A digital-based intelligent hotel management method and system

Abstract

The application relates to the technical field of intelligent hotel management, and discloses an intelligent hotel management method and system based on digitization. The method acquires real-time operation monitoring data and guest interaction request data of an intelligent hotel, and constructs a digital operation state atlas and an interaction decision auxiliary text according to the data; then, based on target service components related to hotel service process resource flow, a digital operation state model of the intelligent hotel is constructed; then, a service resource control strategy model for regulating and controlling service resource output distribution is constructed; then, according to selected hotel operation working points, coupling decision simulation is carried out on the service resource control strategy model and the digital operation state model, and simulation decision result data is obtained; finally, based on the simulation decision result data, the digital operation state atlas and the interaction decision auxiliary text are combined to determine an optimization decision or an abnormal risk indication in intelligent hotel service management. The method improves the effectiveness and precision of intelligent hotel management.

Description

Technical Field

[0001] This invention relates to the field of smart hotel management technology, specifically to a digital-based smart hotel management method and system. Background Technology

[0002] With the rapid development of information technology, the hotel industry is gradually transforming towards intelligence and digitalization, with smart hotels becoming an important direction for industry development. However, current smart hotel management still faces many challenges. Traditional hotel management models often rely on human experience for operational decisions, lacking effective integration and analysis of real-time operational data, resulting in delayed perception of operational status. Daily hotel operations involve multiple aspects such as room service, food and beverage supply, facility maintenance, and security management. The operational data generated by each aspect is scattered across different systems with inconsistent data formats, making it difficult to form a comprehensive view of operational status and hindering managers from quickly grasping the overall operational situation of the hotel.

[0003] In terms of guest service, guest needs are becoming increasingly diverse and personalized. Traditional service response models are mostly reactive, with staff only responding after guests make requests via phone or front desk. This approach is not only inefficient but also makes it difficult to anticipate guest needs. Furthermore, the allocation of hotel service resources relies on fixed processes or manual scheduling. When faced with unforeseen circumstances or fluctuations in guest flow, resource allocation can easily become unbalanced. For example, inefficient scheduling of housekeeping staff can lead to slow room turnover, and insufficient food and beverage supplies can affect food service efficiency, ultimately impacting the guest experience.

[0004] Abnormal risks in hotel operations are difficult to identify and warn of in real time. Equipment malfunctions, safety hazards, and service process loopholes are often only discovered after they occur, and the lack of early warning mechanisms can lead to service interruptions, guest complaints, and even safety incidents. While some existing hotel management systems have data collection capabilities, they primarily focus on data recording and storage, lacking in-depth analysis and decision support capabilities. They cannot transform data into effective management strategies and fail to meet the precise and efficient operational needs of smart hotels. Therefore, how to integrate operational data through digital means, build a scientific management model, and achieve real-time perception of operational status, dynamic optimization of resource allocation, and early warning of risks has become a pressing issue in the field of smart hotel management. Summary of the Invention

[0005] The purpose of this invention is to provide a digital-based smart hotel management method to solve the problems mentioned in the background art.

[0006] To achieve the above objectives, the present invention provides a digital-based smart hotel management method, the method comprising:

[0007] Acquire real-time operational monitoring data and guest interaction request data of smart hotels, and construct a digital operational status map and interactive decision support text based on the real-time operational monitoring data and guest interaction request data;

[0008] The digital operation status model of the smart hotel is constructed based on the target service components of the smart hotel, wherein the target service components are components related to the resource flow of hotel service processes.

[0009] A service resource control strategy model is constructed, which is used to regulate the output allocation of service resources in the digital operation status model.

[0010] Based on the selected hotel operation condition points, a coupled decision simulation is performed on the service resource control strategy model and the digital operation status model to obtain the corresponding simulation decision result data.

[0011] Based on the simulation decision results data, combined with the digital operation status map and the interactive decision-making assistance text, optimization decisions or abnormal risk indicators in smart hotel service management are determined.

[0012] Preferably, when the target service components include a guest room occupancy system, a public area system, and an environmental control system, the construction of the digital operation status model of the smart hotel based on the target service components of the smart hotel includes:

[0013] Based on the target service components of smart hotels, construct dynamic models of guest room occupancy, public area traffic flow, and environmental regulation and control models;

[0014] The guest room occupancy dynamic model, the public area traffic model, and the environmental regulation and control model are integrated to form the digital operation status model;

[0015] The output data of the guest room occupancy dynamic model is used to update the input parameters of the public area traffic model, and the input parameters of the environmental regulation and control model are adjusted based on the output data of the public area traffic model.

