ef). This calculation process involves a formula that takes into account the temperature difference (Tc), the humidity difference (Hc), the preset energy load value reference value (E0), the adjustment coefficient (δ), and the first, second and third weight values ​​(w01, w02, w03).

[0162] The system compares the calculated energy load value with the predicted value of the building's energy load. If the energy load value does not exceed the predicted value, or if it exceeds but the excess load value is lower than the preset load threshold (Et), the system automatically sets the operating parameters of the current energy-consuming equipment according to the expected target parameters entered by the user, such as adjusting the temperature and humidity parameters of equipment such as air conditioners, ventilation coefficients, and humidifiers. If the energy load value exceeds the predicted value and the excess load value is not lower than the preset load threshold, the system automatically sets the operating parameters of the current energy-consuming equipment according to the temperature parameters and humidity parameters corresponding to the predicted value of the building's energy load to ensure that the building's energy consumption is not too high.

[0163] The effect of the above technical solution is: the technical solution can intelligently adjust the operating parameters of energy-consuming equipment according to the predicted value of the building's energy consumption load and the expected target parameters input by the user, thereby improving energy utilization efficiency. By comparing the energy consumption load value and the predicted value, and considering the load threshold, the system can avoid excessive energy consumption and achieve energy saving effects. The system can adjust the operation of energy-consuming equipment according to the target temperature and humidity parameters input by the user to meet the user's comfort requirements. The formulas and weight values ​​in the technical solution can be adjusted and optimized according to actual conditions to meet the needs of different buildings and environments. At the same time, the system also supports the addition of more sensors and devices to expand its functions and application scope. The automated and intelligent adjustment process reduces the need for manual intervention and improves the efficiency of building management.

[0164] In summary, this technical solution has achieved both energy-saving effects and user comfort by intelligently adjusting the operating parameters of energy-consuming equipment. At the same time, its flexibility and scalability also provide possibilities for future optimization and expansion.

[0165] In one embodiment of the present invention, the large model Agent module includes:

[0166] A natural language receiving module, used to receive the natural language input by the user terminal in real time;

[0167] An information conversion module, used to parse the natural language input by the user terminal using the Agent model to obtain the control demand information contained in the natural language, and convert the control demand information into legal parameters that meet the input of the deep neural network module and the intelligent optimization module;

[0168] A legal parameter input module, used to input the legal parameters that meet the requirements of the deep neural network module and the intelligent optimization module into the deep neural network module and the intelligent optimization module respectively;

[0169] The information feedback module is used to collect environmental information data and energy consumption parameters of large buildings in real time using a real-time collection sensor group, and convert the environmental information data and energy consumption parameters of the large buildings into natural language to feed back to the user terminal.

[0170] The working principle of the above technical solution is as follows: the system receives natural language instructions input by users in real time through user terminals (such as mobile phones, computers, voice assistants, etc.). These instructions may include control requirements for building environment (such as temperature, humidity), or optimization requirements for energy consumption parameters. The natural language input by users is parsed using an Agent model (an intelligent agent that can interact on behalf of users or other entities). The Agent model understands user intentions through natural language processing (NLP) technology and extracts control requirement information contained in natural language. Subsequently, the Agent model converts these control requirement information into legal parameters that meet the input requirements of the deep neural network module and the intelligent optimization module. These parameters may include temperature set values, humidity set values, energy consumption optimization targets, etc. The converted legal parameters are input into the deep neural network module and the intelligent optimization module respectively. The deep neural network module may be used to predict the energy consumption load of the building, evaluate the environmental comfort, etc.; while the intelligent optimization module may be used to optimize energy consumption allocation and adjust equipment operation strategies according to the prediction results and user needs. The system collects environmental information data and energy consumption parameters of large buildings provided by the sensor group in real time. These data include temperature, humidity, light intensity, power consumption, water consumption, etc. After being processed, the collected data is converted into natural language form and fed back to the user through the user terminal. In this way, the user can intuitively understand the current environmental conditions and energy consumption of the building, as well as whether the control requirements previously entered are effectively executed.

