Automatic distribution and arrangement method for intelligent hotel guest room cleaning tasks

Abstract

The invention discloses an automatic distribution and arrangement method for intelligent hotel guest room cleaning tasks, and relates to the technical field of scheduling, and the method comprises the following steps: S1, the state information of hotel guest rooms is collected in real time through Internet of Things equipment, such as a sensor and an RFID tag, and the state information of the guest rooms comprises whether the guest rooms are checked in, whether the guest rooms are cleaned, and a cleaning request; according to the automatic distribution and arrangement method for the intelligent hotel guest room cleaning tasks, the cleaning priority of each guest room is calculated; during task arrangement, according to the working time, capability and position of the employees, accurately allocating the guest room cleaning tasks to the most appropriate employees; for guest rooms with special cleaning requirements, employees with corresponding processing capability and experience are arranged for cleaning, meanwhile, the current workload of the employees is considered, excessive task allocation is avoided, efficient matching of guest room requirements and employee resources is achieved, and the overall cleaning efficiency is improved.

Description

Technical Field

[0001] The invention relates to the technical field of scheduling, and in particular to an automatic allocation and arrangement method for intelligent hotel room cleaning tasks. Background Art

[0002] In smart hotels, the automatic allocation and scheduling of cleaning tasks is to improve efficiency and optimize resource utilization. For example, when guests apply for early check-in or late check-out, the hotel needs to adjust the cleaning plan in time to maximize the efficiency of the cleaning staff and minimize the vacant time of the room. This requires the system to respond quickly and reasonably schedule, while taking into account the work efficiency and actual needs of multiple cleaning staff. In reality, the waiting time of cleaning staff, repeated walking or unreasonable task allocation will cause time waste and increase labor costs. How to dynamically adjust cleaning tasks so that all kinds of needs can be met in time is a key challenge. In other words, how to dynamically optimize the order of room cleaning tasks in the smart hotel system to reduce the waiting time of cleaning staff and the distance of round-trip walking, while ensuring priority cleaning of rooms that need to be cleaned urgently is a technical problem that needs to be solved. Summary of the invention

[0003] In order to solve the above technical problems, the present invention is implemented by the following technical solutions: a method for automatically allocating and arranging cleaning tasks for smart hotel rooms, comprising the following steps: S1: Using IoT devices, such as sensors and RFID tags, to collect the status information of hotel rooms in real time, where the status information of the rooms includes whether they are occupied, whether they have been cleaned, and cleaning requests; Obtain dynamic data related to guest rooms through the hotel management system PMS, including reservations, check-ins, and check-outs related to guest rooms, so as to fully understand the usage status of guest rooms; The status information collected by IoT devices is combined with the dynamic data obtained through the hotel management system PMS to form guest room data; S2: Clean and integrate the collected guest room data, remove duplicate or invalid information to ensure data accuracy and timeliness, and form basic data for guest room cleaning tasks; Analyze the basic data through machine learning algorithms and predict the cleaning needs of guest rooms by combining the collected historical data, including room occupancy rate, cleaning cycle, and customer preferences, to obtain prediction results; Based on the prediction results, the deep learning model is used to calculate the cleaning priority of each guest room. It determines which guest rooms need to be cleaned first and which can be postponed to achieve scientific scheduling of cleaning tasks. This prediction capability enables the system to plan cleaning tasks in advance to avoid problems such as insufficient manpower during busy times and waste of resources during idle times. S3: Arrange room cleaning tasks according to the cleaning priorities of different rooms, the working hours and capabilities of employees, ensure that high-priority rooms are handled first, and employees clean the rooms based on the room cleaning tasks; S4: Collect customer evaluations of room cleaning and housekeeping services through the customer feedback platform, obtain evaluation results, and obtain service optimization suggestions based on the evaluation results to adjust the room cleaning tasks; S5: Record the execution results of each cleaning task to form a historical work log; the execution results include cleaning time and feedback information; use machine learning models to analyze historical work logs, find efficiency problems in the cleaning process, and generate efficiency optimization suggestions; so that the intelligence level of the system is continuously improved; Using the hotel floor plan information, a digital hotel map model is constructed; the location of each guest room, corridor, elevator location, and various cleaning tool storage points and employee rest areas are accurately marked in the model and placed as important location nodes; at the same time, each location node is given a unique identification code for subsequent calculation and positioning; By installing an indoor positioning system on employees’ mobile devices: smartphones, a positioning system based on Wi-Fi signal strength can obtain employees’ location coordinates in the hotel in real time; The indoor positioning system continuously sends signals to the surrounding environment and communicates with positioning base stations distributed throughout the hotel. After receiving the signal, the base station calculates the distance between the employee and the base station based on the signal strength and propagation time, and then determines the employee's location through triangulation, and transmits the location information back to the hotel's management system in real time; When there is a cleaning task to be assigned, the management system uses the hotel map model to calculate the distance for the employee to reach each guest room based on the employee's current location and the location of the guest room to be assigned. The shortest path algorithm is used to calculate the distance: Dijkstra's algorithm, which takes into account the actual path and possible obstacles in the hotel. The actual path includes corridors, stairs, and elevators; obstacles include areas under maintenance, and calculates the shortest walking route and its length from the employee's current location to each guest room. When performing cleaning tasks, employees can regularly update the management system on their task completion progress through mobile terminal devices. This includes when employees have finished cleaning a certain area of ​​the guest room, such as cleaning the bathroom, or have completed a specific task, such as changing bed sheets, by clicking the corresponding button on the terminal device to send task progress update information to the system. The system also records the task start time and estimates the remaining time required for employees to complete the current task based on the task progress and the preset standard task duration; the standard task duration includes the average time to complete various cleaning tasks based on historical data statistics; The management system calculates the current workload index of each employee based on the number of tasks that have been assigned but not yet completed, the estimated completion time, and the employee's historical work efficiency. The workload index is calculated as follows: the workload index is equal to the estimated total duration of the assigned tasks divided by the employee's historical average workload per unit time multiplied by the task urgency coefficient; where historical work efficiency is the amount of cleaning tasks or area that can be completed per unit time; where the task urgency coefficient can be set based on the occupancy of the guest room and the special requirements of the guests, and the value range is between 1 and 2; A detailed skill file is established for each cleaning staff in the hotel human resource management system; the file records the basic skill information of the staff, including whether they are proficient in the operation of various cleaning tools and equipment, whether they have special cleaning skills, whether they have received professional housekeeping service training, and the service quality evaluation of the staff in previous work; among them, basic skill information includes proficiency in the operation of different models of vacuum cleaners and mops; whether they have special cleaning skills, including the treatment of carpet stains and cleaning of glass curtain walls; whether they have received professional housekeeping service training, including bed making skills training and bathroom deep cleaning training; the service quality evaluation in previous work includes customer satisfaction score and room inspection score; at the same time, according to the work experience and skill level of the staff, the corresponding skill level is set for each skill item, including 5 levels from elementary to advanced, so as to more accurately evaluate the skill level of the staff; For each guest room to be cleaned, the required cleaning skills and service requirements are analyzed based on the room type, guest occupancy status, and the current hygiene status of the room. The room types include luxury suites, standard rooms, and single rooms; the guest occupancy status includes whether there are children or pets staying, and the length of stay; the current hygiene status of the room includes whether there are special stains, and whether the equipment and facilities are damaged and need repair; According to the employee's skill profile and the room cleaning requirements, the skill matching score between the employee and the room is calculated; for each cleaning skill item, the employee's skill level is compared with the skill level required by the room, according to the set matching rules: the same level score is 1, the higher level score is 1.2, and the lower level score is 0.8; calculate the matching score of the skill, and then weighted sum the scores of all skill items to get the final skill matching score; The management system comprehensively evaluates the distance between the employee and each guest room, the employee workload index, and the skill matching score; and calculates a comprehensive allocation index for each employee-room combination. The calculation formula for the comprehensive allocation index is: ; Among them, the distance weight, workload weight and skill matching weight are set according to the actual operation needs and management priorities of the hotel, and the sum of the three is 1; In the case of focusing on service quality, the hotel sets the skill matching weight to 0.5, the distance weight to 0.3, and the workload weight to 0.2; the system sorts all employee and room combinations according to the comprehensive allocation index. The higher the comprehensive allocation index, the more suitable the employee is to be assigned to the room for cleaning; Cleaning tasks are assigned to corresponding employees in descending order of comprehensive allocation index. During the allocation process, the system will check the workload of employees in real time to ensure that the workload of the assigned employees does not exceed their maximum tolerance, where the maximum tolerance is the workload upper limit set based on the employee's historical work performance and physical condition. If it is found that an employee's workload exceeds the upper limit after the task is assigned, the system will re-evaluate the combination of remaining employees and guest rooms, adjust the task allocation plan, and select other suitable employees for allocation. At the same time, if special circumstances arise: employees suddenly fall ill, emergency tasks are inserted, the system will recalculate the comprehensive allocation index according to the real-time situation, dynamically adjust the assigned tasks, and reallocate the tasks to other more suitable employees to ensure that the room cleaning tasks can be completed efficiently and with high quality, while ensuring that the employees' workload is reasonable and the service quality is stable; after receiving the assigned tasks, employees can view the task details through mobile terminal devices, including the room location, cleaning requirements, and estimated completion time, and go to the room to start cleaning.

