Building heating and ventilation effect evaluation method based on artificial intelligence

Abstract

The invention relates to the technical field of heating ventilation air conditioners, in particular to a building heating ventilation effect evaluation method based on artificial intelligence, which comprises the steps of data acquisition, data preprocessing, feature extraction, artificial intelligence model construction, dynamic evaluation and adjustment and visual display. A plurality of sensors are arranged inside and outside a building to collect multi-source data in real time, the multi-source data are preprocessed, key features such as environment temperature and humidity change trends, airflow distribution, equipment load states and energy efficiency parameters are extracted, a three-classification artificial intelligence model is built through a support vector machine, and the three-classification artificial intelligence model is used for building an artificial intelligence model. The heating and ventilation effect is evaluated in real time, and a report is generated. And finally, the evaluation result is displayed through a visual interface, a user is helped to master the operation state of the heating and ventilation system in real time and propose optimization and adjustment suggestions, through application of the artificial intelligence model, multiple data sources can be comprehensively considered, the effect of the building heating and ventilation system is accurately evaluated, errors of manual evaluation are avoided, and the evaluation accuracy is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of heating, ventilation and air conditioning, and particularly to a method for evaluating the heating and ventilation effect of a building based on artificial intelligence. Background Art

[0002] With the improvement of building energy efficiency standards and the continuous development of intelligent building technologies, the energy efficiency and comfort of building heating, ventilation and air conditioning systems have become key elements in building design and operation. While meeting the requirements of indoor temperature, humidity and air quality, the building heating and ventilation system also needs to maintain a good energy efficiency level to reduce energy consumption and operating costs. Therefore, real-time monitoring and evaluation of the operation effect of the heating and ventilation system have become an important means to improve building energy efficiency and comfort.

[0003] Most of the existing methods for evaluating the heating and ventilation effect of buildings rely on traditional manual experience and regular inspections, and cannot evaluate the operation effect of the heating and ventilation system in real time and accurately. In the prior art, although there are some methods based on data collection and analysis, the following problems often exist: most of the data processing and analysis in the prior art rely on simple statistical methods, which are difficult to process high-dimensional and diverse data features, cannot deeply mine useful patterns and rules, and lack an intelligent evaluation mechanism, and cannot adjust the operation strategy of the heating and ventilation system according to the real-time evaluation results. Therefore, how to improve the intelligent level of heating and ventilation effect evaluation and accurately and comprehensively evaluate the operation effect of the heating and ventilation system has become an urgent technical problem to be solved. Summary of the Invention

[0004] The present invention provides a method for evaluating the heating and ventilation effect of a building based on artificial intelligence.

[0005] A method for evaluating the heating and ventilation effect of a building based on artificial intelligence includes the following steps:

[0006] S1, data collection: By deploying a variety of sensors inside and outside the building, multi-source data is collected in real time, and the multi-source data includes equipment operation status, external climate data, indoor temperature, humidity and air flow velocity;

[0007] S2, data preprocessing: The collected multi-source data is preprocessed, and the preprocessing includes data cleaning, denoising, missing value filling and data standardization;

[0008] S3, feature extraction: Based on the preprocessed multi-source data, key features helpful for evaluating the heating and ventilation effect are extracted, including environmental temperature and humidity change trends, air flow distribution, equipment load status and energy efficiency parameters;

[0009] S4, artificial intelligence model construction: Using the support vector machine algorithm, an artificial intelligence model is established for evaluating the effect of the building heating and ventilation system;

[0010] S5, Dynamic Evaluation and Adjustment: Based on multi-source data collected in real time, the heating and ventilation effect is evaluated in real time through an artificial intelligence model, and corresponding adjustment suggestions are generated;

[0011] S6, Visualization Display: An evaluation report is generated based on the evaluation and displayed through a visual interface.

[0012] Optionally, S1 includes:

[0013] S11, Equipment Operating Status Collection: By installing intelligent sensors on building heating and ventilation equipment, the working status data of the equipment is collected in real time, including equipment switch status, operating mode, temperature control set value, and actual output power;

[0014] S12, External Climate Data Collection: By installing meteorological sensors outside the building, external climate data is collected in real time, including outdoor temperature and humidity;

[0015] S13, Indoor Temperature Collection: By deploying temperature sensors in multiple areas of the building (such as each room and corridor), the temperature data of each indoor area is monitored in real time;

[0016] S14, Indoor Humidity Collection: By installing humidity sensors in multiple areas of the building (such as each room and corridor), the indoor humidity level is monitored in real time;

[0017] S15, Indoor Airflow Velocity Collection: By installing wind speed sensors indoors, the airflow velocity and flow direction data are collected in real time.

