Hotel guest room control system and method based on big data analysis

Abstract

The invention provides a hotel guest room control system and method based on big data analysis, and relates to the field of intelligent control. Temperature time sequence data, humidity time sequence data, carbon dioxide concentration time sequence data and PM2.5 concentration time sequence data of hotel guest rooms are obtained through sensors deployed in the hotel guest rooms; and the time sequence data of the air quality parameter indexes are analyzed to know the air quality condition in the hotel guest room, and the operation of the fresh air system is adaptively controlled based on the air quality condition in the hotel guest room. In this way, timely and accurate adjustment can be made according to the actual air quality condition in the guest room, and therefore the flexibility and the response speed of the fresh air system are improved.

Description

Technical Field

[0001] The present application relates to the field of intelligent control, and more specifically, to a hotel room control system and method based on big data analysis. Background Art

[0002] In the operation of modern hotels, environmental control in guest rooms is a crucial link. As a key device to ensure the air quality in guest rooms, the operation mode of the fresh air system has many limitations. At present, the common control methods of hotel guest room fresh air systems are mainly divided into two categories: preset schedule control and guest manual control. In the preset schedule control method, hotels often set a fixed schedule according to the general work and rest rules. This method seems reasonable, but it does not take into account the actual stay of different guests. Some guests may stay in the room for a long time during non-preset opening time. For example, some business people may need to work in the room during the day. At this time, if the fresh air system is in the closed state according to the preset, the air in the room will gradually become dirty. In the guest manual control method, although the guest has a certain degree of autonomy to set the manual control mode, the guest may not want to trouble and fail to adjust the operation of the fresh air system in time according to the actual situation in the room. In other words, the existing mode of hotel guest room fresh air system control needs to be improved urgently to meet the actual needs of different guests and ensure the air quality in the guest room.

[0003] Therefore, a hotel room control solution based on big data analysis is needed. Summary of the invention

[0004] In view of the shortcomings of the prior art, the present application provides a hotel room control system and method based on big data analysis.

[0005] A hotel room control system based on big data analysis, comprising:

[0006] The hotel room air quality related data collection module is used to obtain the temperature value, humidity value, carbon dioxide concentration value and PM2.5 concentration value of the hotel room at multiple predetermined time points within a predetermined time period;

[0007] A hotel room air quality related data structuring module, for structuring the temperature values, humidity values, carbon dioxide concentration values ​​and PM2.5 concentration values ​​at the plurality of predetermined time points to obtain a time series input matrix of hotel room air quality parameters;

[0008] A hotel room air quality related data encoding module, used for performing time series feature encoding processing on the hotel room air quality parameter time series input matrix to obtain a hotel room air quality parameter detection feature vector;

[0009] The hotel guest room fresh air system control result generation module is used to obtain the control result of the fresh air system based on the hotel guest room air quality parameter detection feature vector.

[0010] A hotel room control method based on big data analysis, comprising:

[0011] Obtain the temperature, humidity, carbon dioxide concentration, and PM2.5 concentration of the hotel room at multiple predetermined time points within a predetermined time period;

[0012] The temperature values, humidity values, carbon dioxide concentration values, and PM2.5 concentration values ​​at the plurality of predetermined time points are structured and sorted to obtain a time series input matrix of hotel room air quality parameters;

[0013] Performing time series feature coding processing on the time series input matrix of the hotel room air quality parameter to obtain a hotel room air quality parameter detection feature vector;

[0014] Based on the hotel room air quality parameter detection feature vector, a control result of the fresh air system is obtained.

[0015] This application has significant technical effects due to the adoption of the above technical solutions:

[0016] The hotel room control system and method based on big data analysis provided by the present application obtains the time series data of temperature, humidity, carbon dioxide concentration and PM2.5 concentration of the hotel room through sensors deployed in the hotel room, analyzes the time series data of these air quality parameter indicators to understand the air quality in the hotel room, and adaptively controls the operation of the fresh air system based on the air quality in the hotel room. In this way, timely and accurate adjustments can be made according to the actual air quality in the guest room, thereby improving the flexibility and response speed of the fresh air system. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] By describing the embodiments of the present application in more detail in conjunction with the accompanying drawings, the above and other purposes, features and advantages of the present application will become more apparent. The accompanying drawings are used to provide a further understanding of the embodiments of the present application and constitute a part of the specification. Together with the embodiments of the present application, they are used to explain the present application and do not constitute a limitation of the present application. In the accompanying drawings, the same reference numerals generally represent the same components or steps.

