Adjustment control method and equipment for central air conditioner

Abstract

According to the central air conditioner adjusting control method and equipment, space temperature adjustment of a public building can be achieved, the convenience of air conditioner management of people in the large public building can be better met, the use requirements of users for air conditioners can be better met, and good office and living environments can be better provided for the users; a user who does not have professional knowledge and operation experience of central air conditioner management can instantly describe the requirement of the building space for the temperature through a simple natural language, and control and adjustment of a central air conditioner machine room and end equipment can be linked, so that the user requirement is met.

Description

Technical Field

[0001] The invention relates to a central air-conditioning adjustment and control method and equipment. Background Art

[0002] Currently, most central air conditioning rooms (CAHs) are still primarily managed manually, requiring professional technicians to operate the equipment on-site through control cabinets or pre-set system management interfaces. This leads to low efficiency, poor convenience, and a high learning curve. Central AC equipment, such as refrigeration units, cooling water pumps, cooling towers, and chilled water pumps, incorporates complex control logic. Operating these devices requires specialized knowledge and extensive experience, and even skilled personnel are prone to omissions and errors during these extensive manual operations.

[0003] In contrast to the outdated management of central air-conditioning rooms in public buildings, people have increasingly higher requirements for the use and comfort of central air-conditioning. There is also a growing demand for air-conditioning management that can adapt to people's needs. For example, during an event in a shopping mall's atrium, it is hoped that the temperature control can be further adapted to the number of people at the event site. People in office areas, for example, hope that the temperature control can be more flexible and convenient. Therefore, central air-conditioning requires a more flexible and convenient management and operation method to match user needs. Summary of the Invention

[0004] The object of the present invention is to provide a central air-conditioning adjustment and control method and equipment.

[0005] To solve the above problems, the present invention provides a central air conditioning adjustment and control method, comprising:

[0006] Obtain management instructions in the form of user text or voice from an on-site voice control panel or an Internet mobile terminal through an interactive terminal;

[0007] Performing semantic understanding on the semantic text of the user instruction through the large model to obtain the device control instruction;

[0008] In a computer room group control system based on load forecasting and deep machine learning structure, an air conditioning equipment adjustment strategy is obtained by performing command judgment based on equipment control commands; a command safety check is performed on the air conditioning equipment adjustment strategy to obtain an equipment adjustment strategy after the safety check;

[0009] Instruction feedback and confirmation: the device adjustment strategy after safety inspection is sent to the user for confirmation;

[0010] The device adjustment strategy after the safety check will be executed and fed back through the execution program, and the results of the execution program will be fed back to the user.

[0011] Furthermore, in the above method, obtaining, through the interactive terminal, a user instruction user text or voice-expressed management instruction from an on-site voice control panel or an Internet mobile terminal includes:

[0012] When receiving a voice input expressing the requirements for the air conditioner temperature management, the speech recognition service or the locally deployed speech recognition model is called to convert the user's voice into text; or the text expressing the requirements for the air conditioner temperature management directly input by the user is received;

[0013] After completing preliminary processing of the voice and text through the interactive terminal, a semantic text containing the user instruction is obtained, and the semantic text of the user instruction is transmitted through the network to a locally deployed large model for processing.

[0014] Furthermore, in the above method, semantic understanding of the semantic text of the user instruction is performed by a large model to obtain a device control instruction, including:

[0015] A local knowledge base is constructed within the large model. The local knowledge base includes documents such as building space information, air conditioning equipment lists, operation and maintenance logs, and equipment operating manuals. The large model obtains the space name, area, and corresponding air conditioning equipment information through the building space information and air conditioning equipment lists in the local knowledge base.

[0016] The large model extracts and analyzes the name of the user's space based on the semantic text of the user's instruction. The large model combines the local knowledge base with the name of the user's space to find the corresponding air conditioning equipment information;

[0017] The large model classifies the semantic text of the user's instruction into corresponding instruction types through prompt word engineering; if the large model fails to parse or understand the semantic text of the user's instruction, it will feedback "instruction failed to parse";

[0018] If the semantic text of the user instruction contains a clear time, the execution time of the instruction is set to the clear time through the semantic analysis of the large model; if the semantic text of the user instruction does not contain a clear time, the execution time is set to be executed immediately;

[0019] Output the device control instructions in json format. The device control instructions output by the large model are constrained to output json strings through prompt, including: the executed air-conditioning equipment information, instruction type, execution instruction value and execution instruction time.

