Smart hotel management method and system based on wireless network

Abstract

The invention discloses a smart hotel management method and system based on a wireless network. The method comprises the following steps: acquiring user information of a customer who registers a hotel from the wireless network; extracting historical data according to the user information to obtain historical data of the customer; performing clustering analysis according to the historical data to obtain user classification information; performing demand analysis according to the user classification information to obtain check-in demand information of the customer; inputting the check-in demand information into a pre-trained recommendation network model, and performing real-time check-in recommendation to obtain check-in recommendation information; performing optimal room allocation calculation according to the check-in recommendation information to obtain optimal room number information; and generating a check-in confirmation signal according to the optimal room number information, and sending the confirmation signal to the user side. According to the method, accurate room recommendation and an optimal allocation scheme can be realized, and the service quality and the management efficiency are improved.

Description

Technical Field

[0001] The present invention relates to the field of wireless network technology, and in particular to a smart hotel management method and system based on wireless network. Background Art

[0002] At present, with the rapid development of the hotel industry and the increasing requirements of customers for hotel service experience, traditional hotel management methods have gradually exposed the problems of low efficiency and lack of intelligence. Under high occupancy rates, hotels need to quickly and efficiently complete room allocation for customers while meeting customers' personalized needs, such as check-in preferences, room locations, and special services. These needs have made smart hotel management an important development direction for the industry. Improving management efficiency and service quality through information technology has become the key to solving existing needs.

[0003] In the existing technology, hotel management currently relies mainly on traditional management methods or preliminary information systems. For example, customer information is manually recorded using a check-in system, and room allocation is performed manually or through a simple electronic system. These methods usually allocate rooms based on the customer's immediate needs or room availability, lacking in-depth data analysis and intelligent optimization support. Some high-end hotels try to use a simple membership management system to provide some customized services based on the customer's historical check-in records, such as giving priority to recommending room types or rooms that members often stay in. However, most of these systems remain at the stage of historical data analysis in a single dimension, limited to the recording and simple matching of static information, and are difficult to cope with the diverse and dynamic needs of customers.

[0004] In summary, it is difficult for existing hotel management systems to accurately obtain customer consumption preferences, resulting in low management efficiency and service quality. Summary of the invention

[0005] The present invention provides a smart hotel management method and system based on a wireless network, so as to achieve accurate room recommendation and optimal allocation scheme, and improve service quality and management efficiency.

[0006] In the first aspect, in order to solve the above technical problems, the present invention provides a smart hotel management method based on a wireless network, comprising: Obtain user information of customers registered at the hotel from the wireless network; Extract historical data based on the user information to obtain the customer's historical data; Performing cluster analysis based on the historical data to obtain user classification information; Conduct demand analysis based on the user classification information to obtain the customer's check-in demand information; Inputting the check-in demand information into a pre-trained recommendation network model to perform real-time check-in recommendation and obtain check-in recommendation information; Calculate the optimal room allocation based on the recommended check-in information to obtain the optimal room number information; Generate a check-in confirmation signal according to the optimal room number information, and send the confirmation signal to the user terminal; The recommendation network model is based on historical occupancy demand information and occupancy information labels as input data, an initial recommendation network model is constructed, and the initial recommendation network model is trained to obtain a recommendation network model.

[0007] As an optional implementation manner, the step of obtaining user information of a customer who has registered a hotel from a wireless network includes: Obtain network fingerprint information when customers connect to the hotel wireless network; According to the network fingerprint information, query the customer's login information to obtain the customer's registration information; Extracting preferences based on the customer registration information to obtain customer preference data; Generate a user profile based on the customer registration information and the preference data to obtain the customer's user information; The network fingerprint information includes the client's IP address, device MAC address, and Wi-Fi signal strength.

[0008] As an optional implementation manner, performing cluster analysis based on the historical data to obtain user classification information includes: Performing data preprocessing according to the historical data to obtain standard data; Perform multi-dimensional feature extraction based on the standard data to obtain multi-dimensional feature data of the user; K-means user clustering is performed based on the user multi-dimensional feature data to obtain user classification information.

[0009] As an optional implementation manner, performing demand analysis based on the user classification information to obtain the customer's check-in demand information includes: Extract features based on the user classification information to obtain key features related to the customer's check-in needs; The key features are used as inputs to a pre-trained demand regression analysis model to obtain the customer's occupancy demand information.

[0010] As an optional implementation, the pre-training process of the demand regression analysis model includes: Initialize support vector machine regression model parameters; Obtain historical customer data, perform data preprocessing, and obtain standard historical customer data; According to the standard historical customer data, model parameter training is performed to obtain an initial demand regression analysis model; According to the initial demand regression analysis model, cross validation and grid optimization search are performed to obtain a demand regression analysis model.

[0011] As an optional implementation, the training process of the pre-trained recommendation network model includes: Initialize the recommended network model parameters; Obtain historical occupancy demand information and occupancy information; constructing a feature matrix according to the occupancy demand information and the occupancy information to obtain model input data; According to the model input data, the model parameters are trained to obtain the trained recommendation network model.