[0018] Figure 1 This is a system block diagram of a hotel room control system based on big data analysis according to an embodiment of the present application.

[0019] Figure 2 This is a data flow diagram of a hotel room control system based on big data analysis according to an embodiment of the present application.

[0020] Figure 3 The present invention is a block diagram of a hotel room air quality related data encoding module in a hotel room control system based on big data analysis according to an embodiment of the present application.

[0021] Figure 4 The present invention is a flowchart of a hotel room control method based on big data analysis according to an embodiment of the present application. DETAILED DESCRIPTION

[0022] Below, the exemplary embodiments according to the present application will be described in detail with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments of the present application, and it should be understood that the present application is not limited to the exemplary embodiments described here.

[0023] As mentioned in the background technology above, in the current hotel room control, the operation mode of the fresh air system is often relatively fixed and lacks flexibility. It may usually be turned on and off according to a preset schedule, or manually controlled by the guest. This control method cannot make timely and accurate adjustments based on the actual air quality in the guest room. Therefore, a hotel room control solution based on big data analysis is expected.

[0024] In recent years, deep learning and neural networks have been widely used in computer vision, natural language processing, text signal processing and other fields. In addition, deep learning and neural networks have also shown a level close to or even beyond that of humans in image classification, object detection, semantic segmentation, text translation and other fields. The development of deep learning and neural networks provides new solutions and solutions for hotel room control.

[0025] Figure 1 This is a system block diagram of a hotel room control system based on big data analysis according to an embodiment of the present application. Figure 2 Schematic diagram of data flow of a hotel room control system based on big data analysis according to an embodiment of the present application. Figure 1 and Figure 2As shown, in the hotel room control system 100 based on big data analysis, it includes: a hotel room air quality related data acquisition module 110, which is used to obtain the temperature value, humidity value, carbon dioxide concentration value and PM2.5 concentration value of the hotel room at multiple predetermined time points within a predetermined time period; a hotel room air quality related data structuring module 120, which is used to structure the temperature value, humidity value, carbon dioxide concentration value and PM2.5 concentration value at the multiple predetermined time points to obtain the hotel room air quality parameter time series input matrix; a hotel room air quality related data encoding module 130, which is used to perform time series feature encoding processing on the hotel room air quality parameter time series input matrix to obtain the hotel room air quality parameter detection feature vector; a hotel room fresh air system control result generation module 140, which is used to obtain the control result of the fresh air system based on the hotel room air quality parameter detection feature vector.

[0026] In the embodiment of the present application, the hotel room air quality related data acquisition module 110 is used to obtain the temperature value, humidity value, carbon dioxide concentration value and PM2.5 concentration value of the hotel room at multiple predetermined time points within a predetermined time period. It should be understood that temperature is an important factor affecting the comfort of indoor air. Too high or too low temperature will make the human body feel uncomfortable. Humidity is equally important for indoor air quality. Too high humidity will cause humid air, which is easy to breed bacteria and mold, affecting human health; too low humidity will make the air dry, which may cause problems such as dry skin and throat discomfort. Carbon dioxide concentration is an important indicator for measuring the freshness of indoor air. High concentrations of carbon dioxide can cause the human body to feel stuffy, dizzy and other discomforts. PM2.5 refers to particles in the air with a diameter of less than or equal to 2.5 microns. They can be suspended in the air for a long time and cause damage to the respiratory system and cardiovascular system. High concentrations of PM2.5 will reduce indoor air quality and affect human health. Temperature, humidity, carbon dioxide and PM2.5, these parameters and indicators together constitute a comprehensive evaluation system of indoor air quality. They influence and interact with each other and jointly determine the comfort and health of the air in the hotel guest rooms. When the temperature continues to rise and the humidity is high, turning on the fresh air system can reduce the temperature and humidity and improve the indoor comfort; when the carbon dioxide concentration continues to rise and exceeds a certain threshold, it means that the air circulation in the guest room is not smooth, and the fresh air system needs to be turned on to introduce fresh air, reduce the carbon dioxide concentration, and improve the freshness of the air; when the indoor PM2.5 concentration is high, the fresh air system can be turned on to introduce outdoor clean air to dilute and reduce the indoor PM2.5 concentration. In general, by obtaining the time series data of these indicators, the dynamic change process of the air quality in the hotel guest room can be more comprehensively understood, so as to make a more accurate fresh air system control decision. In particular, in a specific embodiment of the present application, it can be collected and acquired by temperature sensors, humidity sensors, carbon dioxide sensors and PM2.5 sensors installed in the hotel guest rooms.