[0018] Optionally, S2 includes:

[0019] S21, Data Cleaning: The collected multi-source data is screened to remove invalid data and duplicate data;

[0020] S22, Data Denoising: The collected multi-source data is filtered using mean filtering technology to improve the reliability of the data;

[0021] S23, Missing Value Filling: For missing values that occur during the data collection process, they are filled through linear interpolation.

[0022] S24, Data Standardization: The collected multi-source data is processed for data standardization to make sensor data from different sources and with different units comparable.

[0023] Optionally, S3 includes:

[0024] S31, Extraction of Environmental Temperature and Humidity Change Trends: Historical time series analysis is performed on the preprocessed indoor and outdoor temperature and humidity data to extract the change trends of indoor and outdoor temperature and humidity;

[0025] S32, Extraction of air flow distribution characteristics: Extract the characteristics of air flow distribution by analyzing the collected indoor air flow velocity and direction data;

[0026] S33, Extraction of equipment load status and energy efficiency parameters: Extract equipment load and energy efficiency parameters by collecting the operating status data of building heating, ventilation and air conditioning equipment.

[0027] Optionally, the S4 includes:

[0028] S41, Model construction: Construct an artificial intelligence model based on the support vector machine algorithm;

[0029] S42, Preparation of training data: Generate a training data set according to the extracted key features (trends of environmental temperature and humidity changes, air flow distribution, equipment load status and energy efficiency parameters), and define the classification labels of the training data set;

[0030] S43, Model training: Use the training data set to train the constructed artificial intelligence model.

[0031] Optionally, the S5 includes:

[0032] S51. Real-time data collection and input: Collect multi-source data in real time. After data preprocessing and feature extraction, input the extracted key features into the artificial intelligence model;

[0033] S52. Real-time evaluation: The artificial intelligence model outputs the evaluation result of the building heating, ventilation and air conditioning effect based on the input key features.

[0034] S53. Adjustment suggestions: Generate corresponding adjustment suggestions based on the evaluation results.

[0035] Optionally, the S6 includes:

[0036] S61, Generate an evaluation report: Generate a heating, ventilation and air conditioning effect evaluation report according to the real-time evaluation result of the artificial intelligence model. The report content includes the evaluation result (good effect, average effect or poor effect) and the corresponding adjustment suggestions;

[0037] S62, Visualization interface: Display the evaluation result and the corresponding adjustment suggestions through the visualization interface according to the generated evaluation report;

[0038] S63, Real-time update and display: Automatically refresh the visualization interface according to the changes of real-time multi-source data and the update of evaluation results to ensure that the displayed content is always the latest evaluation result.

[0039] Optionally, the heating, ventilation and air conditioning effect evaluation report supports being exported to various format files, including PDF, Excel or Word formats, which is convenient for users to save, print or further analyze.

[0040] Advantages of the present invention:

[0041] In the present invention, through an evaluation method based on artificial intelligence, combined with multi-source data collection and processing, the effect of a building's heating, ventilation, and air conditioning (HVAC) system can be evaluated efficiently and accurately. By using the support vector machine algorithm to construct an artificial intelligence model for classifying real-time multi-source data, the excellent and poor states of the building's HVAC effect can be accurately identified. The model classification supports three different categories (such as good effect, general effect, and poor effect), thereby providing an evaluation of the operation effect of the HVAC system, helping engineers and managers to timely understand the operation status of the HVAC system, and avoiding potential energy efficiency waste or system failures.

[0042] The present invention can not only conduct a static evaluation of the HVAC system but also generate adjustment suggestions. When a certain category (such as poor effect) is evaluated, intelligent adjustment suggestions can be generated in real time. The generation of the suggestions is based on the classification results, ensuring that each evaluation category corresponds to a different optimization strategy, thereby adjusting the HVAC system in a targeted manner, improving energy utilization efficiency, reducing maintenance costs, and extending the equipment life.

