Campus comprehensive service management method and system based on digital twinning

Abstract

The invention discloses a digital twinborn-based campus comprehensive service management method and system, and relates to the technical field of campus canteen service management. According to the method, a digital twinborn model is established, and a plurality of catering areas in a canteen are monitored; the utilization rate Rct is calculated by extracting the diner number characteristic, the food supply state and the queuing duration characteristic in the regional real-time state set. Therefore, the system can judge whether the resource allocation of each catering area is reasonable or not in advance. According to the method, a food consumption rate Fcx, a dining table turnover coefficient Pds, a customer average action path length Zyr, a tableware equipment load rate Ssy and a saturation evaluation index Bpzs are calculated by performing preprocessing and standardization processing on a regional real-time state set, and a system automatically calculates an unbalance rate Shs when the saturation evaluation index Bpzs exceeds a saturation threshold value K; whether current personnel scheduling, food supply and equipment use are in a balanced state or not is analyzed, and an optimization instruction is triggered in time, so that resource waste and reduction of service quality are avoided.

Description

Technical Field

[0001] The present invention relates to the technical field of campus canteen service management, and specifically to a campus comprehensive service management method and system based on digital twins. Background Art

[0002] With the rapid development of digital and intelligent technologies, the traditional campus management model has been unable to meet the increasingly complex operational needs of modern universities. In order to improve management efficiency, optimize resource allocation, and improve the service experience of teachers and students, digital twin technology has gradually shown great application potential in the field of campus comprehensive service management. Digital twin technology builds a virtual mapping of the physical campus to achieve real-time monitoring, simulation and optimization of physical space, equipment and operating status, thereby effectively solving many problems in the traditional campus management model.

[0003] In the traditional campus management model, there are problems such as single management means, serious information island phenomenon, waste of resources, and untimely response. For example, the infrastructure, logistics support, teaching system and student services of the campus are often managed by different departments, and data sharing is insufficient, resulting in a complex and inefficient management process. For example, in the traditional canteen management method of campus services, manual monitoring and management are the main means. This method is not only time-consuming and labor-intensive, but also prone to human errors, resulting in inefficient management. Especially during peak dining time, there is often congestion in the canteen, and problems such as shortage of tableware, insufficient use of tables and chairs, and insufficient supply of ingredients often occur. These problems directly affect the dining experience of diners and also bring great pressure to managers. Summary of the invention

[0004] In view of the shortcomings of the prior art, the present invention provides a campus comprehensive service management method and system based on digital twins to solve the problems mentioned in the background technology.

[0005] To achieve the above objectives, the present invention is implemented through the following technical solutions: A campus comprehensive service management method based on digital twins, comprising the following steps: S1. Use 3D drawing software to draw an electronic distribution map of the campus cafeteria in advance, divide it into several dining areas, and mark and locate the table positions in each dining area; According to the electronic distribution map, monitoring points are set up in several dining areas, and several groups of sensors are installed around each table and dining equipment to monitor the number of diners, tableware usage, food supply status and queue time in the dining area in real time. At the same time, the food inventory status and the use of cleaning equipment are monitored and recorded to establish a regional real-time status collection; S2. Extract the number of diners, food supply status and queuing time characteristics in the real-time status set of the area, preliminarily analyze the usage of each dining area, obtain the usage rate Rct of each area, and preliminarily determine the allocation plan that needs to be optimized in the current dining area based on the value of the usage rate Rct; S3. After establishing and training the digital twin model using convolutional neural network technology, an optimized catering service scheduling model is constructed; after preprocessing and standardizing the regional real-time status set, feature extraction is performed; the food consumption rate Fcx, table turnover coefficient Pds, customer average action path length Zyr and tableware equipment load rate Ssy are obtained respectively, and after correlation, the saturation evaluation index Bpzs has been obtained; S4. Set the saturation threshold K, and compare the saturation evaluation index Bpzs of each catering area with the saturation threshold K. If the saturation evaluation index Bpzs exceeds the saturation threshold K, calculate the imbalance rate Shs, and analyze whether the current canteen’s personnel scheduling, food supply and equipment use are in a balanced state based on the imbalance rate. If not, trigger the optimization instruction to adjust the catering resource allocation.

[0006] Preferably, S1 comprises: S11. Build a digital twin model of the canteen. Based on 3D modeling technology, build digital twin models of each canteen on campus, including virtual models of the canteen's architectural layout, table distribution, queuing area, and catering equipment location. The digital twin model is updated in real time with actual data to form a digital platform that combines virtual and real. S12. Set up monitoring points in the dining area: According to the electronic distribution map of the canteen, each canteen is divided into several dining areas, including dining area, queuing area and food pick-up area; S13, deploy multiple monitoring points in each dining area, install a number of sensors to monitor data information in the area, collect and classify the data information obtained by each monitoring point, and form a regional real-time status set; the regional real-time status set includes but is not limited to the following data: the number of diners in the dining area, tableware usage, food supply status and queuing time; S14. Clean, denoise and standardize the collected data, and use dimensionless processing technology to convert data in different units into a unified analytical data format; Collect and obtain historical data sets, including daily catering supply records in the monitoring area, records of the number of diners in each meal period, records of equipment usage time, and records of food consumption; The real-time status set of the area includes the number of people in the queue, table occupancy, remaining dishes and equipment status monitored in real time, which are obtained and updated in real time through the sensor network installed in the cafeteria.