[0020] Furthermore, in the above method, the types of the large models include: deepseek and Tongyi Qianwen.

[0021] Furthermore, in the above method, the large model is deployed locally or uses an online large model interface.

[0022] Furthermore, in the above method, the air conditioning equipment adjustment strategy is obtained by performing instruction judgment according to the equipment control instruction, including:

[0023] Establish a load forecasting model based on data including historical outdoor wet-bulb temperatures, historical cooling load values, and air conditioning terminal temperature settings;

[0024] Input information such as the current outdoor wet-bulb temperature, the air conditioning terminal temperature required by the device control instruction, and the ratio of the space area to the total area into the load forecasting model to obtain the actual load demand required according to the user's required temperature;

[0025] Compare the user's required temperature with the current air conditioning unit's temperature setting and the chilled water supply and return temperature difference. If the load adjustment at the air conditioning unit's terminal is determined to meet the actual load demand, the air conditioning unit's adjustment strategy is to only adjust the temperature setting and wind speed at the air conditioning unit's terminal.

[0026] If the air conditioning equipment terminal adjustment cannot meet the actual load demand, it is determined whether the central air conditioning room water pump frequency adjustment and host temperature setting are used. If so, the air conditioning equipment adjustment strategy is to perform actual load demand control to adjust to meet the actual load demand without turning on additional hosts and water pumps. This is called primary cooling source adjustment.

[0027] If the actual load demand can only be determined by adding or subtracting machines from the host and adjusting the number of water pumps turned on, the air-conditioning equipment adjustment strategy is to perform advanced cold source adjustment. The advanced cold source adjustment is achieved by executing the logic of adding and subtracting machines from the refrigeration host. The adding logic opens the cold water inlet and outlet valves, cooling tower fan, cooling water pump and cold water pump in sequence, and finally starts the chiller. A certain delay is required between each step; the subtracting logic is to execute the cooling tower fan, cooling water pump, cold water pump and close the cold water inlet and outlet valves in sequence after the chiller is shut down. There is a preset delay between each step.

[0028] Furthermore, in the above method, the air conditioning equipment adjustment strategy is subjected to an instruction safety check to obtain an equipment adjustment strategy after the safety check, including:

[0029] Determine the equipment association and operation logic in the air conditioning equipment adjustment strategy to obtain the equipment adjustment strategy after safety inspection.

[0030] Furthermore, in the above method, the device adjustment strategy after the security check is executed and fed back through the execution program, and the results of the execution program are fed back to the user, including:

[0031] Send the device adjustment policy that has passed the security check and confirmed by the user to the execution program for execution;

[0032] The execution program feeds back the results of the execution program to the user.

[0033] According to another aspect of the present invention, a computer-readable storage medium is provided, on which computer-executable instructions are stored. When the computer-executable instructions are executed by a processor, the processor is enabled to execute any one of the methods described above.

[0034] According to another aspect of the present invention, there is further provided a computer device, comprising:

[0035] processor; and

[0036] A memory arranged to store computer executable instructions, which when executed cause the processor to: perform any of the methods described above.

[0037] Compared with the existing technology, the present invention is based on the above-mentioned large-model-based central air-conditioning adjustment and control method, which can realize spatial temperature adjustment of public buildings, better meet the convenience of air-conditioning management in large public buildings and better adapt to users' needs for air-conditioning use, and better provide users with a good office and living environment; it enables users who do not have professional knowledge and operating experience in central air-conditioning management to instantly describe the temperature requirements of the building space through simple natural language, and can link the central air-conditioning room and terminal equipment control and adjustment to meet user requirements.

