Hotel guest room service task intelligent scheduling system based on cloud platform

Abstract

The invention discloses a hotel guest room service task intelligent scheduling system based on a cloud platform, and relates to the technical field of hotel service management, the intelligent scheduling system comprises a mobile client, a cloud server and a database system; and the mobile client is used for configuring a special mobile application program running on mobile equipment such as a smart phone or a tablet personal computer for hotel guest room service personnel. According to the intelligent hotel guest room service task scheduling system based on the cloud platform, service personnel can quickly respond to service requirements through real-time task pushing and mobile operation, the task waiting time is shortened, the moving speed of the service personnel is increased through positioning and navigation functions, the service response time is shortened, and the service efficiency is improved. Through detailed recording and picture and video uploading in the service process, service quality tracing and supervision are facilitated, weak links of the service process can be found and improved through data analysis, in addition, special requirements of guests are met through personalized service recommendation, and the satisfaction degree of the guests is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of hotel service management, and specifically to an intelligent scheduling system for hotel room service tasks based on a cloud platform. Background Art

[0002] In the current highly competitive hotel industry, the efficiency and quality of room service are crucial for attracting customers and enhancing the hotel's reputation. The traditional room service mode relies on paper records, walkie-talkie communication, and manual scheduling, which has many drawbacks. Delayed information transmission can lead to delayed service responses, and the cumbersome service process is prone to errors. It is difficult to track the service progress in real time and statistically analyze service data. Moreover, as customer needs become increasingly diverse and personalized, the traditional mode is difficult to quickly adapt to new requirements. Therefore, an intelligent and information-based room service solution is urgently needed.

[0003] Specifically, the traditional room service mode mainly relies on paper records, walkie-talkie communication, and manual scheduling. This method is not only inefficient but also prone to problems such as poor communication and unreasonable task allocation. At the same time, due to the lack of effective data recording and analysis means, hotel management has difficulty accurately understanding the working status and service quality of service personnel and cannot optimize the service process in a targeted manner. Summary of the Invention

[0004] To achieve the above objectives, the present invention is realized through the following technical solutions: An intelligent scheduling system for hotel room service tasks based on a cloud platform, the intelligent scheduling system includes a mobile client, an end-cloud collaboration module, a cloud server, and a database system;

[0005] The mobile client is equipped with a dedicated mobile application running on mobile devices such as smartphones or tablets for hotel room service personnel;

[0006] The end-cloud collaboration module is used to intelligently allocate tasks to different cloud server nodes according to the load conditions of the cloud server;

[0007] The cloud server includes a task management and scheduling module, a data storage and management module, a data analysis and decision support module, and an interface management module, where each module is electrically connected;

[0008] The task management and scheduling module is used to receive service requirements from various hotel channels (such as the front desk reservation system, guest mobile APP requests, intelligent device alarms in the guest room, etc.), and intelligently allocate tasks to service personnel according to task type, priority, service personnel location, and workload factors, and push task notifications to their mobile clients in real time;

[0009] The data storage and management module is used to store data related to guest services, including guest room data, guest data, service staff data, and service task data. The data is structured for easy querying, statistics, and analysis.

[0010] The data analysis and decision support module uses big data analysis technology to deeply mine and analyze the stored data, analyze the service demand patterns for different time periods and room types, predict the peaks and troughs of service demand, and provide a decision-making basis for hotel human resource arrangements and material procurement. By analyzing guest service evaluations and historical demands, it provides recommendations and optimization suggestions for personalized services.

[0011] The interface management module provides docking interfaces with other hotel systems (such as reservation systems, financial management systems, customer relationship management systems, etc.) to achieve data interconnection. For example, it docks with the reservation system to obtain guest check-in and check-out information to arrange guest room services in advance, and docks with the financial management system for service fee accounting and settlement.

[0012] Preferably, the mobile client includes a task receiving and display module, a task processing module, a guest room information query module, a communication module, and a positioning and navigation module. Among them, the modules are electrically connected to each other.

[0013] The task receiving and display module is used to receive guest room service tasks pushed by the cloud server in real time and display the task details in an intuitive list, including the guest room number, service type (such as cleaning, delivering items, maintenance, etc.), priority, and estimated completion time, etc.

[0014] The task processing module allows service staff to click on the task item to enter the processing interface, record the service start time, executed operations (such as the number of sheets replaced, list of replenished items, etc.), and service completion status, and supports taking photos or videos of the service site (such as room damage conditions, post-cleaning effects, etc.) and uploading them to the cloud server as service records.

[0015] The guest room information query module is used to query the basic information of the guest room (such as room type, number of occupants, special guest requirements, etc.), historical service records, and current equipment and facility status (such as whether electrical appliances are working properly, whether furniture is in good condition, etc.) to provide a reference for services.

[0016] The communication module integrates an instant messaging function to enable service staff to communicate with the front desk, other departments (such as the engineering department, food and beverage department, etc.), and guests. For example, they can quickly send and receive messages when encountering problems or coordinating resources.

[0017] The positioning and navigation module is used to use the GPS or indoor positioning technology of the mobile device to provide accurate navigation routes for service staff to reach the guest room, improve service efficiency, and reduce the time spent looking for the guest room.

[0018] Preferably, the database system includes a guest room database, a guest database, a service staff database, and a service task database, wherein the databases are electrically connected to each other;

[0019] The guest room database records in detail the static information and dynamic information of the guest rooms. The static information includes room number, floor, area, room type configuration, etc., and the dynamic information includes occupancy status, cleaning status, equipment failure conditions, etc.;

[0020] The guest database is used to store guest personal information (such as name, gender, contact information, ID number, etc.), occupancy information (such as check-in time, check-out time, reserved room type, etc.), consumption information (such as in-hotel dining, entertainment consumption records), and personalized needs (such as special dietary requirements, preferred room layout, etc.);

[0021] The service staff database contains basic information of service staff (such as name, employee number, position, start time of employment, etc.), skill information (such as proficient service types, whether having professional maintenance skills, etc.), scheduling information (such as work schedule, rest time, etc.), and work performance data (such as service evaluation scores, quantity and quality of tasks completed, etc.);

[0022] The service task database is used to record the whole process data of guest room service tasks from creation (source, time, request content, etc.) to execution (assigned personnel, start time, execution steps, completion time, etc.) and then to evaluation (guest evaluation, internal quality inspection evaluation, etc.).