[0007] Preferably, the utilization rate Rct is calculated by the following formula:

[0008] In the formula, represents the utilization rate of the i-th dining area, represents the number of seats currently used in the i-th dining area, represents the total number of seats in the i-th dining area; represents the average queuing time of the i-th dining area; Indicates the maximum queue time in all dining areas at present. represents the frequency of food supply in the i-th dining area; Indicates the total supply frequency of all current catering areas; , and represents the weight coefficient; and , , , ; According to the value of the utilization rate Rct, the current canteen catering allocation plan that needs to be optimized is preliminarily determined, including: When the utilization rate of the i-th dining area When the value is less than 1, it means that there is no risk of crowding in the i-th dining area, and no adjustment is required, and continuous monitoring is required; When the utilization rate of the i-th dining area =1; it means that all seats in the i-th dining area are occupied and there is no risk of crowding; When 1<the utilization rate of the i-th dining area When the value is less than 1.2, it indicates that there is a risk of congestion in the i-th dining area, and the first deployment plan is generated, including: adding 10% of the existing seats to move tables to vacant locations in the dining area, increasing the number of open pick-up windows by 10%, and increasing the frequency of food supply by 10%; When the utilization rate of the i-th dining area When ≥1.2, it means that there is a risk of congestion in the i-th dining area, and the second deployment plan is generated, including: adding 20% ​​of the existing seats to move tables to vacant locations in the dining area, increasing the number of food pickup windows by 20%, and increasing the frequency of food supply by 20%; guiding 10% of the flow of people to the utilization rate of other i-th dining areas <1 dining area.

[0009] Preferably, S3 includes: S31. Use a convolutional neural network to preliminarily construct an original model, and train and test the original model with a historical data set and a regional real-time status set, and use the trained original model as a digital twin model, respectively obtain feature information in the digital twin model, and train and test the obtained feature information, and use the trained resource identification model as a catering service scheduling model; S32, extracting the consumption characteristics of different foods and the food supply frequency characteristics during the dining time period, and obtaining the food consumption rate Fcx by calculating the following formula:

[0010] In the formula, represents the food consumption rate of the i-th dining area, Indicates the calculation of meal time. represents the frequency of food supply in the i-th dining area; represents the consumption of the jth food, Indicates the number of types, In the i-th dining area within a unit time The total amount of food consumed, Indicates the standard food reserve quantity in the dining area.

[0011] Preferably, S3 further includes: S33, extracting the cleaning time characteristics and table occupancy frequency characteristics of each table during the dining time period, and obtaining the table turnover coefficient Pds by calculating using the following formula:

[0012] In the formula, represents the table turnover coefficient of the i-th dining area, represents the number of occupancy of the kth table, represents the total number of tables in the i-th dining area, Indicates the number of dining areas in the calculation period The number of occupancy of all tables, Indicates the calculation of meal time. It indicates the average cleaning time for each dining table. The longer the cleaning time, the lower the table turnover efficiency.

[0013] Preferably, S3 further includes: S34, extracting the customer action path length characteristics during the dining time period, and calculating the average customer action path length Zyr using the following formula:

[0014] In the formula, represents the average action path length of customers in the i-th dining area, represents the total number of customers in the i-th dining area, represents the distance from the entrance to the selected table of the pth customer, represents the distance from the pth customer's table to the food pick-up point, represents the distance from the queue area of ​​the p-th customer to the dining table, It represents the distance from the table to the checkout point or exit for the pth customer.

[0015] Preferably, S3 further includes: S35, extract the number of times and duration of tableware use during the dining time period and the characteristics of the washing volume of the dishwasher, and calculate the load rate Ssy of the tableware equipment by the following formula:

[0016] In the formula, represents the tableware equipment load rate of the i-th dining area, represents the number of tableware used for the yth time, represents the duration of using tableware for the yth time, represents the number of times tableware is used in the i-th dining area; represents the maximum cleaning volume of the dishwasher equipment in the i-th dining area; Indicates the operating hours of the dishwasher throughout the day.

[0017] Preferably, S3 further includes: S36: The food consumption rate Fcx of the i-th dining area i , table turnover coefficient Pds i 、Customer average action path length Zyr i And tableware equipment load rate Ssy i After dimensionless processing, the saturation evaluation index Bpzs of the i-th catering area is calculated by the following associated formula: i :

[0018] In the formula, and are the food consumption rate Fcx of the i-th dining area i , table turnover coefficient Pds i 、Customer average action path length Zyr i And tableware equipment load rate Ssy i The weight coefficient of , , , , the specific value is set by the user. ; Expressed as the first correction constant.

[0019] Preferably, S4 includes: S41, setting a saturation threshold K, comparing the saturation evaluation index Bpzs of each dining area with the set saturation threshold K, and obtaining a saturation evaluation result, including: When the saturation evaluation index Bpzs of the i-th dining area i > saturation threshold K, it means that the catering area is in an overloaded state, triggering an imbalance warning instruction, and further imbalance analysis is required: When the saturation evaluation index Bpzs of the i-th dining area i ≤ saturation threshold K, it means that the catering area is in normal state and continues to be monitored, and no further imbalance analysis is required: S42. After receiving the imbalance warning instruction, the imbalance rate Shs of the i-th dining area is calculated by the following formula: i :

[0020] S43, when 0<imbalance rate Shs of the i-th dining area i When ≤0.2, the system automatically triggers the first optimization instruction, including: Increase the frequency of food supply in the dining area by 5%-10%, increase the number of cleaning staff by 5%-8%, reduce table cleaning time, adjust the distance between the table and the food pick-up point, and reduce the path length by 5%-10%; increase the cleaning frequency by 5%-10% or add 1-2 dishwashers; When the imbalance rate Shs of the i-th dining area i When the value is greater than 0.2, the system automatically triggers the second optimization instruction, including: Increase the frequency of food supply in the dining area by 11%-20%, increase the number of cleaning staff by 9%-15%, reduce the time for table cleaning, adjust the distance between the table and the food pick-up point, and reduce the path length by 11%-15%; increase the cleaning frequency by 11%-20% or add 3-4 dishwashers.