[0016] Preferably, the step of performing coupled decision simulation on the service resource control strategy model and the digital operation status model based on the selected hotel operation condition points to obtain corresponding simulation decision result data includes:

[0017] Based on the selected hotel operating condition points, a resource allocation control signal is generated through the service resource control strategy model to dynamically adjust the service resource parameters in the digital operating status model.

[0018] Under the influence of resource allocation control signals, a hotel service scenario is simulated, and service resource utilization data and guest satisfaction index data are recorded as the simulation decision result data.

[0019] The service resource utilization data is fed back to the service resource control strategy model to iteratively optimize the resource allocation control signal.

[0020] Preferably, the method further includes:

[0021] Extract a set of candidate service items related to service decisions from a hotel industry knowledge base;

[0022] Based on guest interaction request data and contextual semantic information, semantic disambiguation processing is performed on the candidate service item set to obtain an optimized service option list;

[0023] The optimized service option list is used to initialize the decision parameters of the service resource control strategy model.

[0024] Preferably, the step of determining optimization decisions or abnormal risk indicators in smart hotel service management based on the simulation decision result data, combined with the digital operation status map and the interactive decision-making assistance text, includes:

[0025] If the simulation decision results data meet the preset resource threshold conditions, it is determined that there is a risk of service resource bottleneck or waste.

[0026] Generate optimized resource allocation suggestions or risk warning signals;

[0027] The proposed optimized resource allocation is validated by referring to the contextual semantic information in the interactive decision-making support text.

[0028] Preferably, in cases where there is a risk of service resource bottlenecks or waste, the control strategy parameters in the service resource control strategy model are optimized.

[0029] Based on the optimized control strategy parameters, the service resource control strategy model and the digital operation status model are re-coupled for decision simulation until the target simulation decision result data is obtained. The target simulation decision result data represents the elimination of service resource bottlenecks or waste risks.

[0030] Preferably, a dynamic model of guest room occupancy is constructed, including:

[0031] Based on the distribution of room types and quantities in smart hotels, the room occupancy status is discretized into an equivalent state transition sub-model;

[0032] The state transition sub-models are connected by state transition rules, and the room occupancy sequence logic is set to construct a dynamic model of room occupancy.

[0033] The output data of the guest room occupancy sequence logic is used to drive the input update of the public area traffic model.

[0034] Preferably, an environmental regulation and control model is constructed, including:

[0035] Using environmental parameters as the adjustment boundary, environmental regulation is divided into temperature control unit and humidity control unit;

[0036] The temperature control unit and humidity control unit are defined as independent adjustment modules;

[0037] The independent adjustment modules are integrated through a feedback compensation mechanism to construct an environmental regulation and control model;

[0038] The adjustment output data of the independent adjustment module is calibrated based on the environmental monitoring values ​​in the digital operation status map.

[0039] Preferably, the step of acquiring real-time operational monitoring data and guest interaction request data of the smart hotel, and constructing a digital operational status map and interactive decision-making support text based on the real-time operational monitoring data and guest interaction request data, includes:

[0040] The guest interaction request data is processed by text normalization and semantic structure parsing to obtain a list of service request entities and unstructured context fragments;

[0041] Quantify the correlation between real-time operational monitoring data and generate operational influencing factor indicators;

[0042] Based on the service request entity list, unstructured context fragments, and operational influencing factor indicators, the interactive decision-making assistance text is constructed.

[0043] The digital operation status map is constructed based on real-time operation monitoring data;

[0044] The operational influencing factor indicators are input into the service resource control strategy model to adjust the decision weights.

[0045] Preferably, the present invention also includes a digital-based smart hotel management system, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that, when the processor executes the computer program, it implements the steps of the above-described digital-based smart hotel management method.

[0046] Compared with the prior art, the beneficial effects of the present invention are:

[0047] This digitally-based smart hotel management method provides a systematic solution for smart hotel operations management through multi-dimensional data processing and model building. In terms of data integration, the method acquires real-time operational monitoring data and guest interaction request data to construct a digital operational status map and interactive decision-making support text. This transforms fragmented data scattered across various aspects of the hotel into intuitive visualizations and referable decision-making texts, enabling managers to comprehensively and clearly grasp the hotel's real-time operational status and dynamic guest needs. This breaks down the limitations of data silos in traditional management, making operational information transmission more efficient.

