Hotel guest room cleaning task automatic arrangement system based on artificial intelligence

Abstract

The invention discloses a hotel guest room cleaning task automatic arrangement system based on artificial intelligence, and relates to the technical field of hotel management. The guest room service work station is in communication connection with a guest room state monitoring module, a task arrangement algorithm module, an order grabbing platform module, an incentive mechanism module, a real-time feedback mechanism module and a data analysis module. The hotel guest room cleaning task automatic arrangement system based on artificial intelligence can quickly respond to guest room cleaning requirements by monitoring guest room states and employee working states in real time, collects data of guest room check-in conditions, sanitary conditions and the like in real time by using a sensor technology, and generates and distributes cleaning tasks in combination with real-time positions and working capabilities of employees. The task allocation efficiency is remarkably improved, manual scheduling time and possible errors are reduced, employees receive task notices through mobile application programs, orders can be quickly grabbed and tasks can be quickly executed, and guest room cleaning timeliness is further improved.

Description

Technical Field

[0001] The present invention relates to the technical field of hotel management, and in particular to an automatic scheduling system for hotel room cleaning tasks based on artificial intelligence. Background Art

[0002] As competition in the hotel industry becomes increasingly fierce, hotel managers are paying more and more attention to improving operational efficiency. Cost control is an important consideration in hotel management. In recent years, artificial intelligence technology has made great progress and has been widely used in various fields. In the hotel industry, artificial intelligence technology has also begun to gradually penetrate and change traditional operating methods.

[0003] The traditional way of assigning guest room cleaning tasks mainly relies on manual scheduling, which has problems such as low efficiency, slow response speed, uneven resource allocation, and lack of flexibility and employee participation. Therefore, how to integrate employees' work preferences and actual conditions to meet the efficiency requirements of guest room services is the problem we need to solve. To this end, this paper proposes an automatic scheduling system for hotel room cleaning tasks based on artificial intelligence. Summary of the invention

[0004] To achieve the above objectives, the present invention is implemented through the following technical solutions: an artificial intelligence-based hotel room cleaning task automatic scheduling system, including a room service workstation, the room service workstation is communicatively connected with a room status monitoring module, a task scheduling algorithm module, an order grabbing platform module, an incentive mechanism module, a real-time feedback mechanism module and a data analysis module, wherein the modules are connected by electrical signals; The guest room status monitoring module uses sensor technology to monitor the guest room status in real time, including occupancy, hygiene, temperature and humidity, and door magnetic switch status, and uses wireless communication technology to transmit sensor data to the central server of the guest room service workstation, and then pre-processes the received sensor data, including data cleaning and abnormal value detection, and automatically generates cleaning tasks to improve the timeliness and accuracy of task allocation; The task scheduling algorithm module uses a machine learning algorithm to predict the optimal cleaning time window based on room status information and employee data, and performs task scheduling based on task priority, employee work efficiency, and customer satisfaction factors, thereby optimizing task allocation and improving work efficiency and customer satisfaction. The order grabbing platform module adopts a mobile application, which enables employees to receive task notifications and view task details through the mobile phone APP, and choose to accept or reject tasks according to their own circumstances, thereby improving the flexibility of task allocation and employee participation, and recording employees' order grabbing history and task completion status, providing a basis for subsequent incentive mechanisms and data analysis; The incentive mechanism module rewards employees based on the number of orders they grab, the quality of task completion, and timeliness indicators, so as to stimulate their work enthusiasm and creativity. The rewards include points, bonuses, and honorary titles. The rewards are announced regularly to create a competitive atmosphere and improve the overall service level. In the real-time feedback mechanism module, after completing a task, an employee submits a task completion report through the APP, including task completion time and quality evaluation information. The system automatically collects feedback information to optimize the task allocation algorithm and improve service quality, and regularly generates work reports for management to review and analyze, supporting scientific decision-making; The data analysis module collects employees' order grabbing records, task completion status and customer feedback data, performs data analysis and processing, identifies system problems and deficiencies through data analysis, proposes improvement measures, optimizes task scheduling algorithms and order grabbing mechanisms, and improves system performance and efficiency.