[0012] As an optional implementation manner, performing optimal room allocation calculation according to the check-in recommendation information to obtain optimal room number information includes: Calculate the room waiting time according to the check-in recommendation information to obtain the shortest waiting time; Calculate room selection preferences based on the check-in recommendation information to obtain room preference features; Based on the shortest waiting time and the room preference characteristics, a comprehensive analysis is performed to obtain the optimal room number information.

[0013] As an optional implementation, the calculation formula for calculating the room waiting time is as follows: ; in, Indicates the customer Total waiting time, which is the time it takes for a customer to check in from the time they arrive at the hotel; Indicates the customer The number of people waiting for the selected room, that is, the number of other customers waiting to check in to the room; Indicates room The processing time is the time required for the room to be ready for check-in by the customer; Represents the total number of rooms in the hotel.

[0014] As an optional implementation, the calculation formula for calculating the room selection preference is as follows: ; ; in, Indicates the customer The room selection preference score indicates the customer Regarding the preference for different rooms, the lower the score, the more likely the customer is to choose that room; Indicates room The relative position to the hotel entrance is a distance value. The smaller the value, the closer the room is to the entrance and the higher the customer preference. Indicates the customer In choosing a room The preference function is based on the customer's age. Adjust room selection preferences; Indicates the age of the customer; Indicates the customer Ideal room location, based on the age of the client Adjustment; represents the adjustment factor used to control the relationship between room location and customer preference.

[0015] In a second aspect, the present invention provides a smart hotel management system based on a wireless network, comprising: A data acquisition module, used to acquire user information of customers who have registered with the hotel from the wireless network; A data extraction module, used to extract historical data based on the user information to obtain the customer's historical data; A cluster analysis module, used to perform cluster analysis based on the historical data to obtain user classification information; A demand analysis module, used to perform demand analysis based on the user classification information to obtain the customer's check-in demand information; An occupancy recommendation module is used to input the occupancy demand information into a pre-trained recommendation network model to perform real-time occupancy recommendation and obtain occupancy recommendation information; A room allocation module, used to calculate the optimal room allocation according to the check-in recommendation information to obtain the optimal room number information; The check-in confirmation module is used to generate a check-in confirmation signal according to the optimal room number information and send the confirmation signal to the user terminal.

[0016] In a third aspect, the present invention also provides a computer-readable storage medium, which includes a stored computer program, wherein when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute any one of the above-mentioned wireless network-based smart hotel management methods.

[0017] Compared with the prior art, the present invention has the following beneficial effects: The present invention provides a smart hotel management method based on a wireless network, comprising: obtaining user information of customers who register a hotel from a wireless network; extracting historical data based on the user information to obtain historical data of the customers; performing cluster analysis based on the historical data to obtain user classification information; performing demand analysis based on the user classification information to obtain check-in demand information of the customers; inputting the check-in demand information into a pre-trained recommendation network model to perform real-time check-in recommendation to obtain check-in recommendation information; performing optimal room allocation calculation based on the check-in recommendation information to obtain optimal room number information; generating a check-in confirmation signal based on the optimal room number information, and sending the confirmation signal to a user end; wherein the recommendation network model is based on historical check-in demand information and check-in information labels as input data, constructing an initial recommendation network model, and training the initial recommendation network model to obtain a recommendation network model.

[0018] In the present invention, a smart hotel management method based on wireless network is used to fully utilize wireless sensing technology to obtain the user information of customers in real time, and cluster analysis is performed in combination with historical data to accurately extract the consumption preferences and check-in requirements of customers. By constructing and training a recommendation network model, the system can efficiently provide customers with real-time room recommendations, and generate the optimal room number information by combining the customer's preferences and the room's usage status through the optimal room allocation algorithm, and realize a seamless check-in process through the check-in confirmation signal. This method effectively overcomes the problems of low efficiency and insufficient personalized service of traditional hotel services, not only improving the hotel service efficiency, but also providing customers with a higher quality personalized check-in experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 It is a flowchart of a smart hotel management method based on a wireless network provided by an embodiment of the present invention; Figure 2 The present invention provides a wireless network-based smart hotel management system. DETAILED DESCRIPTION

[0020] At present, with the rapid development of the hotel industry and the increasing requirements of customers for hotel service experience, traditional hotel management methods have gradually exposed the problems of low efficiency and lack of intelligence. Under high occupancy rates, hotels need to quickly and efficiently complete room allocation for customers while meeting customers' personalized needs, such as check-in preferences, room locations, and special services. These needs have made smart hotel management an important development direction for the industry. Improving management efficiency and service quality through information technology has become the key to solving existing needs.

