Intelligent restaurant operation management system based on data analysis

Through an intelligent operation management system based on data analysis, using LSTM model and deep learning technology for real-time data analysis, the best service strategy and cooking suggestions are generated, and the shortcomings of existing systems in real-time data processing and service strategy prediction are solved, and the implementation of the Intelligent management and efficient service of restaurant operations.

CN118917645AInactive Publication Date: 2024-11-08BIG HEAD (GUANGZHOU) SOFTWARE TECH CO LTD

Patent Information

Application Number
CN202411414031.1
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-10-11
Publication Date
2024-11-08
Estimated Expiration
Not applicable · inactive patent

AI Technical Summary

Technical Problem

The existing smart restaurant operation and management system has shortcomings in real-time data processing, service strategy prediction, dish ordering and cooking suggestions, resulting in delayed decision-making and low service efficiency, unable to effectively respond to emergencies, and difficult to accurately reflect customer needs and restaurants. Operation status.

Method used

Provide an intelligent restaurant operation management system based on data analysis, including data collection and preprocessing module, service strategy prediction module, dish ordering and cooking suggestions module, service efficiency analysis and optimization module, and status analysis and early warning module, using the LSTM model Conduct real-time data analysis with deep learning technology, generate the best service strategies and cooking suggestions, optimize service efficiency, and respond to abnormal situations through dynamic early warnings.

Benefits of technology

It significantly improves the service efficiency and customer satisfaction of the restaurant, realizes intelligent management of restaurant operations, ensures the rationality of service strategies and operation stability, reduces customer waiting time, and improves the overall dining experience.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118917645A_ABST
    Figure CN118917645A_ABST
Patent Text Reader

Abstract

The invention discloses a restaurant intelligent operation management system based on data analysis, and relates to the technical field of intelligent catering operation management, and the system comprises the steps: collecting real-time operation data, and carrying out the preprocessing of the collected real-time operation data; inputting the preprocessed real-time operation data into the LSTM model, predicting a service priority score, and generating an optimal service strategy according to the service priority score; on the basis of the optimal service strategy, the order issuing sequence of the dishes is automatically adjusted, and cooking suggestions are generated according to the adjusted order issuing sequence; and executing the cooking suggestion, calculating the service efficiency, evaluating the service efficiency, and optimizing the service strategy according to an evaluation result. Through data collection and preprocessing, real-time operation data is comprehensively obtained, service requirements are predicted, resource allocation is optimized, kitchen efficiency is improved, customer waiting time is shortened, services are analyzed and improved in real time, stable operation is guaranteed, and service efficiency and customer satisfaction are remarkably improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent restaurant operation management, and in particular to an intelligent restaurant operation management system based on data analysis. Background Art

[0002] With the rapid development of information technology, data analysis is increasingly used in all walks of life, especially in the catering industry, where the complexity and variability of operation management have put forward higher requirements for data analysis technology. Traditional restaurant operation management systems often rely on manual experience to make decisions, which is not only inefficient, but also difficult to cope with the pressure of passenger flow during peak hours, resulting in reduced service quality and customer satisfaction. In recent years, with the development of big data analysis and artificial intelligence (AI) technology, more and more intelligent systems have been introduced into the daily operations of restaurants. These systems provide real-time decision support for restaurants by collecting and analyzing restaurant operation data, such as passenger flow, dish sales, customer satisfaction, etc. However, most of the existing intelligent systems focus on the optimization of a single aspect, such as customer relationship management or inventory control, and lack a comprehensive solution that can comprehensively consider all aspects of restaurant operations, including service process optimization, dish recommendation, customer experience improvement, etc.

[0003] Although existing intelligent operation management systems have improved the operational efficiency of restaurants to a certain extent, they still have shortcomings in real-time data processing, service strategy prediction, menu ordering and cooking suggestions. For example, many systems are unable to process and analyze large amounts of complex operational data in real time, resulting in delayed decision-making and inability to effectively respond to emergencies. In addition, existing systems often lack precise algorithm support when predicting service priorities and generating service strategies, making it difficult to accurately reflect the actual needs of customers and the operating status of restaurants. In terms of menu ordering and cooking suggestions, existing systems usually fail to fully consider the actual workflow of the kitchen and the personalized needs of customers, resulting in inflexible and inefficient dish preparation and serving processes. These problems limit the effectiveness of restaurant operation management systems and affect customers' overall dining experience. Summary of the invention

[0004] In view of the above existing problems, the present invention is proposed.