[0171] The effect of the above technical solution is: this technical solution realizes the intelligent interaction between users and building environment and energy consumption management system through natural language processing and Agent model. Users can easily control the building environment and optimize energy consumption through natural language instructions without professional knowledge. The system can accurately extract the control requirements according to the natural language instructions input by the user, and convert them into legal parameters to input into the deep neural network module and intelligent optimization module. This ensures that the system can accurately execute the user's control requirements and improve the comfort and energy efficiency of the building. The system can collect environmental information data and energy consumption parameters of the building in real time, and convert them into natural language form to feedback to the user. This helps users to understand the operating status of the building in a timely manner and make adjustments as needed. Through the collaborative work of the deep neural network module and the intelligent optimization module, the system can achieve efficient optimization of the building's energy consumption. This helps to reduce the operating costs of the building and improve energy efficiency. The technical solution has good scalability. With the continuous development of technology, more sensors, smart devices and optimization algorithms can be further introduced to expand the functions and application scope of the system.

[0172] In summary, this technical solution provides users with a more convenient, efficient and comfortable building environment and energy management experience through the advantages of intelligent interaction, precise control, real-time feedback, efficient optimization and scalability.

[0173] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. An intelligent energy-saving control method for large buildings based on a large model, characterized in that: The large-scale building intelligent energy-saving control method based on the large model includes: Control sensor groups to collect environmental information data and energy consumption parameters of large buildings in real time; Obtaining a predicted value of the building's energy consumption load based on the environmental information data and energy consumption parameters of the large building; Acquire the operating parameters of the current energy-consuming equipment according to the predicted value of the energy consumption load of the building and the expected target parameters input by the user, and adjust the actual parameters of the energy-consuming equipment according to the operating parameters of the current energy-consuming equipment to obtain the adjusted real-time operating parameters of the energy-consuming equipment; The control requirements contained in the natural language input by the user are converted into data information that conforms to the input of the deep neural network module and the intelligent optimization module.

2. According to the large-scale model-based intelligent energy-saving control method for large buildings according to claim 1, it is characterized in that: The control sensor group collects environmental information data and energy consumption parameters of large buildings in real time, including: Extracting the data collection frequency corresponding to the environmental sensor group in the large building; wherein the environmental sensor group includes a temperature sensor and a humidity sensor; Performing data collection control on the environmental sensor group according to the data collection frequency corresponding to the environmental sensor group; Extracting the data collection frequency corresponding to the energy consumption sensor group in the large building; wherein the energy consumption sensor group includes an electricity consumption collection sensor and a water consumption collection sensor; Data collection is controlled for the energy consumption sensor group according to the data collection frequency corresponding to the energy consumption sensor group.

3. According to the large-scale model-based intelligent energy-saving control method for large buildings according to claim 1, it is characterized in that: Obtaining a predicted value of the building's energy consumption load according to the environmental information data and energy consumption parameters of the large building, including: Users input current environment data into the deep neural network model through natural language; The deep neural network model obtains a predicted value of the building energy consumption load according to the current environmental data.