[0043] In the present invention, the evaluation results are displayed through a visualization interface. Through the visualization interface, users can intuitively view the evaluation results of the building's HVAC system and generate a detailed evaluation report. In addition, the evaluation report supports an export function, and users can save or share the report in a standardized format, facilitating further analysis and decision-making. This function enhances the operability and convenience of the system, enabling users to quickly obtain and apply the evaluation results. Brief Description of the Drawings

[0044] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following will briefly introduce the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings in the following description are only those of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0045] Figure 1 It is a schematic diagram of the method flow of an embodiment of the present invention;

[0046] Figure 2 It is a schematic diagram of the S4 and S5 processes of an embodiment of the present invention. Detailed Embodiments

[0047] The following will describe the present invention in detail with reference to the drawings and specific embodiments. At the same time, it should be noted here that in order to make the embodiments more detailed, the following embodiments are the best and preferred embodiments. For some well-known technologies, those skilled in the art can also adopt other alternative methods for implementation; and the drawings are only for more specifically describing the embodiments and are not intended to specifically limit the present invention.

[0048] It should be noted that in the specification, when referring to "an embodiment", "embodiment", "exemplary embodiment", "some embodiments", etc., it indicates that the described embodiment may include specific features, structures or characteristics, but not necessarily every embodiment includes such specific features, structures or characteristics. Additionally, when combining an embodiment to describe a specific feature, structure or characteristic, implementing such feature, structure or characteristic in combination with other embodiments (whether explicitly described or not) should be within the knowledge scope of those skilled in the relevant art.

[0049] Generally, terms can be understood at least in part from their use in context. For example, at least in part depending on the context, the term "one or more" as used herein can be used to describe any feature, structure or characteristic in a singular sense, or can be used to describe a combination of features, structures or characteristics in a plural sense. Additionally, the term "based on" can be understood as not necessarily intended to convey a set of exclusive factors, but rather, at least in part depending on the context, can allow for the existence of other factors that are not necessarily explicitly described.

[0050] As Figure 1 - Figure 2 shown, an artificial intelligence-based method for evaluating the heating, ventilation and air conditioning (HVAC) effect of a building includes the following steps:

[0051] S1, data collection: By deploying a variety of sensors inside and outside the building, multi-source data is collected in real time, and the multi-source data includes equipment operation status, external climate data, indoor temperature, humidity and air flow velocity;

[0052] S2, data preprocessing: Preprocess the collected multi-source data, and the preprocessing includes data cleaning, denoising, missing value filling and data standardization;

[0053] S3, feature extraction: Based on the preprocessed multi-source data, key features helpful for evaluating the HVAC effect are extracted, including the changing trends of environmental temperature and humidity, air flow distribution, equipment load status and energy efficiency parameters;

[0054] S4, artificial intelligence model construction: The support vector machine algorithm is adopted to establish an artificial intelligence model for evaluating the effect of the building HVAC system;

[0055] S5, dynamic evaluation and adjustment: Based on the real-time collected multi-source data, the HVAC effect is evaluated in real time through the artificial intelligence model, and corresponding adjustment suggestions are generated;

[0056] S6, visualization display: An evaluation report is generated according to the evaluation and displayed through a visualization interface.

[0057] S1 includes:

[0058] S11, Collection of equipment operation status: By installing intelligent sensors on building heating, ventilation, and air conditioning (HVAC) equipment, real-time collection of equipment operating status data is carried out, including equipment switch status, operation mode, temperature control set value, and actual output power. The intelligent sensors include:

[0059] Relay status sensor: The relay status sensor is used to monitor the switch status of the equipment in real time. These sensors can detect the on / off status of the equipment power supply, thereby determining whether the equipment is in the on or off state;

[0060] Operation mode sensor: The operation mode sensor and the control system interface are used to obtain the operation mode of the equipment. For example, HVAC equipment sets different operation modes (such as heating, cooling, dehumidification, etc.) through an intelligent control system, and the sensor obtains the current operation mode in real time through the data interface with the equipment control system;

[0061] Thermostat: The thermostat is used to obtain the set temperature value of the equipment. The thermostat is directly connected to the temperature control system of the HVAC equipment and can obtain the target temperature value set by the user;

[0062] Power monitoring sensor: The actual power output of the HVAC equipment is monitored in real time through the power monitoring sensor. The power sensor can accurately measure the power consumption of the equipment during operation, and then calculate the actual output power;

[0063] S12, Collection of external climate data: By installing meteorological sensors outside the building, real-time collection of external climate data is carried out, including outdoor temperature and humidity;