[0005] Therefore, the present invention provides a restaurant intelligent operation management system based on data analysis to solve the problems of the prior art in real-time data processing, accurate prediction of service strategies, personalized menu ordering, cooking suggestions and low restaurant operation efficiency.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions: The present invention provides a restaurant intelligent operation management system based on data analysis, comprising: Data collection and preprocessing module: used to collect real-time operation data and preprocess the collected real-time operation data; Service strategy prediction module: used to input pre-processed real-time operation data into the LSTM model, predict the service priority score, and generate the best service strategy based on the service priority score; Dishes ordering and cooking suggestion module: used to automatically adjust the ordering order of dishes based on the best service strategy, and generate cooking suggestions based on the adjusted ordering order; Service efficiency analysis and optimization module: used to execute cooking suggestions, calculate service efficiency, evaluate service efficiency, and optimize service strategies based on the evaluation results; Status analysis and early warning module: used to analyze the restaurant operation status based on real-time operation data and issue dynamic early warnings based on the analysis results.

[0007] As a preferred solution of the restaurant intelligent operation management system based on data analysis described in the present invention, the specific steps of collecting real-time operation data and preprocessing the collected real-time operation data are as follows: Real-time operation data is collected through infrared sensor detection, Wi-Fi probes and customer self-service terminals. The real-time operation data includes current table usage, customer flow statistics, average number of diners, average dining time, dish return rate, customer complaint rate, dish sales ranking and peak customer flow hours; The collected real-time operational data is subjected to outlier detection, missing value processing and data normalization.

[0008] As a preferred solution of the restaurant intelligent operation management system based on data analysis described in the present invention, the pre-processed real-time operation data is input into the LSTM model to predict the service priority score. The specific steps are as follows: The preprocessed real-time operation data is input into the LSTM model to predict the service priority score. The expression is: ; in, Score the service priority of table C at time t, is the demand frequency of the i-th service demand at time t, is the maximum demand frequency of all service demands at time t, is the demand frequency of the i-th service demand at the C-th table, is the maximum frequency of all service requests from table C. is the time weight of the i-th service demand, is the table weight of the i-th service demand; As a preferred solution of the restaurant intelligent operation management system based on data analysis described in the present invention, wherein: the optimal service strategy is generated according to the service priority score, and the specific steps are as follows: For all tables that need service, score them according to the table service priority The first sorting is done from the highest to the lowest service order; If there are multiple service priority scores for the table If the values ​​are equal, a second sorting is performed according to the service order from high to low number of diners; Generate the best service strategy according to the sorting results of the service order.

[0009] As a preferred solution of the restaurant intelligent operation management system based on data analysis described in the present invention, the specific steps of automatically adjusting the order of dishes based on the best service strategy are as follows: Based on the best service strategy and combined with the order preparation time and waiting time, the urgency of the dish order is calculated, and the expression is: ; in, is the urgency of the order, W is the order The preparation time, W is the order The waiting time, The best service strategy is generated according to the sorting results of the service order; For all unprocessed orders, the order urgency value The order of placing orders from high to low is sorted for the first time. If there are multiple orders, the order urgency is If the values ​​of are equal, the orders are sorted again according to the order of difficulty of making the dishes in the order from low to high; The system automatically adjusts the order of dishes based on the sorting results.

[0010] As a preferred solution of the restaurant intelligent operation management system based on data analysis of the present invention, the specific steps of generating cooking suggestions according to the adjusted order placement sequence are as follows: Based on the adjusted order of dishes, and combined with the kitchen's actual operating capabilities and optimal service strategies, provide specific cooking suggestions to kitchen staff, including the selection of priority dishes, the quantity of dishes to be prepared, and the estimated completion time.

[0011] As a preferred solution of the restaurant intelligent operation management system based on data analysis described in the present invention, the specific steps of executing cooking suggestions and calculating service efficiency are as follows: The central kitchen prepares dishes according to cooking suggestions, and the system updates the preparation status of the dishes. It marks unprepared dishes as to be prepared, and prepared dishes as to be served. After the dishes are confirmed to be served, they are marked as served. For dishes marked as served, the system records the actual completion time and compares it with the estimated completion time based on cooking suggestions to calculate the service efficiency. The expression is: ; Among them, E represents service efficiency, Indicates order The absolute deviation between the actual completion time and the estimated completion time, Indicates order The preparation time of , Ord represents the set of all orders.

