Method and device for determining comfort level of underground space
By constructing a multidimensional environmental feature database for underground space using K-means clustering and decision tree regression models, the problem of multidimensional coordination in underground space comfort evaluation was solved, enabling accurate comfort assessment and long-term environmental quality prediction, thereby improving management efficiency and operational effectiveness.
Patent Information
- Application Number
- CN202511540912.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-10-27
- Publication Date
- 2026-02-06
AI Technical Summary
Existing research has failed to effectively and comprehensively assess the synergistic effects of multidimensional environmental factors in underground spaces, resulting in discrepancies between comfort assessment results and actual perceptions, a lack of ability to predict long-term environmental quality changes, and the subjectivity and one-sidedness of traditional methods.
A multidimensional environmental feature database is constructed using a method based on K-means clustering and decision tree regression model. Through data preprocessing, clustering, and decision tree regression model, future changes in environmental parameters are predicted, a comfort assessment report is generated, and accurate comfort thresholds and intelligent control strategies are provided.
It enables a more scientific and reproducible comfort assessment, comprehensively evaluates the synergistic effects of multi-dimensional environmental factors, predicts long-term environmental quality changes, improves management efficiency and reduces operation and maintenance costs, and supports intelligent energy-saving and environmental control strategies.
Smart Images
Figure CN121480930A_ABST
Abstract
Description
Technical Field
[0001] This disclosure relates to underground space environmental treatment technology, and in particular to a method and apparatus for determining the comfort level of underground spaces. Background Technology
[0002] Urban underground spaces possess characteristics significantly different from above-ground environments, such as enclosed spaces, constant temperature and humidity, and high protective features. Their development and utilization present a series of unique challenges, including significant temperature and humidity differences (above-ground / underground), the potential impact of subway vibrations on the surrounding environment, the conflict between large-space lighting and energy conservation, and issues commonly reported by passengers such as high humidity, poor air quality, lack of natural light, and poor spatial orientation. These problems can easily trigger negative psychological emotions such as anxiety and unease among passengers while waiting for trains. Therefore, minimizing or even mitigating these negative psychological associations in the design of underground spaces is of great significance for improving the quality of life for residents.
[0003] Taking subway systems in large cities as an example, the complexity of environmental comfort management is particularly prominent. In terms of time, early lines suffered from cramped spaces and outdated ventilation designs; while new lines introduced intelligent control, they faced the challenge of balancing energy consumption and comfort. Seasonal and operational time variations further amplified environmental differences, while off-peak periods resulted in wasted equipment idling. In terms of space and population, different groups, such as commuters and tourists, the elderly and young people, exhibited significantly divergent needs regarding efficiency, convenience, clear signage, rest area comfort, and intelligent services. This dynamic evolution of the spatial and temporal environment, intertwined with the diversification of population needs, makes it difficult for a single environmental management strategy to simultaneously address passenger experience and system operational efficiency.
[0004] With the acceleration of urbanization, the environmental comfort of underground spaces has become a research hotspot. Current research focuses on the impact of physical environmental factors such as heat, sound, and light on human comfort and work efficiency. From the perspective of individual environmental factors: In terms of the thermal environment, existing research reveals that underground spaces are characterized by strong thermal stability and high humidity. Although current standards and regulations specify temperature and humidity ranges, they do not consider differences in different climate zones, and the evaluation models deviate from actual perceptions in underground spaces. In terms of the acoustic environment, existing research shows that noise in underground spaces is mainly low-frequency mechanical noise with long reverberation times. In terms of the light environment, existing research indicates that underground spaces rely on artificial lighting. Related studies or regulations mostly focus on illuminance parameters, ignoring color temperature and non-visual physiological effects, and lack systematic evaluation indicators.
[0005] Existing research has found that the interaction of multiple environmental factors in underground spaces significantly impacts overall comfort. For example, high temperatures amplify noise-induced irritation, while high color temperature lighting can alleviate heat discomfort. However, research on the coupling mechanisms of these multiple factors still needs improvement. More importantly, evaluation methods for the comfort of subway space environments are particularly lacking, and a comprehensive evaluation system that integrates objective physical environmental conditions and subjective feelings is absent, leading to discrepancies between evaluation results and actual user perceptions. Therefore, future research should focus on constructing a comprehensive evaluation system that coordinates multiple factors, and combining it with intelligent environmental control technologies and dynamic management strategies to promote the refinement and scientific development of subway space environment comfort evaluation systems.