[0048] A digital operational status model is built based on target service components, focusing on core components related to service process resource flow. This model can accurately map the actual operation of hotel service resources. Instead of modeling all hotel components indiscriminately, it selectively captures key nodes in resource flow, such as room status, cleaning staff allocation, and food and beverage raw material supply. This allows the model to truly reflect the supply and demand relationship and flow efficiency of service resources, providing a precise digital foundation for subsequent resource regulation.

[0049] The construction of the service resource control strategy model provides a dynamic adjustment mechanism for resource output and allocation. This model can flexibly adjust resource allocation schemes based on the actual operation of the hotel, eliminating reliance on fixed processes or manual experience for resource scheduling. When faced with unexpected situations such as peak passenger flow or temporary equipment failures, the model can automatically generate resource allocation suggestions based on real-time data, achieving dynamic resource balance, avoiding resource waste or insufficient supply, and ensuring the smooth operation of service processes.

[0050] By selecting hotel operational scenarios for coupled decision-making simulation, the effectiveness of different strategies can be simulated and verified before actual decision-making. Based on the simulation results data, combined with digital operational status maps and interactive decision support text, managers can more comprehensively assess the potential impact of decisions, thereby selecting the optimal management strategy from multiple potential options. Simultaneously, this process can also promptly identify potential operational anomalies and risks. By analyzing simulation data to identify risk sources, conditions are created for proactive intervention, reducing the adverse impact of risks on hotel operations and guest experience.

[0051] This method integrates digital technology throughout the entire process of hotel operations monitoring, model building, strategy optimization, and risk identification, enabling a shift in operations management from experience-driven to data-driven approaches. This improves the scientific rigor and timeliness of management decisions, helps optimize guest service experience, and promotes increased hotel operational efficiency. Attached Figure Description

[0052] Figure 1This is a schematic diagram illustrating the working principle of the digital-based smart hotel management method described in this invention.

[0053] Figure 2 A flowchart for building a digital operational status model based on target service components;

[0054] Figure 3 A flowchart for obtaining simulation decision result data in coupled decision simulation;

[0055] Figure 4 A flowchart for optimizing service resource risk elimination. Detailed Implementation

[0056] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0057] Please see Figure 1 This invention provides a digital-based smart hotel management method and system, the method comprising:

[0058] A dynamic decision support system is constructed by integrating real-time operational data and customer interaction information. The system first continuously collects two types of core data: real-time operational monitoring data from various sensors and management systems within the hotel, and interactive request data from customer terminal devices. After processing, this data is used to construct two structured information carriers: a digital operational status map that visually presents the overall operational status of the hotel; and interactive decision support text that extracts the semantic features of customer requests and associates them with context to form a standardized instruction set that can be parsed by the decision model. Simultaneously, the system establishes a digital operational status model based on key physical or logical components involved in the hotel's core service processes. This model abstractly represents the dynamic changes in service resources and their interrelationships. To optimize resource allocation, a service resource control strategy model is constructed, defining resource allocation rules and response logic. Under specific hotel operating conditions, the service resource control strategy model and the digital operational status model are coupled and simulated. During the simulation, the control strategy model outputs resource allocation instructions, driving the status model to simulate the operational response of actual service scenarios, and recording simulation decision results data such as resource utilization efficiency and simulated customer satisfaction. Finally, by combining the global situational awareness and semantic details contained in the interactive decision-making support text provided by the digital operation status map, the simulation results are analyzed to identify the optimization space or potential abnormal risks in service resource configuration, and specific optimization decision suggestions or risk warning signals are output.

[0059] Example 1: See Figure 2 When constructing the digital operation status model, sub-models were established and integrated for the guest room occupancy system, public area system, and environmental control system. The guest room occupancy dynamic model first defines each guest room as an independent state node based on the hotel's guest room type distribution and floor layout. The states include seven basic states: vacant, booked but not checked in, checked in, checked out and awaiting cleaning, cleaning in progress, under maintenance, and cleaned and awaiting inspection. Logical connections are established through state transition rules: when a guest checks in, the "vacant" state transitions to "checked in"; check-out triggers a transition from "checked in" to "checked out and awaiting cleaning"; cleaning task allocation causes "checked out and awaiting cleaning" to enter the "cleaning in progress" state; after cleaning is completed and confirmed by the system, it transitions to "cleaned and awaiting inspection"; after quality inspection passes, it returns to "vacant." The guest room occupancy sequence logic manages the timing constraints of state transitions, for example, setting the "under maintenance" state to have a higher priority than the cleaning process, and outputting a real-time guest room status distribution matrix. This matrix serves as the core input parameter for the public area traffic model.