[0038] Compared with the current air conditioning control method, the advantages of the present invention are:

[0039] 1) The execution is convenient and fast. The requirements can be immediately executed to meet the user's requirements and realize the air conditioning temperature adjustment

[0040] 2) Good compatibility and comprehension. No professional knowledge is required, and expression and satisfaction can be achieved through vague and imprecise language. When users control the air conditioner, the forms of expression are diverse and vague. Specifically, for example, the meaning of "adjust the temperature a little higher" and "the temperature is too hot" are different. The first sentence is an active temperature control instruction, which clearly indicates that the current temperature is not hot enough and hopes to set it higher. The second sentence is a passive perception of the temperature. The current temperature is already high and makes people feel hot, but since the user has not issued a clear instruction, the most appropriate way for AI at this time is to ask the user whether to adjust the temperature appropriately. After receiving the user's feedback, the instruction operation will be carried out. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] Figure 1The figure is a flow chart of a central air conditioning adjustment and control method according to an embodiment of the present invention. DETAILED DESCRIPTION

[0042] The present invention is further described in detail below with reference to the accompanying drawings.

[0043] In a typical configuration of the present application, the terminal, the device of the service network and the trusted party all include one or more processors (CPUs), input / output interfaces, network interfaces and memories.

[0044] Memory may include non-permanent storage 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. Memory is an example of a computer-readable medium.

[0045] 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 non-transitory media such as modulated data signals and carrier waves.

[0046] like Figure 1 As shown, the present invention provides a central air conditioning adjustment and control method, the method comprising:

[0047] Step S1, user front-end interaction: obtaining user instructions, user text or voice-expressed management instructions from an on-site voice control panel or an Internet mobile terminal through an interactive terminal.

[0048] Here, the user interaction terminal may be an Internet mobile terminal or a voice control panel deployed in a public building space, which can accept user's language or text input.

[0049] When a voice input expressing the management requirements for the air-conditioning temperature is obtained, the voice recognition service or the locally deployed voice recognition model is called to convert the user's voice into text; or the text expressing the management requirements for the air-conditioning temperature directly input by the user is obtained; then, after completing the preliminary processing of the voice and text through the interactive terminal, a semantic text containing the user's instructions is obtained, and the semantic text of the user's instructions is transmitted through the network to the locally deployed large model for processing.

[0050] For example, a user inputs the voice message "The temperature in conference room 712 is too hot" into the on-site interactive terminal. After the voice analysis service extracts the text, it is sent to the big model.

[0051] For example, a user inputs the voice message "Control the temperature of the mall atrium at 23°C from 2pm to 4pm" into the mobile app. After the voice analysis service extracts the text, it is sent to the big model.

[0052] Step S2: The big model parses the semantic text of the user instruction: the big model performs semantic understanding on the semantic text of the user instruction to obtain the device control instruction;

[0053] Preferably, step S2 includes:

[0054] In step 2.1, deploying or using the big model, the present invention does not limit the type of big model or the deployment method of the big model. For example, the big model can be DeepSeek or Tongyi Qianwen. The big model can be deployed locally or use an online big model interface to understand the semantic text provided by the user interaction terminal through the big model;

[0055] Step 2.2: Build a local knowledge base in the large model. The local knowledge base includes documents such as building space information, air conditioning equipment lists, operation and maintenance logs, and equipment operation manuals. The large model obtains the space name, area, and corresponding air conditioning equipment information through the building space information and air conditioning equipment lists in the local knowledge base.

[0056] Step 2.3: Determine the execution device: The large model extracts and analyzes the name of the user's space based on the semantic text of the user's instruction. The large model combines the local knowledge base with the name of the user's space to find the corresponding air conditioning device information;

[0057] Step 2.4 performs intent classification: the large model uses prompt word engineering to classify the semantic text of the user's command into command types such as "status query" and "temperature adjustment". If the large model fails to parse or understand the semantic text of the user's command, it will feedback "command not parsed";

[0058] Step 2.5, execution time judgment: If the semantic text of the user instruction contains a clear time, the execution instruction time is set to the clear time through large model semantic analysis; if the semantic text of the user instruction does not contain a clear time, the execution time is set to immediate execution.