[0012] As a preferred solution of the restaurant intelligent operation management system based on data analysis described in the present invention, the service efficiency is evaluated and the service strategy is optimized according to the evaluation results. The specific steps are as follows: Define a baseline threshold for service efficiency based on historical data and service goals; When E ≥ &, the service efficiency is considered good; When E<&, it is considered that the service efficiency needs to be improved; When service efficiency is good, maintain the current service strategy and regularly evaluate service efficiency indicators. When service efficiency needs to be improved, organize regular training to improve employees' professional skills and service awareness, review existing service processes, identify bottlenecks and optimize them, introduce performance appraisal and reward mechanisms, and motivate employees to improve work efficiency and service quality.

[0013] As a preferred solution of the restaurant intelligent operation management system based on data analysis described in the present invention, the restaurant operation status is analyzed according to the real-time operation data, and dynamic warning is performed according to the analysis results. The specific steps are as follows: The pre-processed real-time operation data is transmitted to the stream processing framework through Kafka Topic to analyze the restaurant operation status in real time, including the customer-side operation status, waiter-side operation status, kitchen operation status, and order-issuing equipment operation status; The customer side operation status includes: when it is monitored that the number of dishes ordered by the customer on the customer side does not match the number of diners and the bill has not been paid for a long time, the customer side is considered to be in an abnormal state; The waiter side operation status includes: when it is detected that dishes have not been served for a long time and tables have not been served for a long time, the waiter side is considered to be in an abnormal state; The back kitchen operation status includes: when it is monitored that dishes have not been prepared for a long time and the re-preparation rate of dishes is high, the back kitchen is considered to be in an abnormal state; The operation status of the order issuing device includes: when it is detected that the order issuing device fails to issue orders according to the rules, the order issuing device is considered to be in an abnormal state; The restaurant's operating status is summarized through the real-time data visualization tool Grafana to form a dynamic business view. When the restaurant has an abnormal operating status, the dynamic business view immediately issues an early warning and marks the abnormal location.

[0014] The beneficial effects of the present invention are as follows: the restaurant intelligent operation management system can comprehensively and accurately obtain real-time operation data through the data collection and preprocessing module, laying the foundation for optimizing service strategies and improving operational efficiency. The service strategy prediction module can predict future service needs, plan resources in advance, and ensure the rationality of the service strategy. The menu ordering and cooking suggestion modules make kitchen work more efficient and orderly, reduce customer waiting time, and improve service quality. The service efficiency analysis and optimization module helps managers understand the service status in real time and continuously improve service levels. The status analysis and early warning module enables managers to grasp the operating status in a timely manner and respond to abnormal situations, ensuring the stability and safety of restaurant operations. Finally, the system significantly improves the restaurant's service efficiency and customer satisfaction through intelligent analysis and dynamic adjustment, and realizes intelligent management of restaurant operations. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0016] Figure 1 This is a flow chart of the restaurant intelligent operation management system based on data analysis in Example 1.

[0017] Figure 2 This is a flow chart for automatically adjusting the order of dishes based on the best service strategy in Example 1. DETAILED DESCRIPTION

[0018] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the accompanying drawings.

[0019] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0020] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0021] Example 1, reference Figure 1 and Figure 2 , which is the first embodiment of the present invention, and provides a restaurant intelligent operation management system based on data analysis, comprising the following steps: Data collection and preprocessing module: used to collect real-time operation data and preprocess the collected real-time operation data.

[0022] Furthermore, real-time operational data is collected through infrared sensor detection, Wi-Fi probes and customer self-service terminals. The real-time operational data includes current table usage, customer flow statistics, average number of diners, average dining time, dish return rate, customer complaint rate, dish sales ranking and peak customer flow hours.

[0023] The collected real-time operational data is subjected to outlier detection, missing value processing and data normalization.

[0024] It should be noted that the customer self-service terminal refers to an interactive device that allows customers to complete operations such as ordering and payment by themselves.

[0025] Outlier detection is the process of identifying and removing data points that deviate from the normal range through statistical methods or machine learning algorithms, thereby reducing the impact of abnormal data on subsequent analysis results.