[0006] Current research on the comfort of underground spaces has the following gaps: Previous studies have mostly explored the impact of single environmental factors in isolation, such as light or sound, neglecting the fact that people simultaneously receive stimuli from multiple environments, and that overall human comfort is the result of the synergistic effect of multiple senses. Existing research often reflects environmental conditions at specific points in time. While subway systems, as long-term operations, experience aging of equipment such as lighting and train tracks over time, few studies address how environmental quality deteriorates with operational years or how to predict its long-term trends. Traditional research methods rely heavily on conventional statistical analysis and single evaluation indicators, which have many limitations, such as insufficient data validation, low accuracy in comfort assessments, and a lack of ability to predict environmental changes. Summary of the Invention
[0007] This disclosure provides a method and apparatus, electronic device and storage medium to solve the above problems.
[0008] A first aspect of this disclosure provides a method for determining the comfort level of an underground space, comprising: Based on historical passenger flow and historical environmental data of the target underground space, as well as a questionnaire survey of the target underground space, a multidimensional environmental feature database of the target underground space is constructed. After preprocessing the historical passenger flow and historical environmental data, clustering is performed on the preprocessed historical passenger flow and historical environmental data. Based on the clustering results, the comfort level of the target underground space is divided and the dynamic threshold of environmental comfort is optimized. Using a decision tree regression model, the dynamic changes of future environmental parameters of the target underground space over time are predicted based on preprocessed historical passenger flow and historical environmental data. Based on the dynamic changes of the future environmental parameters of the target underground space over time, and the optimized dynamic threshold of environmental comfort, an assessment report on the future comfort of the target underground space is generated.
[0009] In some embodiments of this disclosure, the historical environmental data includes acoustic environmental parameters, light environmental parameters, thermal environmental parameters, and air quality parameters for historical time periods.
[0010] In some embodiments of this disclosure, the data preprocessing includes outlier identification, outlier removal, missing value imputation, and conversion of text data into binary data.
[0011] In some embodiments of this disclosure, the step of clustering the preprocessed historical passenger flow and historical environmental data, classifying the comfort level of the target underground space based on the clustering results, and optimizing the dynamic threshold of environmental comfort includes: The elbow method is used to calculate the sum of squared errors for different K values in order to determine the elbow point on the K-SSE curve. The elbow points were validated based on the silhouette coefficient and the questionnaire to obtain the optimal number of clusters. Based on the optimal number of clusters, the preprocessed historical passenger flow and historical environmental data are clustered. Based on the clustering results, the comfort level of the target underground space is divided and the dynamic threshold of environmental comfort is optimized.
[0012] In some embodiments of this disclosure, the decision tree regression model selects the optimal split point to minimize the weighted mean square error of the split subsets and outputs the label mean of the samples through the leaf nodes.
[0013] In some embodiments of this disclosure, the assessment report includes a comprehensive assessment of the comfort level of the target underground space in each area during peak hours, a recommended adjustment threshold range, areas and environmental indicators predicted to fall out of the comfort threshold range at a future target time, and maintenance plan information with the comfort threshold as the adjustment direction.
[0014] A second aspect of this disclosure provides a device for determining the comfort level of an underground space, comprising: An environmental feature database construction module is used to construct a multi-dimensional environmental feature database of the target underground space based on historical visitor flow and historical environmental data of the target underground space, as well as a questionnaire for the target underground space. The clustering module is used to preprocess the historical passenger flow and historical environmental data, then perform clustering on the preprocessed historical passenger flow and historical environmental data, and classify the comfort level of the target underground space based on the clustering results and optimize the dynamic threshold of environmental comfort. The prediction module is used to predict the dynamic changes of future environmental parameters of the target underground space over time based on the historical passenger flow and historical environmental data after data preprocessing using a decision tree regression model. The output module is used to generate a comprehensive assessment report on the future comfort of the target underground space based on the dynamic change pattern of the future environmental parameters of the target underground space over time and the optimized dynamic threshold of environmental comfort.
[0015] In some embodiments of this disclosure, the historical environmental data includes acoustic environmental parameters, light environmental parameters, thermal environmental parameters, and air quality parameters for historical time periods.
[0016] In some embodiments of this disclosure, the data preprocessing includes outlier identification, outlier removal, missing value imputation, and conversion of text data into binary data.
[0017] In some embodiments of this disclosure, the clustering processing module is used to calculate the sum of squared errors under different K values using the elbow method to determine the elbow points on the K-SSE curve; the clustering processing module is also used to verify the elbow points based on the silhouette coefficient and the questionnaire to obtain the optimal number of clusters; the clustering processing module is also used to perform clustering processing on the preprocessed historical passenger flow and historical environmental data based on the optimal number of clusters, and to classify the comfort level of the target underground space and optimize the dynamic threshold of environmental comfort based on the clustering processing results.
[0018] In some embodiments of this disclosure, the decision tree regression model selects the optimal split point to minimize the weighted mean square error of the split subsets and outputs the label mean of the samples through the leaf nodes.