[0021] In the existing technology, hotel management currently relies mainly on traditional management methods or preliminary information systems. For example, customer information is manually recorded using a check-in system, and room allocation is performed manually or through a simple electronic system. These methods usually allocate rooms based on the customer's immediate needs or room availability, lacking in-depth data analysis and intelligent optimization support. Some high-end hotels try to use a simple membership management system to provide some customized services based on the customer's historical check-in records, such as giving priority to recommending room types or rooms that members often stay in. However, most of these systems remain at the stage of historical data analysis in a single dimension, limited to the recording and simple matching of static information, and are difficult to cope with the diverse and dynamic needs of customers.

[0022] In summary, it is difficult for existing hotel management systems to accurately obtain customer consumption preferences, resulting in low management efficiency and service quality.

[0023] To solve the existing problems, the present invention provides a smart hotel management method and system based on wireless network to achieve accurate room recommendation and optimal allocation plan, and improve service quality and management efficiency.

[0024] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0025] Reference Figure 1 The first embodiment of the present invention provides a smart hotel management method based on a wireless network, comprising the following steps: S11, obtaining user information of a customer who has registered a hotel from a wireless network; S12, extracting historical data based on the user information to obtain the customer's historical data; S13, performing cluster analysis based on the historical data to obtain user classification information; S14, performing demand analysis based on the user classification information to obtain the customer's check-in demand information; S15, inputting the check-in demand information into a pre-trained recommendation network model to perform real-time check-in recommendation to obtain check-in recommendation information; S16, performing optimal room allocation calculation according to the check-in recommendation information to obtain optimal room number information; S17, generating a check-in confirmation signal according to the optimal room number information, and sending the confirmation signal to the user end.

[0026] In step S11, the user information of the customer who registered the hotel is obtained from the wireless network, including: Obtain network fingerprint information when customers connect to the hotel wireless network; According to the network fingerprint information, query the customer's login information to obtain the customer's registration information; Extracting preferences based on the customer registration information to obtain customer preference data; Generate a user profile based on the customer registration information and the preference data to obtain the customer's user information; The network fingerprint information includes the client's IP address, device MAC address, and Wi-Fi signal strength.

[0027] It should be noted that network fingerprint information refers to the unique identifier generated by the customer when connecting to the hotel wireless network, mainly including the client's IP address, device MAC address and Wi-Fi signal strength. This information is collected in real time by the hotel's wireless network equipment (such as routers or access points) as the basic network connection characteristics of the customer's device. Network fingerprint information can automatically identify the identity of the customer's device without the customer having to enter additional information. As the first step for the system to obtain customer information, it provides basic support for subsequent user identity query and portrait generation. At the same time, by analyzing the Wi-Fi signal strength, the location distribution of customers in the hotel can also be obtained, providing a reference for further optimizing the service process. Customer registration information is data provided by customers through official hotel channels (such as booking platforms or check-in registration), including the customer's name, contact information and booking records. This information is provided by the hotel management system or customer database, and the customer's identity is confirmed by matching with the network fingerprint information. As a direct description of the customer's identity, customer registration information can quickly verify whether the customer is a registered user and provide a key basis for subsequent data mining. At the same time, by integrating the customer's registration information, structured data can also be provided for generating user portraits to ensure the integrity and accuracy of the portraits. Preference data is obtained by analyzing and mining customer registration information and historical behavior data (such as historical check-in records, service selection preferences, etc.), including customer consumption habits, room preferences, and special needs. These data come from the hotel big data platform or other service records. After data cleaning and feature extraction, they are used for personalized analysis. Through in-depth analysis of customer needs, the hotel can provide personalized service guidance for customers. For example, before a customer checks in, the system can predict in advance the type of service or room features that the customer may need, thereby optimizing the service experience and improving customer satisfaction. User portraits are comprehensive descriptions generated based on network fingerprint information, customer registration information, and preference data, mainly including basic customer information, consumption habits, interest preferences, etc. These information are integrated through big data modeling technology to form a comprehensive portrayal of the customer.

[0028] In step S12, historical data is extracted based on the user information to obtain the customer's historical data.

[0029] Among them, historical data refers to all records related to consumption and behavior generated by customers in hotels or related services, including but not limited to customers' historical check-in records, payment records, service usage preferences, complaints and suggestions, feedback and evaluations, etc. These data mainly come from the hotel's customer management system (CMS), service record database, and cooperative data interface of third-party platforms. The core role of historical data is to comprehensively trace back customers' service experience and preferences, thereby laying a data foundation for personalized analysis. At the same time, after cleaning and integration, these data can be further used for predictive analysis, providing important support for customers' accurate recommendations and service optimization.

[0030] It should be noted that data extraction is achieved by querying the hotel data platform or associated database based on the customer's user information (such as user ID, registration information or network fingerprint information). Exemplarily, the data extraction technology used includes SQL database query and NoSQL-based distributed retrieval to achieve mixed processing of real-time and batch data. Of course, according to the actual application scenario and user needs, data extraction technology can also use other methods, which are not limited by the present invention. Data extraction can quickly and accurately associate the customer's current user information with historical records, while avoiding data redundancy and repeated processing, ensuring extraction efficiency and data timeliness. In addition, in order to improve the comprehensiveness and accuracy of the extraction, data fusion and matching processing can also be performed on cross-platform historical data.