[0059] Step 2.6, output the device control instructions in json format. The device control instructions output by the large model are constrained to output json strings through prompt, including: the executed air-conditioning equipment information, instruction type (execution instruction name), execution instruction value and execution instruction time, etc.

[0060] Here, for ease of understanding, a specific json format is provided: {"device":"AREA_CENTER","command":"Set temperature","value":"23","date":"2025-06-0514:00"}.

[0061] For example, you can deploy a deepseek large model locally and process and analyze the user text. First, the target area 712 is parsed and the corresponding device is found in the rag database as AC_UNIT_712. Then, the control intention is parsed as temperature adjustment. Finally, the parsed time is set to immediate execution and set to the current time 2025-06-05 11:00. After processing the prompt words and requirements, the large model outputs the final result and sends a json string command {

[0062] "device":"AC_UNIT_712",

[0063] “command”: “temperature adjustment”,

[0064] “value”:“-2”,

[0065] "date":"2025-06-05 11:00",

[0066] }.

[0067] Send specific device control instructions to the load forecasting control system in the form of a JSON string.

[0068] For example, deploy a deepseek large model locally, process and analyze the user text, and parse the time range, target area and temperature parameters; send a json string command {

[0069] "device":"AREA_CENTER",

[0070] "command": "Set temperature",

[0071] “value”:“23”,

[0072] "date":"2025-06-05 14:00",

[0073] }.

[0074] Step S3, command judgment and inspection: In the computer room group control system based on load forecasting and deep machine learning structure, command judgment is performed based on the equipment control command to obtain the air conditioning equipment adjustment strategy; the command safety check is performed on the air conditioning equipment adjustment strategy to obtain the equipment adjustment strategy after the safety check;

[0075] Unlike household air conditioners, temperature regulation in the building space where central air conditioners are located often requires the coordinated control of the central air conditioning room and terminal equipment to achieve temperature regulation. Therefore, it is necessary to make a comprehensive judgment based on the user's requirements, the current state of the internal and external environment, and the status of the equipment operation to consider how to meet the user's requirements. Command judgment is mainly based on the load demand to analyze the degree of adjustment to meet the user's requirements. Command inspection is a safety check that must be performed on the implementation of the command to avoid logical errors in equipment operation that may lead to equipment failure. The following is a breakdown of the specific step S3:

[0076] Preferably, the air conditioning equipment adjustment strategy is obtained by performing instruction judgment according to the equipment control instruction, including:

[0077] Step 3.1: Establish a load forecasting model based on data including historical outdoor wet-bulb temperature, historical cooling load values, and air conditioner terminal temperature settings;

[0078] Step 3.2, determining the actual load demand: Input information such as the current outdoor wet-bulb temperature, the air conditioning terminal temperature required by the equipment control instruction, and the ratio of the space area to the total area into the load forecasting model to obtain the actual load demand required based on the user's required temperature;

[0079] Step 3.3, determine the air conditioning terminal adjustment: compare the user's required temperature with the current air conditioning equipment temperature setting and the chilled water supply and return temperature difference. If it is determined that the load adjustment of the air conditioning equipment terminal can meet the actual load demand, the air conditioning equipment adjustment strategy is to only adjust the temperature setting and wind speed of the air conditioning equipment terminal;

[0080] Step 3.4: Determine primary cooling source adjustment: If the air conditioning equipment terminal adjustment cannot meet the actual load demand, determine whether the central air conditioning room's water pump frequency adjustment and host temperature setting are sufficient. If so, the air conditioning equipment adjustment strategy is to perform actual load demand control to meet the actual load demand without additional host and water pump operation. This is called primary cooling source adjustment.

[0081] Step 3.5: Determine the advanced cooling source adjustment: If the actual load demand can only be met by adding or removing units from the main unit and adjusting the number of water pumps to be turned on, the air conditioning equipment adjustment strategy is to perform advanced cooling source adjustment. This advanced cooling source adjustment is performed by executing the cooling unit addition and removal logic. The addition logic sequentially opens the cold water inlet and outlet valves, the cooling tower fan, the cooling water pump, and the cold water pump, and finally starts the chiller. There is a certain delay between each step. The removal logic sequentially activates the cooling tower fan, the cooling water pump, the cold water pump, and closes the cold water inlet and outlet valves after the chiller is shut down. There is a preset delay between each step.