[0027] In the embodiment of the present application, the hotel room air quality related data structuring module 120 is used to structure the temperature values, humidity values, carbon dioxide concentration values ​​and PM2.5 concentration values ​​at the multiple predetermined time points to obtain the hotel room air quality parameter time series input matrix. Specifically, in the embodiment of the present application, the hotel room air quality related data structuring module is used to: arrange the temperature values, humidity values, carbon dioxide concentration values ​​and PM2.5 concentration values ​​at the multiple predetermined time points according to the time dimension and the sample dimension to obtain the hotel room air quality parameter time series input matrix. It should be understood that the original collected data is often messy and disordered. In order to make the data collected by different sensors more orderly, easy to process and analyze, in the technical solution of the present application, the temperature values, humidity values, carbon dioxide concentration values ​​and PM2.5 concentration values ​​at the multiple predetermined time points can be arranged according to the time dimension and the sample dimension to obtain the hotel room air quality parameter time series input matrix. By arranging the data according to the time dimension, the changes of each parameter index at different time points can be clearly displayed. By arranging according to the sample dimension, the samples of different parameters at the same time point can be integrated together to more perfectly characterize the air quality at that time point. Specifically, each row of the hotel room air quality parameter time series input matrix is ​​the hotel room air quality data of a sample at a time point, and each column is the time series data of a specific parameter sample.

[0028] In the embodiment of the present application, the hotel room air quality related data encoding module 130 is used to perform time series feature encoding processing on the hotel room air quality parameter time series input matrix to obtain the hotel room air quality parameter detection feature vector. Specifically, Figure 3 FIG. 1 is a block diagram of a hotel room air quality related data encoding module in a hotel room control system based on big data analysis according to an embodiment of the present application. Figure 3As shown, the hotel room air quality related data encoding module 130 includes: a hotel room air quality parameter time series feature extraction unit 131, which is used to perform feature extraction processing on the hotel room air quality parameter time series input matrix to obtain a hotel room air quality parameter time series feature matrix; a hotel room air quality parameter time series feature dimension reduction unit 132, which is used to expand the hotel room air quality parameter time series feature matrix to obtain a hotel room air quality parameter time series feature vector; a hotel room air quality parameter time series feature emphasis unit 133, which is used to expand the hotel room air quality parameter time series feature matrix to obtain a hotel room air quality parameter time series feature vector. The matrix is ​​used for feature screening to obtain a hotel room air quality parameter time series emphasis feature matrix; the hotel room air quality parameter time series emphasis feature dimension reduction unit 134 is used to expand the hotel room air quality parameter time series emphasis feature matrix to obtain a hotel room air quality parameter time series emphasis feature vector; the hotel room air quality parameter detection feature generation unit 135 is used to perform heterogeneous feature association fusion based on perspective mapping matching on the hotel room air quality parameter time series feature vector and the hotel room air quality parameter time series emphasis feature vector to obtain the hotel room air quality parameter detection feature vector.

[0029] In the embodiment of the present application, the hotel room air quality parameter time series feature extraction unit 131 is used to perform feature extraction processing on the hotel room air quality parameter time series input matrix to obtain the hotel room air quality parameter time series feature matrix. Specifically, in the embodiment of the present application, the hotel room air quality parameter time series feature extraction unit is used to: pass the hotel room air quality parameter time series input matrix through the air quality time series encoder to obtain the hotel room air quality parameter time series feature matrix. It should be understood that the original air quality parameter time series input matrix may contain a large number of data points, which contain rich information. In order to extract the characteristics that can reflect the changing trend and law of air quality from these information, and to predict and decide whether to turn on the fresh air system based on these characteristics, based on this, in the technical solution of the present application, the hotel room air quality parameter time series input matrix is ​​passed through the air quality time series encoder to obtain the hotel room air quality parameter time series feature matrix. It should be noted that the air quality time series encoder in the present application is a convolutional neural network model using two convolution kernels of different sizes, and the size of the first convolution kernel is larger than the size of the second convolution kernel. Here, different-sized convolution kernels can be used to extract features at different levels. Specifically, large-sized convolution kernels can capture larger-scale, more global features, while small-sized convolution kernels can capture finer, more local features. In this way, through multi-level feature extraction, the changes and patterns of air quality parameters can be more comprehensively reflected. It is worth mentioning that although large-sized convolution kernels can capture a wider range of features, the amount of calculation is relatively large; while small-sized convolution kernels have a smaller amount of calculation, but may not be able to capture enough information. Therefore, by combining the use of convolution kernels of different sizes, the amount of calculation can be reduced while ensuring the performance of the model, thereby improving the operating efficiency of the model.