4. According to the large-scale model-based intelligent energy-saving control method for large buildings according to claim 1, it is characterized in that: The operating parameters of the current energy-consuming equipment are obtained according to the predicted value of the energy consumption load of the building and the expected target parameters input by the user, and the actual parameters of the energy-consuming equipment are adjusted according to the operating parameters of the current energy-consuming equipment to obtain the adjusted real-time operating parameters of the energy-consuming equipment, including: Extracting the predicted value of the building energy consumption load and the expected target parameters input by the user; wherein the expected target parameters input by the user include a target temperature parameter and a target humidity parameter; Obtaining an energy consumption load value of the building energy consumption load according to the expected target parameter input by the user; The energy consumption load value is obtained by the following formula: Among them, E f Indicates the energy consumption load value; E0 indicates the preset energy consumption load value benchmark value; T c Indicates the temperature difference between the target temperature parameter input by the user and the current indoor temperature value; H c Indicates the humidity difference between the target humidity parameter input by the user and the current indoor humidity value; T d Indicates the current indoor temperature value; T k represents a preset temperature reference value; δ represents an adjustment coefficient, and the range of the adjustment coefficient is 0.23-0.41; w 01 、w 02 and w 03 Respectively represent the preset first weight value, second weight value and third weight value; Comparing the energy load value with a predicted value of the building energy load; When the energy consumption load value does not exceed the predicted value of the building energy consumption load, the operating parameters of the current energy-consuming equipment are automatically set according to the expected target parameters input by the user; When the energy consumption load value exceeds the predicted value of the building energy consumption load, and the load value of the energy consumption load value exceeding the building energy consumption load is lower than the preset load threshold, the operating parameters of the current energy consuming equipment are automatically set according to the expected target parameters input by the user; The preset load threshold is obtained by the following formula: Among them, E t Indicates the preset load threshold; E y0 Indicates the preset initial value of the load threshold; E f Indicates the energy consumption load value; E0 indicates the preset energy consumption load value benchmark value; T c Indicates the temperature difference between the target temperature parameter input by the user and the current indoor temperature value; H c Indicates the humidity difference between the target humidity parameter input by the user and the current indoor humidity value; T max Indicates the maximum value of the current indoor temperature change; H max Indicates the current maximum indoor humidity change; k 01 Indicates the preset environmental parameter impact weight value; k 02 Indicates the preset energy consumption impact weight value; When the energy consumption load value exceeds the predicted value of the building energy consumption load, and the energy consumption load value exceeds the load value of the building energy consumption load by not less than the preset load threshold, the operating parameters of the current energy-consuming equipment are automatically set according to the temperature parameters and humidity parameters corresponding to the predicted value of the building energy consumption load.

5. According to the large-scale model-based intelligent energy-saving control method for large buildings according to claim 1, it is characterized in that: The control requirements contained in the natural language input by the user are converted into data information that meets the input of the deep neural network module and the intelligent optimization module, including: Receive natural language input from a user terminal in real time; The agent model is used to parse the natural language input by the user terminal to obtain the control demand information contained in the natural language, and the control demand information is converted into legal parameters that meet the input of the deep neural network module and the intelligent optimization module; Input the legal parameters that meet the requirements of the deep neural network module and the intelligent optimization module into the deep neural network module and the intelligent optimization module respectively; The real-time data collection sensor group collects environmental information data and energy consumption parameters of large buildings in real time, and converts the environmental information data and energy consumption parameters of the large buildings into natural language to feed back to the user terminal.

6. Intelligent energy-saving control system for large buildings based on large models, characterized in that: The large-scale building intelligent energy-saving control system based on the large model includes: Data acquisition control module, used to control the sensor group to collect environmental information data and energy consumption parameters of large buildings in real time; A deep neural network module, used for obtaining a predicted value of the building's energy consumption load based on the environmental information data and energy consumption parameters of the large building; An intelligent optimization module, used to obtain the operating parameters of the current energy-consuming equipment according to the predicted value of the energy consumption load of the building and the expected target parameters input by the user, and adjust the actual parameters of the energy-consuming equipment according to the operating parameters of the current energy-consuming equipment to obtain the adjusted real-time operating parameters of the energy-consuming equipment; The large model Agent module is used to convert the control requirements contained in the natural language input by the user into data information that conforms to the input of the deep neural network module and the intelligent optimization module.

7. The large-scale building intelligent energy-saving control system based on a large model according to claim 6 is characterized in that: The data acquisition control module comprises: A first data acquisition frequency extraction module is used to extract the data acquisition frequency corresponding to the environmental sensor group in the large building; wherein the environmental sensor group includes a temperature sensor and a humidity sensor; A first data acquisition control module, used for performing data acquisition control on the environmental sensor group according to the data acquisition frequency corresponding to the environmental sensor group; A second data acquisition frequency extraction module is used to extract the data acquisition frequency corresponding to the energy consumption sensor group in the large building; wherein the energy consumption sensor group includes an electricity consumption acquisition sensor and a water consumption acquisition sensor; The second data acquisition control module is used to control the data acquisition of the energy consumption sensor group according to the data acquisition frequency corresponding to the energy consumption sensor group.