[0082] Preferably, performing a command safety check on the air conditioning equipment adjustment strategy to obtain the equipment adjustment strategy after the safety check includes:

[0083] Step 3.6: Execute safety check rules: Determine the equipment associations and operation logic in the air conditioning equipment adjustment strategy to obtain the equipment adjustment strategy after the safety check, and avoid equipment failure and damage caused by improper operation. For example, the inspection rules include: the chilled water supply temperature must not be lower than 7°C, check whether the water circulation is established before the chiller is turned on, and after the chiller is turned off, the water pump must run for a period of time before shutting down.

[0084] For example, the system reads the current set temperature (26°C) and actual temperature (26°C) in conference room 712, with the fan operating at medium speed. Status checks and conflict checks are performed to determine that the chilled water supply and return temperature difference is less than or equal to 5°C. Based on the rule base, the system determines that the user's needs can be met by adjusting the current air conditioner terminal temperature. The terminal temperature is set to 24°C and the fan speed is increased. If the fan speed and water valve are already set to maximum, and the chilled water supply and return temperatures are greater than 5°C, the terminal adjustment is deemed ineffective. Further evaluation of the cooling source is performed, and a preliminary adjustment is considered without changing the number of operating units. This involves increasing the chilled water pump speed (+10Hz) and reducing the unit outlet water temperature (-1°C). If the load is still insufficient, additional backup units and pumps are added for further adjustments. Safety check rules are implemented, with a minimum adjustment interval of 10 minutes for pump / unit parameter adjustments. Safety check rules stipulate that the supply water temperature must not fall below 7°C in summer. For example, water circulation must be checked before turning on a chiller, and the pump must run for a period of time before shutting down after the chiller is turned off.

[0085] For example, the mall load is predicted and calculated based on the current external wet-bulb temperature, historical data, preset temperatures, and area. Combined with equipment performance and operation, these commands generate equipment operation control instructions to start host computers CH#1 and CH#2, set the outlet water temperature to 7°C, start chilled water pumps CWP#1 and CWP#2 at 45 Hz, start cooling water pumps CHWP#1 and CHWP#2 at 30 Hz, and start cooling towers CT#1 and CT#2 at 15 Hz.

[0086] Step S4: Instruction feedback and confirmation: the device adjustment strategy after security check is sent to the user for confirmation;

[0087] Here, if the equipment adjustment strategy after the safety inspection is real-time, then after the above-mentioned load judgment, the instruction is immediately fed back to the user for confirmation; if the equipment adjustment strategy after the safety inspection is future-oriented, then the sequence of air-conditioning equipment required to operate according to the equipment adjustment strategy after the safety inspection will be sent to the user for reference and confirmation.

[0088] For example, after judgment and inspection, the management instruction is sent to the user for confirmation, and a suggestion is pushed to adjust the temperature of conference room 712 to 24°C and the fan speed to high speed.

[0089] For example, after judgment and inspection, the management instruction is sent to the user for confirmation, and a suggestion is pushed to control the temperature of the mall atrium at 23°C from 2:00 to 4:00 p.m., and to turn on the cooling towers CT#1 and CT#2, the cooling water pumps CHWP#1 and CHWP#2, the chilled water pumps CWP#1 and CWP#2, and the host CH#1 and CH#2. Please confirm.

[0090] Step S5: The device adjustment strategy after the security check is executed and fed back through the execution program, and the results of the execution program are fed back to the user;

[0091] Preferably, after receiving user confirmation feedback on the device adjustment strategy after the safety check, the device adjustment strategy after the safety check is sent to the execution program. The execution program connects to the PLC / DCS system with the BACnet gateway via the TCP / IP protocol and sends the instructions to the corresponding air conditioning equipment through the decentralized controller for execution. After the execution is completed, the execution program will feedback the execution results to the user. At this point, the entire logic from the user sending the control instruction to the instruction execution and feedback is complete. The specific steps are as follows:

[0092] Step S5.1, sending the device adjustment policy that has passed the security check and confirmed by the user to the execution program for execution;

[0093] In step S5.2, the program is executed and the result of the execution of the program is fed back to the user, for example, "The room air conditioner temperature has been set to 24°C for the user, and it is expected to reach the target temperature in 5 minutes."