[0021] Campus comprehensive service management system based on digital twin, including: The canteen electronic distribution drawing module is used to create a virtual model of the architectural layout and equipment of each canteen based on 3D modeling technology, which is divided into several dining areas. Sensors are arranged in the dining areas to monitor the number of diners, tableware usage, food supply status and queuing time in real time in the dining areas. At the same time, it monitors and records the food inventory status and the usage of cleaning equipment to establish a real-time regional status collection; The regional usage analysis module is used to extract the characteristics of the number of diners, food supply status and queuing time in the regional real-time status set, preliminarily analyze the usage of each dining area, and obtain the usage rate Rct of each area; The preliminary allocation judgment module is used to preliminarily judge the allocation scheme that needs to be optimized in the current catering area according to the value of the utilization rate Rct; The digital twin model building module is used to build and train the digital twin model using convolutional neural network technology, and then construct an optimized catering service scheduling model; perform feature extraction after preprocessing and standardizing the regional real-time status set; obtain the food consumption rate Fcx, table turnover coefficient Pds, customer average action path length Zyr and tableware equipment load rate Ssy respectively, and after correlation, obtain the saturation evaluation index Bpzs; The resource optimization module is used to identify whether the current catering area is in an overloaded state and evaluate the resource allocation through the saturation evaluation index Bpzs; if the saturation evaluation index Bpzs exceeds the saturation threshold K, the imbalance rate Shs is calculated, and the current canteen’s personnel scheduling, food supply and equipment use are analyzed based on the imbalance rate. If not, the optimization instruction is triggered to adjust the catering resource allocation.

[0022] The present invention provides a campus comprehensive service management method and system based on digital twins, which has the following beneficial effects: (1) Traditional campus canteen management relies on manual monitoring, which is not only time-consuming and labor-intensive, but also prone to omissions during busy hours. The present invention sets up multiple monitoring points in the dining area and installs sensors around the dining tables and dining equipment to monitor key data such as the number of diners, tableware usage, food supply status, and queue time in the dining area in real time. These data can be collected and transmitted in real time through the Internet of Things technology, which greatly improves the level of automation in canteen management, reduces the possibility of human errors, and allows managers to always grasp the operating status of the canteen. By extracting the characteristics of the number of diners, food supply status, and queue time in the real-time status set of the area, the system can analyze the usage of each dining area and calculate the usage rate Rct. This enables the system to determine in advance whether the resource allocation of each dining area is reasonable, thereby providing a basis for subsequent optimization and scheduling. Compared with the traditional management method that relies on experience judgment, this method uses intelligent analysis technology to ensure the rational allocation and efficient use of resources.

[0023] (2) Traditional canteens often have problems such as shortage of tableware, insufficient tables and chairs, and insufficient food supply during peak hours, which greatly affects the experience of diners. Through intelligent analysis and real-time scheduling, the present invention can quickly respond to peak demand and adjust personnel and resource allocation in a timely manner. The system can automatically allocate tableware and food ingredients, and warn of food shortages in advance, avoiding user dissatisfaction caused by insufficient supply. After building and training the digital twin model, the system further applies convolutional neural network technology to establish an optimized catering service scheduling model. By preprocessing and standardizing the regional real-time status set, the system can extract multiple key features including food consumption rate Fcx, table turnover coefficient Pds, average customer action path length Zyr, and tableware equipment load rate Ssy. After these features are correlated, the system can calculate the saturation evaluation index Bpzs, and accurately evaluate the operational saturation of the catering area by comparing it with the saturation threshold K. If the saturation evaluation index exceeds the set threshold, the system automatically calculates the imbalance rate Shs, analyzes whether the current personnel scheduling, food supply and equipment use are in a balanced state, and triggers optimization instructions in a timely manner, thereby avoiding resource waste and deterioration of service quality. At the same time, by optimizing the average customer movement path, queuing and waiting time are reduced, improving the user's overall dining experience.

[0024] (3) For canteen managers, the traditional management method requires constant attention to the use of various resources, which is stressful. The present invention uses an intelligent management platform to achieve real-time monitoring and intelligent scheduling of various canteen resources, which helps reduce the work pressure of managers. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] Figure 1 This is a schematic diagram of the steps of the campus comprehensive service management method based on digital twins of the present invention; Figure 2 This is a flowchart diagram of the campus comprehensive service management system based on digital twins of the present invention. DETAILED DESCRIPTION

[0026] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0027] Example 1 See also Figure 1 , the present invention provides a campus comprehensive service management method based on digital twins, comprising the following steps: S1. Use 3D drawing software to draw an electronic distribution map of the campus cafeteria in advance, divide it into several dining areas, and mark and locate the table positions in each dining area; According to the electronic distribution map, monitoring points are set up in several dining areas, and several groups of sensors are installed around each table and dining equipment to monitor the number of diners, tableware usage, food supply status and queue time in the dining area in real time. At the same time, the food inventory status and the use of cleaning equipment are monitored and recorded to establish a regional real-time status collection; S2. Extract the number of diners, food supply status and queuing time characteristics in the real-time status set of the area, preliminarily analyze the usage of each dining area, obtain the usage rate Rct of each area, and preliminarily determine the allocation plan that needs to be optimized in the current dining area based on the value of the usage rate Rct; S3. After establishing and training the digital twin model using convolutional neural network technology, an optimized catering service scheduling model is constructed; after preprocessing and standardizing the regional real-time status set, feature extraction is performed; the food consumption rate Fcx, table turnover coefficient Pds, customer average action path length Zyr and tableware equipment load rate Ssy are obtained respectively, and after correlation, the saturation evaluation index Bpzs has been obtained; S4. Set the saturation threshold K, and compare the saturation evaluation index Bpzs of each catering area with the saturation threshold K. If the saturation evaluation index Bpzs exceeds the saturation threshold K, calculate the imbalance rate Shs, and analyze whether the current canteen’s personnel scheduling, food supply and equipment use are in a balanced state based on the imbalance rate. If not, trigger the optimization instruction to adjust the catering resource allocation.

[0028] In this embodiment, traditional campus canteen management relies on manual monitoring, which is not only time-consuming and laborious, but also prone to omissions during busy hours. However, the present invention sets multiple monitoring points in the dining area and installs sensors around the dining tables and dining equipment to monitor key data such as the number of diners, tableware usage, food supply status, and queuing time in the dining area in real time. These data can be collected and transmitted in real time through the Internet of Things technology, which greatly improves the automation level of canteen management, reduces the possibility of human errors, and allows managers to always grasp the operating status of the canteen.