[0019] In some embodiments of this disclosure, the assessment report includes a comprehensive assessment of the comfort level of the target underground space in each area during peak hours, a recommended adjustment threshold range, areas and environmental indicators predicted to fall out of the comfort threshold range at a future target time, and maintenance plan information with the comfort threshold as the adjustment direction.
[0020] A third aspect of this disclosure provides an electronic device, comprising: Memory, used to store computer program products; A processor is configured to execute a computer program product stored in the memory, and when the computer program product is executed, to implement the method described in the first aspect above.
[0021] A fourth aspect of this disclosure provides a computer-readable storage medium having computer program instructions stored thereon, which, when executed by a processor, implement the method described in the first aspect above.
[0022] A fifth aspect of this disclosure provides a computer program product including computer program instructions that, when executed by a processor, cause the processor to perform the method described in the first aspect.
[0023] The method and apparatus for determining the comfort level of underground spaces disclosed in this embodiment are based on an objective comfort level classification method using unsupervised machine learning. This overcomes the subjectivity and bias of traditional assessment methods, making the assessment results more scientific and reproducible. It can comprehensively assess the synergistic effects of multi-dimensional environmental factors such as sound, light, heat, and air quality, and its evaluation results are closer to the actual comprehensive experience of passengers. It achieves long-term prediction of the degradation of subway environmental quality, providing predictive maintenance warnings for operators, significantly improving management efficiency and the scientific nature of decision-making, and reducing the total life-cycle operation and maintenance costs. By providing more accurate and broader comfort thresholds, and combining this with the analysis of the spatiotemporal distribution of pollutants, it provides core algorithms and data support for realizing intelligent energy-saving environmental control strategies (such as on-demand ventilation and dynamic lighting) for "on-demand regulation." In this embodiment, the K-means model and the decision tree regression model are combined in a unique way, meaning that the dynamic environmental parameter thresholds of the K-means clustering results can be used for processing in the decision tree regression model (e.g., sample-based model training and prediction after complete training).
[0024] The technical solutions of this disclosure will be further described in detail below with reference to the accompanying drawings and embodiments. Attached Figure Description
[0025] The accompanying drawings, which form part of this specification, illustrate embodiments of this disclosure and, together with the description, serve to explain the principles of this disclosure.
[0026] This disclosure will become clearer with reference to the accompanying drawings and the following detailed description, wherein: Figure 1 This is a flowchart illustrating a method for determining the comfort level of underground space in one embodiment of this disclosure; Figure 2 This is a schematic diagram of a questionnaire as an example of this disclosure; Figure 3 This is a schematic diagram illustrating the workflow of a method for determining the comfort level of underground spaces, as shown in one example of this disclosure. Figure 4 This is a structural block diagram of a device for determining the comfort level of an underground space according to one embodiment of the present disclosure; Figure 5 This is a structural block diagram of an electronic device in one embodiment of the present disclosure. Detailed Implementation
[0027] Various exemplary embodiments of the present disclosure will now be described in detail with reference to the accompanying drawings. It should be noted that, unless otherwise specifically stated, the relative arrangement, numerical expressions, and values of the components and steps set forth in these embodiments do not limit the scope of the present disclosure.
[0028] Those skilled in the art will understand that the terms "first," "second," etc., in the embodiments of this disclosure are only used to distinguish different steps, devices, or modules, and do not represent any specific technical meaning, nor do they indicate a necessary logical order between them.
[0029] It should also be understood that in the embodiments disclosed herein, "a plurality of" may refer to two or more, and "at least one" may refer to one, two or more.
[0030] It should also be understood that any component, data or structure mentioned in the embodiments of this disclosure can generally be understood as one or more unless expressly defined or given to the contrary in the context.
[0031] Furthermore, the term "and / or" in this disclosure is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. Additionally, the character " / " in this disclosure generally indicates that the preceding and following related objects have an "or" relationship.
[0032] It should also be understood that the description of the various embodiments in this disclosure emphasizes the differences between the various embodiments, and the similarities or similarities can be referred to each other. For the sake of brevity, they will not be described in detail.
[0033] The following description of at least one exemplary embodiment is merely illustrative and is in no way intended to limit this disclosure or its application or use.
[0034] Techniques, methods, and equipment known to those skilled in the art may not be discussed in detail, but where appropriate, such techniques, methods, and equipment should be considered part of the specification.
[0035] It should be noted that similar labels and letters in the following figures indicate similar items; therefore, once an item is defined in one figure, it does not need to be discussed further in subsequent figures.
[0036] The embodiments disclosed herein can be applied to electronic devices such as terminal devices, computer systems, and servers, and can operate together with a wide range of other general-purpose or special-purpose computing system environments or configurations. Examples of well-known terminal devices, computing systems, environments, and / or configurations suitable for use with electronic devices such as terminal devices, computer systems, and servers include, but are not limited to: personal computer systems, server computer systems, thin clients, thick clients, handheld or laptop devices, microprocessor-based systems, set-top boxes, programmable consumer electronics, network PCs, minicomputer systems, mainframe computer systems, and distributed cloud computing environments including any of the above systems, etc.