[0094] For example, after the user confirms the instruction, the instruction is sent to the execution program, which connects to the PLC / DCS system with the BACnet gateway through the TCP / IP protocol, and sends the instruction to the specific device through the distributed controller. After the execution is completed, the result is fed back to the user: "Control the air-conditioning host to adjust the water supply temperature. The air-conditioning host and water pump adjustment have been executed for the user. The terminal temperature of conference room 712 is adjusted to 24 degrees Celsius. The temperature adjustment is expected to be completed in 25 minutes."

[0095] For example, after the user confirms the instruction, the instruction is sent to the execution program, which connects to the PLC / DCS system with the BACnet gateway through the TCP / IP protocol, and sends the instruction to the specific device through the distributed controller. After execution, the result is fed back to the user: "Based on the temperature trend of the day and the user's temperature requirements, the predicted cooling demand is set to 11700KWH. Based on this requirement, it is necessary to turn on the cooling towers CT#1 and CT#2, set the frequency to 30HZ, turn on the cooling water pumps CHWP#1 and CHWP#2 at 40HZ, turn on the chilled water pumps CWP#1 and CWP#2, set the frequency to 40HZ, turn on the host CH#1 and CH#2, set the outlet water temperature to 7°C, and start pre-cooling at 13:30. It is expected that the temperature in the target area will reach 23°C around 13:55."

[0096] According to another aspect of the present invention, a computer-readable storage medium is provided, on which computer-executable instructions are stored. When the computer-executable instructions are executed by a processor, the processor is enabled to execute any one of the methods described above.

[0097] According to another aspect of the present invention, there is further provided a computer device, comprising:

[0098] processor; and

[0099] A memory arranged to store computer executable instructions, which when executed cause the processor to: perform any of the methods described above.

[0100] To sum up, the present invention is based on the above-mentioned large-model-based central air-conditioning adjustment and control method, which can realize spatial temperature adjustment of public buildings, better meet the convenience of air-conditioning management in large public buildings and better adapt to users' needs for air-conditioning use, and can better provide users with a good office and living environment; it enables users who do not have professional knowledge and operating experience in central air-conditioning management to instantly describe the temperature requirements of the building space through simple natural language, and can link the central air-conditioning room and terminal equipment control and adjustment to meet user requirements.

[0101] Compared with the current air conditioning control method, the advantages of the present invention are:

[0102] 1) The execution is convenient and fast, and the air conditioning temperature can be adjusted immediately after the request is made.

[0103] 2) Good compatibility and comprehension. No professional knowledge is required, and expression and satisfaction can be achieved through vague and imprecise language. When users control air conditioning, the forms of expression are diverse and vague. Specifically, for example, the meaning of "adjust the temperature a little higher" and "the temperature is too hot" are different. The first sentence is an active temperature control instruction, which clearly indicates that the current temperature is not hot enough and hopes to set the temperature higher. The second sentence is a passive perception of the temperature. The current temperature is already high, making people feel hot, but because the user has not issued a clear instruction, the most appropriate way for AI at this time is to ask the user whether the temperature needs to be lowered appropriately, and then perform the instruction operation after receiving the user's feedback. The precise understanding of user semantics based on the large model and appropriate prompt word engineering can transform user expressions into air conditioning control execution instructions. 3) Command execution is precise and safe. User commands are not directly issued to equipment for execution. Instead, they undergo the following steps: 1) load forecast assessment, which evaluates the overall air conditioning load and provides a numerical basis for subsequent logical judgment; 2) intelligent adjustment logic judgment, which determines the load and determines whether the equipment involved in the command execution is adjusted at the terminal, such as the frequency and settings of the cooling source equipment, or whether the cooling source equipment is added or subtracted; and 3) comprehensive safety rule checks to eliminate parameter errors, incorrect operation sequences, or logical conflicts. After these steps are completed, the command is handed over to the specific equipment for execution, ensuring the safety and stability of system operation.