[0005] Preferably, in the guest room status monitoring module, the generation process of the cleaning task includes: Install various types of sensors in hotel guest rooms, including infrared sensors (to detect whether guests are in the room), temperature and humidity sensors (to monitor the comfort of the room environment) and door magnetic switches (to determine the door switch status). The sensors collect room status data in real time, including occupancy status, hygiene status, temperature and humidity readings and door magnetic switch status. Among them, the hygiene status is comprehensively evaluated based on the frequency of room use and the last cleaning time; Transmit the room status data collected by the sensor to the central server of the room service workstation through wireless communication technology (Wi-Fi or Zigbee), and optimize the communication protocol to ensure the efficiency and reliability of data transmission and reduce data loss or delay; The central server pre-processes the received room status data, including data cleaning and outlier detection, and removes noise and erroneous data through data cleaning; Based on the preprocessed data, the guest room status is analyzed to determine whether a cleaning task needs to be generated. When the room is vacant and has not been cleaned for more than three days, the system automatically generates a cleaning task, including the task type, task priority, and estimated completion time. The task types are daily cleaning and deep cleaning, and the generated cleaning tasks are output to the task scheduling module as the basis for subsequent task allocation. The guest room status information is updated simultaneously, and the room is marked as "to be cleaned" so that employees and management can understand the guest room status in real time.

[0006] Preferably, in the task scheduling algorithm module, the process of optimizing task allocation includes: Extract pre-processed guest room status information data, collect employee data, analyze employee work efficiency, skill level and shift information, clean and organize the collected employee data, remove invalid and abnormal data, and ensure data accuracy and completeness; Adopt collaborative filtering machine learning algorithms to predict the best cleaning time window based on the collected room status information and employee data, and comprehensively analyze the time patterns of guests' check-in and check-out, as well as the hotel's operational needs, to optimize and adjust the predicted time window; Prioritize cleaning tasks based on the cleanliness of guest rooms and guest needs, and rate employees based on their work efficiency, skill level, and shift schedule to assess their ability to complete cleaning tasks; Comprehensively analyze task priorities, employee ratings, and customer satisfaction factors, calculate the overall task rating, and then schedule the tasks.

[0007] Preferably, the expression for predicting the optimal cleaning time window is: ; in, is the predicted optimal cleaning time window, is the activation function, is a weight matrix, which contains the parameters obtained through learning and represents the influence of different features on the optimal cleaning time window. is the input feature vector, including , , , , , and , The time when the room was last cleaned. The estimated check-out time for the room. The estimated check-in time for the room. The frequency of use of the guest room. For the work efficiency of employees, For the skill level of employees, For employee scheduling, is the bias term; The expression of the employee score is: ; in, is the employee rating, It is the work efficiency of employees. is the average work efficiency of all employees, is the skill level of the employees, is the average skill level of all employees, is the employee's scheduling score, is the average scheduling score of all employees.

[0008] Preferably, the expression of the task comprehensive score is: ; in, It is the comprehensive score of the task, reflecting the urgency and importance of the task. , and, are weight coefficients, corresponding to the weights of employee ratings, task priorities, and customer satisfaction, respectively. is the employee rating, is the maximum value of the employee's rating, is the urgency of the task, is the average value of task urgency, is the standard deviation of task urgency, is the customer satisfaction score for the current task , is the average customer satisfaction score, It is the highest score of customer satisfaction.

[0009] Preferably, the order grabbing platform module specifically includes: The system publishes tasks to the order grabbing platform based on the results of the task scheduling algorithm module. Task details include task type, location, required skills, estimated completion time and priority. When a new task is released, the mobile application will promptly remind employees to check it through push notifications. Employees can view all pending tasks in the task list through the mobile APP. Employees click on a task in the task list to view the detailed description and requirements of the task, and evaluate whether they are suitable to accept the task based on their own capabilities, time and location factors. If they decide to accept the task, they click the "Grab Order" button to grab the order. If the task has been grabbed by other employees, the system prompts that the task has been grabbed. The system assigns the task to the first employee who successfully grabs the order based on the employee's order grabbing operation. After the employee successfully grabs the order, he / she needs to confirm that he / she accepts the task and promises to complete it within the specified time. Record the employee's order grabbing history, including order grabbing time, task name and task status, and record the employee's task completion status, including task completion time and quality evaluation.