[0004] Preferably, the historical data includes room occupancy rate, cleaning cycle, and customer preference.

[0005] Preferably, step S3 also includes allocating the scheduled cleaning tasks to corresponding cleaning staff in combination with the staff's location, workload and skill matching, and the cleaning tasks include work plans and task lists, so as to reduce the staff's waiting time and unnecessary moving distance, and ensure that each employee has a clear work plan and task list.

[0006] Preferably, based on the prediction results, the cleaning priority of each guest room is calculated by a deep learning model; that is, based on factors such as room occupancy rate, cleaning cycle, and customer preference, the priority calculation formula is as follows: Room cleaning priority: ; in, : The room occupancy rate of the i-th room; : The cleaning cycle of the i-th room, unit: day; : Customer preference for the i-th room; : They are the weight coefficients of room occupancy rate, cleaning cycle, and customer preference, which are used to adjust the priority of different factors; :Customer preference vector Converted to a single priority score.

[0007] Preferably, the room cleaning tasks are arranged according to the cleaning priorities of different rooms, the working hours of the employees, and the abilities of the employees. The process of arranging the room cleaning tasks is as follows: Staff arrangement: ; in, ; ; }; ; in, : Indicates whether employee j is assigned to clean room i; : Total number of guest rooms; : total number of employees; : The weight of employee j cleaning room i; : The workload of employee j is defined as: ; The maximum workload that employee j can bear.

[0008] Preferably, the method further includes a dynamic task adjustment mechanism, S5: the dynamic task adjustment mechanism is used to reallocate and optimize tasks according to the real-time changing guest room status and employee status during the cleaning process, step S5 includes the following steps: S51: The location information and task completion status of employees are monitored in real time through IoT devices. When changes in the guest room status are detected, including early or late check-out, the system can quickly capture these changes and update the cleaning requirements and priorities of the guest rooms. S52: During the task execution process, when it is found that the originally scheduled cleaning tasks are no longer optimal, including when new urgent cleaning requests are added or when employees are overloaded, the cleaning tasks are re-optimized according to the current situation, that is, the order of the cleaning tasks is re-optimized; and based on the path optimization algorithm, such as the approximate solution of the traveling salesman problem, the optimal walking path of the employees is calculated to reduce the moving distance and waiting time, optimize the cleaning efficiency, and complete the re-optimization of the cleaning tasks under the current situation; S53: Employees submit task completion reports through mobile terminal devices to generate task feedback. The cleaning tasks are dynamically updated based on the task feedback. Based on the real-time feedback from employees, including task completion status and emergencies, timely adjustments are made to ensure the smooth execution of the tasks.