[0026] Missing value processing uses interpolation techniques such as mean filling, nearest neighbor interpolation, or predictive models to fill in the missing parts of the data to ensure that the data is complete to support more reliable analysis.

[0027] Data normalization is to scale the data to a specified range, such as the [0,1] interval, through linear transformation to eliminate the impact of dimension, so that data of different scales can be compared and analyzed under the same standard.

[0028] Service strategy prediction module: used to input preprocessed real-time operation data into the LSTM model, predict the service priority score, and generate the best service strategy based on the service priority score.

[0029] Furthermore, the LSTM model is constructed using the TensorFlow deep learning framework, and the parameters of the LSTM model are set, including the hidden layer size, time step, and batch size. For example, the hidden layer size is 128 units, the time step is 12 (assuming that data is collected every 60 minutes and the data of the past 12 hours is used), and the batch size is 32.

[0030] The loss function is defined as the mean square error (MSE) to quantify the difference between the predicted value and the true value, so as to optimize the model parameters and make the prediction results more accurate. The expression is: ; in, is the loss function used to measure the model parameters The difference between the predicted value and the true value, N is the number of samples, is the true value of the nth sample, i.e., the actual service demand, is the predicted value of the nth sample, that is, the service demand predicted by the model.

[0031] It should be noted that the sample refers to the specific observations in the restaurant operation data, each of which contains historical dining service data and current table food order information, etc.

[0032] The Adam optimizer is used for parameter update.

[0033] It should be noted that the process of using the Adam optimizer to update parameters is to dynamically adjust the learning rate of each parameter in each iteration based on the first-order moment estimate (moving average) and second-order moment estimate (variance of unbiased estimate) of the gradient, so as to update the model parameters more efficiently, speed up the training process and help the model converge to the optimal solution better. For example, when training the LSTM model, the Adam optimizer will adjust the learning rate based on the historical information of the current gradient, making the parameter update more robust and effectively reducing the value of the loss function even in the face of non-stationary objective functions.

[0034] The preprocessed real-time operation data is input into the LSTM model to predict the service priority score. The expression is: ; in, Score the service priority of table C at time t, is the demand frequency of the i-th service demand at time t, is the maximum demand frequency of all service demands at time t, is the demand frequency of the i-th service demand at the C-th table, is the maximum frequency of all service requests from table C. is the time weight of the i-th service demand, is the table weight of the i-th service demand; For all tables that need service, score them according to the table service priority The first sorting is done from high to low service order.

[0035] If there are multiple service priority scores for the table If the values ​​are equal, the second sorting is performed according to the service order from high to low number of diners. The expression is: ; in, is the priority score of the secondary sorting of table C, is the number of diners at the Cth table, and k is the coefficient that adjusts the impact of the number of diners.

[0036] Generate the best service strategy according to the sorting results of the service order.

[0037] It should be noted that this process starts with a score based on the service priority of the table at a specific point in time. All tables are sorted, and the higher the score, the higher the service priority; for those tables with the same service priority score, they are further sorted according to the number of diners at the table. Perform secondary sorting, adjust the sorting through a sigmoid function, and finally formulate the optimal service strategy based on the above sorting results.

[0038] It should also be noted that the service order is sorted from high to low according to the number of diners because tables with more diners usually require faster service responses to reduce customers' waiting time and improve the overall dining experience and table turnover efficiency.

[0039] Dishes ordering and cooking suggestion module: used to automatically adjust the ordering order of dishes based on the best service strategy, and generate cooking suggestions based on the adjusted ordering order; Furthermore, based on the best service strategy and combined with the order preparation time and waiting time, the urgency of the order is calculated as follows: ; in, is the urgency of the order, W is the order The preparation time, W is the order The waiting time, The best service strategy is generated according to the sorting results of the service order; For all unprocessed orders, the order urgency value The order of placing orders from high to low is sorted for the first time. If there are multiple orders, the order urgency is If the values ​​of are equal, the orders are sorted again according to the order of difficulty of making the dishes in the order from low to high; The system automatically adjusts the order of dishes according to the sorting results; It should be noted that the urgency sorting is chosen because it can reflect the urgency of the order, while the difficulty sorting of dishes ensures that when the urgency is the same, simple and quick dishes are prepared first to quickly relieve kitchen pressure and increase the speed of serving food. By calculating the urgency of dish orders and combining the actual operating capabilities of the kitchen, the system can automatically optimize the order of orders to ensure that the most urgent orders are processed first, thereby improving service efficiency and customer satisfaction.