[0037] Electronic devices such as terminal devices, computer systems, and servers can be described in the general context of computer system executable instructions (such as program modules) executed by a computer system. Typically, program modules can include routines, programs, object programs, components, logic, data structures, etc., which perform specific tasks or implement specific abstract data types. Computer systems / servers can be implemented in distributed cloud computing environments, where tasks are executed by remote processing devices linked through communication networks. In distributed cloud computing environments, program modules can reside on local or remote computing system storage media, including storage devices.
[0038] Figure 1 This is a flowchart illustrating a method for determining the comfort level of an underground space according to one embodiment of this disclosure. Figure 1 As shown, a method for determining the comfort level of an underground space includes the following steps: S1: Based on historical passenger flow and environmental data of the target underground space, as well as questionnaires targeting the target underground space, construct a multi-dimensional environmental characteristic database of the target underground space.
[0039] Objective data collection: In outdoor areas and typical spaces of subway stations (station hall, platform, transfer passage, carriage), professional instruments (such as high-speed cameras, sound level meters, spectrophotometers, thermal environment testers, air quality detectors, etc.) are used to simultaneously collect subway passenger flow and at least four major categories and more than twenty corresponding environmental parameters at specific times and spaces.
[0040] Visitor traffic: number of people, area size, time period.
[0041] In some embodiments of this disclosure, historical environmental data includes the following historical time periods: Acoustic environment parameters: Equivalent continuous A-weighted sound pressure level ( L Aeq )wait.
[0042] Light environment parameters: Illuminance (E), correlated color temperature (CCT), color rendering index (Ra), color tolerance (SDCM), blue light hazard efficacy (KB.V), etc.
[0043] Thermal environment parameters: air temperature (Ta), black bulb temperature (Tg), wet bulb black bulb temperature (WBGT), relative humidity (RH), wind speed (v), etc.
[0044] Air quality parameters: carbon dioxide (CO2), PM2.5, PM10, formaldehyde (HCHO), total volatile organic compounds (TVOC), etc.
[0045] Subjective data collection: Through standardized questionnaires, passengers' ratings of their individual perceptions of the current environment (such as temperature, brightness, and noise level) and overall psychological comfort were collected (see [link to questionnaire]). Figure 2 ).
[0046] S2: After preprocessing the historical passenger flow and historical environmental data, cluster the preprocessed historical passenger flow and historical environmental data, and classify the comfort level of the target underground space based on the clustering results and optimize the dynamic threshold of environmental comfort.
[0047] In some embodiments of this disclosure, data preprocessing includes outlier identification, outlier removal, missing value imputation, and conversion of text data into binary data.
[0048] In some embodiments of this disclosure, step S2 may include the following steps: S2-1: Calculate the sum of squared errors for different K values using the elbow method to determine the elbow point on the K-SSE curve; S2-2: Based on the silhouette coefficient and questionnaire, the elbow points are validated to obtain the optimal number of clusters; S2-3: Based on the optimal number of clusters, perform clustering on the preprocessed historical passenger flow and historical environmental data, and classify the comfort level of the target underground space based on the clustering results and optimize the dynamic threshold of environmental comfort.
[0049] In the data preprocessing for the K-means clustering algorithm, the average value is calculated for multiple data points in the same subway station space. For outliers and missing samples, preliminary clustering is performed first, and then the mean within the same category is used to fill the missing values. To determine the optimal number of clusters (K), a three-step method is adopted: (i) preliminary screening is performed using the elbow method, that is, the sum of squared errors (SSE) under different K values is calculated to determine the "elbow" point on the K-SSE curve; (ii) verification is performed using the silhouette coefficient (SC); and (iii) verification analysis is performed using questionnaire survey data. K-means clustering can accurately identify different areas within the subway station based on environmental data, adaptively optimize the comfort cluster centers, and return the threshold corresponding to each cluster. The output cluster labels can be intuitively associated with the subjective voting results of passengers. Comfort clustering and zoning can be performed based on the sound and light environment data of subway stations in large cities. The results can be compared with existing environmental standards (such as ANSIC78.377-2017 and GB50157-2013) to classify comfort levels and extract key parameters to optimize the comprehensive comfort threshold.
[0050] The corresponding functions for the K-means algorithm are shown in formulas (1) and (2), where formula (1) J The objective function is denoted as (also known as the distortion function / clustering criterion function); Formula (2) µ k The cluster center in formula (1) The updated formula.