[0060] The public area traffic model targets the lobby, restaurant, meeting rooms, and gym, receiving real-time data from the guest room occupancy dynamic model. The model calculates pedestrian density through spatial grid division and predicts service demand for each area based on historical behavioral data. For example, based on the day's group check-in information, it predicts peak lobby traffic between 2:00 PM and 4:00 PM, generating a dining queue time prediction table based on restaurant seating capacity. Output data includes a regional heatmap coordinate set (X-axis for time interval, Y-axis for area number, Z-axis for pedestrian density value) and a service waiting time matrix. The environmental control model employs a dual-module architecture: the temperature control unit receives the target temperature setpoint and real-time monitoring values, calculating cooling output based on heat load parameters; the humidity control unit generates dehumidification commands based on the target humidity and measured values, integrating moisture source parameters. A feedback compensation mechanism dynamically adjusts the output weights of the two modules by comparing environmental sensor data in the digital operation status map in real time. Finally, the three sub-models are integrated to form a unified data flow: changes in guest room status trigger updates to public area pedestrian traffic predictions, and pedestrian traffic data dynamically corrects environmental control target values.

[0061] Example 2: See Figure 3 The coupled decision-making simulation process begins with selecting a typical operating condition, such as the dinner peak period from 18:00 to 20:00 on Friday. The service resource control strategy model generates initial resource allocation control signals based on the operating condition characteristics: defining the restaurant waiter scheduling vector. ;

[0062] in This represents the waiter scheduling scheme vector. This represents the number of people allocated to the i-th dining area, where n is the total number of dining areas; energy consumption quotas for air conditioning zones are set. ,in This represents the energy consumption limit for region k. It is the energy consumption coefficient constant. Let k be the area of ​​region k. For the real-time pedestrian density in area k, the energy consumption coefficient is set to 0.85. Control signals are input into the digital operation status model for scenario simulation: In the restaurant area, the model calculates food delivery efficiency based on the number of waiters and generates a waiting time series based on guest arrival rate; in the environmental control module, the air conditioning power output is dynamically adjusted according to the energy consumption quota. Service resource utilization indicators are recorded during the simulation. Feedback is fed back to the strategy model to trigger iterative optimization: when the energy consumption matching degree is greater than 1.1, the energy consumption coefficient is automatically lowered to 0.78 and the energy consumption quota is regenerated; when the effective working hour rate is less than 75%, the waiter scheduling vector is adjusted. Simultaneously, a candidate service item set is extracted from the hotel domain knowledge base, and semantic disambiguation is performed on real-time interactive requests such as "need a high chair": the "child" attribute is associated with age, and "high chair" is mapped to facility code FAC-07. Combined with the context, an optimized service option list is generated [Service item: child seat provision, priority: P1, associated resource: storage area B-12]. This list initializes the decision parameters of the strategy model and sets resource allocation weights. (in This represents the weighting coefficient (higher than the average of 0.6), which drives the next round of simulation optimization.

[0063] Example 3: See Figure 4 The simulation decision-making data analysis employs a multi-threshold judgment mechanism. Resource utilization thresholds are set: an effective working hour rate below 60% is considered idle, and above 90% is considered overloaded; the energy consumption deviation threshold is set to trigger an early warning when the absolute value of the deviation between actual energy consumption and the quota is greater than 0.2; the satisfaction threshold is set at 80 points (out of 100). When simulation data shows that the effective working hour rate of waiters is 58% during a certain period, the air conditioning energy consumption matching degree is 1.25, and the satisfaction score is 76 points, the system determines that there are risks of resource idleness, energy waste, and service quality. Optimization suggestions are generated: "Reduce the allocation of 3 waiters from the west area to the east area during the 18:30-19:30 period," and "Increase the target temperature of the banquet hall air conditioning by 1℃." These suggestions require verification through interactive decision-making auxiliary text. Risk warning signals are coded as ERR-07 (resource mismatch) and ERR-12 (energy efficiency anomaly). Trigger strategy parameter optimization: the regional weight coefficient in the waiter scheduling algorithm is increased from 0.4 to 0.6, and the air conditioning energy consumption coefficient is decreased from 0.9 to 0.75. The simulation was re-simulated based on the new parameters: After adjustment, the effective working hours rate of the waiters in the East Zone was 68%, the energy consumption matching degree of the banquet hall air conditioning was 1.08, and the satisfaction score was 83. Iteration continued until the target simulation results were achieved: effective working hours rate above 65%, energy consumption matching degree below 1.1, and satisfaction score above 80. The optimized loop termination condition was set to a convergence state where the risk indicators of two consecutive simulations were both below the threshold.