[0040] Based on the adjusted order of dishes, combined with the actual operation capabilities and best service strategies of the kitchen, the system provides specific cooking suggestions to the kitchen staff, including the selection of priority dishes, the number of dishes to be prepared, and the estimated completion time. For example, based on the adjusted order of dishes, the system finds that the order for table A is the most urgent, so it recommends to the kitchen to prepare the dishes for table A first, and informs the kitchen staff to prepare the specific number of dishes required for the table, such as two servings of beef fried rice and one serving of sweet and sour pork ribs; at the same time, the system also provides an estimated completion time, such as it is expected that these dishes will be prepared within 15 minutes, to guide the kitchen to complete the cooking tasks efficiently and orderly.

[0041] Service efficiency analysis and optimization module: used to execute cooking suggestions, calculate service efficiency, evaluate service efficiency, and optimize service strategies based on the evaluation results.

[0042] Furthermore, the central kitchen prepares dishes according to cooking suggestions, and the system updates the preparation status of the dishes at the same time, marking unprepared dishes as to be prepared, prepared dishes as to be served, and dishes as served after confirmation of being served; for example, when the kitchen receives instructions from the system, it starts preparing dishes for table A; during the preparation process, dishes that have not yet been prepared will be marked as "to be prepared"; once the sweet and sour spare ribs are finished, their status will be updated to "to be served"; when the waiter delivers the sweet and sour spare ribs to table A and confirms that the customer has started to enjoy it, the system finally updates the status of the dish to "served". This series of status changes are achieved through real-time tracking and updating of the system.

[0043] For dishes marked as served, the system records the actual completion time and compares it with the estimated completion time based on cooking suggestions to calculate the service efficiency. The expression is: ; Among them, E represents service efficiency, Indicates order The absolute deviation between the actual completion time and the estimated completion time, Indicates order Preparation time, Ord represents the set of all orders; It should be noted that ;in, It is an order The actual completion time. This refers to the time required for the dish to be actually prepared and served after the customer places the order. It is an order The estimated completion time of the dish. This is the system's pre-estimated completion time of the dish based on various factors (such as the efficiency of the kitchen, the complexity of the dish, etc.); Based on historical data and service goals (improving the restaurant's overall service efficiency and customer satisfaction, ensuring a smooth and efficient service process), define a service efficiency benchmark threshold.

[0044] When E≥&, the service efficiency is considered to be good; when the service efficiency is good, maintain the current service strategy and evaluate the service efficiency indicators regularly (such as weekly or monthly) to ensure that they remain above the benchmark threshold.

[0045] When E<&, it is considered that the service efficiency needs to be improved; when the service efficiency needs to be improved, organize regular training to improve employees' professional skills and service awareness, and ensure that they are familiar with the latest service processes and technologies; review the existing service processes, find out the bottlenecks and optimize them, such as simplifying the ordering process, improving internal collaboration in the kitchen, etc.; introduce performance appraisal and reward mechanisms to motivate employees to improve work efficiency and service quality.

[0046] It should also be noted that the specific skills training is: a half-day training is organized every month, focusing on the latest self-service ordering system. The training content includes the system's operating procedures, solutions to common problems, and how to guide customers to use the self-service ordering machine. Through practical operation exercises, it ensures that every waiter can use the new system proficiently to improve ordering efficiency and service quality.

[0047] Reviewing existing service processes specifically means: Through data analysis, identifying reasons why efficiency needs to be improved, such as delayed order processing or inaccurate information entry, and optimizing relevant processes in a targeted manner.

[0048] Performance appraisal and rewards are as follows: monthly performance appraisals are conducted on waiters, and they are evaluated based on indicators such as customer satisfaction scores, speed and accuracy of completing orders, etc. Bonuses are given to outstanding employees and they are publicly praised at employee meetings. For example, for waiters who receive the highest customer satisfaction scores for three consecutive months, additional bonuses are given and they are awarded the title of "Best Waiter of the Month".

[0049] Status analysis and early warning module: used to analyze the restaurant operation status based on real-time operation data and issue dynamic early warnings based on the analysis results.