[0030] In the embodiment of the present application, the hotel room air quality parameter time series feature dimension reduction unit 132 is used to expand the hotel room air quality parameter time series feature matrix to obtain the hotel room air quality parameter time series feature vector. It should be understood that in the hotel room air quality parameter time series feature matrix, each row corresponds to the hotel room air quality feature at a time point. In order to use a simpler data structure to store and process these features, thereby reducing the complexity and cost of data processing, based on this, the hotel room air quality parameter time series feature matrix is ​​expanded. Through the expansion process, the two-dimensional feature matrix becomes a one-dimensional feature vector, and the dimension of the feature data is reduced, but the feature information in the original feature matrix is ​​not lost.

[0031] In the embodiment of the present application, the hotel room air quality parameter time series feature emphasis unit 133 is used to perform feature screening processing on the hotel room air quality parameter time series feature matrix to obtain the hotel room air quality parameter time series feature emphasis matrix. Specifically, in the embodiment of the present application, the hotel room air quality parameter time series feature emphasis unit is used to: pass the hotel room air quality parameter time series feature matrix through the air quality time series feature emphasizer to obtain the hotel room air quality parameter time series feature emphasize matrix. It should be understood that although the hotel room air quality parameter time series feature matrix obtained after preliminary feature extraction can extract important information from the original data, some key features may still not be prominent enough and difficult to be effectively used by subsequent algorithms. In order to further strengthen these key features and make them more significant, thereby improving the algorithm's ability to identify and utilize key information, in the technical solution of the present application, it is necessary to input the hotel room air quality parameter time series feature matrix into the air quality time series feature emphasizer for secondary processing. It should be noted that the air quality time series feature emphasizer is a convolutional neural network model using a spatial attention mechanism. The spatial attention mechanism can automatically assign weights to different features, thereby highlighting key features and suppressing unimportant features, which allows the system to pay more attention to the features that have the greatest impact on the prediction results, thereby improving feature utilization and system performance. And because the attention mechanism can automatically adjust weights to adapt to different input data, the model can better cope with noise and abnormal situations, thereby improving the stability and reliability of the system.

[0032] In the embodiment of the present application, the hotel room air quality parameter timing emphasis feature dimension reduction unit 134 is used to expand the hotel room air quality parameter timing emphasis feature matrix to obtain the hotel room air quality parameter timing emphasis feature vector. It should be understood that the hotel room air quality parameter timing emphasis feature matrix, which is a two-dimensional matrix form, may be relatively complex in data storage, transmission and processing. In order to improve data processing efficiency, the hotel room air quality parameter timing emphasis feature matrix may be expanded to obtain a one-dimensional vector. In the one-dimensional vector form, the fusion and selection between different features become easier, and this flexibility helps to optimize model performance and improve prediction accuracy.

[0033] In an embodiment of the present application, the hotel room air quality parameter detection feature generation unit 135 is used to perform heterogeneous feature association fusion based on perspective mapping matching on the hotel room air quality parameter time series feature vector and the hotel room air quality parameter time series emphasis feature vector to obtain the hotel room air quality parameter detection feature vector. It should be understood that the hotel room air quality parameter time series feature vector represents the original data features of the hotel room air quality parameters changing over time, and the hotel room air quality parameter time series emphasis feature vector represents the key features after further processing, which may not be so significant in the original data, but have a greater impact on the representative air quality. In order to obtain a comprehensive feature vector that contains both basic information and key emphasis information, the hotel room air quality parameter time series feature vector and the hotel room air quality parameter time series emphasis feature vector can be fused in the present application.