[0064] Example 4: The dynamic model construction process for guest room occupancy is based on a hotel with 320 guest rooms. A state transition sub-model is established according to room type. The state transition rule base contains 42 logical rules, such as rule R07: when the cleaning completion event is triggered and the quality inspection score is greater than 90, "Cleaning in Progress" transitions to "Vacant Room for Sale"; rule R15: after a repair request event is triggered, regardless of the current state, the system is forced to enter "Under Repair". The guest room occupancy sequence logic manages global transitions through a state transition matrix. The matrix dimension is 7 (number of states) × 7 (number of states), and the element values ​​are transition condition codes. The real-time output data format is shown in Table 1.

[0065] Table 1: Real-time distribution of guest room status;

[0066]

[0067] When constructing the environmental regulation control model, the temperature control unit adopts a proportional-integral-derivative control algorithm: input target temperature value. Measured temperature value Output cooling capacity ,in: Indicates the cooling output. This is the proportionality coefficient. The integral coefficient is... These are the differential coefficients. Indicates temperature deviation. For the integral term of deviation, This represents the differential term of the deviation. The humidity control unit calculates the dehumidification capacity using a nonlinear function based on the humidity difference. The feedback compensation mechanism calculates the coupling weights of temperature and humidity control through an exponential decay function, and the final output is a weighted combination of the temperature control output and the humidity control output. The model reads sensor data from the digital operation status map every 5 minutes, and generates a device instruction set after calibration.

[0068] Example 5: Real-time operation monitoring data processing includes sensor network data and interaction request data. Guest interaction requests are normalized: the voice request "Please book a meeting room for 8:00 AM tomorrow" is converted to the text "Book a meeting room for 8:00 AM tomorrow"; spelling correction "wify password" is corrected to "WiFi password"; terminology standardization "breakfast" and "breakfast" are standardized to "breakfast". Semantic structure parsing extracts core entities: the request "Extend check-out until 2:00 PM" is parsed into the action entity [delayed check-out], the time entity [2:00 PM], and the object entity [room number]. Unstructured context fragments are used to extract feature vectors through a long short-term memory network model, such as generating a feature code [CTX-109] for "Need a quiet room with a child". Operational influencing factor indicators are calculated using the Pearson correlation coefficient. For example, the correlation coefficient between room occupancy rate and elevator usage frequency is calculated to be 0.92, generating the indicator "Elevator load factor = 0.92 × occupancy rate".

[0069] A digital operation status graph is constructed using a graph database to store nodes and edges: 320 guest room nodes (attributes include room type and status), 45 equipment nodes (attributes include power and status), and 8 area nodes (attributes include capacity). Edge relationships include "affiliation," "status association," and "data flow." During real-time graph rendering, node colors map to status, and edge widths are proportional to energy consumption data. Interactive decision-making support text is structured and stored in JSON format: {"request_id":"REQ-202508191203","entities":"food delivery","coffee","hot"],"context":"CTX-109","impact_indicator":"food delivery person utilization 0.85"}. This text-driven service resource control strategy model adjusts the weights of decision tree branches, automatically downgrading the response priority of non-urgent requests.

[0070] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus.

[0071] Although embodiments of the invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the appended claims and their equivalents.