[0023] Preferably, in the terminal-cloud collaboration module, the process of intelligently allocating tasks to different cloud server nodes includes:

[0024] Continuously monitor the load conditions of cloud servers, including indicators such as CPU usage rate, memory occupancy rate, and network bandwidth. By regularly collecting the indicator data of cloud server load conditions, the running status of each cloud server node can be grasped in real time, ensuring a comprehensive understanding of the system's resource utilization;

[0025] Based on the collected cloud server load conditions, conduct a load assessment on each cloud server node. Through comparative analysis, identify the nodes in a high-load state, as well as the nodes in a low-load or idle state, and mark them;

[0026] Receive service requirements from various channels of the hotel, and classify and prioritize the tasks according to task types and priority factors. Among them, the guest room cleaning task belongs to a regular task, and the emergency repair task has a higher priority, ensuring that high-priority tasks can be processed first;

[0027] Combined with the load conditions of cloud servers and the classification and priorities of tasks, comprehensively analyze factors such as node load, task priority, task type, and load balancing among nodes to determine the optimal task allocation plan, ensure that tasks are allocated to suitable cloud server nodes, and achieve the maximization of resource utilization;

[0028] After the task allocation plan is determined, immediately execute the task allocation operation, push the tasks to the specified cloud server nodes for processing. At the same time, continuously monitor the execution of task allocation to ensure that the tasks can be executed smoothly and achieve the expected results.

[0029] Preferably, the specific process of evaluating the load of each cloud server node includes:

[0030] According to the hardware configurations and performances of each cloud server node, set corresponding index benchmark values for the indicators of each cloud server node;

[0031] Analyze the load condition index data of each cloud server node, compare the difference between the preset index benchmark value and the real-time index data, and clarify the load deviation situation of each cloud server node;

[0032] Based on the comprehensive load deviation situation, calculate the load classification index, compare and analyze it with the set load threshold, identify the load status of cloud server nodes, distinguish nodes in high-load status, low-load status, and idle status, and then mark the load status of each cloud server node according to the results of the comparison and analysis.

[0033] Preferably, the determination process of the optimal task allocation plan includes:

[0034] Comprehensively collect the real-time load information of each cloud server node through monitoring tools, establish a node load information database, deeply analyze the collected load information, calculate the load classification index of each node, and evaluate the current load status of the node;

[0035] According to factors such as the nature of the task, the type of required resources, and the execution time requirements, conduct a detailed classification of the tasks to be allocated, divide the tasks into different types. At the same time, according to the urgency and importance of the tasks, set corresponding priorities for each type of task. Tasks with higher priorities need to be allocated resources first to ensure the timely execution of critical tasks;

[0036] Comprehensively consider the load information of the nodes and the requirements of the tasks, analyze whether each node can meet the resource conditions required for task execution. For high-load nodes, avoid allocating too many new tasks to prevent node overload. For low-load nodes, appropriately increase task allocation to improve resource utilization. According to the type and priority of the tasks, preferentially allocate high-priority tasks to nodes that can meet their resource requirements to ensure the smooth execution of critical tasks;

[0037] Based on a comprehensive consideration of node load, task priority, and task type, a load balancing strategy is formulated to dynamically adjust task allocation, ensuring relative load balance among nodes. When the load of a certain node is too high, part of the tasks are migrated to other nodes with lower load for execution. When the load of a certain node is too low, tasks can be migrated from other nodes to improve the resource utilization rate of this node;

[0038] According to the formulated task allocation plan and load balancing strategy, tasks are allocated to suitable cloud server nodes for execution. During the task execution process, the load conditions and task execution status of each node are monitored in real time to discover and handle problems such as node overload and task execution failure.

[0039] Preferably, in the task management and scheduling module, the process of task allocation and push includes:

[0040] Receive service demands from various channels of the hotel. The channels include but are not limited to the front desk reservation system, requests initiated by guests through the mobile APP, alarms issued by intelligent devices in the guest rooms, etc. The received service demands include various types such as room cleaning, equipment maintenance, food delivery service, and luggage storage;

[0041] For each received service demand, conduct a preliminary analysis to determine the specific type of the task, the urgency (i.e., priority), and the required service skill information;

[0042] According to the characteristics of the task and factors such as the skills, location, and current workload of the service personnel, calculate the skill matching degree function by combining the matching degree between the service task type and the service personnel's skills, calculate the location distance function based on the distance between the current location of the service personnel and the location of the guest room where the service task is located, and the closer the distance, the higher the score. Calculate the workload saturation function based on the ratio of the currently assigned task volume of the service personnel to the maximum workload;

[0043] Based on the calculated skill matching degree function, location distance function, and workload saturation function, use a weighted matching algorithm to calculate the matching degree score between each service personnel and the task, select the service personnel with the highest matching degree score, and intelligently allocate tasks. If the service personnel is busy or not matched, find the next best match;

[0044] Once the task is allocated, the system immediately pushes the task details to the mobile client of the corresponding service personnel to ensure that the service personnel can receive the task notification in a timely manner and track the execution status of the task, including whether the service personnel has received the task, whether they have started to execute, and the completion status of the task.