[0009] Preferably, step S3 further includes a task load balancing mechanism based on employee capabilities and working hours, comprising the following steps: S31: Evaluate the work ability of each employee through historical data to obtain evaluation results, where the work ability includes the average time to complete the task and the work quality evaluation; S32: During the cleaning task allocation process, balance is performed based on the current workload of each employee; avoid allocating too many tasks to certain employees. When an employee's task load exceeds a preset load, redistribute the branch load of the employee's task load and redistribute part of the employee's tasks to other employees with lower workloads, so as to ensure that the workload of all employees is relatively balanced; S33: For employees' proactive overtime requests or temporary leave needs, the task allocation is adjusted according to the employees' actual working hours to ensure task completion and the employees' flexibility needs. The system can flexibly arrange tasks based on the employees' actual working hours to avoid assigning new cleaning tasks when employees are about to get off work or during their rest time, thereby achieving flexible management of working hours.

[0010] Preferably, step S31 also includes: S311: according to the ability evaluation result of each employee, setting the ability index for the employee for reference in task allocation.

[0011] Preferably, step S1 includes a multi-source data integration mechanism for unified management and analysis of data from different sources. The management and analysis process is as follows: S11: Through the API interface, the dynamic data from the hotel management system PMS, the status information from the IoT devices, and the task feedback information from the customer feedback system are integrated into a unified database; data sharing and interaction between systems are achieved, and the accuracy and real-time nature of the data are improved; S12: Conduct fusion analysis on dynamic data, status information and task feedback from different sources to obtain room status and customer needs; through correlation analysis of the above data, discover the potential relationship between room status and customer needs, and provide more targeted reference for task scheduling; S13: Based on information visualization, the cleaning tasks, room status, and employee status are displayed to the management personnel in the form of charts, and a query window is set up to provide corresponding data according to different query conditions, so that the management personnel can supervise and make decisions on the system. Among them, the query conditions include date, room number, and employee name; information display and query are realized.

[0012] Preferably, step S4 comprises the following steps: S41: Collecting customers' evaluations of room cleaning and housekeeping services through a customer feedback platform to generate feedback information, performing natural language processing on the collected feedback information to extract customers' main demands and opinions, and conducting quantitative evaluation of service quality based on customers' feedback information to obtain evaluation results; wherein the customer feedback platform includes mobile applications and room tablets; S42: Based on the evaluation results obtained from the customer feedback analysis, the task allocation algorithm is continuously optimized in combination with the self-learning mechanism, and the room cleaning tasks are adjusted to obtain service optimization suggestions, including increasing the cleaning frequency or improving the cleaning sequence for frequently complained cleaning areas, so as to better meet the different needs of different customers; The process of using machine learning models to analyze historical work logs, discovering efficiency issues in the cleaning process, and generating efficiency optimization suggestions is as follows: Get cleaning time from historical work logs, analyze its patterns in different time periods, dates, room types, and employee efficiency at different times; classify and count customer feedback information, and analyze the problem distribution pattern by combining timestamps and room numbers; cleaning time includes start time, end time, and duration; customer feedback information includes feedback on cleaning, items, and equipment; Adopt decision tree algorithm, establish model with factors related to room cleaning efficiency as variables, train and adjust parameters with historical data, verify with validation set, and improve if it does not meet the requirements until the performance reaches the standard, and establish efficiency evaluation model; The relevant data of the current room cleaning task is input into the efficiency evaluation model. The model predicts the theoretical cleaning efficiency. At the same time, the actual execution results are compared with the predicted results to find out where the efficiency differences exist. Among them, the relevant data include room type, occupancy status, and employee allocation; cleaning efficiency includes expected cleaning time and expected cleaning quality score; according to the importance coefficient of each factor in the model, analyze which factors contribute more to the efficiency difference and generate targeted optimization suggestions.

[0013] The present invention provides a method for automatically allocating and arranging cleaning tasks for smart hotel guest rooms, which has the following beneficial effects: This method of automatic allocation and scheduling of smart hotel room cleaning tasks calculates the cleaning priority of each room by combining machine learning algorithms to analyze room data, including room occupancy rate, cleaning cycle and customer preferences. When scheduling tasks, the room cleaning tasks are accurately allocated to the most suitable employees based on their working hours, abilities and locations. For rooms with special cleaning requirements, employees with corresponding processing capabilities and experience are arranged to clean them. At the same time, the current workload of employees is taken into consideration to avoid over-allocation of tasks, thereby achieving efficient matching of room needs and employee resources and improving overall cleaning efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] Figure 1 The present invention is a flowchart of a method for automatically allocating and arranging intelligent hotel room cleaning tasks. DETAILED DESCRIPTION

[0015] The present invention is further described in detail below in conjunction with the accompanying drawings and specific embodiments. The embodiments of the present invention are provided for the purpose of illustration and description, and are not intended to be exhaustive or to limit the present invention to the disclosed forms. Many modifications and variations will be apparent to those of ordinary skill in the art. The embodiments are selected and described in order to better illustrate the principles and practical applications of the present invention, and to enable those of ordinary skill in the art to understand the present invention and thereby design various embodiments with various modifications suitable for specific uses.