[0050] Furthermore, the pre-processed real-time operation data is transmitted to the stream processing framework through Kafka Topic to analyze the restaurant operation status in real time, including the customer-side operation status, waiter-side operation status, back kitchen operation status, and order-issuing equipment operation status; The customer-side operating status includes: when it is monitored that the number of dishes ordered by customers does not match the number of diners (for example, two guests ordered ten dishes) and the checkout has not been paid for a long time, the customer-side is considered to be in an abnormal state; for example, if a table of customers has not paid after the average checkout time (for example, more than 30 minutes) after the end of the meal, the system will monitor the checkout time data in real time and find that the checkout time of the table is abnormally extended, thereby determining that the customer-side is in an abnormal state.

[0051] The operational status of the waiter side includes: when it is monitored that the dishes have not been served for a long time and the table has not been served for a long time, the waiter side is considered to be in an abnormal state; assuming that after a table of customers places an order, the dishes stay in the kitchen for more than the set reasonable time (for example, more than 30 minutes), the system monitors the kitchen's serving time data in real time and finds that the serving time of the order is abnormally extended, thus determining that the waiter side is in an abnormal state.

[0052] The operating status of the back kitchen includes: when it is monitored that dishes have not been completed for a long time and the dish re-making rate is high, the back kitchen is considered to be in an abnormal state; assuming that the time from the ordering to the completion of a dish exceeds the set reasonable time (for example, more than 20 minutes), the system monitors the kitchen's production time data in real time and finds that the production time of the dish is abnormally extended, thus determining that the back kitchen is in an abnormal state.

[0053] The operating status of the order issuing equipment includes: when it is monitored that the order issuing equipment does not issue orders according to the rules, the order issuing equipment is considered to be in an abnormal state; assuming that after a table of customers places an order, the time the dishes stay in the kitchen exceeds the set reasonable time (for example, more than 30 minutes), the system monitors the kitchen's meal delivery time data in real time and finds that the meal delivery time of the order is abnormally extended, thereby determining that the waiter's end is in an abnormal state.

[0054] The real-time data visualization tool Grafana is used to summarize the restaurant's operating status and form a dynamic business view. When the restaurant has an abnormal operating status, the dynamic business view immediately issues an alert and marks the abnormal location. Assuming that the time from ordering to the completion of a dish exceeds the set reasonable time (for example, more than 20 minutes), the system monitors the kitchen's production time data in real time and finds that the preparation time of the dish is abnormally extended, thus determining that the kitchen is abnormal.

[0055] It should be noted that the normal location refers to the specific link or equipment where the abnormality occurs during the restaurant operation, such as a table, a waiter, a workstation in the kitchen, or the specific fault point of the order-issuing equipment.

[0056] In summary, the restaurant intelligent operation management system of the present invention can comprehensively and accurately obtain real-time operation data through the data collection and preprocessing module, laying the foundation for optimizing service strategies and improving operational efficiency. The service strategy prediction module can predict future service needs, plan resources in advance, and ensure the rationality of the service strategy. The menu ordering and cooking suggestion module makes kitchen work more efficient and orderly, reduces customer waiting time, and improves service quality. The service efficiency analysis and optimization module helps managers understand the service status in real time and continuously improve the service level. The status analysis and early warning module enables managers to grasp the operating status in a timely manner and respond to abnormal situations, ensuring the stability and safety of restaurant operations. Finally, the system significantly improves the service efficiency and customer satisfaction of the restaurant through intelligent analysis and dynamic adjustment, and realizes the intelligent management of restaurant operations.

[0057] Example 2, referring to Table 1, is the second example of the present invention. To further verify the technical solution of the present invention, experimental simulation data of a restaurant intelligent operation management system based on data analysis is provided.

[0058] This experiment was conducted in a large chain restaurant located in the city center. The restaurant has an average daily customer flow of about 500 people and is open from 10 am to 10 pm. The experiment lasted for one week, covering both weekdays and weekends. Before the experiment, the necessary hardware facilities, including infrared sensors, Wi-Fi probes, and customer self-service terminals, were installed and debugged. These devices were used to collect restaurant operation data in real time, such as table usage, customer flow statistics, average number of diners, average dining time, return rate, customer complaint rate, dish sales ranking, and peak customer flow hours.