[0034] In particular, considering that the time series feature vector of the air quality parameter of the hotel room is obtained by processing the air quality time series encoder, it contains the information of the changes of different air quality parameter indicators over time; while the time series emphasis feature vector of the air quality parameter of the hotel room is obtained by the air quality time series feature emphasizer, which emphasizes the changes of air quality parameter indicators at certain key time points. That is, the time series feature vector of the air quality parameter of the hotel room contains the average change trend over a long period of time, while the time series emphasis feature vector of the air quality parameter of the hotel room may pay more attention to the drastic changes in a short period of time. This difference in time scale will lead to the heterogeneity of features. Due to the significant heterogeneity between feature vectors, the fused feature vector may not accurately express the characteristics of the original data, thereby reducing the certainty of feature expression. Moreover, feature fusion depends on the smooth transition and continuity of feature vectors in feature space. Since the time series feature vector of the air quality parameter of the hotel room and the time series emphasis feature vector of the air quality parameter of the hotel room have different distributions and structures in feature space, direct fusion may lead to non-smooth feature manifolds, affecting the certainty of feature expression. Therefore, in the technical solution of the present application, the hotel room air quality parameter time series feature vector and the hotel room air quality parameter time series emphasis feature vector are subjected to heterogeneous feature association fusion based on perspective mapping matching to obtain a hotel room air quality parameter detection feature vector.

[0035] Specifically, in an embodiment of the present application, the hotel room air quality parameter time series feature vector and the hotel room air quality parameter time series emphasis feature vector are subjected to heterogeneous feature association fusion based on perspective mapping matching to obtain a hotel room air quality parameter detection feature vector, including: constructing a hotel room air quality parameter detection distance topological matrix between the hotel room air quality parameter time series feature vector and the hotel room air quality parameter time series emphasis feature vector; constructing a hotel room air quality parameter detection feature value granularity association matrix between the hotel room air quality parameter time series feature vector and the hotel room air quality parameter time series emphasis feature vector; and performing a correlation analysis on the hotel room air quality parameter detection distance topological matrix based on the hotel room air quality parameter detection distance topological matrix. The hotel room air quality parameter detection characteristic value granularity association matrix is ​​topologically associated modulated to obtain the hotel room air quality parameter detection topological modulation association matrix; the hotel room air quality parameter detection topological modulation association matrix is ​​used as the perspective co-projection space, the hotel room air quality parameter time series feature vector and the hotel room air quality parameter time series emphasis feature vector are projected to the perspective co-projection space to obtain the perspective modulated hotel room air quality parameter time series feature vector and the perspective modulated hotel room air quality parameter time series emphasis feature vector; the perspective modulated hotel room air quality parameter time series feature vector and the perspective modulated hotel room air quality parameter time series emphasis feature vector are fused to obtain the hotel room air quality parameter detection feature vector.

[0036] In an embodiment of the present application, another expression of performing heterogeneous feature association fusion based on perspective mapping matching on the hotel room air quality parameter time series feature vector and the hotel room air quality parameter time series emphasis feature vector to obtain the hotel room air quality parameter detection feature vector can be: processing the hotel room air quality parameter time series feature vector and the hotel room air quality parameter time series emphasis feature vector with the following formula to obtain the hotel room air quality parameter detection feature vector; wherein, the formula is:

[0037] M t =D(V1,V2)

[0038]

[0039]

[0040] V c =α·V1+β·V2

[0041] Wherein, V1 represents the time series feature vector of the hotel room air quality parameter, V2 represents the time series emphasis feature vector of the hotel room air quality parameter, and D(V1, V2) is the hotel room air quality parameter detection distance topological matrix between the hotel room air quality parameter time series feature vector and the hotel room air quality parameter time series emphasis feature vector, that is, d i，j =d(v 1i , v 2j ), d i，j is the eigenvalue of the position (i, j) in the distance topology matrix of the hotel room air quality parameter detection distance, d(v 1i , v 2j ) represents the distance between the eigenvalue of the i-th position of the hotel room air quality parameter time series eigenvector and the eigenvalue of the j-th position of the hotel room air quality parameter time series emphasis eigenvector, and V1 and V2 are both column vectors, M t represents the hotel room air quality parameter detection distance topological matrix, T represents the transpose of the vector, Represents matrix multiplication, M v represents the eigenvalue granularity correlation matrix of the hotel room air quality parameter detection, exp represents the natural exponential function, M c represents the hotel room air quality parameter detection topological modulation association matrix, V1′ represents the time series feature vector of the hotel room air quality parameter modulation by the perspective, V2′ represents the time series emphasis feature vector of the hotel room air quality parameter modulation by the perspective, α and β represent weighted hyperparameters, V c Represents the hotel room air quality parameter detection feature vector.