[0051] (1) (2) in, n Indicates the total number of samples; x i Indicates the first i One sample, i ∈{1,2,…, n}; c i Indicates sample x i The index of the cluster to which it belongs. c i ∈{1,2,…, K}, K This indicates the pre-defined number of clusters; Indicates sample x i Cluster c i The center; Indicates sample x i To its cluster center The square of the Euclidean distance; C k Belongs to the k A sample set of each cluster; | C k | represents a set C k The number of samples in the middle; Represents a set C k Summation of all samples in the dataset.
[0052] S3: Using a decision tree regression model, predict the dynamic changes of future environmental parameters of the target underground space over time based on historical passenger flow and historical environmental data after data preprocessing.
[0053] In some embodiments of this disclosure, the decision tree regression model selects the optimal split point to minimize the weighted mean square error of the split subsets and outputs the label mean of the samples through the leaf nodes.
[0054] Long-term prediction of environmental comfort based on decision tree regression. First, combining on-site environmental data, the decision tree regression algorithm is used to predict the changes in environmental parameters of subway systems in large cities over five time points: 2, 3, 5, 10, and 20 years. Then, the results are compared with the dynamic comfort threshold proposed based on the K-means algorithm to analyze and judge the changes in environmental comfort under different time and spatial conditions, thereby proposing improvement strategies for optimizing subway environmental comfort.
[0055] By utilizing the decision tree regression algorithm, environmental comfort can be further quantified, enabling the prediction of changes in environmental comfort over operating time, thus facilitating effective management and service of subway operations.
[0056] The specific steps are as follows: Preprocess the data: (i) Use the 3sigma method to identify outliers and fill in the mean of outliers and missing values. (ii) Encode the data of the two non-text categories, location and spatial type, in the independent variables into a format that computers can recognize using 0 and 1. (iii) Then, construct a tree structure using the training set environment data to predict continuous variables: the root node represents the entire sample set, the intermediate nodes correspond to the judgment conditions of the feature variables, and the leaf nodes output the prediction results. The core of the decision tree lies in the feature segmentation criteria and the leaf node prediction rules, as shown in formulas (3) and (4).
[0057] Segmentation Criterion (Minimizing Variance): Decision trees recursively select the best feature. j and optimal segmentation threshold t The dataset is divided into two subsets. The selection criterion is to minimize the sum of the weighted mean squared errors (MSEs) of the two subsets (left and right) resulting from the split.
[0058] (3) in, ( j *, t* () represents the optimal feature and segmentation threshold; N This indicates the number of samples in the current node. N left and N right These are the sample numbers of the left and right subsets after the split, respectively. MSE left and MSE right These are the mean squared errors of the left and right subsets, respectively. The MSE is calculated as follows: ,in y i It is the first in the subset i The true value of each sample It is the average of the true values of all samples in this subset.
[0059] Prediction rule: For a trained decision tree, when a new data sample falls into a leaf node, its predicted value is... The target value for all training samples contained in this leaf node. y i The arithmetic mean.
[0060] (4) in, N leaf This indicates the number of training samples contained in the leaf node; y i This indicates the leaf node with the [missing information] th ... i The true target value of each training sample.
[0061] S4: Based on the dynamic changes of future environmental parameters of the target underground space over time, and the optimized dynamic threshold of environmental comfort, generate an assessment report on the future comfort of the target underground space.
[0062] In some embodiments of this disclosure, the assessment report includes a comprehensive assessment of the comfort levels of the target underground space in various areas during peak hours, recommended adjustment threshold ranges, areas and environmental indicators predicted to fall outside the comfort threshold range at future target time points, and maintenance plan information with the comfort threshold as the adjustment direction.
[0063] Step S2 yields the optimal number of K-means clusters (K) and the cluster center values during off-peak periods. Step S3 provides the prediction data from decision tree regression. The comfort level classification is confirmed using the K value, and then, in accordance with existing environmental regulations, the environmental comfort thresholds for different time periods are optimized using the cluster center values. Finally, using these comfort thresholds as a reference, the predicted values of future environmental parameters are compared to produce the final modular output, including: Comprehensive assessment unit: It can automatically generate comprehensive assessment results of the comfort level of each area at different times during off-peak periods, determine the quality of environmental comfort, and output recommended adjustment threshold ranges.
[0064] Predictive Unit: It can predict in advance when a certain environmental indicator in a certain area will fall below the comfort threshold range, and thus issue an early warning to the operator.
[0065] The intelligent environmental control module uses comfort thresholds as a reference for control direction and future changes in environmental indicators as a guide. It proposes forward-looking and precise maintenance plans for subway management and operation systems, transforming passive maintenance into proactive maintenance and improving energy efficiency to ensure passenger comfort.