[0064] S13, Collection of indoor temperature: By deploying temperature sensors in multiple areas of the building (such as each room and corridor), real-time monitoring of the temperature data in each indoor area is carried out. The temperature data collected by the sensors provides intuitive temperature information for evaluating the HVAC effect inside the building and helps to judge the temperature control effect in each area;

[0065] S14, Collection of indoor humidity: By installing humidity sensors in multiple areas of the building (such as each room and corridor), the indoor humidity level is monitored in real time. These data can reflect the humidity distribution inside the building, further help to evaluate the effect of the HVAC system on indoor humidity regulation, and provide a basis for the optimization of air conditioning and humidification equipment;

[0066] S15, Collection of indoor air flow velocity: By installing wind speed sensors indoors, real-time collection of air flow velocity and flow direction data is carried out. The air flow velocity and flow direction data can reflect whether the HVAC system effectively distributes air flow and helps to evaluate the impact of air flow distribution on the uniformity of temperature and humidity, and then judge the comprehensive effect of the HVAC system.

[0067] S2 includes:

[0068] S21, Data cleaning: Screen the multi-source data collected, and remove invalid data and duplicate data, specifically including:

[0069] Data integrity check: Check whether each piece of data is complete, and delete or mark the missing items;

[0070] Duplicate data detection: Compare the data collected by the same sensor within the same time period, and delete the duplicate records;

[0071] S22, Data denoising: Use the mean filtering technique to filter the multi-source data collected to improve the reliability of the data, specifically including:

[0072] Filter processing: Use the mean filtering technique to smooth the data with large fluctuations collected by the sensor and remove the random noise;

[0073] Data processing flow: For the sensor data at each time step:

[0074] Obtain the data at the current moment and several moments before and after it;

[0075] Perform an average calculation on this data to obtain a new value;

[0076] Output the new value as the data at the current moment to replace the original collected value;

[0077] Repeat this process until all the data is processed;

[0078] S23, Missing value filling: For the missing values that occur during the data collection process, fill them through linear interpolation to ensure the integrity of the data;

[0079] Linear interpolation method: For the missing data points, use the linear relationship between the valid data points before and after to fill them. Specifically, if the temperature data at a certain moment is missing, then according to the data values T 1 (data at the previous moment) and T 2 (data at the next moment), use the linear interpolation formula to fill it, expressed as:

[0080]

[0081] Among them, T 1 is the data at the previous moment, T 2 is the data at the next moment, t 1 and t 2 are the previous and next moments respectively, and t fill is the time point where the missing value is located.

[0082] S24, Data standardization: Perform data standardization processing on the multi-source data collected to make the sensor data from different sources and with different units comparable, specifically including:

[0083] Z-Score normalization: By calculating the mean and standard deviation of the data, the data is converted into a standard normal distribution with zero mean and unit variance, which is applicable to comparing sensor data of different scales.

[0084] S3 includes:

[0085] S31, extraction of environmental temperature and humidity change trends: Conduct historical time series analysis on the preprocessed indoor and outdoor temperature and humidity data to extract the change trends of indoor and outdoor temperature and humidity. The specific method is as follows:

[0086] Calculate the historical fluctuation range, periodic changes, and long-term change trends of indoor and outdoor temperature and humidity data;

[0087] Analyze the correlation between temperature data and humidity data, extract the main trends of temperature and humidity changes, and form feature vectors;

[0088] S32, extraction of airflow distribution characteristics: By analyzing the collected indoor airflow velocity and flow direction data, extract the characteristics of airflow distribution, specifically including:

[0089] Based on the preprocessed airflow velocity and flow direction data, use spatial interpolation methods (such as Kriging interpolation) to establish a distribution map of the airflow field;

[0090] Analyze the uniformity of the airflow field, the distribution range of airflow velocity, and the local airflow changes in specific areas;

[0091] Extract the spatial characteristics of airflow distribution, including the position of the maximum flow velocity and the airflow concentration area;

[0092] S33, extraction of equipment load status and energy efficiency parameters: By collecting the operating status data of building heating, ventilation, and air conditioning equipment, extract equipment load and energy efficiency parameters, specifically including:

[0093] Analyze the working status of the equipment (such as switch status, operating mode, temperature control set value, etc.) and calculate the load level of the equipment;

[0094] Evaluate the energy efficiency parameters of the equipment by the ratio of the temperature control set value to the actual output power;

[0095] Combined with historical load data, extract the energy efficiency performance of the equipment under different load statuses, including the correlation between load and energy efficiency.