[0059] First, the experiment conducted a week of data collection in a large restaurant chain, covering different weekdays and weekends from Monday to Sunday to fully reflect daily operations.

[0060] Secondly, by deploying infrared sensors, Wi-Fi probes, and self-service ordering terminals, we collected operational data such as customer flow, dining time, and order information within the restaurant in real time, and performed data cleaning and standardization preprocessing.

[0061] Next, the long short-term memory (LSTM) model was used to analyze the collected data to predict the service priority score for each time period. Based on the score, the optimal service strategy for different customer groups was generated, optimizing the order of dishes and cooking time schedule in the kitchen.

[0062] Finally, the system not only continuously monitors and records key indicators in the entire service process, such as serving speed and customer flow, but also verifies the effectiveness and advantages of the method of the present invention through in-depth data analysis, thereby improving service efficiency.

[0063] The specific operating data is shown in Table 1 below: Table 1 Operational data statistics

[0064] Through the data analysis of the above table, it can be clearly seen that in different time periods, the method of the present invention shows significant advantages in improving service efficiency. Compared with the traditional management model, the present invention significantly improves the service response speed and service quality by introducing an intelligent operation management system based on data analysis. For example, during the Sunday dinner period with a large passenger flow, although the number of customers reached 280 and the average number of diners was 3.5, the method of the present invention was still able to improve the service efficiency to 0.92, which is much higher than the average level under the traditional management method. This shows that even during peak hours, the intelligent system can effectively optimize the service process, reduce customer waiting time, and improve the overall dining experience.

[0065] The data analysis-based restaurant intelligent operation and management system of the present invention can not only significantly improve service efficiency, but also optimize resource allocation while ensuring customer satisfaction. Especially during periods with large customer flow, such as Sunday dinner time, the system can effectively shorten the average dining time and reduce the return rate of dishes, which reflects the strong advantages and excellent performance of the present invention in dealing with peak hours.

[0066] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A restaurant intelligent operation management system based on data analysis, characterized by: include, Data collection and preprocessing module: used to collect real-time operation data and preprocess the collected real-time operation data; Service strategy prediction module: used to input pre-processed real-time operation data into the LSTM model, predict the service priority score, and generate the best service strategy based on the service priority score; Dishes ordering and cooking suggestion module: used to automatically adjust the ordering order of dishes based on the best service strategy, and generate cooking suggestions based on the adjusted ordering order; Service efficiency analysis and optimization module: used to execute cooking suggestions, calculate service efficiency, evaluate service efficiency, and optimize service strategies based on the evaluation results; Status analysis and early warning module: used to analyze the restaurant's operating status based on real-time operating data and issue dynamic early warnings based on the analysis results.

2. The restaurant intelligent operation management system based on data analysis as claimed in claim 1, characterized in that: The real-time operation data is collected and pre-processed, and the specific steps are as follows: Real-time operation data is collected through infrared sensor detection, Wi-Fi probes and customer self-service terminals. The real-time operation data includes current table usage, customer flow statistics, average number of diners, average dining time, dish return rate, customer complaint rate, dish sales ranking and peak customer flow hours; The collected real-time operational data is subjected to outlier detection, missing value processing and data normalization.

3. The restaurant intelligent operation management system based on data analysis as claimed in claim 2, characterized in that: The preprocessed real-time operation data is input into the LSTM model to predict the service priority score. The specific steps are as follows: The preprocessed real-time operation data is input into the LSTM model to predict the service priority score. The expression is: ;in, Score the service priority of table C at time t, is the demand frequency of the i-th service demand at time t, is the maximum demand frequency of all service demands at time t, is the demand frequency of the i-th service demand at the C-th table, is the maximum frequency of all service requests from table C. is the time weight of the i-th service demand, is the table weight of the i-th service demand.

4. The restaurant intelligent operation management system based on data analysis as claimed in claim 3, characterized in that: The optimal service strategy is generated according to the service priority score. The specific steps are as follows: For all tables that need service, score them according to the table service priority The first sorting is done from the highest to the lowest service order; If there are multiple service priority scores for the table If the values ​​are equal, a second sorting is performed according to the service order from high to low number of diners; Generate the best service strategy according to the sorting results of the service order.