[0010] Preferably, the incentive mechanism module specifically includes: Automatically collect employee data on the number of orders they have taken, the quality and timeliness of their task completion, including order success rate, task completion rate, task completion time, and customer evaluation, and set specific conditions and quantities for awarding points, bonuses, and honorary titles. Employees earn points by completing tasks, and the points can be used to redeem prizes or upgrade levels. Based on the evaluation results of employees, corresponding bonuses are issued, and employees with outstanding performance are awarded the honorary titles of "Excellent Employee" and "Service Star"; Evaluate employee performance based on the number of orders they grab, the quality of task completion, and timeliness, and calculate the points, bonuses, and honorary titles that each employee deserves; Based on the calculation results, corresponding points, bonuses and honorary titles are allocated to employees, and the employees are notified of the reward status through the mobile application. The employee reward status is announced regularly on the mobile application, including the points ranking list, bonus distribution list and honorary title winners.

[0011] Preferably, in the real-time feedback mechanism module, the process of generating the work report includes: After completing a task, the employee enters the task details page through the mobile application (APP) and fills in the task completion report on the task details page, including the task completion time and quality evaluation information. After the employee confirms that everything is correct, he submits the task completion report. The system automatically records the report submission time and submitter information; The system extracts the task completion reports submitted by employees, cleans and organizes the collected data to ensure the accuracy and completeness of the data, and then conducts statistical analysis on the data, analyzes the quality evaluation information, and identifies problems and improvement points in the service; Generate work reports regularly every week, including task completion status, employee performance and service quality analysis, and distribute them to managers for review and analysis.

[0012] Preferably, in the data analysis module, the process of identifying system problems and deficiencies includes: Extract and collect employee order grabbing records, task completion status and customer feedback data, and determine the evaluation indicators of the corresponding data, among which the evaluation indicator of order grabbing records is the employee order grabbing success rate, the evaluation indicator of task completion status is the task completion rate, and the evaluation indicator of customer feedback data is the customer satisfaction score. Integrate data from different sources into a unified data table to obtain a data sequence table; Preset abnormal thresholds for each indicator in order grabbing records, task completion status, and customer feedback data, identify indicators that deviate from the abnormal thresholds in the data sequence table, and comprehensively analyze and calculate the abnormal detection index to identify problems and improvement points in the service process; Based on the identified problems and improvement points, improvement measures are proposed, including optimizing the task scheduling algorithm, improving the order grabbing mechanism, and strengthening employee training.

[0013] Preferably, the expression of the anomaly detection index is: ; in, is the anomaly detection index, The larger the value of, the higher the abnormality. is the success rate of employees grabbing orders, is the preset abnormal threshold of order grabbing success rate. is the task completion rate, is the preset abnormal threshold of task completion rate, is the customer satisfaction rating, is the preset abnormal threshold of customer satisfaction score, The value range is between 0 and 1, where 0 indicates no abnormality and 1 indicates a very high degree of abnormality.

[0014] The present invention provides an artificial intelligence-based hotel room cleaning task automatic scheduling system, which has the following beneficial effects: 1. This AI-based hotel room cleaning task automatic scheduling system can quickly respond to room cleaning needs by real-time monitoring of room status and employee work status. It uses sensor technology to collect real-time data such as room occupancy and hygiene conditions, and generates and assigns cleaning tasks based on the real-time location and work ability of employees. It significantly improves the efficiency of task allocation, reduces the time and possible errors of manual scheduling, and thus speeds up the response speed of room service. Employees receive task notifications through mobile applications, can quickly grab orders and execute tasks, and further improve the timeliness of room cleaning.