[0016] like Figure 1 As shown, the present invention provides a technical solution: a method for automatically allocating and arranging cleaning tasks for smart hotel rooms, comprising the following steps: S1: Use IoT devices, such as sensors and RFID tags, to collect the status information of hotel rooms in real time. The status information of the rooms includes whether they are occupied, whether they have been cleaned, and cleaning requests; Obtain dynamic data related to guest rooms through the hotel management system PMS, including reservations, check-ins, and check-outs related to guest rooms, so as to fully understand the usage status of guest rooms; The status information collected by IoT devices is combined with the dynamic data obtained through the hotel management system PMS to form guest room data; S2: Clean and integrate the collected guest room data, remove duplicate or invalid information to ensure data accuracy and timeliness, and form basic data for guest room cleaning tasks; The basic data is analyzed through machine learning algorithms, and the cleaning needs of guest rooms are predicted based on historical data, including room occupancy rate, cleaning cycle, and customer preferences. Based on the prediction results, the deep learning model calculates the cleaning priority of each guest room, determines which guest rooms need to be cleaned first and which can be postponed, so as to achieve scientific scheduling of cleaning tasks; this prediction capability enables the system to plan cleaning tasks in advance, avoiding the problem of insufficient manpower during busy times and wasted resources during idle times. S3: Arrange room cleaning tasks according to the cleaning priorities of different rooms, the working hours and capabilities of employees, ensure that high-priority rooms are handled first, and employees clean the rooms based on the room cleaning tasks; S4: Collect customer evaluations of room cleaning and housekeeping services through the customer feedback platform, obtain evaluation results, and obtain service optimization suggestions based on the evaluation results to adjust the room cleaning tasks; S5: Record the execution results of each cleaning task to form a historical work log; the execution results include cleaning time and feedback information; use machine learning models to analyze historical work logs, identify efficiency problems in the cleaning process, and generate efficiency optimization suggestions; so that the intelligence level of the system continues to improve.

[0017] Through the collaboration between IoT devices and the hotel management system PMS, room status and dynamic data are integrated to provide a 360-degree perspective for hotel operations; managers can know the room occupancy, cleaning and reservation status in real time, and accurately grasp the pulse of the hotel business, such as promptly discovering a surge in room reservations during popular periods and allocating resources in advance; the integration of multi-source data helps to gain in-depth insights into customer behavior and demand patterns; by analyzing historical data and real-time status, room demand trends can be predicted, resource allocation can be optimized, and resource idleness or shortages can be avoided.

[0018] Through machine learning algorithms, the value of data is mined, the demand for room cleaning is predicted, and the priority is calculated in combination with deep learning models. High-priority rooms are cleaned first to improve customer satisfaction. The room priority, employee working hours and capabilities are comprehensively considered to achieve the optimal match between tasks and employees. Efficient completion of tasks is ensured, such as assigning complex tasks to experienced employees and simple tasks to novices. Reasonable task allocation balances employee workload, avoids overwork or idleness, stimulates employee enthusiasm and creativity, and improves work efficiency and service quality, such as employees providing better services at appropriate task intensity.