[0104] The detailed contents of the various device embodiments of the present invention can be found in the corresponding parts of the various method embodiments, which will not be repeated here.

[0105] Obviously, those skilled in the art may make various changes and modifications to this application without departing from the spirit and scope of this application. Thus, if these modifications and variations of this application fall within the scope of the claims of this application and their equivalents, this application is intended to include these modifications and variations.

[0106] It should be noted that the present invention can be implemented in software and / or a combination of software and hardware, for example, can be implemented using an application specific integrated circuit (ASIC), a general purpose computer or any other similar hardware device. In one embodiment, the software program of the present invention can be executed by a processor to implement the steps or functions described above. Similarly, the software program of the present invention (including related data structures) can be stored in a computer-readable recording medium, for example, a RAM memory, a magnetic or optical drive or a floppy disk and similar devices. In addition, some steps or functions of the present invention can be implemented using hardware, for example, as a circuit that cooperates with a processor to perform each step or function.

[0107] In addition, a portion of the present invention may be applied as a computer program product, such as computer program instructions, which, when executed by a computer, can call or provide the method and / or technical solution according to the present invention through the operation of the computer. The program instructions for calling the method of the present invention may be stored in a fixed or removable recording medium, and / or transmitted through a data stream in a broadcast or other signal-carrying medium, and / or stored in a working memory of a computer device that operates according to the program instructions. Here, according to one embodiment of the present invention, a device is included, which includes a memory for storing computer program instructions and a processor for executing the program instructions, wherein, when the computer program instructions are executed by the processor, the device is triggered to operate based on the aforementioned methods and / or technical solutions according to multiple embodiments of the present invention.

[0108] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above and that the invention can be implemented in other specific forms without departing from the spirit or essential features of the invention. Therefore, from any point of view, the embodiments should be regarded as exemplary and non-restrictive, and the scope of the invention is defined by the appended claims rather than the above description, and it is intended that all changes that fall within the meaning and scope of the equivalents of the claims be encompassed within the present invention. Any figure marks in the claims should not be regarded as limiting the claims involved. In addition, it is clear that the word "comprising" does not exclude other units or steps, and the singular does not exclude the plural. Multiple units or devices stated in the device claim may also be implemented by one unit or device through software or hardware. Words such as first and second are used to indicate names and do not indicate any particular order.

Claims

1. A central air conditioning control method, characterized in that: include: Obtain management instructions in the form of user text or voice from an on-site voice control panel or an Internet mobile terminal through an interactive terminal; Performing semantic understanding on the semantic text of the user instruction through the large model to obtain the device control instruction; In a computer room group control system based on load forecasting and deep machine learning structure, an air conditioning equipment adjustment strategy is obtained by performing command judgment based on equipment control commands; a command safety check is performed on the air conditioning equipment adjustment strategy to obtain an equipment adjustment strategy after the safety check; Instruction feedback and confirmation: the device adjustment strategy after safety inspection is sent to the user for confirmation; The device adjustment strategy after the safety check will be executed and fed back through the execution program, and the results of the execution program will be fed back to the user.

2. The central air conditioning control method according to claim 1, wherein: Through the interactive terminal, obtain user instructions from the on-site voice control panel or the Internet mobile terminal. User text or voice management instructions include: When receiving a voice input expressing the requirements for the air conditioner temperature management, the speech recognition service or the locally deployed speech recognition model is called to convert the user's voice into text; or the text expressing the requirements for the air conditioner temperature management directly input by the user is received; After completing preliminary processing of the voice and text through the interactive terminal, a semantic text containing the user instruction is obtained, and the semantic text of the user instruction is transmitted through the network to a locally deployed large model for processing.