[0045] Preferably, in the task receiving and displaying module, the process of receiving and displaying guest room service tasks includes:

[0046] The task receiving and displaying module establishes a network connection with the cloud server to ensure real-time reception of task pushes. When the cloud server has a new guest room service task, it pushes the task data to the task receiving and displaying module. The task data includes the room number, service type (such as cleaning, delivery, repair, etc.), priority, and estimated completion time information;

[0047] Perform format verification on the received task data to ensure data integrity and accuracy. By parsing the task data, extract the room number, service type, priority, and estimated completion time information to prepare for subsequent task display;

[0048] Based on the parsed task data, construct a task list, sort the tasks according to priority and estimated completion time factors, so that service personnel can quickly find the tasks that need to be processed first. In the task list, display the details of each task in the form of entries, including the room number, service type, priority, and estimated completion time, presenting the information clearly and readably for service personnel to quickly understand the task content;

[0049] Real-time monitor the status changes of tasks, including the receiving, executing, and completing stages of tasks. When the task status changes, the task receiving and displaying module updates the corresponding entries in the task list to ensure that service personnel can keep track of the latest progress of tasks in real time;

[0050] Service personnel can click on any task item in the task list to view detailed task information, including specific service requirements and special needs of the guest in the room, and track the execution status of the task to determine whether the task has been claimed, is in progress, or has been completed. Service personnel can operate on the task item to mark the task as "received", "in progress", or "completed", and feedback the status to the cloud server to update the task status.

[0051] Preferably, in the task processing module, the process of task processing includes:

[0052] Service personnel click on the task item to be processed in the task list of the task receiving and displaying module, and the system loads the corresponding task processing interface according to the clicked task item;

[0053] The task processing interface automatically records the time when the service personnel enter the interface as the service start time. During the service process, the time that has been served is displayed on the task processing interface so that service personnel can master the service progress;

[0054] Service personnel perform corresponding service operations according to the task requirements, such as changing bed sheets, replenishing items, etc. And on the task processing interface, service personnel record the specific operations performed, such as the number of bed sheets changed, the list of replenished items, etc. Furthermore, the system will verify the input of service personnel to ensure the accuracy and integrity of the data;

[0055] After service personnel complete the service, on the task processing interface;

[0056] Service personnel can use the camera of the mobile device to take photos or videos of the service site, record the situation before and after the service, such as the damage condition of the room, the effect after cleaning, etc., and synchronously upload the taken photos or videos together with the record of service operations to the cloud server as part of the service record;

[0057] After service personnel complete the service, click the "Complete Service" button on the task processing interface to mark the task as "Completed" and record the service completion time.

[0058] Preferably, in the data analysis and decision support module, the process of predicting service demand includes:

[0059] Extract historical service demand data from various hotel business systems, including but not limited to the room reservation system, customer service system, inventory management system, etc. Clean, integrate, and standardize the collected data to ensure the accuracy and consistency of the data, and build a data warehouse to classify, organize, and store the data for subsequent analysis and mining;

[0060] Based on the extracted historical service demand data, analyze the service demand patterns for different time periods and room types, identify the patterns and trends of service demand. Among them, analyze the service demand patterns for different time periods (such as weekdays, weekends, holidays, etc.) to identify service peaks and troughs, analyze the service demand for different room types (such as single rooms, double rooms, suites, etc.) to understand guests' preferences and trends, analyze guests' service evaluations to understand guests' satisfaction and opinions on the service, and analyze guests' historical demands to identify guests' personalized needs and preferences;

[0061] Adopt the time series analysis method based on the ARIMA model to analyze the historical service demand data, use the seasonal ARIMA model for modeling and prediction, predict the quantity and type distribution of service demand in the next week through the model, provide a decision-making basis for hotel resource allocation (service personnel scheduling, material reserve, etc.), and continuously optimize and adjust the model in combination with the actual service demand data monitored in real time to improve the accuracy of prediction;

[0062] Arrange the scheduling and dispatching of hotel service staff according to the predicted quantity and type distribution of service demands. Based on the prediction results, reserve guest room supplies and consumables in advance to ensure material supply during peak service periods. Provide personalized service recommendations based on guests' historical demands and preferences to improve guests' satisfaction.

[0063] The present invention provides an intelligent scheduling system for hotel guest room service tasks based on a cloud platform, which has the following beneficial effects:

[0064] First, the intelligent scheduling system for hotel guest room service tasks based on the cloud platform enables service staff to quickly respond to service demands through real-time task push and mobile operations, reducing task waiting time. The positioning and navigation functions are used to improve the moving speed of service staff and shorten service response time. By detailed recording during the service process and uploading of photos and videos, it is convenient for service quality traceability and supervision, and data analysis can be carried out to discover weak links in the service process and make improvements. In addition, personalized service recommendations are provided to meet guests' special needs and improve guests' satisfaction.

[0065] Second, the intelligent scheduling system for hotel guest room service tasks based on the cloud platform enables managers to understand service progress, staff working status, and resource usage at any time through real-time monitoring and centralized management of service data, providing a scientific basis for decision-making, which helps to optimize staff scheduling, material procurement, and service processes. And guests can initiate service requests through various convenient methods and track service progress in real time. Personalized service and quick response meet guests' diverse needs, creating a comfortable and convenient accommodation environment, reducing paper records and manual communication links, lowering labor and material costs, accurately allocating resources to avoid resource waste, and indirectly reducing hotel operation costs and improving economic benefits by optimizing service processes and improving work efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0066] Figure 1 It is a module diagram of an intelligent scheduling system for hotel guest room service tasks based on the cloud platform of the present invention;

[0067] Figure 2 It is a schematic diagram of the task allocation algorithm of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0068] The present invention will be further described in detail below in conjunction with the drawings and specific embodiments. The embodiments of the present invention are given for the purpose of illustration and description, and are not exhaustive or limit the present invention to the disclosed form. Many modifications and variations are obvious to those of ordinary skill in the art. The embodiments are selected and described to better illustrate the principles and practical applications of the present invention, and enable those of ordinary skill in the art to understand the present invention and thus design various embodiments with various modifications suitable for specific purposes.