[0031] In step S13, cluster analysis is performed based on the historical data to obtain user classification information, including: Performing data preprocessing according to the historical data to obtain standard data; Perform multi-dimensional feature extraction based on the standard data to obtain multi-dimensional feature data of the user; K-means user clustering is performed based on the user multi-dimensional feature data to obtain user classification information.

[0032] It should be noted that data preprocessing is the process of cleaning, normalizing and converting historical data, with the purpose of removing noise, filling missing values, unifying data formats and eliminating possible outliers in the data. Through this process, historical data is converted into standard data that is consistent and suitable for analysis, providing a basis for subsequent feature extraction and cluster analysis. In an embodiment of the present invention, the data preprocessing technology used includes standardization processing (such as normalizing numerical data), data noise reduction (such as using filters to remove invalid data), and missing value filling (such as using mean interpolation or regression model prediction) to ensure the quality of processed data. Of course, according to different actual application scenarios and user needs, data preprocessing technology can also use other methods, and the present invention is not limited to this.

[0033] It is worth noting that multidimensional feature extraction is based on standard data, and through feature engineering, important information related to customer classification is identified, including check-in frequency, average length of stay, consumption amount, service preference, number of complaints, etc. These features are derived from the hotel's customer management system (CMS) and historical record database, and after feature construction and selection, multidimensional feature data of users is formed. The purpose of multidimensional feature extraction is to structure and quantify the potential behavior patterns in historical data, and provide input variables with discrimination for clustering algorithms, thereby improving the accuracy and effect of classification.

[0034] Among them, K-means clustering is a classic unsupervised learning algorithm, and its core idea is to divide users into several categories according to their behavioral characteristics. The specific implementation includes: initializing K cluster centers; assigning each user to the nearest cluster center according to the Euclidean distance; updating the cluster center according to the assignment result; repeating the above process until the cluster center converges or the maximum number of iterations is reached. Through the K-means algorithm, customers can be grouped into different categories according to the user's multi-dimensional feature data to obtain user classification information. These classification information reflects the commonalities and differences of customers, and provides strong support for subsequent demand analysis and recommendation algorithms. Exemplarily, the preset maximum number of iterations is set to 500 times. Of course, according to the actual application scenario and user needs, the maximum number of iterations can also be set to 300 times, 700 times, etc., and the present invention is not limited to this.

[0035] In step S14, the demand analysis is performed based on the user classification information to obtain the customer's check-in demand information, including: Extract features based on the user classification information to obtain key features related to the customer's check-in needs; The key features are used as inputs to a pre-trained demand regression analysis model to obtain the customer's occupancy demand information.

[0036] It should be noted that feature extraction is to further filter out key features directly related to customer accommodation needs from user classification information. These key features include customer budget range, room type preferences (such as luxury suites, standard rooms, etc.), length of stay, specific service needs (such as breakfast, conference room use, etc.) and personalized requirements (such as landscape rooms, non-smoking rooms). For example, these features are derived from the user's historical consumption records, customer classification labels and feedback data in the hotel management system, and the core features that best represent customer needs are filtered out through the principal component analysis algorithm.

[0037] The pre-training process of the demand regression analysis model includes: Initialize support vector machine regression model parameters; Obtain historical customer data, perform data preprocessing, and obtain standard historical customer data; According to the standard historical customer data, model parameter training is performed to obtain an initial demand regression analysis model; According to the initial demand regression analysis model, cross validation and grid optimization search are performed to obtain a demand regression analysis model.

[0038] It is worth noting that the demand regression analysis model is a tool that uses regression algorithms to model the relationship between customer key features and occupancy requirements. In an embodiment of the present invention, the pre-trained demand regression analysis model uses support vector machine regression (SVR) technology, which is characterized by strong modeling capabilities for nonlinear data and good generalization performance. Support Vector Regression (SVR) is the application of support vector machine (SVM) technology in regression problems. The core idea of ​​SVR is to find an optimal hyperplane (or regression function) so that the deviation of most training data points from the hyperplane is less than a set tolerance (ε), and minimize the number of support vectors (that is, the data points are on the "boundary" defined by the support vector machine). SVR has a strong processing capability for high-dimensional data, especially when the feature space is complex and the nonlinear relationship is obvious. SVR can handle this complexity well by selecting a suitable kernel function. SVR can avoid overfitting by maximizing the interval and limiting the complexity of the model, especially when the amount of data is small.

[0039] It should be noted that the training data consists of the key features of historical customers and actual demand labels, including the booked room type, check-in time period, and special requirements. By standardizing the historical data, inputting the model for parameter training, and optimizing the model hyperparameters through cross-validation, the accuracy and robustness of the prediction results are ensured. In practical applications, the key features extracted from the user classification information are input into the trained demand regression analysis model to predict and output the customer's check-in demand information. This information can reflect the personalized needs of customers and guide subsequent recommendations and allocation strategies. In the pre-training process, the data preprocessing step is a key link to ensure the quality of input data. First, data cleaning is to remove inconsistent, repeated or erroneous data points to avoid their adverse effects on model training. Missing value filling operations can handle the missing parts in the data. Common filling methods include mean filling, median filling, or using more complex interpolation methods to ensure data integrity.