[0096] S4 includes:

[0097] S41, model construction: Based on the support vector machine algorithm, construct an artificial intelligence model;

[0098] S42. Training data preparation: Based on the extracted key features (environmental temperature and humidity change trends, air flow distribution, equipment load status, and energy efficiency parameters), generate a training data set and define the classification labels for the training data set. The classification labels for the data set are defined as:

[0099] Good effect: Indicates that the HVAC system is operating well, and the environmental temperature, humidity, air flow distribution, and equipment load status are all within the set range, with high comfort in the building;

[0100] Average effect: Indicates that the HVAC system is operating moderately, there are certain temperature and humidity unevenness or air flow problems, the equipment load is relatively high, but it has not reached the system overload state;

[0101] Poor effect: Indicates that the HVAC system is operating poorly, the environmental temperature and humidity are abnormal, the air flow distribution is uneven, the equipment load is too high or there is energy waste, and the building does not meet the comfort standard;

[0102] The training data set includes samples of the above three categories. Each sample in the data set includes the environmental temperature and humidity change trends, air flow distribution, equipment load status, and energy efficiency parameter feature values;

[0103] S43. Model training: Use the training data set to train the constructed artificial intelligence model. The goal of the artificial intelligence model is to classify the building HVAC effect based on the input features (environmental temperature and humidity change trends, air flow distribution, equipment load status, and energy efficiency parameters). The optimization goal of the artificial intelligence model is to maximize the classification margin, and the objective function is expressed as;

[0104]

[0105] where, x i is the feature vector of the i-th sample, y i is the class label of the i-th sample, w is the normal vector of the classification hyperplane, b is the bias term, and ||w|| is the maximization target of the hyperplane distance.

[0106] S5 includes:

[0107] S51. Real-time data collection and input: Real-time collect multi-source data. After data preprocessing and feature extraction, input the extracted key features into the artificial intelligence model;

[0108] S52. Real-time evaluation: Based on the input key features, the artificial intelligence model outputs the evaluation result of the building HVAC effect. The evaluation result includes three categories:

[0109] Good effect: The HVAC system is operating well and meets the comfort requirements of the building;

[0110] Average effect: There are slight problems with the HVAC system and adjustments are required;

[0111] Poor effect: There are serious problems with the HVAC system, and it needs to be repaired or optimized immediately.

[0112] S53. Adjustment suggestions: Based on the evaluation results, corresponding adjustment suggestions are generated. The adjustment suggestions include:

[0113] Good effect: No adjustment is required, and the existing operation mode should be maintained;

[0114] Average effect: It is recommended to adjust the equipment operation mode and temperature control set value to optimize the working efficiency of the air conditioner or heating equipment;

[0115] Poor effect: It is recommended to stop the machine and troubleshoot, or replace the faulty equipment, and perform manual adjustment or inspection of temperature and humidity.

[0116] S6 includes:

[0117] S61, Generate an evaluation report: According to the real-time evaluation results of the artificial intelligence model, generate an HVAC effect evaluation report. The report content includes the evaluation results (good effect, average effect or poor effect) and corresponding adjustment suggestions;

[0118] S62, Visual interface: According to the generated evaluation report, display the evaluation results and corresponding adjustment suggestions through a visual interface;

[0119] S63, Real-time update display: According to the changes in real-time multi-source data and the update of the evaluation results, automatically refresh the visual interface to ensure that the displayed content is always the latest evaluation result.

[0120] The HVAC effect evaluation report supports being exported to various format files, including PDF, Excel or Word formats, which is convenient for users to save, print or further analyze.

[0121] This invention covers any substitutions, modifications, equivalent methods and solutions made within the essence and scope of this invention. To enable the public to have a thorough understanding of this invention, specific details are described in detail in the following preferred embodiments of this invention. However, those skilled in the art can fully understand this invention even without the description of these details. Additionally, to avoid unnecessary confusion to the essence of this invention, well-known methods, processes, procedures, components and circuits, etc. are not described in detail.

[0122] The above are only the preferred embodiments of this invention. It should be noted that for those of ordinary skill in the art in this technical field, without departing from the principle of this invention, several improvements and refinements can be made, and these improvements and refinements should also be regarded as the protection scope of this invention.