[0069] The first embodiment is as follows Figure 1 , Figure 2 As shown, the present invention provides a technical solution: an intelligent scheduling system for hotel room service tasks based on a cloud platform. The intelligent scheduling system includes a mobile client, an edge-cloud collaboration module, a cloud server, and a database system;

[0070] The mobile client is equipped with a dedicated mobile application running on a mobile device such as a smartphone or a tablet for hotel room service staff;

[0071] Furthermore, the mobile client includes a task receiving and displaying module, a task processing module, a guest room information query module, a communication module, and a positioning and navigation module. Among them, the modules are electrically connected to each other;

[0072] The task receiving and displaying module is used to receive the hotel room service tasks pushed by the cloud server in real time and display the task details in an intuitive list, including the room number, service type (such as cleaning, delivering items, repairing, etc.), priority, and estimated completion time, etc.;

[0073] The task processing module allows the service staff to click on the task item to enter the processing interface, record the service start time, executed operations (such as the number of sheets changed, replenishment item list, etc.), and service completion status, and supports taking photos or videos of the service site (such as room damage situation, cleaning effect, etc.) and uploading them to the cloud server as service records;

[0074] The guest room information query module is used to query the basic guest room information (such as room type, number of occupants, special guest requirements, etc.), historical service records, and current equipment and facility status (such as whether the electrical appliances are working properly, whether the furniture is intact, etc.) to provide reference for the service;

[0075] The communication module integrates an instant messaging function to enable service staff to communicate with the front desk, other departments (such as the engineering department, the catering department, etc.), and guests. For example, when encountering problems or coordinating resources, messages can be quickly sent and received;

[0076] The positioning and navigation module is used to use the GPS or indoor positioning technology of the mobile device to provide accurate navigation routes for service staff to reach the guest rooms, improve service efficiency, and reduce the time for finding guest rooms;

[0077] The edge-cloud collaboration module is used to intelligently allocate tasks to different cloud server nodes according to the load conditions of the cloud servers, continuously monitor the load conditions of the cloud servers, including indicators such as CPU usage rate, memory occupancy rate, and network bandwidth. By regularly collecting the indicator data of the cloud server load conditions, it can grasp the running status of each cloud server node in real time, ensuring a comprehensive understanding of the system's resource utilization. Based on the collected cloud server load conditions, it conducts a load assessment on each cloud server node. Through comparative analysis, it identifies the nodes in a high-load state, as well as the nodes in a low-load or idle state, and marks them. It receives service demands from various channels of the hotel, classifies and prioritizes the tasks according to task types and priority factors. Among them, room cleaning tasks are regular tasks, and emergency repair tasks have a higher priority, ensuring that high-priority tasks can be processed first. Combining the load conditions of the cloud servers and the classification and priority of the tasks, it comprehensively analyzes factors such as node load, task priority, task type, and load balance among nodes to determine the optimal task allocation plan, ensuring that tasks are allocated to suitable cloud server nodes to achieve the maximization of resource utilization. After the task allocation plan is determined, it immediately executes the task allocation operation, pushes the tasks to the specified cloud server nodes for processing. At the same time, it continuously monitors the execution status of the task allocation to ensure that the tasks can be executed smoothly and achieve the expected results;

[0078] In addition, the specific process of conducting a load assessment on each cloud server node includes:

[0079] According to the hardware configurations and performances of each cloud server node, corresponding indicator baseline values are set for the indicators of each cloud server node. Analyze the load condition indicator data of each cloud server node, compare the difference between the preset indicator baseline value and the real-time indicator data, and clarify the load deviation situation of each cloud server node. Based on the comprehensive load deviation situation, calculate the load classification index, and conduct a comparative analysis with the set load threshold to identify the load status of the cloud server nodes, distinguish the nodes in a high-load state, a low-load state, and an idle state, and then mark the load status of each cloud server node according to the results of the comparative analysis;

[0080] The expression of the load classification index is:

[0081]

[0082] In the formula, LCI is the load classification index, which is used to comprehensively reflect the load status of the node. ΔCPU, ΔMEM, and ΔNET respectively represent the deviations of CPU usage rate, memory occupancy rate, and network bandwidth, that is, the difference between the real-time value and the baseline value of each indicator, B CPU 、B MEM 、B NETRespectively represent the baseline values of CPU usage rate, memory occupancy rate, and network bandwidth, R CPU 、R MEM 、R NET respectively represent the data of CPU usage rate, memory occupancy rate, and network bandwidth collected in real time. When the load status of the node is close to the baseline value, ΔCPU, ΔMEM, and ΔNET are all close to 0. Therefore, LCI is also close to 0, indicating that the node load is normal. When the load status of the node deviates from the baseline value, the absolute values of ΔCPU, ΔMEM, and ΔNET increase, resulting in an increase in LCI. Especially when a certain index seriously deviates from the baseline value, its contribution to LCI will increase significantly;

[0083] The determination process of the optimal task allocation scheme includes:

[0084] Comprehensively collect the real-time load information of each cloud server node through monitoring tools, and establish a node load information database. Deeply analyze the collected load information, calculate the load classification index of each node, evaluate the current load status of the node. According to the nature of the task, the type of required resources, and the execution time requirement factors, conduct a detailed classification of the tasks to be allocated, and divide the tasks into different types. At the same time, according to the urgency and importance of the tasks, set corresponding priorities for each type of task. Tasks with higher priorities need to be allocated resources first to ensure the timely execution of critical tasks. Consider the load information of the nodes and the requirements of the tasks comprehensively, and analyze whether each node can meet the resource conditions required for task execution. For high-load nodes, avoid allocating too many new tasks to prevent node overload. For low-load nodes, appropriately increase the task allocation to improve resource utilization. According to the type and priority of the tasks, give priority to allocating high-priority tasks to the nodes that can meet their resource requirements to ensure the smooth execution of critical tasks. On the basis of comprehensively considering node load, task priority, and task type, formulate a load balancing strategy to dynamically adjust task allocation to ensure relatively balanced load among nodes. When a certain node has too high a load, migrate some tasks to other nodes with lower loads for execution. When a certain node has too low a load, tasks can be migrated from other nodes to improve the resource utilization of this node. According to the formulated task allocation scheme and load balancing strategy, allocate tasks to the appropriate cloud server nodes for execution, and during the task execution process, monitor the load situation and task execution status of each node in real time, and discover and handle problems such as node overload and task execution failure;