3. The central air conditioning control method according to claim 1, wherein: The semantic text of the user instruction is semantically understood by the large model to obtain the device control instruction, including: A local knowledge base is constructed within the large model. The local knowledge base includes documents such as building space information, air conditioning equipment lists, operation and maintenance logs, and equipment operating manuals. The large model obtains the space name, area, and corresponding air conditioning equipment information through the building space information and air conditioning equipment lists in the local knowledge base. The large model extracts and analyzes the name of the user's space based on the semantic text of the user's instruction. The large model combines the local knowledge base with the name of the user's space to find the corresponding air conditioning equipment information; The large model classifies the semantic text of the user's instruction into corresponding instruction types through prompt word engineering; if the large model fails to parse or understand the semantic text of the user's instruction, it will feedback "instruction failed to parse"; If the semantic text of the user instruction contains a clear time, the execution time of the instruction is set to the clear time through the semantic analysis of the large model; if the semantic text of the user instruction does not contain a clear time, the execution time is set to be executed immediately; Output the device control instructions in json format. The device control instructions output by the large model are constrained to output json strings through prompt, including: the executed air-conditioning equipment information, instruction type, execution instruction value and execution instruction time.

4. The central air conditioning control method according to claim 1 or 2, characterized in that: The types of large models include: deepseek and Tongyi Qianwen.

5. The central air conditioning control method according to claim 1, wherein: The large model is deployed locally or uses an online large model interface.

6. The central air conditioning control method according to claim 1, wherein: The air conditioning equipment adjustment strategy is obtained by judging the command according to the equipment control command, including: Establish a load forecasting model based on data including historical outdoor wet-bulb temperatures, historical cooling load values, and air conditioning terminal temperature settings; Input information such as the current outdoor wet-bulb temperature, the air conditioning terminal temperature required by the device control instruction, and the ratio of the space area to the total area into the load forecasting model to obtain the actual load demand required according to the user's required temperature; Compare the user's required temperature with the current air conditioning unit's temperature setting and the chilled water supply and return temperature difference. If the load adjustment at the air conditioning unit's terminal is determined to meet the actual load demand, the air conditioning unit's adjustment strategy is to only adjust the temperature setting and wind speed at the air conditioning unit's terminal. If the air conditioning equipment terminal adjustment cannot meet the actual load demand, it is determined whether the central air conditioning room water pump frequency adjustment and host temperature setting are used. If so, the air conditioning equipment adjustment strategy is to perform actual load demand control to adjust to meet the actual load demand without turning on additional hosts and water pumps. This is called primary cooling source adjustment. If the actual load demand can only be determined by adding or subtracting machines from the host and adjusting the number of water pumps turned on, the air-conditioning equipment adjustment strategy is to perform advanced cold source adjustment. The advanced cold source adjustment is achieved by executing the logic of adding and subtracting machines from the refrigeration host. The adding logic opens the cold water inlet and outlet valves, cooling tower fan, cooling water pump and cold water pump in sequence, and finally starts the chiller. A certain delay is required between each step; the subtracting logic is to execute the cooling tower fan, cooling water pump, cold water pump and close the cold water inlet and outlet valves in sequence after the chiller is shut down. There is a preset delay between each step.

7. The central air conditioning control method according to claim 6, characterized in that: Performing a command safety check on the air conditioning equipment adjustment strategy to obtain an equipment adjustment strategy after the safety check, including: Determine the equipment association and operation logic in the air conditioning equipment adjustment strategy to obtain the equipment adjustment strategy after safety inspection.

8. The central air conditioning control method according to claim 1, wherein: The device adjustment strategy after the safety check is executed and feedback is provided through the execution program, and the results of the execution program are fed back to the user, including: Send the device adjustment policy that has passed the security check and confirmed by the user to the execution program for execution; The execution program feeds back the results of the execution program to the user.

9. A computer-readable storage medium having computer-executable instructions stored thereon, wherein: When the computer executable instructions are executed by a processor, the processor is caused to perform the method according to any one of claims 1 to 8.

10. A computer device, wherein: include: processor; as well as A memory arranged to store computer executable instructions which, when executed, cause the processor to: perform the method according to any one of claims 1 to 8.

Images