Claims

1. A building HVAC effect evaluation method based on artificial intelligence, characterized in that: The following steps are involved: S1, data collection: by deploying a variety of sensors inside and outside the building, multi-source data is collected in real time, including equipment operation status, external climate data, indoor temperature, humidity and airflow speed; S2, data preprocessing: preprocess the collected multi-source data, including data cleaning, denoising, missing value filling and data standardization; S3, feature extraction: Based on the preprocessed multi-source data, key features that are helpful in evaluating the HVAC effect are extracted, including the trend of ambient temperature and humidity changes, airflow distribution, equipment load status and energy efficiency parameters; S4, AI model construction: Using support vector machine algorithm, an AI model is built to evaluate the effectiveness of building HVAC systems; S5, dynamic evaluation and adjustment: Based on multi-source data collected in real time, the HVAC effect is evaluated in real time through artificial intelligence models, and corresponding adjustment suggestions are generated; S6, Visualization Display: Generate an evaluation report based on the evaluation and display it through a visualization interface.

2. The method for evaluating building HVAC effects based on artificial intelligence according to claim 1 is characterized in that: The S1 includes: S11, equipment operation status collection: by installing intelligent sensors on building HVAC equipment, the equipment's working status data is collected in real time, including equipment switch status, operation mode, temperature control set value and actual output power; S12, external climate data collection: by installing meteorological sensors on the outside of the building, real-time external climate data, including outdoor temperature and humidity; S13, indoor temperature collection: by deploying temperature sensors in multiple areas of the building, real-time monitoring of temperature data of various indoor areas; S14, indoor humidity collection: by installing humidity sensors in multiple areas of the building, the indoor humidity level is monitored in real time; S15, indoor air flow velocity collection: by installing wind speed sensors indoors, real-time air flow velocity and flow direction data are collected.

3. The method for evaluating building HVAC effects based on artificial intelligence according to claim 2 is characterized in that: The S2 includes: S21, data cleaning: screening the collected multi-source data to remove invalid data and duplicate data; S22, data denoising: use mean filtering technology to filter the collected multiple sources to improve the reliability of the data; S23, missing value filling: missing values ​​that occur during data collection are filled by linear interpolation; S24, data standardization: Perform data standardization on the collected multi-source data to make sensor data from different sources and different units comparable.

4. The method for evaluating building HVAC effects based on artificial intelligence according to claim 3 is characterized in that: The S3 includes: S31, extraction of environmental temperature and humidity change trend: performing historical time series analysis on the pre-processed indoor and outdoor temperature and humidity data to extract the change trend of indoor and outdoor temperature and humidity; S32, air flow distribution feature extraction: extracting air flow distribution features by analyzing the collected indoor air flow velocity and flow direction data; S33, equipment load status and energy efficiency parameter extraction: extract equipment load and energy efficiency parameters by collecting operating status data of building HVAC equipment.

5. The method for evaluating building HVAC effects based on artificial intelligence according to claim 4 is characterized in that: The S4 includes: S41, Model construction: Build artificial intelligence model based on support vector machine algorithm; S42, training data preparation: generating a training data set based on the extracted key features, and defining classification labels for the training data set; S43, model training: Use training data sets to train the constructed artificial intelligence model.

6. The method for evaluating building HVAC effects based on artificial intelligence according to claim 5 is characterized in that: The S5 includes: S51. Real-time data collection and input: Real-time data collection from multiple sources, after data preprocessing and feature extraction, the extracted key features are input into the trained artificial intelligence model; S52. Real-time evaluation: The AI ​​model outputs the building HVAC effect evaluation results based on the key features of the input; S53. Adjustment suggestions: Generate corresponding adjustment suggestions based on the evaluation results.

7. The method for evaluating building HVAC effects based on artificial intelligence according to claim 6 is characterized in that: The S6 includes: S61, generate an evaluation report: generate a HVAC effect evaluation report based on the real-time evaluation results of the artificial intelligence model, and the report content includes the evaluation results and corresponding adjustment suggestions; S62, Visualization interface: Based on the generated evaluation report, the evaluation results and corresponding adjustment suggestions are displayed through the visualization interface; S63, real-time update display: automatically refresh the visualization interface according to the changes in real-time multi-source data and the updates of evaluation results.

8. The method for evaluating building HVAC effects based on artificial intelligence according to claim 7 is characterized in that: The HVAC effect evaluation report can be exported to multiple file formats, including PDF, Excel or Word, to facilitate users to save, print or further analyze.

Images