[0085] The cloud server includes a task management and scheduling module, a data storage and management module, a data analysis and decision support module, and an interface management module. Among them, the modules are electrically connected to each other;

[0086] The task management and scheduling module is used to receive service requirements from various hotel channels (such as front desk reservation systems, guest mobile APP requests, intelligent device alarms in guest rooms, etc.). According to task types, priorities, service staff locations, and workload factors, it intelligently assigns tasks to service staff and real - time pushes task notifications to their mobile clients. It receives service requirements from various hotel channels, including but not limited to front desk reservation systems, requests initiated by guests through mobile APPs, alarms issued by intelligent devices in guest rooms, etc. The received service requirements include various types such as room cleaning, equipment repair, food delivery service, and luggage storage. For each received service requirement, a preliminary analysis is carried out to determine the specific type of the task, the urgency level (i.e., priority), and the required service skill information. According to the characteristics of the task and the skills, location, and current workload factors of the service staff, a skill matching degree function is calculated by combining the matching degree between the service task type and the service staff's skills. A location distance function is calculated based on the distance between the current location of the service staff and the location of the guest room where the service task is located. The closer the distance, the higher the score. A workload saturation function is calculated based on the ratio of the current assigned task volume of the service staff to the maximum workload. Based on the calculated skill matching degree function, location distance function, and workload saturation function, a weighted matching algorithm is used to calculate the matching degree score between each service staff and the task. The service staff with the highest matching degree score is selected to intelligently assign the task. If the service staff is busy or not matched, the next best match is searched for. Once the task is assigned, the system immediately pushes the task details to the mobile client of the corresponding service staff to ensure that the service staff can receive the task notification in a timely manner and track the execution status of the task, including whether the service staff has received the task, whether they have started to execute it, and the completion status of the task;

[0087] Further, the calculation formula for the skill matching degree function is:

[0088]

[0089] Among them, f skill (T, S) is the skill matching degree function, representing the skill matching degree score between task T and service staff S. n is the number of skills that the service staff needs to meet. a k is the importance weight of the k - th skill, reflecting the relative importance of different skills in the task. s k is the proficiency score of the service staff in the k - th skill. b is an adjustment index used to balance the influence of the summation result. The value range of f skill (T, S) is between 0 and 1. When all s k are 1, that is, the service staff is completely proficient in all skills, the value of f skill (T, S) will be close to 1, indicating a perfect skill match. If all s kAll are 0, that is, the service staff has no required skills, f skill (T, S) will be close to 0, indicating no skill match. When s k increases, will tend to 1. Therefore, the overall summation result will increase, making f skill (T, S) increase. When s k decreases, will tend to 0, resulting in the overall summation result decreasing, making f skill (T, S) decrease;

[0090] The calculation formula for the position distance function is:

[0091]

[0092] where f distance (T, S) is the position distance function, indicating the position distance score between the service staff p s and the guest room where the task is located p t . d(p s , p t ) is the actual distance between the service staff p s and the guest room where the task is located p t . d max is the maximum distance between the service staff in the hotel and the task guest room, used for normalization. α and β are adjustment parameters, used to control the attenuation speed and amplitude of the distance score. The value range of f distance (T, S) is between 0 and 1. When d(p s , p t ) is equal to 0, that is, the service staff is exactly at the position of the task guest room, f distance (T, S) will be close to 1, indicating the highest position distance score. When d(p s , p t ) is equal to d max , that is, the service staff is at the farthest position in the hotel, f distance (T, S) will be close to 0, indicating the lowest position distance score. When d(p s , p t ) increases, increases, decreases, increases. Therefore, f distance (T, S) decreases. When d(p s , p t ) decreases, decreases, increases, decreases. Therefore, f distance (T, S) increases;

[0093] The calculation formula of the workload saturation function is as follows:

[0094]

[0095] Among them, f workload (T, S) is the workload saturation function, representing the workload saturation score of service staff S. T(S) is the amount of tasks currently assigned to service staff S, and T max is the maximum workload of service staff S, which is used for normalization. γ is an adjustment parameter used to control the growth rate of the workload saturation score. The value range of f workload (T, S) is between 0 and 1. When T(S) is equal to 0, that is, the service staff has not been assigned any tasks, the value of f workload (T, S) will be close to 0, indicating the lowest workload saturation. When T(S) is equal to T max , that is, the service staff has reached the maximum workload, the value of f workload (T, S) will be close to 1, indicating the highest workload saturation. When T(S) increases, increases, increases, so f workload (T, S) increases. When T(S) decreases, decreases, decreases, so f workload (T, S) decreases;

[0096] Furthermore, the calculation formula of the matching degree score is as follows:

[0097] M(T, S) = ω1 × f skill (T, S) + ω2 × f distance (T, S) + ω3 × f workload (T, S);