[0019] Using the hotel floor plan information, a digital hotel map model is constructed; the location of each guest room, corridor, elevator location, and various cleaning tool storage points and employee rest areas are accurately marked in the model and placed as important location nodes; at the same time, each location node is given a unique identification code for subsequent calculation and positioning; By installing an indoor positioning system on employees’ mobile devices: smartphones, a positioning system based on Wi-Fi signal strength can obtain employees’ location coordinates in the hotel in real time; The indoor positioning system continuously sends signals to the surrounding environment and communicates with positioning base stations distributed throughout the hotel. After receiving the signal, the base station calculates the distance between the employee and the base station based on the signal strength and propagation time, and then determines the employee's location through triangulation, and transmits the location information back to the hotel's management system in real time; When there is a cleaning task to be assigned, the management system uses the hotel map model to calculate the distance for the employee to reach each guest room based on the employee's current location and the location of the guest room to be assigned. The shortest path algorithm is used to calculate the distance: Dijkstra's algorithm, which takes into account the actual path and possible obstacles in the hotel. The actual path includes corridors, stairs, and elevators; obstacles include areas under maintenance, and calculates the shortest walking route and its length from the employee's current location to each guest room. It should be further explained that, in the specific implementation process, if an employee is in the employee lounge on the second floor of the hotel and there are multiple guest rooms to be cleaned, the system will calculate the shortest distance from the employee to the guest rooms on the second floor, third floor and other floors respectively, taking into account the use of elevators and the convenience of stair access, and generate a path information including distance and estimated walking time for each guest room. The use of elevators includes the possibility of a longer waiting time during peak hours. When performing cleaning tasks, employees can regularly update the management system on their task completion progress through mobile terminal devices. This includes when employees have finished cleaning a certain area of ​​the guest room, such as cleaning the bathroom, or have completed a specific task, such as changing bed sheets, by clicking the corresponding button on the terminal device to send task progress update information to the system. The system also records the task start time and estimates the remaining time required for employees to complete the current task based on the task progress and the preset standard task duration; the standard task duration includes the average time to complete various cleaning tasks based on historical data statistics; It should be further explained that, in the specific implementation process, if the standard total duration of a room cleaning task is 60 minutes, and the employee has been working for 30 minutes and has completed 50% of the task, the system estimates that the remaining time may be about 30 minutes based on the remaining task volume and the historical average completion speed; The management system calculates the current workload index of each employee based on the number of tasks that have been assigned but not yet completed, the estimated completion time, and the employee's historical work efficiency. The workload index is calculated as follows: the workload index is equal to the estimated total duration of the assigned tasks divided by the employee's historical average workload per unit time multiplied by the task urgency coefficient; where historical work efficiency is the amount of cleaning tasks or area that can be completed per unit time; where the task urgency coefficient can be set based on the occupancy of the guest room and the special requirements of the guests, and the value range is between 1 and 2; It should be further explained that, in the specific implementation process, the task urgency coefficient for the guest rooms that are about to be occupied is set to 1.5, while the task urgency coefficient for the ordinary guest rooms is 1; by calculating the workload index, the system intuitively understands the current busyness of each employee, and the larger the value, the heavier the workload, among which, the occupancy of the guest rooms includes the higher task urgency of the guest rooms that are about to be occupied; A detailed skill file is established for each cleaning staff in the hotel human resource management system; the file records the basic skill information of the staff, including whether they are proficient in the operation of various cleaning tools and equipment, whether they have special cleaning skills, whether they have received professional housekeeping service training, and the service quality evaluation of the staff in previous work; among them, basic skill information includes proficiency in the operation of different models of vacuum cleaners and mops; whether they have special cleaning skills, including the treatment of carpet stains and cleaning of glass curtain walls; whether they have received professional housekeeping service training, including bed making skills training and bathroom deep cleaning training; the service quality evaluation in previous work includes customer satisfaction score and room inspection score; at the same time, according to the work experience and skill level of the staff, the corresponding skill level is set for each skill item, including 5 levels from elementary to advanced, so as to more accurately evaluate the skill level of the staff; For each guest room to be cleaned, the required cleaning skills and service requirements are analyzed based on the room type, guest occupancy status, and the current hygiene status of the room. The room types include luxury suites, standard rooms, and single rooms; the guest occupancy status includes whether there are children or pets staying, and the length of stay; the current hygiene status of the room includes whether there are special stains, and whether the equipment and facilities are damaged and need repair; It should be further explained that in the specific implementation process, luxury suites require employees to have a higher level of bed-making skills and furniture maintenance knowledge; guest rooms with children need to focus on cleaning the floor and areas that children may touch, and have higher safety requirements for cleaning products; and guest rooms with pets require employees to master effective pet hair cleaning methods and deodorization techniques; According to the employee's skill profile and the room cleaning requirements, the skill matching score between the employee and the room is calculated; for each cleaning skill item, the employee's skill level is compared with the skill level required by the room, according to the set matching rules: the same level score is 1, the higher level score is 1.2, and the lower level score is 0.8; calculate the matching score of the skill, and then weighted sum the scores of all skill items to get the final skill matching score; It should be further explained that, in the specific implementation process, for a luxury suite that requires advanced bed-making skills and intermediate carpet cleaning skills, if an employee has an advanced bed-making skill score of 1.2 and an intermediate carpet cleaning skill score of 1, assuming that the weight of the bed-making skill is 0.6 and the weight of the carpet cleaning skill is 0.4, then the employee's skill matching score = 1.2*0.6+1*0.4=1.12 points; The management system comprehensively evaluates the distance between the employee and each guest room, the employee workload index, and the skill matching score; and calculates a comprehensive allocation index for each employee-room combination. The calculation formula for the comprehensive allocation index is: ; Among them, the distance weight, workload weight and skill matching weight are set according to the actual operation needs and management priorities of the hotel, and the sum of the three is 1; In the case of focusing on service quality, the hotel sets the skill matching weight to 0.5, the distance weight to 0.3, and the workload weight to 0.2; the system sorts all employee and room combinations according to the comprehensive allocation index. The higher the comprehensive allocation index, the more suitable the employee is to be assigned to the room for cleaning; Cleaning tasks are assigned to corresponding employees in descending order of comprehensive allocation index. During the allocation process, the system will check the workload of employees in real time to ensure that the workload of the assigned employees does not exceed their maximum tolerance, where the maximum tolerance is the workload upper limit set based on the employee's historical work performance and physical condition. If it is found that an employee's workload exceeds the upper limit after the task is assigned, the system will re-evaluate the combination of remaining employees and guest rooms, adjust the task allocation plan, and select other suitable employees for allocation. At the same time, if special circumstances arise: employees suddenly fall ill, emergency tasks are inserted, the system will recalculate the comprehensive allocation index according to the real-time situation, dynamically adjust the assigned tasks, and reallocate the tasks to other more suitable employees to ensure that the room cleaning tasks can be completed efficiently and with high quality, while ensuring that the employees' workload is reasonable and the service quality is stable; after receiving the assigned tasks, employees can view the task details through mobile terminal devices, including the room location, cleaning requirements, and estimated completion time, and go to the room to start cleaning.

[0020] With the help of IoT devices to monitor employee location information and task completion in real time, as well as to respond immediately to changes in room status, the hotel can dynamically adjust the allocation of cleaning tasks; when an emergency occurs, the system can quickly re-plan tasks and give priority to nearby employees with matching skills to clean, ensuring that the hotel can flexibly respond to various emergencies and improve operational adaptability and agility.

[0021] During the task execution process, the optimal walking path for employees is calculated based on actual conditions to reduce the ineffective walking time of employees in the hotel. This measure can significantly improve the work efficiency of employees, especially in large hotels or with complex guest room layouts. The shortest walking route is planned for employees so that they can reach the next work location faster, thereby completing more room cleaning tasks within a limited working time and improving room turnover.

[0022] Historical data includes room occupancy, cleaning cycles, and guest preferences.

[0023] Step S3 also includes allocating the scheduled cleaning tasks to the corresponding cleaning staff in combination with the staff's location, workload and skill matching, and the cleaning tasks include work plans and task lists, so as to reduce the staff's waiting time and unnecessary moving distance, and ensure that each employee has a clear work plan and task list.

[0024] It should be further explained that, during the specific implementation process, for guest rooms with carpet stains or special cleaning needs, employees with professional cleaning skills and experience are arranged to handle them to ensure that the cleaning quality of the guest rooms meets high standards; high-quality cleaning services can directly enhance customers' overall impression of the hotel and increase the possibility of customers staying again.

[0025] During the task allocation process, room cleaning tasks of different types and difficulty levels are assigned to employees with corresponding skills based on their skill matching.

[0026] Based on the prediction results, the deep learning model is used to calculate the cleaning priority of each guest room; that is, based on factors such as room occupancy rate, cleaning cycle, and customer preference, the priority calculation formula is as follows: Room cleaning priority: ; in, : The room occupancy rate of the i-th room; : The cleaning cycle of the i-th room, unit: day; : Customer preference for the i-th room; : They are the weight coefficients of room occupancy rate, cleaning cycle, and customer preference, which are used to adjust the priority of different factors; :Customer preference vector Converted to a single priority score.