[0029] By extracting the characteristics of the number of diners, food supply status and queuing time in the real-time status set of the area, the system can analyze the usage of each dining area and calculate the utilization rate Rct. This enables the system to determine in advance whether the resource allocation of each dining area is reasonable, thereby providing a basis for subsequent optimization and scheduling. Compared with the traditional management method that relies on experience judgment, this method uses intelligent analysis technology to ensure the rational allocation and efficient use of resources.

[0030] Traditional canteens often have problems such as shortage of tableware, insufficient use of tables and chairs, and insufficient supply of ingredients during peak hours, which greatly affects the experience of diners. Through intelligent analysis and real-time scheduling, the present invention can quickly respond to peak demand and adjust personnel and resource allocation in a timely manner. The system can automatically allocate tableware and ingredients, and warn of the shortage of ingredients in advance, avoiding user dissatisfaction caused by insufficient supply. After building and training the digital twin model, the system further applies convolutional neural network technology to establish an optimized catering service scheduling model. By preprocessing and standardizing the regional real-time state set, the system can extract multiple key features including food consumption rate Fcx, table turnover coefficient Pds, customer average action path length Zyr, and tableware equipment load rate Ssy. After these features are correlated with each other, the system can calculate the saturation evaluation index Bpzs, and accurately evaluate the operational saturation of the catering area by comparing it with the saturation threshold K. If the saturation evaluation index exceeds the set threshold, the system automatically calculates the imbalance rate Shs, analyzes whether the current personnel scheduling, food supply and equipment use are in a balanced state, and triggers optimization instructions in a timely manner, thereby avoiding resource waste and a decline in service quality. At the same time, by optimizing the average customer movement path, queuing and waiting time are reduced, improving the user's overall dining experience.

[0031] For canteen managers, the traditional management method requires constant attention to the use of various resources, which is stressful. The present invention realizes real-time monitoring and intelligent scheduling of various canteen resources through an intelligent management platform, which helps reduce the work pressure of managers.

[0032] Example 2 This embodiment is an explanation of the embodiment 1. Specifically, S1 includes: S11. Build a digital twin model of the canteen. Based on 3D modeling technology, build digital twin models of each canteen on campus, including virtual models of the canteen's architectural layout, table distribution, queuing area, and catering equipment location. The digital twin model is updated in real time with actual data to form a digital platform that combines virtual and real. S12. Set up monitoring points in the dining area: According to the electronic distribution map of the canteen, each canteen is divided into several dining areas, including dining area, queuing area and food pick-up area; S13, deploy multiple monitoring points in each dining area, install a number of sensors to monitor data information in the area, collect and classify the data information obtained by each monitoring point, and form a regional real-time status set; the regional real-time status set includes but is not limited to the following data: the number of diners in the dining area, tableware usage, food supply status and queuing time; Several sensors include: Infrared sensors: used to monitor the number of diners in each dining area. By placing infrared sensors at the entrance, queuing area and near each dining table, the system can capture the entry and exit of customers and the occupancy status of each table in real time, ensuring accurate monitoring of the number of diners.

[0033] Weight sensor: Installed in the tableware recycling area and food pick-up area. The weight sensor can monitor the use of tableware and the consumption of food, and provide real-time feedback on whether the food supply is sufficient and whether the tableware is sufficient, thus avoiding inconvenience caused by tableware shortage or food supply shortage.

[0034] Cameras and image recognition sensors: used to monitor the status of queue areas and catering equipment. The combination of cameras and image recognition technology can automatically analyze queue lengths and customer behavior patterns, helping managers determine whether to increase service staff or open more pick-up windows.

[0035] RFID sensor: used to track the circulation of tableware. By equipping each tableware with an RFID tag, the system can monitor the frequency of use, cleaning status and whether the tableware is lost in real time, thereby helping managers to allocate tableware resources in a timely manner.

[0036] S14. Clean, denoise and standardize the collected data, and use dimensionless processing technology to convert data in different units into a unified analytical data format; Collect and obtain historical data sets, including daily catering supply records in the monitoring area, records of the number of diners in each meal period, records of equipment usage time, and records of food consumption; The real-time status set of the area includes the number of people in the queue, table occupancy, remaining dishes and equipment status monitored in real time, which are obtained and updated in real time through the sensor network installed in the cafeteria.

[0037] In this embodiment, the real-time status set of the area is collected, and the actual operation data of several dining areas of the cafeteria are synchronized in real time, so as to realize the dynamic monitoring and optimization management of each dining area. Especially during peak hours, the system can timely adjust various resources, reasonably allocate dining space, and reduce congestion and waste of resources. For example, through real-time monitoring of data such as the number of diners in each area of ​​the cafeteria, the use of tableware, the number of people in line, and the status of food supply, managers can more accurately judge the load of each area and perform scheduling optimization in time when saturation is reached. This not only improves the overall management efficiency, but also improves the experience of diners and ensures smooth operation during peak hours.

[0038] Example 3 This embodiment is an explanation of the embodiment 1. Specifically, the usage rate Rct is calculated by the following formula:

[0039] In the formula, represents the utilization rate of the i-th dining area, represents the number of seats currently used in the i-th dining area, represents the total number of seats in the i-th dining area; represents the average queuing time of the i-th dining area; Indicates the maximum queue time in all dining areas at present. represents the frequency of food supply in the i-th dining area; Indicates the total supply frequency of all current catering areas; , and represents the weight coefficient; and , , , ; According to the value of the utilization rate Rct, the current canteen catering allocation plan that needs to be optimized is preliminarily determined, including: When the utilization rate of the i-th dining area When the value is less than 1, it means that there is no risk of crowding in the i-th dining area, and no adjustment is required, and continuous monitoring is required; When the utilization rate of the i-th dining area =1; it means that all seats in the i-th dining area are occupied and there is no risk of crowding; When 1<the utilization rate of the i-th dining area When the value is less than 1.2, it indicates that there is a risk of congestion in the i-th dining area, and the first deployment plan is generated, including: adding 10% of the existing seats to move tables to vacant locations in the dining area, increasing the number of open pick-up windows by 10%, and increasing the frequency of food supply by 10%; When the utilization rate of the i-th dining area When ≥1.2, it means that there is a risk of congestion in the i-th dining area, and the second deployment plan is generated, including: adding 20% ​​of the existing seats to move tables to vacant locations in the dining area, increasing the number of food pickup windows by 20%, and increasing the frequency of food supply by 20%; guiding 10% of the flow of people to the utilization rate of other i-th dining areas <1 dining area.