[0015] 2. The hotel room cleaning task automatic scheduling system based on artificial intelligence realizes the optimal management of labor by intelligently analyzing the room status and employee work data. It can schedule and allocate tasks according to the urgency of the room cleaning task and the employee's work ability and location factors to ensure that each task can be completed efficiently. Moreover, through the order-grabbing platform module, employees can choose to accept or reject tasks according to their own circumstances, which not only improves the job satisfaction of employees, but also reduces the waste of human resources and realizes the rational allocation of resources. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 This is a module diagram of an artificial intelligence-based hotel room cleaning task automatic scheduling system of the present invention; Figure 2 A flowchart for optimizing task allocation for the present invention; Figure 3Flowchart for identifying system problems and deficiencies for the present invention. DETAILED DESCRIPTION

[0017] 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.

[0018] The first embodiment, as Figure 1 , Figure 2 As shown, the present invention provides a technical solution: an artificial intelligence-based hotel room cleaning task automatic scheduling system, including a room service workstation, the room service workstation is communicatively connected with a room status monitoring module, a task scheduling algorithm module, an order grabbing platform module, an incentive mechanism module, a real-time feedback mechanism module and a data analysis module, wherein the modules are connected by electrical signals; The guest room status monitoring module uses sensor technology to monitor the guest room status in real time, including occupancy status, sanitary conditions, temperature and humidity, and door magnetic switch status. It uses wireless communication technology to transmit sensor data to the central server of the guest room service workstation, and then pre-processes the received sensor data, including data cleaning and outlier detection, and automatically generates cleaning tasks to improve the timeliness and accuracy of task allocation. Various types of sensors are installed in hotel guest rooms, including infrared sensors (to detect whether guests are in the room), temperature and humidity sensors (to monitor the comfort of the room environment) and door magnetic switches (to determine the door switch status). The sensors collect guest room status data in real time, including occupancy status, sanitary conditions, temperature and humidity readings, and door magnetic switch status. Among them, the sanitary conditions are comprehensively evaluated by the frequency of room use and the last cleaning time. The guest room status data collected by the sensor is transmitted to the central server of the guest room service workstation through wireless communication technology (Wi-Fi or Zigbee), and the communication protocol is optimized to ensure To ensure the efficiency and reliability of data transmission and reduce data loss or delay, the central server pre-processes the received guest room status data, including data cleaning and outlier detection. Through data cleaning, noise and erroneous data, such as invalid sensor readings and duplicate data, are removed to improve data quality. Abnormal data, such as sudden and drastic changes in temperature and humidity, frequent false alarms of door magnetic switches, etc., are detected through statistical analysis methods such as the 3σ principle and box plot analysis. Abnormal situations are identified and handled in a timely manner to avoid interference with task allocation. Based on the pre-processed data, the guest room status is analyzed to determine whether a cleaning task needs to be generated. When the room is vacant and has not been cleaned for more than three days, the system automatically generates a cleaning task, including task type, task priority and estimated completion time. Among them, the task types are daily cleaning and deep cleaning, and the generated cleaning tasks are output to the task scheduling module as the basis for subsequent task allocation. The guest room status information is updated synchronously, and the room is marked as "to be cleaned" so that employees and management can understand the guest room status in real time. The task scheduling algorithm module uses a machine learning algorithm to predict the optimal cleaning time window based on the guest room status information and employee data, and performs task scheduling based on the task priority, employee work efficiency and customer satisfaction factors, optimizes task allocation, improves work efficiency and customer satisfaction, extracts pre-processed guest room status information data, collects employee data, analyzes employee work efficiency, skill level and scheduling information, cleans and organizes the collected employee data, removes invalid and abnormal data, and ensures the accuracy and completeness of the data. It uses a collaborative filtering machine learning algorithm to predict the optimal cleaning time window based on the collected guest room status information and employee data, and comprehensively analyzes the time patterns of guest check-in and check-out, as well as the hotel's operational needs, optimizes and adjusts the predicted time window, determines the priority of cleaning tasks based on the sanitation of the guest rooms and guest needs, and rates employees based on their work efficiency, skill level and scheduling, evaluates their ability to complete cleaning tasks, comprehensively analyzes task priority, employee ratings and customer satisfaction factors, calculates the comprehensive task rating, and then schedules tasks; Furthermore, the expression for predicting the optimal cleaning time window is: ; in, is the predicted optimal cleaning time window, It is an activation function, which can be ReLU, Sigmoid, etc., used to convert linear results into nonlinear results that are more in line with actual needs. is a weight matrix, which contains the parameters obtained through learning and represents the influence of different features on the optimal cleaning time window. is