[0027] Arrange the room cleaning tasks according to the cleaning priorities of different guest rooms, the working hours and abilities of the staff. The process of arranging the room cleaning tasks is as follows: Staff arrangement: ; in, ; ; }; ; in, : Indicates whether employee j is assigned to clean room i; : Total number of guest rooms; : total number of employees; : The weight of employee j cleaning room i; : The workload of employee j is defined as: ; The maximum workload that employee j can bear.

[0028] The method further includes a dynamic task adjustment mechanism, S5: the dynamic task adjustment mechanism is used to reallocate and optimize tasks according to the real-time changing guest room status and employee status during the cleaning process, step S5 includes the following steps: S51: The location information and task completion status of employees are monitored in real time through IoT devices. When changes in the guest room status are detected, including early or late check-out, the system can quickly capture these changes and update the cleaning requirements and priorities of the guest rooms. S52: During the task execution process, when it is found that the originally scheduled cleaning tasks are no longer optimal, including when new urgent cleaning requests are added or when employees are overloaded, the cleaning tasks are re-optimized according to the current situation, that is, the order of the cleaning tasks is re-optimized; and based on the path optimization algorithm, such as the approximate solution of the traveling salesman problem, the optimal walking path of the employees is calculated to reduce the moving distance and waiting time, optimize the cleaning efficiency, and complete the re-optimization of the cleaning tasks under the current situation; S53: Employees submit task completion reports through mobile terminal devices to generate task feedback. The cleaning tasks are dynamically updated based on the task feedback. Based on the real-time feedback from employees, including task completion status and emergencies, timely adjustments are made to ensure the smooth execution of the tasks.

[0029] Step S3 also includes a task load balancing mechanism based on employee capabilities and working hours, including the following steps: S31: Evaluate the work ability of each employee through historical data to obtain evaluation results, where the work ability includes the average time to complete the task and the work quality evaluation; S32: During the cleaning task allocation process, balance is performed based on the current workload of each employee; avoid allocating too many tasks to certain employees. When an employee's task load exceeds a preset load, redistribute the branch load of the employee's task load and redistribute part of the employee's tasks to other employees with lower workloads, so as to ensure that the workload of all employees is relatively balanced; S33: For employees' proactive overtime requests or temporary leave needs, the task allocation is adjusted according to the employees' actual working hours to ensure task completion and the employees' flexibility needs. The system can flexibly arrange tasks based on the employees' actual working hours to avoid assigning new cleaning tasks when employees are about to get off work or during their rest time, thereby achieving flexible management of working hours.

[0030] By evaluating employees' work capabilities through historical data and setting capability indexes, the hotel can more objectively and fairly arrange tasks based on employees' actual capabilities. Employees with strong capabilities have the opportunity to undertake more challenging and important tasks, while employees with relatively weaker capabilities can start with basic tasks and gradually improve their skills. This capability-based task allocation method can not only improve work efficiency, but also stimulate employees' work enthusiasm and self-improvement motivation. The task load balancing mechanism ensures that employees' workload is within a reasonable range to avoid overwork or underwork. When an employee's task load exceeds the preset value, timely adjustments are made to ensure the employee's physical health and job satisfaction. At the same time, the task allocation can be flexibly adjusted for employees' overtime requests or temporary leave needs, which reflects the hotel's respect for employees' personal needs and helps create a good working atmosphere and employee relations.

[0031] Step S31 also includes: S311: according to the ability evaluation result of each employee, setting the ability index for the employee for reference in task allocation.

[0032] Step S1 includes a multi-source data integration mechanism, which is used to uniformly manage and analyze data from different sources. The management and analysis process is as follows: S11: Through the API interface, the dynamic data from the hotel management system PMS, the status information from the IoT devices, and the task feedback information from the customer feedback system are integrated into a unified database; data sharing and interaction between systems are achieved, and the accuracy and real-time nature of the data are improved; S12: Conduct fusion analysis on dynamic data, status information and task feedback from different sources to obtain room status and customer needs; through correlation analysis of the above data, discover the potential relationship between room status and customer needs, and provide more targeted reference for task scheduling; S13: Based on information visualization, the cleaning tasks, room status, and employee status are displayed to the management personnel in the form of charts, and a query window is set up to provide corresponding data according to different query conditions, so that the management personnel can supervise and make decisions on the system. Among them, the query conditions include date, room number, and employee name; information display and query are realized.

[0033] Step S4 includes the following steps: S41: Collecting customers' evaluations of room cleaning and housekeeping services through a customer feedback platform to generate feedback information, performing natural language processing on the collected feedback information to extract customers' main demands and opinions, and conducting quantitative evaluation of service quality based on customers' feedback information to obtain evaluation results; wherein the customer feedback platform includes mobile applications and room tablets; S42: Based on the evaluation results obtained from the customer feedback analysis, the task allocation algorithm is continuously optimized in combination with the self-learning mechanism, and the room cleaning tasks are adjusted to obtain service optimization suggestions, including increasing the cleaning frequency or improving the cleaning sequence for frequently complained cleaning areas, so as to better meet the different needs of different customers; Through efficient and intelligent hotel room cleaning task allocation and scheduling methods, it is possible to achieve scientific management of room cleaning tasks, improve cleaning efficiency, balance employee workload, and continuously improve service quality through IoT devices, machine learning algorithms, and dynamic optimization mechanisms to meet the diverse needs of hotels and customers.