8. The large-scale building intelligent energy-saving control system based on a large model according to claim 6 is characterized in that: The deep neural network module comprises: A data input module is used for users to input current environment data into the deep neural network model through natural language; A prediction value acquisition module is used for the deep neural network model to obtain a prediction value of the building energy consumption load according to the current environmental data.

9. The large-scale building intelligent energy-saving control system based on a large model according to claim 6 is characterized in that: The intelligent optimization module comprises: An expected target parameter extraction module is used to extract the predicted value of the building energy consumption load and the expected target parameters input by the user; wherein the expected target parameters input by the user include a target temperature parameter and a target humidity parameter; An energy consumption load value acquisition module is used to acquire the energy consumption load value of the building energy consumption load according to the expected target parameters input by the user; The energy consumption load value is obtained by the following formula: Among them, E f Indicates the energy consumption load value; E0 indicates the preset energy consumption load value benchmark value; T c Indicates the temperature difference between the target temperature parameter input by the user and the current indoor temperature value; H c Indicates the humidity difference between the target humidity parameter input by the user and the current indoor humidity value; T d Indicates the current indoor temperature value; T k represents a preset temperature reference value; δ represents an adjustment coefficient, and the range of the adjustment coefficient is 0.23-0.41; w 01 、w 02 and w 03 Respectively represent the preset first weight value, second weight value and third weight value; A load value comparison module, used to compare the energy consumption load value with the predicted value of the building energy consumption load; A first operating parameter setting module, used for automatically setting the operating parameters of the current energy-consuming equipment according to the expected target parameters input by the user when the energy consumption load value does not exceed the predicted value of the building energy consumption load; A second operating parameter setting module is used to automatically set the operating parameters of the current energy-consuming equipment according to the expected target parameters input by the user when the energy consumption load value exceeds the predicted value of the building energy consumption load and the load value of the energy consumption load value exceeding the building energy consumption load is lower than a preset load threshold; The preset load threshold is obtained by the following formula: Among them, E t Indicates the preset load threshold; E y0 Indicates the preset initial value of the load threshold; E f Indicates the energy consumption load value; E0 indicates the preset energy consumption load value benchmark value; T c Indicates the temperature difference between the target temperature parameter input by the user and the current indoor temperature value; H c Indicates the humidity difference between the target humidity parameter input by the user and the current indoor humidity value; T max Indicates the maximum value of the current indoor temperature change; H max Indicates the current maximum indoor humidity change; k 01 Indicates the preset environmental parameter impact weight value; k 02 Indicates the preset energy consumption impact weight value; The third operating parameter setting module is used to automatically set the operating parameters of the current energy-consuming equipment according to the temperature parameters and humidity parameters corresponding to the predicted value of the energy consumption load of the building when the energy consumption load value exceeds the predicted value of the energy consumption load of the building and the load value of the energy consumption load exceeding the building energy consumption load is not lower than a preset load threshold.

10. The large-scale building intelligent energy-saving control system based on a large model according to claim 6 is characterized in that: The large model Agent module includes: A natural language receiving module, used to receive the natural language input by the user terminal in real time; An information conversion module, used to parse the natural language input by the user terminal using the Agent model to obtain the control demand information contained in the natural language, and convert the control demand information into legal parameters that meet the input of the deep neural network module and the intelligent optimization module; A legal parameter input module, used to input the legal parameters that meet the requirements of the deep neural network module and the intelligent optimization module into the deep neural network module and the intelligent optimization module respectively; The information feedback module is used to collect environmental information data and energy consumption parameters of large buildings in real time using a real-time collection sensor group, and convert the environmental information data and energy consumption parameters of the large buildings into natural language to feed back to the user terminal.

Images