the input feature vector, including , , , , , and , The time when the room was last cleaned. The estimated check-out time for the room. The estimated check-in time for the room. The frequency of use of the guest room. For the work efficiency of employees, For the skill level of employees, For employee scheduling, is the bias term; The expression for employee rating is: ; in, is the employee rating, It is the work efficiency of employees. is the average work efficiency of all employees, is the skill level of the employees, is the average skill level of all employees, is the employee's scheduling score, is the average scheduling score of all employees. Above average hour, Will increase when the skill level of employees Above average hour, Will increase when the employee's scheduling score Above average hour, will increase; Furthermore, the expression of the comprehensive score of the task is: ; in, It is the comprehensive score of the task, reflecting the urgency and importance of the task. , and, are weight coefficients, corresponding to the weights of employee ratings, task priorities, and customer satisfaction, respectively. is the employee rating, is the maximum value of the employee's rating, is the urgency of the task, is the average value of task urgency, is the standard deviation of task urgency, is the customer satisfaction score for the current task , is the average customer satisfaction score, is the maximum score of customer satisfaction. When task urgency, employee ratings, and customer satisfaction are all high, The value of will increase, indicating that the overall score of the task is high and should be given priority. The greater the deviation of the task urgency from the average urgency, The value of will increase or decrease accordingly, depending on whether the urgency is above or below the average, customer satisfaction The higher, The value of will also increase, indicating that customer satisfaction has a positive impact on the overall task score; The order grabbing platform module uses a mobile application to allow employees to receive task notifications and view task details through the mobile APP. They can choose to accept or reject tasks according to their own circumstances, thereby improving the flexibility of task allocation and employee participation. It also records employees' order grabbing history and task completion status, providing a basis for subsequent incentive mechanisms and data analysis. The system publishes tasks to the order grabbing platform based on the results of the task scheduling algorithm module. Task details include task type, location, required skills, estimated completion time and priority. When a new task is released, the mobile application will promptly remind employees to check it through push notifications. Employees can view all tasks to be grabbed in the task list through the mobile APP. For tasks, employees click on the tasks in the task list to view the detailed description and requirements of the tasks, and evaluate whether they are suitable for accepting the tasks based on their own capabilities, time and location factors. If they decide to accept the tasks, they click on the "Grab Order" button to grab the orders. If the tasks have been grabbed by other employees, the system prompts that the tasks have been grabbed. The system assigns the tasks to the first employee who successfully grabs the orders based on the employees' grabbing operations. After successfully grabbing the orders, the employees need to confirm that they accept the tasks and promise to complete the tasks within the specified time. The employee's grabbing history is recorded, including the grabbing time, task name and task status, and the employee's task completion status is recorded, including the task completion time and quality evaluation. The incentive mechanism module rewards employees based on the number of orders they grab, the quality of task completion and timeliness indicators, so as to stimulate their work enthusiasm and creativity. Among them, the forms of rewards include points, bonuses and honorary titles. The rewards are announced regularly to create a competitive atmosphere and improve the overall service level. The module automatically collects the indicator data related to the number of orders they grab, the quality of task completion and timeliness, including the order grab success rate, task completion rate, task completion time and customer evaluation, and sets the specific reward issuance conditions and quantities in the form of points, bonuses and honorary titles. Employees obtain points by completing tasks, and the points can be used to exchange for prizes or upgrade levels. According to the evaluation results of employees, corresponding bonuses are issued, and the honorary titles of "Excellent Employee" and "Service Star" are awarded to employees with outstanding performance. According to the number of orders they grab, the quality of task completion and timeliness data of employees, the employee's performance is evaluated, and the points, bonuses and honorary titles that each employee deserves are calculated. According to the calculation results, the corresponding points, bonuses and honorary titles are allocated to employees, and the rewards are notified to employees through mobile applications. The rewards of employees are announced regularly on mobile applications, including the points ranking list, the bonus distribution list and the honorary title winners; Real-time feedback mechanism module: after completing a task, employees submit a task completion report through the APP, including task completion time and quality evaluation information. The system automatically collects feedback information to optimize the task allocation algorithm and improve service quality, and regularly generates work reports for management to review and analyze, supporting scientific decision-making; The data analysis module collects employees' order grabbing records, task completion status and customer feedback data, performs data analysis and processing, identifies system problems and deficiencies through data analysis, proposes improvement measures, optimizes task scheduling algorithms and order grabbing mechanisms, and improves system performance and efficiency.