[0042] That is, in the technical solution of the present application, the hotel room air quality parameter time series feature vector and the hotel room air quality parameter time series emphasis feature vector are subjected to heterogeneous feature association fusion based on perspective mapping matching, which first constructs a hotel room air quality parameter detection distance topological matrix between the hotel room air quality parameter time series feature vector and the hotel room air quality parameter time series emphasis feature vector. This step utilizes the idea of ​​graph theory, takes the characteristic values ​​of each position in the hotel room air quality parameter time series feature vector and the hotel room air quality parameter time series emphasis feature vector as nodes, and uses the distance metric function to determine the low-dimensional embedding expression of the edges between nodes, so as to construct a feature expression that can quantify the topological association relationship between the hotel room air quality parameter time series feature vector and the hotel room air quality parameter time series emphasis feature vector. This step is crucial to understanding the spatial distribution of data points and their mutual connections, and also provides basic structural information for subsequent steps.

[0043] Next, a hotel room air quality parameter detection characteristic value granularity association matrix between the hotel room air quality parameter time series feature vector and the hotel room air quality parameter time series emphasis feature vector is constructed. This step focuses on exploring the correlation between the internal attributes of the feature vector. In a specific example, the product between the hotel room air quality parameter time series feature vector and the transposed vector of the hotel room air quality parameter time series emphasis feature vector is calculated to obtain the hotel room air quality parameter detection characteristic value granularity association matrix. Furthermore, the hotel room air quality parameter detection characteristic value granularity association matrix is ​​topologically associated modulated based on the hotel room air quality parameter detection distance topological matrix to obtain the hotel room air quality parameter detection topological modulation association matrix. That is, the characteristic value granularity association information of the hotel room air quality parameter time series feature vector and the hotel room air quality parameter time series emphasis feature vector is driven to walk on the distance topological map to construct a method for mapping the hotel room air quality parameter time series feature vector and the hotel room air quality parameter time series emphasis feature vector to a low-dimensional modulation perspective co-projection space domain with continuous high-dimensional regression space attributes.

[0044] Next, the hotel room air quality parameter detection topological modulation association matrix is ​​used as the perspective co-projection space, and the hotel room air quality parameter time series feature vector and the hotel room air quality parameter time series emphasis feature vector are projected into the perspective co-projection space to obtain the perspective modulation hotel room air quality parameter time series feature vector and the perspective modulation hotel room air quality parameter time series emphasis feature vector. That is, the key to this technical solution is to find an implicit third space with modulation capability, in which as much information of the original high-dimensional data as possible is retained, so that the converted new feature vector not only reduces the dimension, but also maintains the relative position relationship between the original features.

[0045] Finally, the perspective modulated hotel room air quality parameter time series feature vector and the perspective modulated hotel room air quality parameter time series emphasis feature vector are fused to obtain the hotel room air quality parameter detection feature vector. Fusion can be achieved in a variety of forms, ranging from simple arithmetic average to complex ensemble learning algorithms, depending on the application scenario and the goals pursued. The final hotel room air quality parameter detection feature vector combines the main features of the two sets of input data and provides a more comprehensive data representation, which is not only conducive to improving the performance of machine learning models, but also promotes the ability of cross-modal or multi-source data analysis, thereby significantly enhancing the understanding and utilization efficiency of complex data structures.

[0046] In the embodiment of the present application, the hotel room fresh air system control result generation module 140 is used to obtain the control result of the fresh air system based on the hotel room air quality parameter detection feature vector. Specifically, in the embodiment of the present application, the hotel room fresh air system control result generation module is used to: pass the hotel room air quality parameter detection feature vector through the fresh air system control classifier to obtain the fresh air system control result, and the fresh air system control result is used to indicate whether the fresh air system needs to be turned on at the current time point. It should be understood that in order to make a decision based on the information in the hotel room air quality parameter detection feature vector, the hotel room air quality parameter detection feature vector needs to be input into the fresh air system control classifier. The fresh air system control classifier is an algorithm model based on deep learning, which can learn and analyze the input feature vector to output the control result. This model will learn a large amount of historical data during the training process to grasp the complex relationship between air quality parameters and fresh air system control. Through the fresh air system control result, the opening and closing of the fresh air system can be accurately controlled, so that the air quality in the guest room can be improved in time and unnecessary energy consumption and waste can be avoided.

[0047] In summary, the hotel room control system 100 based on big data analysis according to the embodiment of the present application is explained, which obtains the temperature time series data, humidity time series data, carbon dioxide concentration time series data and PM2.5 concentration time series data of the hotel room through the sensors deployed in the hotel room, understands the air quality in the hotel room by analyzing the time series data of these air quality parameter indicators, and adaptively controls the operation of the fresh air system based on the air quality in the hotel room. In this way, timely and accurate adjustments can be made according to the actual air quality in the guest room, thereby improving the flexibility and response speed of the fresh air system.