[0040] Exemplarily, the filling method is set to median filling. Of course, according to different actual application scenarios and user needs, the filling method can also be set to mean filling, etc., which is not limited by the present invention. Feature engineering is to transform or select data, extract the most predictive features, and adjust the scale of features through normalization methods so that features of different dimensions can be treated more fairly in the model. In order to optimize the performance of the SVR model, cross validation and grid optimization search are commonly used tuning methods. Cross validation can help evaluate the generalization ability of the model and avoid performance degradation due to uneven training data or overfitting. Grid optimization search finds the optimal parameter settings by traversing different hyperparameter combinations (regularization parameter C, kernel function parameters and tolerance ε) to further improve the accuracy and stability of the model.

[0041] In step S15, the check-in demand information is input into a pre-trained recommendation network model to perform real-time check-in recommendation to obtain check-in recommendation information.

[0042] The training process of the pre-trained recommendation network model includes: Initialize the recommended network model parameters; Obtain historical occupancy demand information and occupancy information; constructing a feature matrix according to the occupancy demand information and the occupancy information to obtain model input data; According to the model input data, the model parameters are trained to obtain the trained recommendation network model.

[0043] It should be noted that in step S15, the key to inputting the check-in demand information into the pre-trained recommendation network model and performing real-time check-in recommendations is to ensure that the format and characteristics of the input information are consistent with the expectations of the model. Specifically, the check-in demand information should be pre-processed so that it can be effectively used in the recommendation system. For example, the user's check-in preferences, historical check-in data, current date and other information need to be converted into feature vectors suitable for the model and standardized or normalized so that the model can quickly and accurately generate recommendation results. The recommendation network model is based on deep learning, including architectures such as convolutional neural networks (CNN), recurrent neural networks (RNN) or Transformer.

[0044] In an embodiment of the present invention, the recommendation network model adopts the Transformer architecture, combined with the self-attention mechanism (Self-Attention), which can effectively capture the long-distance dependencies in the user's check-in demand information. The advantages of the Transformer model lie in its parallel computing capabilities and its ability to efficiently process long sequence data, and are particularly suitable for processing complex check-in demand data containing multi-dimensional information such as time, location, and preferences. Through a multi-layer self-attention mechanism, the model can automatically learn the relationship between different features in the input demand information, and then generate personalized check-in recommendations. The model can provide personalized check-in recommendations by learning the implicit rules in a large amount of historical check-in data. When making real-time recommendations, the model can quickly calculate the optimal recommendation results based on the real-time input demand information. In addition, the training phase of the recommendation network model requires the use of a large amount of historical check-in data, including user behavior data, room features, time factors, etc., to ensure the accuracy and generalization ability of the model.

[0045] In step S16, performing optimal room allocation calculation according to the check-in recommendation information to obtain optimal room number information includes: Calculate the room waiting time according to the check-in recommendation information to obtain the shortest waiting time; Calculate room selection preferences based on the check-in recommendation information to obtain room preference features; Based on the shortest waiting time and the room preference characteristics, a comprehensive analysis is performed to obtain the optimal room number information.

[0046] It should be noted that in step S16, the optimal room allocation calculation refers to making room allocation decisions through a series of comprehensive analysis steps combined with the user's check-in recommendation information to ensure that the most suitable room is allocated to the user. This process balances the user's expectations and actual available resources by calculating the room waiting time and the user's room selection preference characteristics, ensuring that the room allocation is both efficient and meets the user's needs.

[0047] In the embodiment of the present invention, the room allocation calculation adopts a multi-objective optimization method, which is implemented by comprehensively considering the shortest waiting time and the user's room preference characteristics (such as room location, floor, facilities, etc.). In practical applications, the use of this method can effectively reduce the user's waiting time and improve the user's satisfaction and experience with room selection. Specifically, the calculation of the shortest waiting time takes into account factors such as the current room's idle state, the user's arrival time, and the room's cleanliness and preparation; while the calculation of room selection preferences is based on the user's historical behavior data and recommendation information, and analyzes the user's preference characteristics for room type, location, etc. By combining the calculation results of the two, the system can efficiently select the best choice from the candidate rooms, ensuring that the use of resources is optimized while meeting user expectations. This room allocation calculation method ensures that it can respond quickly and make accurate allocation decisions in actual operations, while ensuring that the user experience can be maximized when resources are limited.

[0048] The calculation formula for the room waiting time is as follows: ; in, Indicates the customer Total waiting time, which is the time it takes for a customer to check in from the time they arrive at the hotel; Indicates the customer The number of people waiting for the selected room, that is, the number of other customers waiting to check in to the room; Indicates room The processing time is the time required for the room to be ready for check-in by the customer; Indicates the total number of rooms in the hotel, indicating that the waiting time of all rooms needs to be considered when allocating rooms.