[0019] The second embodiment is based on the first embodiment. Figure 3 As shown, in the real-time feedback mechanism module, the process of generating a work report includes: After completing a task, employees access the task details page through the mobile application (APP) and fill in the task completion report on the task details page, including the task completion time and quality evaluation information. After the employee confirms that everything is correct, the employee submits the task completion report. The system automatically records the submission time and submitter information of the report. The system extracts the task completion report submitted by the employee and cleans and organizes the collected data to ensure the accuracy and completeness of the data, and then performs statistical analysis on the data, analyzes the quality evaluation information, identifies problems and improvement points in the service, and generates work reports regularly every week. The work reports include the task completion status, employee performance and service quality analysis, and distribute the work reports to managers for review and analysis. In the data analysis module, the process of identifying system problems and deficiencies includes: Extract and collect data on employees' order grabbing records, task completion status, and customer feedback, and determine the evaluation indicators of the corresponding data, among which the evaluation indicator of order grabbing records is the employee's order grabbing success rate, the evaluation indicator of task completion status is the task completion rate, and the evaluation indicator of customer feedback data is the customer satisfaction score. Integrate data from different sources into a unified data table to obtain a data sequence table, preset the abnormal threshold of each indicator in the order grabbing records, task completion status, and customer feedback data, and calculate the abnormal detection index by comprehensively analyzing and identifying the indicators that deviate from the abnormal threshold in the data sequence table, identify problems and improvement points in the service process, and propose improvement measures based on the identified problems and improvement points, including optimizing the task scheduling algorithm, improving the rationality and fairness of task allocation, improving the order grabbing mechanism, reducing malicious order grabbing and order grabbing failures, and strengthening employee training to improve task completion quality and customer satisfaction. Furthermore, the expression of the anomaly detection index is: ; in, is the anomaly detection index, The larger the value of, the higher the abnormality. is the success rate of employees grabbing orders, is the preset abnormal threshold of order grabbing success rate. is the task completion rate, is the preset abnormal threshold of task completion rate, is the customer satisfaction rating, is the preset abnormal threshold of customer satisfaction score, The value range is between 0 and 1, where 0 indicates no abnormality and 1 indicates a very high degree of abnormality.