[0098] Among them, M(T, S) is the matching degree score, and ω1, ω2, and ω3 are weight coefficients, which respectively represent the importance of skill matching degree, location distance, and workload saturation. f skill (T, S) is the skill matching degree function, which is calculated according to the matching degree between the service task type and the service staff's skills. The value range of f skill (T, S) is from 0 to 1. f distance (T, S) is the location distance function, which is calculated according to the distance between the current location of the service staff and the location of the guest room where the service task is located. The closer the distance, the higher the score. The value range of f distance (T, S) is from 0 to 1. f workload (T, S) is the workload saturation function, which is calculated according to the ratio of the amount of tasks currently assigned to the service staff to the maximum workload. The lower the saturation, the higher the score. f workload(T, S) ranges from 0 to 1. The cloud server selects the service staff with the highest score according to the calculated matching degree score to assign tasks, and the weight coefficient can be dynamically adjusted according to the specific needs and operation conditions of the hotel;

[0099] Data storage and management module, which is used to store the data related to room service, including room data, guest data, service staff data and service task data. The data is processed in a structured way for query, statistics and analysis;

[0100] Data analysis and decision support module, which uses big data analysis technology to deeply mine and analyze the stored data, analyzes the service demand rules of different time periods and room types, predicts the peaks and troughs of service demand, provides a decision-making basis for the hotel's human resource arrangement and material procurement, and provides recommendations and optimization suggestions for personalized services by analyzing guest service evaluations and historical demands;

[0101] Interface management module, which provides docking interfaces with other hotel systems (such as reservation system, financial management system, customer relationship management system, etc.) to achieve data interconnection and interoperability. For example, it docks with the reservation system to obtain guest check-in and check-out information to arrange room service in advance, and docks with the financial management system to calculate and settle service fees.

[0102] The second embodiment, based on the first embodiment, please refer to Figure 1 、 Figure 2 As shown, the database system includes a guest room database, a guest database, a service staff database and a service task database. Among them, the databases are electrically connected; the guest room database details the static and dynamic information of the guest rooms. The static information includes room number, floor, area, room type configuration, etc., and the dynamic information includes occupancy status, cleaning status and equipment failure conditions, etc. The guest database is used to store guest personal information (such as name, gender, contact information, ID number, etc.), check-in information (such as check-in time, check-out time, reserved room type, etc.), consumption information (such as in-hotel dining, entertainment consumption records) and personalized needs (such as special dietary requirements, preferred room layout, etc.). The service staff database contains basic information of service staff (such as name, work number, position, start time of employment, etc.), skill information (such as service types they are good at, whether they have professional maintenance skills, etc.), scheduling information (such as work schedule, rest time, etc.) and work performance data (such as service evaluation scores, quantity and quality of tasks completed, etc.). The service task database is used to record the whole process data of room service tasks from creation (source, time, request content, etc.) to execution (assigned personnel, start time, execution steps, completion time, etc.) and then to evaluation (guest evaluation, internal quality inspection evaluation, etc.);

[0103] In the task receiving and display module, the process of receiving and displaying room service tasks includes:

[0104] The task receiving and display module establishes a network connection with the cloud server to ensure real-time reception of task pushes. When the cloud server has new guest room service tasks, it pushes the task data to the task receiving and display module. The task data includes the guest room number, service type (such as cleaning, delivery, repair, etc.), priority, and estimated completion time information. It performs format verification on the received task data to ensure data integrity and accuracy, and by parsing the task data, extracts the guest room number, service type, priority, and estimated completion time information to prepare for subsequent task display. According to the parsed task data, it constructs a task list, sorts the tasks according to priority and estimated completion time factors so that service personnel can quickly find the tasks that need to be processed first. In the task list, it displays the details of each task in the form of entries, including the guest room number, service type, priority, and estimated completion time, presenting the information in a clear and readable manner for service personnel to quickly understand the task content. It monitors the status changes of tasks in real time, including the receiving, execution, and completion stages of tasks. When the task status changes, the task receiving and display module updates the corresponding entry in the task list to ensure that service personnel can keep abreast of the latest progress of tasks. Service personnel can click on any task item in the task list to view detailed task information, including specific service requirements and special needs of the guest in the guest room, and track the execution status of the task to determine whether the task has been claimed, is in progress, or has been completed. Service personnel can operate on the task item to mark the task as "received", "in progress", or "completed", and feedback the status to the cloud server to update the task status;

[0105] In the task processing module, the process of task processing includes:

[0106] In the task list of the task receiving and display module, the service staff clicks on the task item to be processed. The system loads the corresponding task processing interface according to the clicked task item. The task processing interface automatically records the time when the service staff enters the interface as the service start time. During the service process, the time of service already provided is displayed on the task processing interface so that the service staff can keep track of the service progress. The service staff performs corresponding service operations according to the task requirements, such as changing the bedsheet, replenishing items, etc. And on the task processing interface, the service staff records the specific operations performed, such as the number of bedsheets changed, the list of replenished items, etc. Then the system validates the input of the service staff to ensure the accuracy and integrity of the data. After the service staff completes the service, on the task processing interface, the service staff can use the camera of the mobile device to take photos or videos of the service site, record the conditions before and after the service, such as the damage situation of the room, the effect after cleaning, etc., and synchronously upload the taken photos or videos along with the record of the service operations to the cloud server as part of the service record. After the service staff completes the service, clicks the "Complete Service" button on the task processing interface, marks the task as "Completed", and records the service completion time;

[0107] In the data analysis and decision support module, the process of predicting service demand includes:

[0108] Extract historical service demand data from various hotel business systems, including but not limited to the room reservation system, customer service system, inventory management system, etc. Clean, integrate, and standardize the collected data to ensure the accuracy and consistency of the data, and build a data warehouse to classify, organize, and store the data for subsequent analysis and mining. Based on the extracted historical service demand data, analyze the service demand patterns for different time periods and room types, identify the patterns and trends of service demand. Among them, analyze the service demand patterns for different time periods (such as weekdays, weekends, holidays, etc.) to identify service peaks and troughs, analyze the service demand for different room types (such as single rooms, double rooms, suites, etc.) to understand guests' preferences and trends, analyze guests' service evaluations to understand guests' satisfaction and opinions on the service, analyze guests' historical demands to identify guests' personalized needs and preferences. Adopt the time series analysis method based on the ARIMA model to analyze the historical service demand data, use the seasonal ARIMA model for modeling and prediction, predict the quantity and type distribution of service demand for the next week through the model, provide a decision-making basis for hotel resource allocation (service staff scheduling, material reserves, etc.), and continuously optimize and adjust the model by combining the actual service demand data monitored in real time to improve the accuracy of the prediction. According to the predicted quantity and type distribution of service demand, arrange the scheduling of hotel service staff, and based on the prediction results, reserve guest room supplies and consumables in advance to ensure the material supply during service peaks. Provide personalized service recommendations based on guests' historical demands and preferences to improve guests' satisfaction;

[0109] Further, based on the time series analysis formula of the ARIMA model, the specific expression is:

[0110]

[0111] where, Y t represents the predicted service demand at time point t, μ is the mean of the time series, p is the order of the autoregressive term, representing the relationship between the current value and the values at the past p time points, is the autoregressive coefficient, representing the influence of the i-th past value on the current value, q is the order of the moving average term, representing the relationship between the current error term and the errors at the past q time points, θ j is the moving average coefficient, representing the influence of the j-th past error term on the current value, ε t is the error term at time point t, δ s is the seasonal effect, calculated through the seasonal period S and the seasonal coefficient Δ, s is the time period within the seasonal cycle, t is the total time point, S is the length of the seasonal cycle, Y t ranges from 0 to 1, but the actual predicted value will be adjusted according to the actual value of the service demand. When and θ j increase, the predicted value Y t will increase according to the past service demand and error terms, and the seasonal effect δ s will vary according to the position of the time point within the seasonal cycle, affecting the predicted value Y t .

[0112] Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art and related fields without creative efforts shall fall within the protection scope of the present invention. The structures, devices, and operation methods not specifically described and explained in the present invention, unless otherwise specified and limited, are implemented according to the conventional means in the art.

Claims

1. An intelligent scheduling system for hotel room service tasks based on a cloud platform, characterized in that, The intelligent scheduling system includes a mobile client, an edge-cloud collaboration module, a cloud server, and a database system; The mobile client is equipped with a dedicated mobile application running on a mobile device such as a smartphone or a tablet for hotel room service staff; The edge-cloud collaboration module is used to intelligently allocate tasks to different cloud server nodes according to the load conditions of the cloud server; The cloud server includes a task management and scheduling module, a data storage and management module, a data analysis and decision support module, and an interface management module, where each module is electrically connected; The task management and scheduling module is used to receive service requirements from various channels of the hotel, intelligently allocate tasks to service staff according to factors such as task type, priority, service staff location, and workload, and push task notifications to their mobile clients in real time; The data storage and management module is used to store data related to room service, including room data, guest data, service staff data, and service task data; The data analysis and decision support module uses big data analysis technology to deeply mine and analyze the stored data, analyze the service demand patterns in different time periods and room types, and predict service demands; The interface management module provides docking interfaces with other hotel systems to achieve data interconnection and interoperability.

2. The intelligent scheduling system for hotel room service tasks based on a cloud platform according to claim 1, wherein: The mobile client includes a task receiving and display module, a task processing module, a room information query module, a communication module, and a positioning and navigation module, where each module is electrically connected; The task receiving and display module is used to receive room service tasks pushed by the cloud server in real time and display task details in an intuitive list; In the task processing module, when a service staff clicks on a task item to enter the processing interface, the service start time, executed operations, and service completion status are recorded; The room information query module is used to query basic room information, historical service records, and current equipment and facility status; The communication module integrates instant messaging functions to enable service staff to communicate with the front desk, other departments, and guests; The positioning and navigation module is used to provide a navigation route to the guest room for service staff using the GPS or indoor positioning technology of the mobile device.

3. The intelligent scheduling system for hotel room service tasks based on a cloud platform according to claim 2, wherein: The database system includes a guest room database, a guest database, a service staff database, and a service task database, where each database is electrically connected; The guest room database details the static and dynamic information of the guest rooms. The static information includes room number, floor, area, and room type configuration, and the dynamic information includes occupancy status, cleaning status, and equipment failure conditions; The guest database is used to store guest personal information, check-in information, consumption information, and personalized needs; The service staff database contains basic information, skill information, work schedule information, and work performance data of service staff; The service task database is used to record the whole process data of room service tasks from creation to execution and then to evaluation.

4. An intelligent scheduling system for hotel room service tasks based on a cloud platform according to claim 3, characterized in that: In the edge-cloud collaboration module, the process of intelligently allocating tasks to different cloud server nodes includes: Continuously monitoring the load conditions of the cloud server, including indicators such as CPU usage rate, memory occupancy rate, and network bandwidth; Based on the collected load conditions of cloud servers, conduct load assessment on each cloud server node. Through comparative analysis, identify the nodes in high-load state, as well as the nodes in low-load or idle state, and mark them; Receive service requirements from various channels of the hotel, and classify and prioritize the tasks according to task type and priority factors; Combining the load conditions of cloud servers and the classification and priority of tasks, comprehensively analyze factors such as node load, task priority, task type, and load balancing among nodes to determine the optimal task allocation plan; After the task allocation plan is determined, immediately execute the task allocation operation, push the tasks to the designated cloud server nodes for processing, and at the same time, continuously monitor the execution status of task allocation.

5. The intelligent scheduling system for hotel room service tasks based on a cloud platform according to claim 4, wherein: The specific process of conducting load assessment on each cloud server node includes: According to the hardware configuration and performance of each cloud server node, set corresponding index baseline values for the indicators of each cloud server node; Analyze the load condition index data of each cloud server node, compare the difference between the preset index baseline value and the real-time index data, and clarify the load deviation situation of each cloud server node; Based on the comprehensive load deviation situation, calculate the load classification index, compare and analyze it with the set load threshold, identify the load status of cloud server nodes, distinguish the nodes in high-load state, low-load state, and idle state, and then mark the load status of each cloud server node according to the results of the comparative analysis.