[0049] It should be noted that the room waiting time calculation formula is to find the optimal room allocation solution by optimizing the waiting time and processing time of each room. Representing the customer The total time required from arrival at the hotel to check-in is determined by two main factors: the number of people waiting for the room and room processing time .in, It means that the customer The number of other customers who have selected the same room and are waiting to check in upon arrival; and It means room The processing time is the time required for the room to be ready for check-in. In order to obtain the optimal room allocation solution, it is necessary to Comprehensive analysis is performed in each room to minimize the total waiting time of customers. This means that when allocating rooms, it is necessary not only to consider the idle status and processing time of each room, but also the impact of other customers on the room. For example, if there are already multiple customers waiting in a room, the waiting time allocated to the new customer may increase, so it is necessary to weigh the waiting time of all rooms and optimize the allocation of each room. Exemplarily, in an embodiment of the present invention, the room waiting time calculation also takes into account dynamic factors, such as customer arrival time, room cleaning status, and current room occupancy. In this way, the system can calculate the shortest waiting time in real time and provide the most suitable room allocation for each customer.

[0050] The calculation formula for the room selection preference calculation is as follows: ; ; in, Indicates the customer The room selection preference score indicates the customer Regarding the preference for different rooms, the lower the score, the more likely the customer is to choose that room; Indicates room The relative position to the hotel entrance is a distance value. The smaller the value, the closer the room is to the entrance and the higher the customer preference. Indicates the customer In choosing a room The preference function when Adjust room selection preferences. The preference function reflects the changes in customer demand for room location. Indicates the age of the customer. The older the customer is, the more likely they are to prefer a room closer to the hotel entrance. Indicates the customer Ideal room location, based on the age of the client Adjustment; Represents the adjustment factor used to control the relationship between room location and customer preference.

[0051] It should be noted that the room selection preference calculation formula evaluates the customer's preference for different rooms based on the customer's personal characteristics (such as age) and room location, thereby achieving personalized room allocation. Representing clients The preference score for different rooms is calculated, and the lower the score, the more likely the customer is to choose that room. This score is composed of two parts: the relative location of the room to the hotel entrance. and customer preference function Specifically, Indicates room The distance from the hotel entrance, the smaller the distance, the more customers tend to choose a room close to the entrance, so the preference is higher. It is used to determine the age of the customer. Adjust the preference for room selection. As customers age, they may be more inclined to choose rooms closer to the hotel entrance, so the preference function takes this change into account and further adjusts the priority of room selection. Is a customer The ideal room location is adjusted based on the age of the client. For older clients, the ideal room location is more likely to be closer to the entrance to reduce the burden of movement. Adjustment Factor It is used to control the relationship between room location and customer preference, so that room selection preference can more accurately reflect customer needs.

[0052] It should be noted that the comprehensive consideration analysis is to use the shortest waiting time and room preference characteristics as input factors, perform multi-objective optimization calculations, and balance customer satisfaction and resource utilization efficiency. Exemplarily, the present invention adopts a weighted scoring method to assign a weight score to each room, and comprehensively considers the shortest waiting time and room preference characteristics, so as to ensure that the room allocation can not only meet the customer's needs for quick check-in, but also meet the customer's preferences as much as possible. In an embodiment of the present invention, the comprehensive consideration analysis process specifically includes: in order to make the shortest waiting time and room preference characteristics comparable, firstly, the two data are standardized and their values ​​are mapped to the range of [0,1] to avoid deviations caused by different dimensions; secondly, weights are assigned to the shortest waiting time and room preference characteristics respectively, and the comprehensive score of the room is calculated; finally, the optimal room number is obtained based on the comprehensive score result of the room. The calculation formula for the comprehensive score is as follows: ; in, After the standardization room The shortest waiting time, For standardized rooms Preference features, For the comprehensive rating, and Respectively represent the shortest waiting time and the preference feature weights. In the real-time example of the present invention, and They are set to 0.4 and 0.6 respectively. Of course, the actual application scenarios and user needs vary. and It can also be set to other values ​​such as 0.3 and 0.7, which is not limited in the present invention.

[0053] In step S17, a check-in confirmation signal is generated according to the optimal room number information, and the confirmation signal is sent to the user terminal.

[0054] It should be noted that the generation and sending of check-in confirmation signals refers to the generation of confirmation signals containing key information such as customer room information and check-in date by processing the optimal room number information, and delivering it to the customer in a timely manner. This process ensures the accuracy of the confirmation signal content and smooth communication with the user end, so that the customer can receive their check-in arrangements in a timely and clear manner.