[0066] Figure 3 This is a schematic diagram illustrating the workflow of a method for determining the comfort level of underground spaces, as shown in one example of this disclosure. Figure 3 As shown, the method for determining the comfort level of underground spaces may include the following process: After preprocessing the raw data, including historical passenger flow, historical environmental data, and questionnaires, including outlier identification, outlier removal, missing value imputation, and binary conversion of text data, the system proceeds as follows: First, based on the preprocessed data, the optimal cluster number K is determined, K-means clustering analysis is performed, the (environmental) comfort threshold is optimized, and the comfort level and dynamic (environmental comfort) threshold are determined. Second, based on the preprocessed data, the algorithm arithmetic is optimized, a decision tree (regression model) is constructed, and long-term environmental change prediction is performed. The predicted values are compared with the optimized thresholds to determine whether the comfort threshold requirements are met. If the comfort threshold requirements are not met, the environmental parameters that are not met are calculated and the environmental adjustment system (used to adjust acoustic, lighting, thermal, and air quality parameters) and related equipment are optimized based on passenger flow changes and spatial location at different (future) time periods. If the comfort threshold requirements are met, the predicted indicators of various environmental parameters are output, thereby generating a comprehensive evaluation report and predictive adjustment strategies.
[0067] In this embodiment, the objective comfort level classification method based on unsupervised machine learning overcomes the subjectivity and one-sidedness of traditional assessment methods, making the assessment results more scientific and reproducible. It can comprehensively evaluate the synergistic effects of multi-dimensional environmental factors such as sound, light, heat, and air quality, and its evaluation results are closer to passengers' actual comprehensive experience. It achieves long-term prediction of the degradation of subway environmental quality, providing predictive maintenance warnings for operators, significantly improving management efficiency and the scientific nature of decision-making, and reducing the total life-cycle operation and maintenance costs. By providing more accurate and broader comfort thresholds, and combining them with the analysis of the spatiotemporal distribution of pollutants, it provides core algorithms and data support for realizing intelligent energy-saving environmental control strategies such as on-demand ventilation and dynamic lighting. In this embodiment, the K-means model and the decision tree regression model are combined in a unique way, that is, the dynamic environmental parameter threshold of the K-means clustering results can be used for the processing of the decision tree regression model (e.g., sample-based model training and prediction after complete training).
[0068] Figure 4 This is a structural block diagram of a device for determining the comfort level of an underground space according to one embodiment of this disclosure. Figure 4 As shown, the device for determining the comfort level of underground spaces includes: The environmental feature database construction module 100 is used to construct a multi-dimensional environmental feature database of the target underground space based on the historical passenger flow and historical environmental data of the target underground space, as well as a questionnaire for the target underground space. The clustering processing module 200 is used to perform data preprocessing on historical passenger flow and historical environmental data, and then perform clustering on the preprocessed historical passenger flow and historical environmental data. Based on the clustering results, the comfort level of the target underground space is divided and the dynamic threshold of environmental comfort is optimized. The prediction module 300 is used to predict the dynamic changes of future environmental parameters of the target underground space over time based on the decision tree regression model and preprocessed historical passenger flow and historical environmental data. The output module 400 is used to generate a comprehensive assessment report on the future comfort of the target underground space based on the dynamic changes of future environmental parameters of the target underground space over time and the optimized dynamic threshold of environmental comfort.
[0069] In some embodiments of this disclosure, historical environmental data includes acoustic environmental parameters, light environmental parameters, thermal environmental parameters, and air quality parameters for historical time periods.
[0070] In some embodiments of this disclosure, data preprocessing includes outlier identification, outlier removal, missing value imputation, and conversion of text data into binary data.
[0071] In some embodiments of this disclosure, the clustering processing module 200 is used to calculate the sum of squared errors under different K values using the elbow method to determine the elbow point on the K-SSE curve; the clustering processing module 200 is also used to verify the elbow point based on the silhouette coefficient and the questionnaire to obtain the optimal number of clusters; the clustering processing module 200 is also used to perform clustering processing on the preprocessed historical passenger flow and historical environmental data based on the optimal number of clusters, and to classify the comfort level of the target underground space and optimize the dynamic threshold of environmental comfort based on the clustering processing results.
[0072] In some embodiments of this disclosure, the decision tree regression model selects the optimal split point to minimize the weighted mean square error of the split subsets and outputs the label mean of the samples through the leaf nodes.
[0073] In some embodiments of this disclosure, the assessment report includes a comprehensive assessment of the comfort levels of the target underground space in various areas during peak hours, recommended adjustment threshold ranges, areas and environmental indicators predicted to fall outside the comfort threshold range at future target time points, and maintenance plan information with the comfort threshold as the adjustment direction.