[0034] The process of using machine learning models to analyze historical work logs, discovering efficiency issues in the cleaning process, and generating efficiency optimization suggestions is as follows: Get cleaning time from historical work logs, analyze its patterns in different time periods, dates, room types, and employee efficiency at different times; classify and count customer feedback information, and analyze the problem distribution pattern by combining timestamps and room numbers; cleaning time includes start time, end time, and duration; customer feedback information includes feedback on cleaning, items, and equipment; Adopt decision tree algorithm, establish model with factors related to room cleaning efficiency as variables, train and adjust parameters with historical data, verify with validation set, and improve if it does not meet the requirements until the performance reaches the standard, and establish efficiency evaluation model; Input the relevant data of the current guest room cleaning task into the efficiency evaluation model, and the model predicts the theoretical cleaning efficiency. At the same time, compare the actual execution results with the predicted results to find out where the efficiency differences exist; the relevant data include room type, occupancy, and staff allocation; cleaning efficiency includes the estimated cleaning time and the estimated cleaning quality score; according to the importance coefficient of each factor in the model, analyze which factors contribute more to the efficiency difference and generate targeted optimization suggestions; The process of generating targeted optimization suggestions is as follows: If it is diagnosed that the skill level of employees is the main factor affecting efficiency, optimization suggestions include providing targeted training courses on room cleaning techniques and equipment operation specifications; and reasonably allocating room tasks based on employee skill differences, allocating complex rooms to employees with higher skills and simple rooms to employees whose skills need to be improved, so as to gradually improve overall efficiency; If the cleaning process is unreasonable and leads to efficiency problems, the optimization suggestion is to redesign the cleaning process and adopt a more efficient cleaning sequence, including from the top of the room to the ground and from the inside to the outside, to reduce the number of replacements of cleaning tools and cleaning supplies and improve cleaning efficiency; at the same time, formulate a standardized cleaning operation process manual for employees to learn and follow, to ensure that each employee works according to the most optimized process; In the case where equipment and tool failures affect efficiency, it is recommended to establish a regular equipment maintenance and inspection system to promptly detect and repair faulty equipment; at the same time, according to the type of guest rooms and cleaning needs, reasonably equip efficient and easy-to-use cleaning equipment and tools, including new vacuum cleaners and mops, to improve the speed and quality of cleaning work; If it is found that unreasonable task allocation leads to uneven workload among employees, thus affecting overall efficiency, optimization suggestions are to reallocate tasks based on employee capabilities, working hours and room characteristics, and adopt more scientific task scheduling algorithms, including the improved Hungarian algorithm. While considering employee capabilities and room priorities, the overall efficiency of task allocation is optimized to ensure that the workload of each employee is relatively balanced, avoid overwork of some employees and affect efficiency, and give full play to the work capabilities of employees; Apply the generated efficiency optimization suggestions to the actual guest room cleaning tasks, and track and observe the changes in cleaning efficiency within one month; collect the guest room cleaning time, customer feedback, and employee work status after the optimization suggestions are implemented, and compare and analyze the data with those before the optimization; including calculating the reduction ratio of the average cleaning time and the improvement of customer satisfaction, and evaluating the actual effect of the optimization suggestions; Adjust suggestions based on evaluation results: If the optimization suggestions have significant effects after implementation, including a significant reduction in cleaning time and a significant increase in customer satisfaction, these optimization measures will be solidified into standard operating procedures and their effects will be continuously monitored to prevent efficiency issues from recurring; if the effects are not obvious or new problems arise, it is necessary to re-analyze the data, find out the reasons, adjust the optimization suggestions or propose new improvement plans; this may include discovering that the original suggestions for employee skills training have problems with impractical training content or unreasonable training schedules in actual implementation, then the training plan needs to be optimized to make it more in line with actual work needs; at the same time, continue to collect and analyze new historical work log data, and continuously improve the efficiency evaluation model to provide support for generating more effective optimization suggestions.

[0035] By analyzing historical work logs, hotels can identify efficiency issues in the guest room cleaning process, such as unreasonable cleaning procedures and improper use of equipment, and generate corresponding optimization suggestions. Managers adjust and improve management processes based on these suggestions, and continuously optimize each aspect of guest room cleaning. For example, if it is found that the cleaning time of a certain type of guest room is too long, after analyzing the reasons, the cleaning order can be adjusted, more efficient cleaning tools can be replaced, or employee division of labor can be optimized, thereby improving overall work efficiency and reducing operating costs.

[0036] It should be further explained that, in the specific implementation process, by collecting and analyzing customer preference data, the hotel can fully consider the customer's personalized needs when assigning room cleaning tasks; for customers who are accustomed to using specific brands of toiletries or have special requirements for room temperature and humidity, the hotel can make corresponding preparations and adjustments during the room cleaning process to provide customers with more considerate and personalized services; this service method that pays attention to the customer's detailed needs can enhance the customer's favorability and loyalty to the hotel.

[0037] After the evaluation information collected by the customer feedback platform is processed by natural language and quantitatively analyzed, the hotel can gain an in-depth understanding of customer satisfaction with room cleaning and services; timely adjust room cleaning tasks and service processes based on customers' main demands and opinions; schedule tasks based on room cleaning priorities to ensure that rooms are cleaned at the most appropriate time; give priority to rooms with high occupancy rates and rooms where new guests are about to check in to ensure that guests can always stay in clean and tidy rooms; at the same time, consider the work efficiency and ability of employees and reasonably allocate tasks to avoid a decline in cleaning quality due to excessive tasks or a waste of human resources due to too light tasks, thereby providing customers with efficient and stable cleaning services.

[0038] Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field and related fields without creative work should fall within the scope of protection of the present invention. The structures, devices and operating methods not specifically described and explained in the present invention are implemented according to the conventional means in the field unless otherwise specified and limited.