[0055] Exemplarily, the check-in confirmation signal is generated by an automated process, and the room number, check-in time, room type and other information are generated through the background system, and customized generation is performed in combination with the customer's reservation information. In actual applications, the check-in confirmation signal is sent to the client through a variety of communication channels (such as email, SMS, APP push, etc.). This process ensures that customers can obtain confirmation information at the first time, avoiding any inconvenience in the check-in process. At the same time, the system will also take into account the needs of different user terminals, such as push notifications for mobile users, and emails for customers who book through traditional methods. In order to enhance the user experience, the confirmation signal can also contain some additional information, such as hotel services, room facilities introduction, etc., so as to improve customer satisfaction.

[0056] Reference Figure 2 The second embodiment of the present invention provides a smart hotel management system based on a wireless network, including: A data acquisition module, used to acquire user information of customers who have registered with the hotel from the wireless network; A data extraction module, used to extract historical data based on the user information to obtain the customer's historical data; A cluster analysis module, used to perform cluster analysis based on the historical data to obtain user classification information; A demand analysis module, used to perform demand analysis based on the user classification information to obtain the customer's check-in demand information; An accommodation recommendation module is used to input the accommodation demand information into a pre-trained recommendation network model to make real-time accommodation recommendations and obtain accommodation recommendation information; A room allocation module, used to calculate the optimal room allocation according to the check-in recommendation information to obtain the optimal room number information; The check-in confirmation module is used to generate a check-in confirmation signal according to the optimal room number information and send the confirmation signal to the user terminal.

[0057] It should be noted that the wireless network-based smart hotel management system provided in an embodiment of the present invention is used to execute all the process steps of the wireless network-based smart hotel management method in the above-mentioned embodiment. The working principles and beneficial effects of the two correspond one to one, so they will not be repeated here.

[0058] In summary, in the present invention, through the intelligent hotel management method based on wireless network, wireless sensing technology is fully utilized to obtain the user information of customers in real time, and cluster analysis is performed in combination with historical data to accurately extract the consumption preferences and check-in requirements of customers. By constructing and training the recommendation network model, the system can efficiently provide customers with real-time room recommendations, and generate the optimal room number information through the optimal room allocation algorithm combined with the customer's preferences and the room's usage status, and realize a seamless check-in process through the check-in confirmation signal. This method effectively overcomes the problems of low efficiency and insufficient personalized service of traditional hotel services, not only improving the hotel service efficiency, but also providing customers with a higher quality personalized check-in experience.

[0059] The embodiment of the present invention further provides a terminal device. The terminal device includes: a processor, a memory, and a computer program stored in the memory and executable on the processor, such as a smart hotel management program based on a wireless network. When the processor executes the computer program, the steps in the above-mentioned smart hotel management method embodiments based on a wireless network are implemented, such as Figure 1 Alternatively, the processor implements the functions of each module / unit in the above-mentioned system embodiments when executing the computer program.

[0060] Exemplarily, the computer program may be divided into one or more modules / units, which are stored in the memory and executed by the processor to implement the present invention. The one or more modules / units may be a series of computer program instruction segments capable of implementing specific functions, which are used to describe the execution process of the computer program in the terminal device.

[0061] The terminal device may be a computing device such as a desktop computer, a notebook, a PDA, and a smart tablet. The terminal device may include, but is not limited to, a processor and a memory. Those skilled in the art will appreciate that the above components are merely examples of terminal devices and do not constitute a limitation on the terminal device. The terminal device may include more or fewer components than the above components, or may combine certain components, or different components. For example, the terminal device may also include input and output devices, network access devices, buses, etc.

[0062] The processor may be a central processing unit (CPU), other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor, etc. The processor is the control center of the terminal device, and uses various interfaces and lines to connect various parts of the entire terminal device.

[0063] The memory can be used to store the computer program and / or module, and the processor realizes various functions of the terminal device by running or executing the computer program and / or module stored in the memory, and calling the data stored in the memory. The memory can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, an application required for at least one function (such as a sound playback function, an image playback function, etc.), etc.; the data storage area can store data created according to the use of the mobile phone (such as audio data, a phone book, etc.), etc. In addition, the memory can include a high-speed random access memory, and can also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0064] Wherein, if the module / unit integrated in the terminal device is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on such an understanding, the present invention implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. Wherein, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include: any entity or system capable of carrying the computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium. It should be noted that the content contained in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media do not include electric carrier signals and telecommunication signals.

[0065] It should be noted that the system embodiment described above is merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. In addition, in the drawings of the system embodiment provided by the present invention, the connection relationship between the modules indicates that there is a communication connection between them, which may be specifically implemented as one or more communication buses or signal lines. A person of ordinary skill in the art may understand and implement it without paying any creative effort.

[0066] The specific embodiments described above further illustrate the purpose, technical solutions and beneficial effects of the present invention. It should be understood that the above description is only a specific embodiment of the present invention and is not intended to limit the scope of protection of the present invention. It is particularly pointed out that for those skilled in the art, any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the scope of protection of the present invention.