[0074] It should be noted that the specific implementation of the device for determining the comfort level of underground space in this disclosure is similar to the specific implementation of the method for determining the comfort level of underground space in this disclosure, and the technical effects of the device for determining the comfort level of underground space in this disclosure are similar to the technical effects of the method for determining the comfort level of underground space in this disclosure. For details, please refer to the description of the method for determining the comfort level of underground space. In order to reduce redundancy, it will not be described again.
[0075] In addition, this disclosure also provides an electronic device, including: Memory, used to store computer programs; A processor is configured to execute a computer program stored in the memory, wherein, when the computer program is executed, it implements the method for determining the comfort level of underground space as described in any of the above embodiments of the present disclosure.
[0076] Below, for reference Figure 5 To describe an electronic device according to embodiments of this disclosure. For example... Figure 5 As shown, the electronic device includes one or more processors and memory.
[0077] A processor can be a central processing unit (CPU) or other form of processing unit with data processing and / or instruction execution capabilities, and can control other components in an electronic device to perform desired functions.
[0078] The memory can store one or more computer program products, and the memory can include various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory. The volatile memory may include, for example, random access memory (RAM) and / or cache memory. The non-volatile memory may include, for example, read-only memory (ROM), hard disk, flash memory, etc. One or more computer program products can be stored on the computer-readable storage medium, and the processor can run the computer program products to implement the methods for determining the comfort level of underground spaces according to the various embodiments of this disclosure described above, and / or other desired functions.
[0079] In one example, the electronic device may also include input devices and output devices, which are interconnected via a bus system and / or other forms of connection mechanism (not shown).
[0080] In addition, the input device may also include, for example, a keyboard, a mouse, etc.
[0081] This output device can output various information to the outside, including determined distance information, direction information, etc. The output device may include, for example, a display, a speaker, a printer, and a communication network and its connected remote output devices, etc.
[0082] Of course, for the sake of simplicity, Figure 5 Only some of the components of the electronic device relevant to this disclosure are shown, omitting components such as buses, input / output interfaces, etc. In addition, the electronic device may include any other suitable components depending on the specific application.
[0083] In addition to the methods and devices described above, embodiments of this disclosure may also be computer program products comprising computer program instructions that, when executed by a processor, cause the processor to perform the steps in the methods for determining the comfort level of underground spaces according to various embodiments of this disclosure as described in the foregoing sections of this specification.
[0084] The computer program product can be written in any combination of one or more programming languages to perform the operations of the embodiments of this disclosure. The programming languages include object-oriented programming languages such as Java and C++, as well as conventional procedural programming languages such as C or similar languages. The program code can be executed entirely on a user's computing device, partially on a user's computing device, as a standalone software package, partially on a user's computing device and partially on a remote computing device, or entirely on a remote computing device or server.
[0085] Furthermore, embodiments of this disclosure may also be computer-readable storage media storing computer program instructions thereon, which, when executed by a processor, cause the processor to perform the steps in the method for determining the comfort level of an underground space according to various embodiments of this disclosure as described in the foregoing portion of this specification.
[0086] The computer-readable storage medium may be any combination of one or more readable media. A readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may be, for example, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of readable storage media (a non-exhaustive list) include: an electrical connection having one or more wires, a portable disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof.
[0087] The basic principles of this disclosure have been described above with reference to specific embodiments. However, it should be noted that the advantages, benefits, and effects mentioned in this disclosure are merely examples and not limitations, and should not be considered as essential features of each embodiment of this disclosure. Furthermore, the specific details disclosed above are for illustrative and facilitative purposes only, and are not limitations. These details do not limit the scope of this disclosure to the necessity of employing the aforementioned specific details for implementation.
[0088] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on its differences from other embodiments. Similar or identical parts between embodiments can be referred to interchangeably. For system embodiments, since they largely correspond to method embodiments, the description is relatively simple; relevant parts can be referred to the descriptions in the method embodiments.
[0089] The block diagrams of devices, apparatuses, devices, and systems disclosed herein are merely illustrative examples and are not intended to require or imply that they must be connected, arranged, or configured in the manner shown in the block diagrams. As those skilled in the art will recognize, these devices, apparatuses, devices, and systems can be connected, arranged, and configured in any manner. Words such as “comprising,” “including,” “having,” etc., are open-ended terms meaning “including but not limited to,” and are used interchangeably with them. The terms “or” and “and” as used herein refer to the terms “and / or,” and are used interchangeably with them unless the context clearly indicates otherwise. The term “such as” as used herein refers to the phrase “such as but not limited to,” and is used interchangeably with it.
[0090] The methods and apparatus of this disclosure may be implemented in many ways. For example, they may be implemented by software, hardware, firmware, or any combination of software, hardware, and firmware. The above-described order of steps for the methods is for illustrative purposes only, and the steps of the methods of this disclosure are not limited to the order specifically described above unless otherwise specifically stated. Furthermore, in some embodiments, this disclosure may also be implemented as a program recorded on a recording medium, the program including machine-readable instructions for implementing the methods according to this disclosure. Thus, this disclosure also covers recording media storing programs for performing the methods according to this disclosure.