[0020] 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. An artificial intelligence-based hotel room cleaning task automatic scheduling system, including a room service workstation, characterized in that: The room service workstation is communicatively connected with a room status monitoring module, a task scheduling algorithm module, an order grabbing platform module, an incentive mechanism module, a real-time feedback mechanism module and a data analysis module, wherein the modules are electrically connected with each other; The guest room status monitoring module uses sensor technology to monitor the guest room status in real time, including occupancy, hygiene, temperature and humidity, and door magnetic switch status, and automatically generates cleaning tasks; The task scheduling algorithm module uses a machine learning algorithm to predict the optimal cleaning time window based on room status information and employee data, and performs task scheduling based on task priority, employee work efficiency, and customer satisfaction factors to optimize task allocation; The order grabbing platform module adopts a mobile application, which enables employees to receive task notifications and view task details through the mobile phone APP, and choose to accept or reject tasks according to their own circumstances; The incentive mechanism module rewards employees based on the number of orders they grab, the quality of task completion, and timeliness indicators, so as to stimulate their work enthusiasm and creativity; The real-time feedback mechanism module allows employees to submit task completion reports through the APP after completing tasks, including task completion time and quality evaluation information, and generate work reports regularly; The data analysis module collects employees' order grabbing records, task completion status and customer feedback data, performs data analysis and processing, identifies system problems and deficiencies, and proposes improvement measures.

2. The hotel room cleaning task automatic scheduling system based on artificial intelligence according to claim 1 is characterized by: In the guest room status monitoring module, the generation process of the cleaning task includes: Install various types of sensors in hotel guest rooms, including infrared sensors, temperature and humidity sensors, and door magnetic switches. The sensors collect room status data in real time, including occupancy, hygiene conditions, temperature and humidity readings, and door magnetic switch status. Among them, the hygiene condition is comprehensively evaluated based on the frequency of room use and the last cleaning time; Transmit the room status data collected by the sensor to the central server of the room service workstation through wireless communication technology, and optimize the communication protocol; The central server pre-processes the received room status data, including data cleaning and outlier detection, and removes noise and erroneous data through data cleaning; Based on the preprocessed data, the guest room status is analyzed to determine whether a cleaning task needs to be generated. When the room is vacant and has not been cleaned for more than three days, the system automatically generates a cleaning task, including the task type, task priority, and estimated completion time. The task types are daily cleaning and deep cleaning, and the generated cleaning tasks are output to the task scheduling module. The guest room status information is updated synchronously, and the room is marked as "to be cleaned".

3. The hotel room cleaning task automatic scheduling system based on artificial intelligence according to claim 2 is characterized by: In the task scheduling algorithm module, the process of optimizing task allocation includes: Extract pre-processed guest room status information data, collect employee data, analyze employee work efficiency, skill level and shift scheduling information, and clean and organize the collected employee data; Adopt collaborative filtering machine learning algorithms to predict the best cleaning time window based on the collected room status information and employee data, and comprehensively analyze the time patterns of guests' check-in and check-out, as well as the hotel's operational needs, to optimize and adjust the predicted time window; Prioritize cleaning tasks based on the cleanliness of guest rooms and guest needs, and rate employees based on their work efficiency, skill level, and shift schedule to assess their ability to complete cleaning tasks; Comprehensively analyze task priorities, employee ratings, and customer satisfaction factors, calculate the overall task rating, and then schedule the tasks.

4. The hotel room cleaning task automatic scheduling system based on artificial intelligence according to claim 3 is characterized by: The expression for predicting the optimal cleaning time window is: ; in, is the predicted optimal cleaning time window, is the activation function, is a weight matrix, which indicates the influence of different features on the optimal cleaning time window. is the input feature vector, including , , , , , and , The time when the room was last cleaned. The estimated check-out time for the room. The estimated check-in time for the room. The frequency of use of the guest room. For the work efficiency of employees, For the skill level of employees, For employee scheduling, is the bias term; The expression of the employee rating is: ; in, is the employee rating, It is the work efficiency of employees. is the average work efficiency of all employees, is the skill level of the employees, is the average skill level of all employees, is the employee's scheduling score, is the average scheduling score of all employees.

5. The hotel room cleaning task automatic scheduling system based on artificial intelligence according to claim 4 is characterized by: The expression of the comprehensive score of the task is: ； in, is the overall score of the task. , and, are weight coefficients, corresponding to the weights of employee ratings, task priorities, and customer satisfaction, respectively. is the employee rating, is the maximum value of the employee's rating, is the urgency of the task, is the average value of task urgency, is the standard deviation of task urgency, is the customer satisfaction score for the current task , is the average customer satisfaction score, It is the highest score of customer satisfaction.