[0040] In this embodiment, the system can monitor the usage of each dining area in the cafeteria in real time by calculating the usage rate Rct through a formula. According to the usage rate of each area, the system can accurately determine which areas have insufficient resources or too many people, thereby triggering the corresponding allocation plan and allocating resources in a timely manner. Compared with the traditional management method that relies on manual experience, the present invention significantly improves the management efficiency of the cafeteria, especially during peak hours, it can effectively avoid congestion.

[0041] By setting different utilization rate thresholds (such as utilization rate <1, =1, 1 < utilization rate <1.2 and utilization rate ≥1.2), the present invention can quickly determine whether there is a risk of congestion in the dining area and automatically generate a corresponding allocation plan. When the utilization rate of a dining area exceeds the set value, the system automatically takes measures, such as adding seats, increasing queuing windows and supply frequency, to ensure reasonable allocation of resources and alleviate congestion. This dynamic adjustment mechanism greatly improves the service experience of the cafeteria and avoids the inconvenience caused by congestion.

[0042] The present invention can not only automatically adjust the number of seats and supply frequency of each dining area, but also flexibly allocate personnel and resources according to the utilization rate of different areas. For example, when the utilization rate exceeds 1.2, the system can automatically guide 10% of the flow of people to relatively idle dining areas, further reducing the load pressure of a single area. This intelligent diversion solution improves the overall resource utilization efficiency and avoids resource waste and unnecessary supply shortages.

[0043] Example 3 This embodiment is an explanation of the embodiment 1. Specifically, S3 includes: S31. Use a convolutional neural network to preliminarily construct an original model, and train and test the original model with a historical data set and a regional real-time status set, and use the trained original model as a digital twin model to obtain feature information in the digital twin model, and use the acquired feature information for training and testing, and use the trained resource identification model as a catering service scheduling model; the feature information includes the consumption characteristics of different foods during the dining time period, the frequency of food supply, the cleaning time characteristics of each table during the dining time period, the number of table occupancy characteristics, the length of customer action paths during the dining time period, the number of times and duration of tableware use during the dining time period, and the cleaning volume characteristics of dishwasher equipment.

[0044] S32, extracting the consumption characteristics of different foods and the food supply frequency characteristics during the dining time period, and obtaining the food consumption rate Fcx by calculating the following formula:

[0045] In the formula, represents the food consumption rate of the i-th dining area, Indicates the calculation of meal time. represents the frequency of food supply in the i-th dining area; represents the consumption of the jth food, Indicates the number of types, In the i-th dining area within a unit time The total amount of food consumed, Indicates the standard food reserve in the dining area. By calculating the food consumption rate Fcx through the formula, the present invention can monitor the consumption of different types of food in each dining area in real time and reasonably evaluate the supply demand of food in each time period. Based on this, the system can dynamically adjust the frequency of food supply to ensure that high-demand food can be replenished in time during peak meal times to avoid food waste and supply shortage. This function effectively improves the rationality and efficiency of food supply and reduces the operating costs of the canteen.

[0046] S33, extracting the cleaning time characteristics and table occupancy frequency characteristics of each table during the dining time period, and obtaining the table turnover coefficient Pds by calculating using the following formula:

[0047] In the formula, represents the table turnover coefficient of the i-th dining area, represents the number of occupancy of the kth table, represents the total number of tables in the i-th dining area, Indicates the number of dining areas in the calculation period The number of occupancy of all tables, Indicates the calculation of meal time. Indicates the average cleaning time of each table. The longer the cleaning time, the lower the table turnover efficiency. By monitoring the number of occupancy and cleaning time of the table, the system can calculate the table turnover coefficient Pds. This indicator helps to identify which tables have low cleaning efficiency or frequently used table areas, and then helps managers to reasonably arrange staff cleaning and table allocation to maximize the utilization of the table. Improving the turnover efficiency of the table can not only speed up the overall operation of the cafeteria, but also reduce the time customers wait for seats and improve the dining experience.

[0048] S34, extracting the customer action path length characteristics during the dining time period, and calculating the average customer action path length Zyr using the following formula:

[0049] In the formula, represents the average action path length of customers in the i-th dining area, represents the total number of customers in the i-th dining area, represents the distance from the entrance to the selected table of the pth customer, represents the distance from the pth customer's table to the food pick-up point, represents the distance from the queue area of ​​the p-th customer to the dining table, Indicates the distance from the table to the checkout point or exit for the pth customer. By calculating the length of the customer's path from the entrance, table to the pick-up point, etc., the present invention can optimize the customer's route and reduce unnecessary detours or congestion. For layout adjustments within the dining area, the system can provide improvement suggestions based on actual data, such as optimizing the distance between the table and the pick-up point, the design of the queuing area, etc. This path optimization can not only shorten the time for customers to pick up their meals and improve the efficiency of restaurant operations, but also improve customer convenience and bring a better dining experience.

[0050] S35, extract the number of times and duration of tableware use during the dining time period and the characteristics of the washing volume of the dishwasher, and calculate the load rate Ssy of the tableware equipment by the following formula:

[0051] In the formula, represents the tableware equipment load rate of the i-th dining area, represents the number of tableware used for the yth time, represents the duration of using tableware for the yth time, represents the number of times tableware is used in the i-th dining area; represents the maximum cleaning volume of the dishwasher equipment in the i-th dining area; Indicates the operation time of the dishwasher equipment throughout the day. By calculating the load rate of the tableware equipment, the present invention can effectively monitor the use of tableware and the cleaning of the dishwasher equipment. According to the frequency of tableware use and the cleaning load, the system can optimize the supply and cleaning scheduling of tableware during peak hours to avoid operational bottlenecks caused by insufficient tableware or overloaded dishwashers. At the same time, the reasonable allocation of tableware use and equipment cleaning time can also help improve the use efficiency of the equipment, extend the service life of the equipment, and reduce the maintenance cost of the equipment.