[0091] It should also be noted that in the apparatus, devices, and methods of this disclosure, the components or steps can be disassembled and / or recombined. These disassemblies and / or recombinations should be considered as equivalent solutions to this disclosure.
[0092] The above description of the disclosed aspects is provided to enable any person skilled in the art to make or use this disclosure. Various modifications to these aspects will be readily apparent to those skilled in the art, and the general principles defined herein may be applied to other aspects without departing from the scope of this disclosure. Therefore, this disclosure is not intended to be limited to the aspects shown herein, but rather to be carried out within the widest scope consistent with the principles and novel features disclosed herein.
[0093] The above description has been given for purposes of illustration and description. Furthermore, this description is not intended to limit the embodiments of this disclosure to the forms disclosed herein. Although numerous exemplary aspects and embodiments have been discussed above, those skilled in the art will recognize certain variations, modifications, alterations, additions, and sub-combinations therein.
Claims
1. A method for determining the comfort level of an underground space, characterized in that, include: Based on historical passenger flow and historical environmental data of the target underground space, as well as a questionnaire survey of the target underground space, a multidimensional environmental feature database of the target underground space is constructed. After preprocessing the historical passenger flow and historical environmental data, clustering is performed on the preprocessed historical passenger flow and historical environmental data. Based on the clustering results, the comfort level of the target underground space is divided and the dynamic threshold of environmental comfort is optimized. Using a decision tree regression model, the dynamic changes of future environmental parameters of the target underground space over time are predicted based on preprocessed historical passenger flow and historical environmental data. Based on the dynamic changes of the future environmental parameters of the target underground space over time, and the optimized dynamic threshold of environmental comfort, an assessment report on the future comfort of the target underground space is generated.
2. The method according to claim 1, characterized in that, The historical environmental data includes acoustic environment parameters, light environment parameters, thermal environment parameters, and air quality parameters for historical time periods.
3. The method according to claim 1, characterized in that, The data preprocessing includes outlier identification, outlier removal, missing value filling, and conversion of text data into binary data.
4. The method according to claim 1, characterized in that, The process of clustering preprocessed historical passenger flow and historical environmental data, classifying the comfort level of the target underground space based on the clustering results, and optimizing the dynamic threshold for environmental comfort includes: The elbow method is used to calculate the sum of squared errors for different K values in order to determine the elbow point on the K-SSE curve. The elbow points were validated based on the silhouette coefficient and the questionnaire to obtain the optimal number of clusters. Based on the optimal number of clusters, the preprocessed historical passenger flow and historical environmental data are clustered. Based on the clustering results, the comfort level of the target underground space is divided and the dynamic threshold of environmental comfort is optimized.
5. The method according to claim 1, characterized in that, The decision tree regression model selects the optimal split point to minimize the weighted mean square error of the split subsets and outputs the label mean of the samples through the leaf nodes.
6. The method according to claim 1, characterized in that, The assessment report includes a comprehensive assessment of the comfort levels of the target underground space in each area during peak hours, recommended adjustment threshold ranges, areas and environmental indicators predicted to fall below the comfort threshold range at future target times, and maintenance plan information with the comfort threshold as the adjustment direction.
7. A device for determining the comfort level of an underground space, characterized in that, include: An environmental feature database construction module is used to construct a multi-dimensional environmental feature database of the target underground space based on historical visitor flow and historical environmental data of the target underground space, as well as a questionnaire for the target underground space. The clustering module is used to preprocess the historical passenger flow and historical environmental data, then perform clustering on the preprocessed historical passenger flow and historical environmental data, and classify the comfort level of the target underground space based on the clustering results and optimize the dynamic threshold of environmental comfort. The prediction module is used to predict the dynamic changes of future environmental parameters of the target underground space over time based on the historical passenger flow and historical environmental data after data preprocessing using a decision tree regression model. The output module is used to generate a comprehensive assessment report on the future comfort of the target underground space based on the dynamic change pattern of the future environmental parameters of the target underground space over time and the optimized dynamic threshold of environmental comfort.
8. An electronic device, characterized in that, include: Memory, used to store computer program products; A processor is configured to execute a computer program product stored in the memory, wherein, when the computer program product is executed, it implements the method described in any one of claims 1-6.
9. A computer-readable storage medium having computer program instructions stored thereon, characterized in that, When the computer program instructions are executed by the processor, they implement the method described in any one of claims 1-6.
10. A computer program product, characterized in that, It includes computer program instructions that, when executed by a processor, cause the processor to perform the method described in any one of claims 1-6.