[0048] As described above, the hotel room control system 100 based on big data analysis according to the embodiment of the present application can be implemented in various terminal devices, such as a server for hotel room control based on big data analysis, etc. In one example, the hotel room control system 100 based on big data analysis according to the embodiment of the present application can be integrated into the terminal device as a software module and / or a hardware module. For example, the hotel room control system 100 based on big data analysis can be a software module in the operating system of the terminal device, or can be an application developed for the terminal device; of course, the hotel room control system 100 based on big data analysis can also be one of the many hardware modules of the terminal device.

[0049] Alternatively, in another example, the hotel room control system 100 based on big data analysis and the terminal device may also be separate devices, and the hotel room control system 100 based on big data analysis may be connected to the terminal device via a wired and / or wireless network and transmit interactive information in accordance with an agreed data format.

[0050] Figure 4 FIG. 1 is a flow chart of a hotel room control method based on big data analysis according to an embodiment of the present application. Figure 4 As shown, in the hotel room control method based on big data analysis, it includes: S110, obtaining the temperature value, humidity value, carbon dioxide concentration value and PM2.5 concentration value of the hotel room at multiple predetermined time points within a predetermined time period; S120, structured sorting of the temperature values, humidity values, carbon dioxide concentration values ​​and PM2.5 concentration values ​​at the multiple predetermined time points to obtain a time series input matrix of hotel room air quality parameters; S130, performing time series feature coding processing on the time series input matrix of hotel room air quality parameters to obtain a hotel room air quality parameter detection feature vector; S140, obtaining the control result of the fresh air system based on the hotel room air quality parameter detection feature vector.

[0051] Here, those skilled in the art can understand that the specific operations of each step in the above-mentioned hotel room control method based on big data analysis have been referred to above. Figures 1 to 3 The invention has been introduced in detail in the description of the hotel room control system based on big data analysis, and therefore, its repeated description will be omitted.

[0052] In summary, the hotel room control method based on big data analysis according to the embodiment of the present application is explained, which obtains the temperature time series data, humidity time series data, carbon dioxide concentration time series data and PM2.5 concentration time series data of the hotel room through the sensors deployed in the hotel room, understands the air quality in the hotel room by analyzing the time series data of these air quality parameter indicators, and adaptively controls the operation of the fresh air system based on the air quality in the hotel room. In this way, timely and accurate adjustments can be made according to the actual air quality in the guest room, thereby improving the flexibility and response speed of the fresh air system.

Claims

1. A hotel room control system based on big data analysis, characterized in that: include: The hotel room air quality related data collection module is used to obtain the temperature value, humidity value, carbon dioxide concentration value and PM2.5 concentration value of the hotel room at multiple predetermined time points within a predetermined time period; A hotel room air quality related data structuring module, for structuring the temperature values, humidity values, carbon dioxide concentration values ​​and PM2.5 concentration values ​​at the plurality of predetermined time points to obtain a time series input matrix of hotel room air quality parameters; A hotel room air quality related data encoding module, used for performing time series feature encoding processing on the hotel room air quality parameter time series input matrix to obtain a hotel room air quality parameter detection feature vector; The hotel guest room fresh air system control result generation module is used to obtain the control result of the fresh air system based on the hotel guest room air quality parameter detection feature vector.

2. The hotel room control system based on big data analysis according to claim 1 is characterized in that: The hotel room air quality related data structuring module is used to: arrange the temperature values, humidity values, carbon dioxide concentration values ​​and PM2.5 concentration values ​​at the multiple predetermined time points according to the time dimension and the sample dimension to obtain the hotel room air quality parameter time series input matrix.

3. The hotel room control system based on big data analysis according to claim 2 is characterized in that: The hotel room air quality related data encoding module includes: A hotel room air quality parameter time series feature extraction unit, used for performing feature extraction processing on the hotel room air quality parameter time series input matrix to obtain a hotel room air quality parameter time series feature matrix; A hotel room air quality parameter time series feature dimensionality reduction unit, used for expanding the hotel room air quality parameter time series feature matrix to obtain a hotel room air quality parameter time series feature vector; A hotel room air quality parameter time series feature emphasis unit, used for performing feature screening processing on the hotel room air quality parameter time series feature matrix to obtain a hotel room air quality parameter time series emphasis feature matrix; A hotel room air quality parameter time series emphasis feature dimension reduction unit, used for expanding the hotel room air quality parameter time series emphasis feature matrix to obtain a hotel room air quality parameter time series emphasis feature vector; The hotel room air quality parameter detection feature generation unit is used to perform heterogeneous feature association fusion based on perspective mapping matching on the hotel room air quality parameter time series feature vector and the hotel room air quality parameter time series emphasis feature vector to obtain the hotel room air quality parameter detection feature vector.