[0052] S36: The food consumption rate Fcx of the i-th dining area i , table turnover coefficient Pds i 、Customer average action path length Zyr i And tableware equipment load rate Ssy i After dimensionless processing, the saturation evaluation index Bpzs of the i-th catering area is calculated by the following associated formula: i :

[0053] In the formula, and are the food consumption rate Fcx of the i-th dining area i , table turnover coefficient Pds i 、Customer average action path length Zyr i And tableware equipment load rate Ssy i The weight coefficient of , , , , the specific value is set by the user. ; Expressed as the first correction constant.

[0054] In this embodiment, the weight coefficient (for example and ) is used to adjust the saturation evaluation index (Bpzs) of each parameter i ), users can adjust according to different operational goals or actual conditions. This can flexibly reflect the actual conditions of different dining areas. For example, some dining areas may pay more attention to table turnover rate rather than food consumption rate. With this method, catering managers can more accurately evaluate the saturation of each dining area and make corresponding adjustments, thereby improving the operational efficiency of the dining area, optimizing resource allocation, and enhancing the dining experience of customers.

[0055] Example 4 This embodiment is an explanation of the embodiment 1. Specifically, S4 includes: S41, setting a saturation threshold K, comparing the saturation evaluation index Bpzs of each dining area with the set saturation threshold K, and obtaining a saturation evaluation result, including: When the saturation evaluation index Bpzs of the i-th dining area i > saturation threshold K, it means that the catering area is in an overloaded state, triggering an imbalance warning instruction, and further imbalance analysis is required: When the saturation evaluation index Bpzs of the i-th dining area i ≤ saturation threshold K, it means that the catering area is in normal state and continues to be monitored, and no further imbalance analysis is required: S42. After receiving the imbalance warning instruction, the imbalance rate Shs of the i-th dining area is calculated by the following formula: i :

[0056] S43, when 0<imbalance rate Shs of the i-th dining area iWhen ≤0.2, it means that the imbalance is relatively mild and a milder adjustment strategy is adopted. The system automatically triggers the first optimization instruction, including: Increase the frequency of food supply in the dining area by 5%-10%, increase the number of cleaning staff by 5%-8%, reduce table cleaning time, adjust the distance between the table and the food pick-up point, and reduce the path length by 5%-10%; increase the cleaning frequency by 5%-10% or add 1-2 dishwashers; When the imbalance rate Shs of the i-th dining area i When it is greater than 0.2, it indicates that the imbalance is serious and the system takes stronger optimization measures. The system automatically triggers the second optimization instruction, including: Increase the frequency of food supply in the dining area by 11%-20%, increase the number of cleaning staff by 9%-15%, reduce the time for table cleaning, adjust the distance between the table and the food pick-up point, and reduce the path length by 11%-15%; increase the cleaning frequency by 11%-20% or add 3-4 dishwashers.

[0057] In this embodiment, the system automatically matches the corresponding optimization strategy according to different imbalance levels, and can make targeted adjustments from slight imbalance to severe imbalance, avoiding excessive or insufficient intervention. By increasing the frequency of food supply, the allocation of cleaning staff, and reducing the time of table cleaning, the system can effectively improve the operating efficiency of the catering area, so that customer experience and resource utilization are optimized at the same time.

[0058] Example 5 Campus comprehensive service management system based on digital twin, please refer to Figure 2 ,include: The canteen electronic distribution drawing module is used to create a virtual model of the architectural layout and equipment of each canteen based on 3D modeling technology, which is divided into several dining areas. Sensors are arranged in the dining areas to monitor the number of diners, tableware usage, food supply status and queuing time in real time in the dining areas. At the same time, it monitors and records the food inventory status and the usage of cleaning equipment to establish a real-time regional status collection; The regional usage analysis module is used to extract the characteristics of the number of diners, food supply status and queuing time in the regional real-time status set, preliminarily analyze the usage of each dining area, and obtain the usage rate Rct of each area; The preliminary allocation judgment module is used to preliminarily judge the allocation scheme that needs to be optimized in the current catering area according to the value of the utilization rate Rct; The digital twin model building module is used to build and train the digital twin model using convolutional neural network technology, and then construct an optimized catering service scheduling model; perform feature extraction after preprocessing and standardizing the regional real-time status set; obtain the food consumption rate Fcx, table turnover coefficient Pds, customer average action path length Zyr and tableware equipment load rate Ssy respectively, and after correlation, obtain the saturation evaluation index Bpzs; The resource optimization module is used to identify whether the current catering area is in an overloaded state and evaluate the resource allocation through the saturation evaluation index Bpzs; if the saturation evaluation index Bpzs exceeds the saturation threshold K, the imbalance rate Shs is calculated, and the current canteen’s personnel scheduling, food supply and equipment use are analyzed based on the imbalance rate. If not, the optimization instruction is triggered to adjust the catering resource allocation.

[0059] In this embodiment, first, the canteen electronic distribution drawing module uses 3D modeling technology to create a virtual model of each canteen, which can monitor the number of diners, tableware usage, food supply status and queue time in real time. This real-time monitoring not only improves the accuracy of the data, but also provides a solid foundation for subsequent analysis.

[0060] Secondly, the regional usage analysis module preliminarily analyzes the utilization rate (Rct) of each dining area by extracting the characteristics of the number of diners and the length of waiting time, so that managers can quickly grasp the usage of each area and identify demand peaks and troughs.

[0061] On this basis, the preliminary allocation judgment module can formulate an optimization plan based on the utilization rate data to ensure the rational allocation of resources. The digital twin model establishment module uses convolutional neural network technology to train an optimized catering service scheduling model, realize feature extraction and standardized processing of real-time status sets, and provide a scientific basis for further decision-making.