6. The intelligent scheduling system for hotel room service tasks based on a cloud platform according to claim 5, characterized in that: The determination process of the optimal task allocation plan includes: Comprehensively collect the real-time load information of each cloud server node through monitoring tools, establish a node load information database, deeply analyze the collected load information, calculate the load classification index of each node, and evaluate the current load status of the node; According to factors such as the nature of the task, the type of required resources, and the execution time requirement, conduct a detailed classification of the tasks to be allocated, divide the tasks into different types, and at the same time, set corresponding priorities for each type of task according to the urgency and importance of the task; Comprehensively consider the load information of the nodes and the requirements of the tasks, and analyze whether each node can meet the resource conditions required for task execution; On the basis of comprehensively considering node load, task priority, and task type, formulate a load balancing strategy to dynamically adjust task allocation; According to the formulated task allocation plan and load balancing strategy, allocate the tasks to the appropriate cloud server nodes for execution, and during the task execution process, monitor the load conditions and task execution status of each node in real time, and discover and handle problems such as node overload and task execution failure.

7. An intelligent scheduling system for hotel room service tasks based on a cloud platform according to claim 1, characterized in that: In the task management and scheduling module, the process of task allocation and pushing includes: Receive service requirements from various channels of the hotel, and the received service requirements include various types such as room cleaning, equipment maintenance, food delivery service, and luggage storage; For each received service requirement, conduct a preliminary analysis to determine the specific type, urgency, and required service skill information of the task; Based on the characteristics of the task and factors such as the skills, location, and current workload of the service staff, a skill matching degree function is calculated by combining the matching degree between the service task type and the service staff's skills. A location distance function is calculated based on the distance between the current location of the service staff and the location of the guest room where the service task is located. The closer the distance, the higher the score. A workload saturation function is calculated based on the ratio of the current assigned task volume of the service staff to the maximum workload. Based on the calculated skill matching degree function, location distance function, and workload saturation function, a weighted matching algorithm is used to calculate the matching degree score between each service staff and the task. The service staff with the highest matching degree score is selected to allocate the task intelligently. If the service staff is busy or not matched, the next best match is searched for. Once the task is allocated, the system immediately pushes the task details to the mobile client of the corresponding service staff and tracks the execution status of the task, including whether the service staff has received the task, whether they have started to execute it, and the completion status of the task.

8. The intelligent scheduling system for hotel room service tasks based on a cloud platform according to claim 1, wherein: In the task receiving and displaying module, the process of receiving and displaying guest room service tasks includes: The task receiving and displaying module establishes a network connection with the cloud server. When there is a new guest room service task on the cloud server, the task data is pushed to the task receiving and displaying module. The task data includes the guest room number, service type, priority, and estimated completion time information. Perform format verification on the received task data, and extract the guest room number, service type, priority, and estimated completion time information by parsing the task data. Based on the parsed task data, construct a task list, sort the tasks according to factors such as priority and estimated completion time. In the task list, display the details of each task in the form of entries, including the guest room number, service type, priority, and estimated completion time. Monitor the status changes of the tasks in real time, including the receiving, executing, and completing stages of the tasks. When the task status changes, the task receiving and displaying module updates the corresponding entry in the task list. The service staff can click on any task item in the task list to view the detailed task information, including specific service requirements and special needs of the guest in the guest room, and track the execution status of the task to determine whether the task has been claimed, is in progress, or has been completed. The service staff can operate on the task item to mark the task as "received", "in progress", or "completed", and feedback the status to the cloud server to update the task status.

9. An intelligent scheduling system for hotel room service tasks based on a cloud platform according to claim 8, characterized in that: In the task processing module, the process of task processing includes: The service staff clicks on the task item to be processed in the task list of the task receiving and displaying module, and the system loads the corresponding task processing interface according to the clicked task item. The task processing interface automatically records the time when the service staff enters the interface as the service start time. During the service processing, the elapsed service time is displayed on the task processing interface. The service staff performs the corresponding service operations according to the task requirements, and on the task processing interface, the service staff records the specific operations performed. Then the system will verify the input of the service staff. After the service staff completes the service, on the task processing interface; Service staff can use the camera of the mobile device to take photos or videos of the service site, record the conditions before and after the service, and synchronously upload the taken photos or videos along with the records of service operations to the cloud server as part of the service records; After the service staff completes the service, click the "Complete Service" button on the task processing interface to mark the task as "Completed" and record the service completion time.

10. The intelligent scheduling system for hotel room service tasks based on a cloud platform according to claim 1, wherein: In the data analysis and decision support module, the process of predicting service demand includes: Extract historical service demand data from various business systems of the hotel, clean, integrate, and standardize the collected data, and build a data warehouse to classify, organize, and store the data; Based on the extracted historical service demand data, analyze the service demand patterns at different time periods and room types, identify the patterns and trends of service demand. Among them, analyze the service demand patterns at different time periods to identify service peaks and troughs, analyze the service demand for different room types to understand guests' preferences and trends, analyze guests' service evaluations to understand guests' satisfaction and opinions on the service, and analyze guests' historical demands to identify guests' personalized needs and preferences; Adopt the time series analysis method based on the ARIMA model to analyze the historical service demand data, use the seasonal ARIMA model for modeling and prediction, and predict the quantity and type distribution of service demand in the next week through the model to provide a decision-making basis for hotel resource allocation; Arrange the scheduling and dispatching of hotel service staff according to the predicted quantity and type distribution of service demand. According to the prediction results, reserve guest room supplies and consumables in advance, and provide personalized service recommendations based on guests' historical demands and preferences.

Images