Claims

1. A digitally-based smart hotel management method, characterized in that, The method includes: Acquire real-time operational monitoring data and guest interaction request data of smart hotels, and construct a digital operational status map and interactive decision support text based on the real-time operational monitoring data and guest interaction request data; The digital operation status model of the smart hotel is constructed based on the target service components of the smart hotel, wherein the target service components are components related to the resource flow of hotel service processes. A service resource control strategy model is constructed, which is used to regulate the output allocation of service resources in the digital operation status model. Based on the selected hotel operation condition points, a coupled decision simulation is performed on the service resource control strategy model and the digital operation status model to obtain the corresponding simulation decision result data. Based on the simulation decision results data, combined with the digital operation status map and the interactive decision assistance text, optimization decisions or abnormal risk indicators in smart hotel service management are determined. The step involves performing coupled decision simulation on the service resource control strategy model and the digital operation status model based on the selected hotel operating condition points to obtain corresponding simulation decision result data, including: Based on the selected hotel operating condition points, a resource allocation control signal is generated through the service resource control strategy model to dynamically adjust the service resource parameters in the digital operating status model. Under the influence of resource allocation control signals, a hotel service scenario is simulated, and service resource utilization data and guest satisfaction index data are recorded as the simulation decision result data. The service resource utilization data is fed back to the service resource control strategy model to iteratively optimize the resource allocation control signal; The process of acquiring real-time operational monitoring data and guest interaction request data of smart hotels, and constructing a digital operational status map and interactive decision support text based on the real-time operational monitoring data and guest interaction request data, includes: The guest interaction request data is processed by text normalization and semantic structure parsing to obtain a list of service request entities and unstructured context fragments; Quantify the correlation between real-time operational monitoring data and generate operational influencing factor indicators; Based on the service request entity list, unstructured context fragments, and operational influencing factor indicators, the interactive decision-making assistance text is constructed. The digital operation status map is constructed based on real-time operation monitoring data; The operational influencing factor indicators are input into the service resource control strategy model to adjust the decision weights.

2. The digital-based smart hotel management method according to claim 1, characterized in that, When the target service components include a guest room occupancy system, a public area system, and an environmental control system, the construction of a digital operational status model of the smart hotel based on the target service components includes: Based on the target service components of smart hotels, construct dynamic models of guest room occupancy, public area traffic flow, and environmental regulation and control models; The guest room occupancy dynamic model, the public area traffic model, and the environmental regulation and control model are integrated to form the digital operation status model; The output data of the guest room occupancy dynamic model is used to update the input parameters of the public area traffic model, and the input parameters of the environmental regulation and control model are adjusted based on the output data of the public area traffic model.

3. The digital-based smart hotel management method according to claim 1, characterized in that, The method further includes: Extract a set of candidate service items related to service decisions from a hotel industry knowledge base; Based on guest interaction request data and contextual semantic information, semantic disambiguation processing is performed on the candidate service item set to obtain an optimized service option list; The optimized service option list is used to initialize the decision parameters of the service resource control strategy model.

4. The digital-based smart hotel management method according to claim 1, characterized in that, Based on the simulation decision-making result data, combined with the digital operation status map and the interactive decision-making assistance text, the determination of optimization decisions or abnormal risk indicators in smart hotel service management includes: If the simulation decision results data meet the preset resource threshold conditions, it is determined that there is a risk of service resource bottleneck or waste. Generate optimized resource allocation suggestions or risk warning signals; The proposed optimized resource allocation is validated by referring to the contextual semantic information in the interactive decision-making support text.

5. The digital-based smart hotel management method according to claim 4, characterized in that, In situations where there is a risk of service resource bottlenecks or waste, optimize the control strategy parameters in the service resource control strategy model. Based on the optimized control strategy parameters, the service resource control strategy model and the digital operation status model are re-coupled for decision simulation until the target simulation decision result data is obtained. The target simulation decision result data represents the elimination of service resource bottlenecks or waste risks.

6. The digital-based smart hotel management method according to claim 2, characterized in that, Construct a dynamic model of guest room occupancy, including: Based on the distribution of room types and quantities in smart hotels, the room occupancy status is discretized into an equivalent state transition sub-model; The state transition sub-models are connected by state transition rules, and the room occupancy sequence logic is set to construct a dynamic model of room occupancy. The output data of the guest room occupancy sequence logic is used to drive the input update of the public area traffic model.

7. The digital-based smart hotel management method according to claim 2, characterized in that, Construct an environmental regulation and control model, including: Using environmental parameters as the adjustment boundary, environmental regulation is divided into temperature control unit and humidity control unit; The temperature control unit and humidity control unit are defined as independent adjustment modules; The independent adjustment modules are integrated through a feedback compensation mechanism to construct an environmental regulation and control model; The adjustment output data of the independent adjustment module is calibrated based on the environmental monitoring values ​​in the digital operation status map.

8. A digitally based smart hotel management system, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the digital-based smart hotel management method according to any one of claims 1 to 7.

Images