[0062] Finally, the resource optimization module identifies the overload status through the calculation of the saturation evaluation index (Bpzs) and the imbalance rate (Shs), and adjusts the resource allocation according to the actual situation. This series of measures not only improves the operational efficiency of the canteen, but also enhances the dining experience of customers, reduces the waiting time, ensures the timeliness and safety of food supply, realizes the maximum utilization and optimal allocation of resources, and plays an important positive role in improving the overall service quality of the campus.

[0063] The threshold is set to facilitate comparison. The size of the threshold depends on the amount of sample data and the number of bases set by technicians in this field for each group of sample data; as long as it does not affect the proportional relationship between the parameter and the quantized value.

[0064] The above formulas are obtained by collecting a large amount of data for software simulation and selecting a formula that is close to the actual value. The coefficients in the formula are set by technical personnel in this field according to actual conditions. The above is only a preferred specific implementation manner of the present invention, but the protection scope of the present invention is not limited to this. Any technical personnel familiar with the technical field within the technical scope disclosed by the present invention, according to the technical solution and the inventive concept of the present invention, make equivalent replacement or change, which should be covered within the protection scope of the present invention.

Claims

1. A campus comprehensive service management method based on digital twins, characterized in that: The following steps are involved: S1. Use 3D drawing software to draw an electronic distribution map of the campus cafeteria in advance, divide it into several dining areas, and mark and locate the table positions in each dining area; According to the electronic distribution map, monitoring points are set up in several dining areas, and several groups of sensors are installed around each table and dining equipment to monitor the number of diners, tableware usage, food supply status and queue time in the dining area in real time. At the same time, the food inventory status and the use of cleaning equipment are monitored and recorded to establish a regional real-time status collection; S2. Extract the number of diners, food supply status and queuing time characteristics in the real-time status set of the area, preliminarily analyze the usage of each dining area, obtain the usage rate Rct of each area, and preliminarily determine the allocation plan that needs to be optimized in the current dining area based on the value of the usage rate Rct; S3. After establishing and training the digital twin model using convolutional neural network technology, an optimized catering service scheduling model is constructed; after preprocessing and standardizing the regional real-time status set, feature extraction is performed; the food consumption rate Fcx, table turnover coefficient Pds, customer average action path length Zyr and tableware equipment load rate Ssy are obtained respectively, and after correlation, the saturation evaluation index Bpzs has been obtained; S4. Set the saturation threshold K, and compare the saturation evaluation index Bpzs of each catering area with the saturation threshold K. If the saturation evaluation index Bpzs exceeds the saturation threshold K, calculate the imbalance rate Shs, and analyze whether the current canteen’s personnel scheduling, food supply and equipment use are in a balanced state based on the imbalance rate. If not, trigger the optimization instruction to adjust the catering resource allocation.

2. The campus comprehensive service management method based on digital twin according to claim 1 is characterized in that: S1 includes: S11. Build a digital twin model of the canteen. Based on 3D modeling technology, build digital twin models of each canteen on campus, including virtual models of the canteen's architectural layout, table distribution, queuing area, and catering equipment location. The digital twin model is updated in real time with actual data to form a digital platform that combines virtual and real. S12. Set up monitoring points in the dining area: According to the electronic distribution map of the canteen, each canteen is divided into several dining areas, including dining area, queuing area and food pick-up area; S13, deploy multiple monitoring points in each dining area, install a number of sensors to monitor data information in the area, collect and classify the data information obtained by each monitoring point, and form a regional real-time status set; the regional real-time status set includes but is not limited to the following data: the number of diners in the dining area, tableware usage, food supply status and queuing time; S14. Clean, denoise and standardize the collected data, and use dimensionless processing technology to convert data in different units into a unified analytical data format; Collect and obtain historical data sets, including daily catering supply records in the monitoring area, records of the number of diners in each meal period, records of equipment usage time, and records of food consumption; The real-time status set of the area includes the number of people in the queue, table occupancy, remaining dishes and equipment status monitored in real time, which are obtained and updated in real time through the sensor network installed in the cafeteria.

3. The campus comprehensive service management method based on digital twin according to claim 1 is characterized in that: The utilization rate Rct is calculated by the following formula: In the formula, represents the utilization rate of the i-th dining area, represents the number of seats currently used in the i-th dining area, represents the total number of seats in the i-th dining area; represents the average queuing time of the i-th dining area; Indicates the maximum queue time in all dining areas at present. represents the frequency of food supply in the i-th dining area; Indicates the total supply frequency of all current catering areas; , and represents the weight coefficient; and , , , ; According to the value of the utilization rate Rct, the current canteen catering allocation plan that needs to be optimized is preliminarily determined, including: When the utilization rate of the i-th dining area When the value is less than 1, it means that there is no risk of crowding in the i-th dining area, and no adjustment is required, and continuous monitoring is required; When the utilization rate of the i-th dining area =1; it means that all seats in the i-th dining area are occupied and there is no risk of crowding; When 1<the utilization rate of the i-th dining area When the value is less than 1.2, it indicates that there is a risk of congestion in the i-th dining area, and the first deployment plan is generated, including: adding 10% of the existing seats to move tables to vacant locations in the dining area, increasing the number of open pick-up windows by 10%, and increasing the frequency of food supply by 10%; When the utilization rate of the i-th dining area When ≥1.2, it means that there is a risk of congestion in the i-th dining area, and the second deployment plan is generated, including: adding 20% ​​of the existing seats to move tables to vacant locations in the dining area, increasing the number of food pickup windows by 20%, and increasing the frequency of food supply by 20%; guiding 10% of the flow of people to the utilization rate of other i-th dining areas <1 dining area.

4. The campus comprehensive service management method based on digital twin according to claim 1 is characterized in that S3 include: S31. Use a convolutional neural network to preliminarily construct an original model, and train and test the original model with a historical data set and a regional real-time status set, and use the trained original model as a digital twin model, respectively obtain feature information in the digital twin model, and train and test the obtained feature information, and use the trained resource identification model as a catering service scheduling model; S32, extracting the consumption characteristics of different foods and the food supply frequency characteristics during the dining time period, and obtaining the food consumption rate Fcx by calculating the following formula: In the formula, represents the food consumption rate of the i-th dining area, Indicates the calculation of meal time. represents the frequency of food supply in the i-th dining area; represents the consumption of the jth food, Indicates the number of types, In the i-th dining area within a unit time The total amount of food consumed, Indicates the standard food reserve quantity in the dining area.