4. The hotel room control system based on big data analysis according to claim 3 is characterized in that: The hotel room air quality parameter time series feature extraction unit is used to: pass the hotel room air quality parameter time series input matrix through an air quality time series encoder to obtain the hotel room air quality parameter time series feature matrix.

5. The hotel room control system based on big data analysis according to claim 4 is characterized in that: The hotel room air quality parameter timing feature emphasis unit is used to: pass the hotel room air quality parameter timing feature matrix through the air quality timing feature emphasizer to obtain the hotel room air quality parameter timing emphasis feature matrix.

6. The hotel room control system based on big data analysis according to claim 5 is characterized in that: The air quality time series encoder is a convolutional neural network model using two convolution kernels of different sizes, the size of the first convolution kernel is larger than the size of the second convolution kernel, and the air quality time series feature emphasizer is a convolutional neural network model using a spatial attention mechanism.

7. The hotel room control system based on big data analysis according to claim 6 is characterized in that: The hotel room air quality parameter detection feature generation unit is used to: Constructing a hotel room air quality parameter detection distance topological matrix between the hotel room air quality parameter time series feature vector and the hotel room air quality parameter time series emphasis feature vector; Constructing a hotel room air quality parameter detection characteristic value granularity association matrix between the hotel room air quality parameter time series characteristic vector and the hotel room air quality parameter time series emphasis characteristic vector; Based on the hotel room air quality parameter detection distance topological matrix, the hotel room air quality parameter detection characteristic value granularity association matrix is ​​topologically associated modulated to obtain a hotel room air quality parameter detection topological modulation association matrix; Taking the hotel room air quality parameter detection topological modulation association matrix as the perspective co-projection space, projecting the hotel room air quality parameter time series feature vector and the hotel room air quality parameter time series emphasis feature vector into the perspective co-projection space to obtain the perspective modulation hotel room air quality parameter time series feature vector and the perspective modulation hotel room air quality parameter time series emphasis feature vector; The view angle modulation hotel room air quality parameter time series feature vector and the view angle modulation hotel room air quality parameter time series emphasis feature vector are integrated to obtain the hotel room air quality parameter detection feature vector.

8. The hotel room control system based on big data analysis according to claim 7 is characterized in that: The hotel room fresh air system control result generation module is used to: pass the hotel room air quality parameter detection feature vector through the fresh air system control classifier to obtain the fresh air system control result, and the fresh air system control result is used to indicate whether the fresh air system needs to be turned on at the current time point.

9. A hotel room control method based on big data analysis, characterized in that: include: Obtain the temperature, humidity, carbon dioxide concentration, and PM2.5 concentration of the hotel room at multiple predetermined time points within a predetermined time period; The temperature values, humidity values, carbon dioxide concentration values, and PM2.5 concentration values ​​at the plurality of predetermined time points are structured and sorted to obtain a time series input matrix of hotel room air quality parameters; Performing time series feature coding processing on the time series input matrix of the hotel room air quality parameter to obtain a hotel room air quality parameter detection feature vector; Based on the hotel room air quality parameter detection feature vector, a control result of the fresh air system is obtained.

10. The hotel room control method based on big data analysis according to claim 9 is characterized in that: Performing time series feature coding processing on the time series input matrix of the hotel room air quality parameter to obtain a hotel room air quality parameter detection feature vector, including: Performing feature extraction processing on the hotel room air quality parameter time series input matrix to obtain a hotel room air quality parameter time series feature matrix; Expanding the hotel room air quality parameter time series feature matrix to obtain a hotel room air quality parameter time series feature vector; Performing feature screening processing on the hotel room air quality parameter time series feature matrix to obtain a hotel room air quality parameter time series emphasis feature matrix; Expanding the hotel room air quality parameter time series emphasis feature matrix to obtain a hotel room air quality parameter time series emphasis feature vector; The hotel room air quality parameter time series feature vector and the hotel room air quality parameter time series emphasis feature vector are subjected to heterogeneous feature association fusion based on perspective mapping matching to obtain the hotel room air quality parameter detection feature vector.

Images