Claims

1. A smart hotel management method based on wireless network, characterized in that: Executed by the server, including: Obtain user information of customers registered at the hotel from the wireless network; Extract historical data based on the user information to obtain the customer's historical data; Performing cluster analysis based on the historical data to obtain user classification information; Conduct demand analysis based on the user classification information to obtain the customer's check-in demand information; Inputting the check-in demand information into a pre-trained recommendation network model to perform real-time check-in recommendation and obtain check-in recommendation information; Calculate the optimal room allocation based on the recommended check-in information to obtain the optimal room number information; Generate a check-in confirmation signal according to the optimal room number information, and send the confirmation signal to the user terminal; The recommendation network model is based on historical occupancy demand information and occupancy information labels as input data, an initial recommendation network model is constructed, and the initial recommendation network model is trained to obtain a recommendation network model.

2. The wireless network-based smart hotel management method according to claim 1, characterized in that: The method of obtaining user information of a customer who has registered a hotel from a wireless network includes: Obtain network fingerprint information when customers connect to the hotel wireless network; According to the network fingerprint information, query the customer's login information to obtain the customer's registration information; Extracting preferences based on the customer registration information to obtain customer preference data; Generate a user profile based on the customer registration information and the preference data to obtain the customer's user information; The network fingerprint information includes the client's IP address, device MAC address, and Wi-Fi signal strength.

3. The wireless network-based smart hotel management method according to claim 1, characterized in that: The cluster analysis is performed based on the historical data to obtain user classification information, including: Performing data preprocessing according to the historical data to obtain standard data; Perform multi-dimensional feature extraction based on the standard data to obtain multi-dimensional feature data of the user; K-means user clustering is performed based on the user multi-dimensional feature data to obtain user classification information.

4. The wireless network-based smart hotel management method according to claim 1, characterized in that: The step of performing demand analysis based on the user classification information to obtain the customer's check-in demand information includes: Extract features based on the user classification information to obtain key features related to the customer's check-in needs; The key features are used as inputs to a pre-trained demand regression analysis model to obtain the customer's occupancy demand information.

5. The wireless network-based smart hotel management method according to claim 4 is characterized in that: The pre-training process of the demand regression analysis model includes: Initialize support vector machine regression model parameters; Obtain historical customer data, perform data preprocessing, and obtain standard historical customer data; According to the standard historical customer data, model parameter training is performed to obtain an initial demand regression analysis model; According to the initial demand regression analysis model, cross validation and grid optimization search are performed to obtain a demand regression analysis model.

6. The wireless network-based smart hotel management method according to claim 1, characterized in that: The training process of the pre-trained recommendation network model includes: Initialize the recommended network model parameters; Obtain historical occupancy demand information and occupancy information; constructing a feature matrix according to the occupancy demand information and the occupancy information to obtain model input data; According to the model input data, the model parameters are trained to obtain the trained recommendation network model.

7. The wireless network-based smart hotel management method according to claim 1, characterized in that: The step of performing optimal room allocation calculation according to the check-in recommendation information to obtain optimal room number information includes: Calculate the room waiting time according to the check-in recommendation information to obtain the shortest waiting time; Calculate room selection preferences based on the check-in recommendation information to obtain room preference features; Based on the shortest waiting time and the room preference characteristics, a comprehensive analysis is performed to obtain the optimal room number information.

8. The wireless network-based smart hotel management method according to claim 7, characterized in that: The calculation formula for the room waiting time is as follows: ； in, Indicates the customer Total waiting time, which is the time it takes for a customer to check in from the time they arrive at the hotel; Indicates the customer The number of people waiting for the selected room, that is, the number of other customers waiting to check in to the room; Indicates room The processing time is the time required for the room to be ready for check-in by the customer; Represents the total number of rooms in the hotel.

9. The wireless network-based smart hotel management method according to claim 7, characterized in that: The calculation formula for the room selection preference calculation is as follows: ； ； in, Indicates the customer The room selection preference score indicates the customer Regarding the preference for different rooms, the lower the score, the more likely the customer is to choose that room; Indicates room The relative position to the hotel entrance is a distance value. The smaller the value, the closer the room is to the entrance and the higher the customer preference. Indicates the customer In choosing a room The preference function is based on the customer's age. Adjust room selection preferences; Indicates the age of the customer; Indicates the customer Ideal room location, based on the age of the client Adjustment; Represents the adjustment factor used to control the relationship between room location and customer preference.

10. A smart hotel management system based on wireless network, characterized in that: include: A data acquisition module, used to acquire user information of customers who have registered with the hotel from the wireless network; A data extraction module, used to extract historical data based on the user information to obtain the customer's historical data; A cluster analysis module, used to perform cluster analysis based on the historical data to obtain user classification information; A demand analysis module, used to perform demand analysis based on the user classification information to obtain the customer's check-in demand information; An accommodation recommendation module is used to input the accommodation demand information into a pre-trained recommendation network model to make real-time accommodation recommendations and obtain accommodation recommendation information; A room allocation module, used to calculate the optimal room allocation according to the check-in recommendation information to obtain the optimal room number information; The check-in confirmation module is used to generate a check-in confirmation signal according to the optimal room number information and send the confirmation signal to the user terminal.

Images