5. The campus comprehensive service management method based on digital twin according to claim 4 is characterized in that: S3 also includes: S33, extracting the cleaning time characteristics and table occupancy frequency characteristics of each table during the dining time period, and obtaining the table turnover coefficient Pds by calculating using the following formula: In the formula, represents the table turnover coefficient of the i-th dining area, represents the number of occupancy of the kth table, represents the total number of tables in the i-th dining area, Indicates the number of dining areas in the calculation period The number of occupancy of all tables, Indicates the calculation of meal time. It indicates the average cleaning time for each dining table. The longer the cleaning time, the lower the table turnover efficiency.

6. The campus comprehensive service management method based on digital twin according to claim 5 is characterized in that: S3 also includes: S34, extracting the customer action path length characteristics during the dining time period, and calculating the average customer action path length Zyr using the following formula: In the formula, represents the average action path length of customers in the i-th dining area, represents the total number of customers in the i-th dining area, represents the distance from the entrance to the selected table of the pth customer, represents the distance from the pth customer's table to the food pick-up point, represents the distance from the queue area of ​​the p-th customer to the dining table, It represents the distance from the table to the checkout point or exit for the pth customer.

7. The campus comprehensive service management method based on digital twin according to claim 6 is characterized in that: S3 also includes: S35, extract the number of times and duration of tableware use during the dining time period and the characteristics of the washing volume of the dishwasher, and calculate the load rate Ssy of the tableware equipment by the following formula: In the formula, represents the tableware equipment load rate of the i-th dining area, represents the number of tableware used for the yth time, represents the duration of using tableware for the yth time, represents the number of times tableware is used in the i-th dining area; represents the maximum cleaning volume of the dishwasher equipment in the i-th dining area; Indicates the operating hours of the dishwasher throughout the day.

8. The campus comprehensive service management method based on digital twin according to claim 7 is characterized in that: S3 also includes: S36: The food consumption rate Fcx of the i-th dining area i , table turnover coefficient Pds i 、Customer average action path length Zyr i And tableware equipment load rate Ssy i After dimensionless processing, the saturation evaluation index Bpzs of the i-th catering area is calculated by the following associated formula: i : In the formula, and are the food consumption rate Fcx of the i-th dining area i , table turnover coefficient Pds i 、Customer average action path length Zyr i And tableware equipment load rate Ssy i The weight coefficient of , , , , the specific value is set by the user. ; Expressed as the first correction constant.

9. The campus comprehensive service management method based on digital twin according to claim 8 is characterized in that S4 include: S41, setting a saturation threshold K, comparing the saturation evaluation index Bpzs of each dining area with the set saturation threshold K, and obtaining a saturation evaluation result, including: When the saturation evaluation index Bpzs of the i-th dining area i > saturation threshold K, it means that the catering area is in an overloaded state, triggering an imbalance warning instruction, and further imbalance analysis is required: When the saturation evaluation index Bpzs of the i-th dining area i ≤ saturation threshold K, it means that the catering area is in normal state and continues to be monitored, and no further imbalance analysis is required: S42. After receiving the imbalance warning instruction, the imbalance rate Shs of the i-th dining area is calculated by the following formula: i : S43, when 0<imbalance rate Shs of the i-th dining area i When ≤0.2, the system automatically triggers the first optimization instruction, including: Increase the frequency of food supply in the dining area by 5%-10%, increase the number of cleaning staff by 5%-8%, reduce table cleaning time, adjust the distance between the table and the food pick-up point, and reduce the path length by 5%-10%; increase the cleaning frequency by 5%-10% or add 1-2 dishwashers; When the imbalance rate Shs of the i-th dining area i When the value is greater than 0.2, the system automatically triggers the second optimization instruction, including: Increase the frequency of food supply in the dining area by 11%-20%, increase the number of cleaning staff by 9%-15%, reduce the time for table cleaning, adjust the distance between the table and the food pick-up point, and reduce the path length by 11%-15%; increase the cleaning frequency by 11%-20% or add 3-4 dishwashers.

10. A campus comprehensive service management system based on digital twins, applied to a campus comprehensive service management method based on digital twins as claimed in any one of claims 1 to 9, characterized in that: include: The canteen electronic distribution drawing module is used to create a virtual model of the architectural layout and equipment of each canteen based on 3D modeling technology, which is divided into several dining areas. Sensors are arranged in the dining areas to monitor the number of diners, tableware usage, food supply status and queuing time in real time in the dining areas. At the same time, it monitors and records the food inventory status and the usage of cleaning equipment to establish a real-time regional status collection; The regional usage analysis module is used to extract the characteristics of the number of diners, food supply status and queuing time in the regional real-time status set, preliminarily analyze the usage of each dining area, and obtain the usage rate Rct of each area; The preliminary allocation judgment module is used to preliminarily judge the allocation scheme that needs to be optimized in the current catering area according to the value of the utilization rate Rct; The digital twin model building module is used to build and train the digital twin model using convolutional neural network technology, and then construct an optimized catering service scheduling model; perform feature extraction after preprocessing and standardizing the regional real-time status set; obtain the food consumption rate Fcx, table turnover coefficient Pds, customer average action path length Zyr and tableware equipment load rate Ssy respectively, and after correlation, obtain the saturation evaluation index Bpzs; The resource optimization module is used to identify whether the current catering area is in an overloaded state and evaluate the resource allocation through the saturation evaluation index Bpzs; if the saturation evaluation index Bpzs exceeds the saturation threshold K, the imbalance rate Shs is calculated, and the current canteen’s personnel scheduling, food supply and equipment use are analyzed based on the imbalance rate. If not, the optimization instruction is triggered to adjust the catering resource allocation.

Images