Claims

1. A method for automatically allocating and arranging cleaning tasks for smart hotel rooms, characterized in that: The steps include: S1: Using IoT devices to collect the status information of hotel rooms in real time, the status information of the rooms includes whether they are occupied, whether they have been cleaned, and cleaning requests; obtaining dynamic data related to the rooms through the hotel management system PMS, including reservations, check-ins, and check-outs related to the rooms; combining the status information with the dynamic data to form room data; S2: Clean and integrate the collected guest room data, remove duplicate or invalid information to ensure data accuracy and timeliness, and form basic data for guest room cleaning tasks; analyze the basic data through machine learning algorithms, and predict the cleaning needs of guest rooms in combination with historical data to obtain prediction results. The historical data includes room occupancy rate, cleaning cycle, and customer preferences; based on the prediction results, calculate the cleaning priority of each guest room through a deep learning model; S3: Arrange room cleaning tasks according to the cleaning priorities of different guest rooms, the working hours and capabilities of employees, and employees clean the guest rooms based on the room cleaning tasks; S4: Collect customer evaluations of room cleaning and housekeeping services through the customer feedback platform, obtain evaluation results, and obtain service optimization suggestions based on the evaluation results to adjust the room cleaning tasks; S5: Record the execution results of each cleaning task to form a historical work log; the execution results include cleaning time and feedback information; use the machine learning model to analyze the historical work log, find out the efficiency problems in the cleaning process, and generate efficiency optimization suggestions.

2. The method for automatically allocating and arranging intelligent hotel room cleaning tasks according to claim 1, characterized in that: The historical data includes room occupancy rate, cleaning cycle, and customer preferences.

3. The method for automatically allocating and arranging intelligent hotel room cleaning tasks according to claim 2, characterized in that: Step S3 also includes allocating the scheduled cleaning tasks to corresponding cleaning employees in combination with the employees' positions, workloads, and skill matching, wherein the cleaning tasks include work plans and task lists.

4. The method for automatically allocating and arranging intelligent hotel room cleaning tasks according to claim 3, characterized in that: Based on the prediction results, the deep learning model is used to calculate the cleaning priority of each guest room; that is, based on factors such as room occupancy rate, cleaning cycle, and customer preference, the priority calculation formula is as follows: Room cleaning priority: ; in, : The room occupancy rate of the i-th room; : The cleaning cycle of the i-th room, unit: day; : Customer preference for the i-th room; : They are the weight coefficients of room occupancy rate, cleaning cycle, and customer preference, which are used to adjust the priority of different factors; :Customer preference vector Converted to a single priority score.

5. The method for automatically allocating and arranging intelligent hotel room cleaning tasks according to claim 4, characterized in that: Arrange the room cleaning tasks according to the cleaning priorities of different guest rooms, the working hours and abilities of the staff. The process of arranging the room cleaning tasks is as follows: Staff arrangement: ; in, ; ； }； ； in, : Indicates whether employee j is assigned to clean room i; : Total number of guest rooms; : total number of employees; : The weight of employee j cleaning room i; : The workload of employee j is defined as: ; The maximum workload that employee j can bear.

6. The method for automatically allocating and arranging intelligent hotel room cleaning tasks according to claim 5, characterized in that: The method further includes a dynamic task adjustment mechanism, S5: the dynamic task adjustment mechanism is used to reallocate and optimize tasks according to the real-time changing guest room status and employee status during the cleaning process, step S5 includes the following steps: S51: Use IoT devices to monitor employees’ location information and task completion in real time. When changes in the guest room status are detected, including early or late check-out, the cleaning requirements and priorities of the guest rooms are updated; S52: During the task execution process, when it is found that the originally scheduled cleaning task is no longer optimal, including when an emergency cleaning request is added or the employee is overloaded, the cleaning task is re-optimized according to the current situation; and based on the path optimization algorithm, the optimal walking path of the employee is calculated; S53: The employee submits a task completion report through a mobile terminal device to generate task feedback, and the cleaning task is dynamically updated based on the task feedback.

7. The method for automatically allocating and arranging intelligent hotel room cleaning tasks according to claim 6, characterized in that: Step S3 also includes a task load balancing mechanism based on employee capabilities and working hours, including the following steps: S31: Evaluate the work ability of each employee through historical data to obtain evaluation results, where the work ability includes the average time to complete the task and the work quality evaluation; S32: During the cleaning task allocation process, balance is performed based on the current workload of each employee; when the employee's task load exceeds a preset load, the branch loads in the employee's task load are redistributed; S33: For employees’ proactive overtime requests or temporary leave needs, adjust the assignment of tasks based on their actual working hours to ensure task completion and meet employees’ flexibility needs.

8. The method for automatically allocating and arranging intelligent hotel room cleaning tasks according to claim 7, characterized in that: Step S31 also includes: S311: according to the ability evaluation result of each employee, setting the ability index for the employee for reference in task allocation.

9. The method for automatically allocating and arranging intelligent hotel room cleaning tasks according to claim 8, characterized in that: Step S1 includes a multi-source data integration mechanism, which is used to uniformly manage and analyze data from different sources. The management and analysis process is as follows: S11: Through the API interface, the dynamic data from the hotel management system PMS, the status information from the IoT devices, and the task feedback information from the customer feedback system are integrated into a unified database; S12: Fusion analysis of dynamic data, status information and task feedback from different sources to obtain room status and customer needs; S13: Based on information visualization, the cleaning tasks, room status, and employee status are displayed to the management personnel in the form of charts, and a query window is set up to provide corresponding data according to different query conditions, so as to facilitate the management personnel to supervise and make decisions on the system; among which, the query conditions include date, room number, and employee name.

10. The method for automatically allocating and arranging intelligent hotel room cleaning tasks according to claim 9, characterized in that: Step S4 includes the following steps: S41: Collecting customers' evaluations of room cleaning and housekeeping services through a customer feedback platform to generate feedback information, performing natural language processing on the collected feedback information to extract customers' main demands and opinions, and conducting quantitative evaluation of service quality based on customers' feedback information to obtain evaluation results; wherein the customer feedback platform includes mobile applications and room tablets; S42: Based on the evaluation results obtained from the customer feedback analysis, the task allocation algorithm is continuously optimized in combination with the self-learning mechanism, and the room cleaning tasks are adjusted to obtain service optimization suggestions to meet the different needs of different customers.

Images