6. The hotel room cleaning task automatic scheduling system based on artificial intelligence according to claim 5 is characterized by: The order grabbing platform module specifically includes: The system publishes tasks to the order grabbing platform based on the results of the task scheduling algorithm module. Task details include task type, location, required skills, estimated completion time and priority. When a new task is released, the mobile application will remind employees to check it through push notifications. Employees can check all the tasks to be grabbed in the task list through the mobile APP; Employees click on a task in the task list to view the detailed description and requirements of the task, and evaluate whether they are suitable to accept the task based on their own capabilities, time and location factors. If they decide to accept the task, they click the "Grab Order" button to grab the order. If the task has been grabbed by other employees, the system prompts that the task has been grabbed. The system assigns the task to the first employee who successfully grabs the order based on the employee's order grabbing operation. After the employee successfully grabs the order, he / she needs to confirm that he / she accepts the task and promises to complete it within the specified time. Record the employee's order grabbing history, including order grabbing time, task name and task status, and record the employee's task completion status, including task completion time and quality evaluation.

7. The hotel room cleaning task automatic scheduling system based on artificial intelligence according to claim 1 is characterized by: The incentive mechanism module specifically includes: Automatically collect employee data on the number of orders they have taken, the quality and timeliness of their task completion, including order success rate, task completion rate, task completion time, and customer evaluation, and set specific conditions and quantities for awarding points, bonuses, and honorary titles; Evaluate employee performance based on the number of orders they grab, the quality of task completion, and timeliness, and calculate the points, bonuses, and honorary titles that each employee deserves; Based on the calculation results, corresponding points, bonuses and honorary titles are allocated to employees, and the employees are notified of the reward status through the mobile application. The employee reward status is announced regularly on the mobile application, including the points ranking list, bonus distribution list and honorary title winners.

8. The hotel room cleaning task automatic scheduling system based on artificial intelligence according to claim 1 is characterized by: In the real-time feedback mechanism module, the process of generating a work report includes: After completing a task, the employee enters the task details page through the mobile application and fills in the task completion report on the task details page, including the task completion time and quality evaluation information. After the employee confirms that everything is correct, he submits the task completion report, and the system automatically records the report submission time and submitter information; The system extracts the task completion reports submitted by employees, cleans and organizes the collected data, and then conducts statistical analysis on the data, analyzes the quality evaluation information, and identifies problems and improvement points in the service; Generate work reports regularly every week, including task completion status, employee performance and service quality analysis, and distribute them to managers for review and analysis.

9. The hotel room cleaning task automatic scheduling system based on artificial intelligence according to claim 1 is characterized by: In the data analysis module, the process of identifying system problems and deficiencies includes: Extract and collect employee order grabbing records, task completion status and customer feedback data, and determine the evaluation indicators of the corresponding data, among which the evaluation indicator of order grabbing records is the employee order grabbing success rate, the evaluation indicator of task completion status is the task completion rate, and the evaluation indicator of customer feedback data is the customer satisfaction score. Integrate data from different sources into a unified data table to obtain a data sequence table; Preset abnormal thresholds for each indicator in order grabbing records, task completion status, and customer feedback data, identify indicators that deviate from the abnormal thresholds in the data sequence table, and comprehensively analyze and calculate the abnormal detection index to identify problems and improvement points in the service process; Based on the identified problems and improvement points, improvement measures are proposed, including optimizing the task scheduling algorithm, improving the order grabbing mechanism, and strengthening employee training.

10. The hotel room cleaning task automatic scheduling system based on artificial intelligence according to claim 9 is characterized in that: The expression of the anomaly detection index is: ; in, is the anomaly detection index, is the success rate of employees grabbing orders, is the preset abnormal threshold of order grabbing success rate. is the task completion rate, is the preset abnormal threshold of task completion rate, is the customer satisfaction rating, is the preset abnormal threshold of customer satisfaction score.

Images