5. The restaurant intelligent operation management system based on data analysis as claimed in claim 4, characterized in that: The specific steps of automatically adjusting the order of dishes based on the best service strategy are as follows: Based on the best service strategy and combined with the order preparation time and waiting time, the urgency of the dish order is calculated, and the expression is: ;in, is the urgency of the order, W is the order The preparation time, W is the order The waiting time, The best service strategy is generated according to the sorting results of the service order; For all unprocessed orders, the order urgency value The order of placing orders from high to low is sorted for the first time. If there are multiple orders, the order urgency is If the values ​​of are equal, the orders are sorted again according to the order of difficulty of making the dishes in the order from low to high; The system automatically adjusts the order of dishes based on the sorting results.

6. The restaurant intelligent operation management system based on data analysis as claimed in claim 5, characterized in that: The cooking suggestion is generated according to the adjusted order order, and the specific steps are as follows: Based on the adjusted order of dishes, and combined with the kitchen's actual operating capabilities and optimal service strategies, provide specific cooking suggestions to kitchen staff, including the selection of priority dishes, the quantity of dishes to be prepared, and the estimated completion time.

7. The restaurant intelligent operation management system based on data analysis as claimed in claim 6, characterized in that: The specific steps of executing cooking suggestions and calculating service efficiency are as follows: The central kitchen prepares dishes according to cooking suggestions, and the system updates the preparation status of the dishes. It marks unprepared dishes as to be prepared, and prepared dishes as to be served. After the dishes are confirmed to be served, they are marked as served. For dishes marked as served, the system records the actual completion time and compares it with the estimated completion time based on cooking suggestions to calculate the service efficiency. The expression is: ; Where E represents service efficiency, Indicates order The absolute deviation between the actual completion time and the estimated completion time, Indicates order The preparation time of , Ord represents the set of all orders.

8. The restaurant intelligent operation management system based on data analysis as claimed in claim 7, characterized in that: The service efficiency is evaluated and the service strategy is optimized according to the evaluation results. The specific steps are as follows: Define a baseline threshold for service efficiency based on historical data and service goals; When E ≥ &, the service efficiency is considered good; When E<&, it is considered that the service efficiency needs to be improved; When service efficiency is good, maintain the current service strategy and regularly evaluate service efficiency indicators; When service efficiency needs to be improved, organize regular training to enhance employees' professional skills and service awareness, review existing service processes, identify bottlenecks and optimize them, introduce performance appraisal and reward mechanisms, and motivate employees to improve work efficiency and service quality.

9. The restaurant intelligent operation management system based on data analysis as claimed in claim 8, characterized in that: The restaurant operation status is analyzed based on real-time operation data, and dynamic warning is issued based on the analysis results. The specific steps are as follows: The pre-processed real-time operation data is transmitted to the stream processing framework through Kafka Topic to analyze the restaurant operation status in real time, including the customer-side operation status, waiter-side operation status, kitchen operation status, and order-issuing equipment operation status; The customer side operation status includes: when it is monitored that the number of dishes ordered by the customer on the customer side does not match the number of diners and the bill has not been paid for a long time, the customer side is considered to be in an abnormal state; The waiter side operation status includes: when it is detected that dishes have not been served for a long time and tables have not been served for a long time, the waiter side is considered to be in an abnormal state; The back kitchen operation status includes: when it is monitored that dishes have not been prepared for a long time and the re-preparation rate of dishes is high, the back kitchen is considered to be in an abnormal state; The operation status of the order issuing device includes: when it is detected that the order issuing device fails to issue orders according to the rules, the order issuing device is considered to be in an abnormal state; The restaurant's operating status is summarized through the real-time data visualization tool Grafana to form a dynamic business view. When the restaurant has an abnormal operating status, the dynamic business view immediately issues an early warning and marks the abnormal location.

Citation Information

Patent Citations

  • A restaurant order placing sequence optimization allocation method and a management system

    CN109934383A

  • Intelligent catering kitchen order management system and order arrangement method thereof

    CN112116499A

  • Post-kitchen dish dividing and order distributing system

    CN115082259A

Cited By

  • Restaurant meal delivery control system and control method thereof

    CN120562754A

  • Order ordering control system for unmanned intelligent kitchen

    CN120782523A

  • Intelligent hotel management method and system based on digitization

    CN120996502A

  • Dynamic zoning canteen people flow density monitoring method and system

    CN121329222A