A smart noodle restaurant unmanned back kitchen scheduling method and system

Abstract

The application provides a smart noodle shop unmanned back kitchen scheduling method and system. The method comprises the following steps: obtaining effective increase data through classification and calculation of historical order data in a preset time period of the noodle shop and order data in the same period, obtaining item influence weight data according to the increase influence data, obtaining correction increase data through processing, obtaining comprehensive increase data according to the correction increase data and effective increase data corresponding to the prediction date, and then obtaining prediction order data and raw material procurement data; thereby, through the calculation of the effective increase data, the correction increase data and the comprehensive increase data, the accurate prediction of the order data and the automatic inventory scheduling of the unmanned back kitchen are realized.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of intelligent management of catering, in particular to a smart noodle restaurant unmanned kitchen scheduling method and system. BACKGROUND

[0002] Under the intelligent development trend of the catering industry, the traditional noodle restaurant kitchen is facing many challenges. On the one hand, manual operation has the problems of low efficiency and high labor cost. For example, during peak hours, order sequence confusion and order backlog may occur, resulting in long waiting time for customers. On the other hand, manual operation cannot guarantee the standardized production of each meal, and the cooking time may deviate, affecting the quality and taste of the meal. Although some noodle restaurants have introduced automated equipment, due to the lack of effective scheduling management methods, the equipment cannot be fully utilized, and the unmanned and efficient operation of the kitchen cannot be realized. In the prior art, there is also a lack of integrated solutions for noodle restaurant kitchen order processing, matching user health conditions, and ingredient management, which cannot meet the needs of modern consumers for efficient, stable, and personalized catering services.

[0003] In view of the above problems, there is an urgent need for effective technical solutions. SUMMARY

[0004] The purpose of the present application is to provide a smart noodle restaurant unmanned kitchen scheduling method and system, which can realize accurate prediction of order data and automatic inventory scheduling of unmanned kitchen through calculation of effective growth data, corrected growth data, and comprehensive growth data.

[0005] The present application also provides a smart noodle restaurant unmanned kitchen scheduling method, comprising the following steps:

[0006] Obtain historical order data and same-period order data in a preset time period of the noodle restaurant, and calculate the effective growth data after classification;

[0007] Obtain the growth influence data of the predicted date of the noodle restaurant, respectively query the preset growth influence weight data list to obtain the sub-item influence weight data, and calculate the corrected growth data according to the sub-item influence weight data;

[0008] Calculate the comprehensive growth data according to the corrected growth data and the effective growth data corresponding to the predicted date, and calculate the predicted order data and the corresponding raw material purchase data according to the comprehensive growth data.

[0009] Optionally, in the smart noodle restaurant unmanned kitchen scheduling method described in the present application, the historical order data and same-period order data in a preset time period of the noodle restaurant are obtained, and the effective growth data is calculated after classification, which specifically includes:

[0010] Obtain historical order data of the noodle restaurant in a preset time period, and classify to obtain historical stage order data, including historical working day order data and historical rest day order data;

[0011] Obtain order data of the noodle restaurant in the same period, and classify to obtain same period stage order data, including same period working day order data and same period rest day order data;

[0012] According to the historical stage order data and the same period stage order data, the increase data is calculated and obtained, and the arithmetic mean is calculated to obtain effective increase data, including working day effective increase data and rest day effective increase data.

[0013] Optionally, in the intelligent noodle restaurant unmanned kitchen scheduling method described in the present application, the increase influence data of the predicted date of the noodle restaurant is obtained, the preset increase influence weight data list is inquired to obtain item influence weight data, and the corrected increase data is calculated according to the item influence weight data, specifically including:

[0014] Obtain the increase influence data of the predicted date of the noodle restaurant, including weather temperature change data, activity influence data and member change data;

[0015] According to the increase influence data, the preset increase influence weight data list is inquired to obtain item influence weight data, including temperature change weight data, activity influence weight data and member change weight data;

[0016] According to the item influence weight data, the corrected increase data is calculated.

[0017] Optionally, in the intelligent noodle restaurant unmanned kitchen scheduling method described in the present application, the comprehensive increase data is calculated according to the corrected increase data and the effective increase data corresponding to the predicted date, and the predicted order data and the corresponding raw material preparation data are calculated according to the comprehensive increase data, specifically including:

[0018] Obtain the type data of the predicted date, including working day data or rest day data;

[0019] If the type data is working day data, the comprehensive increase data is calculated according to the corrected increase data and the working day effective increase data;

[0020] If the type data is rest day data, the comprehensive increase data is calculated according to the corrected increase data and the rest day effective increase data;

[0021] According to the comprehensive increase data, the predicted order data and the corresponding raw material preparation data are calculated.

[0022] Optionally, in the intelligent noodle restaurant unmanned kitchen scheduling method described in the present application, it further includes:

[0023] obtain current order progress data and historical order progress data corresponding to the current time progress;

[0024] divide the current order progress data by the historical order progress data to obtain a relative order progress index;

[0025] compare the relative order progress index with a preset order status evaluation threshold to obtain an order progress status;

[0026] extract a first threshold and a second threshold according to the preset order status evaluation threshold, and the first threshold is greater than the second threshold;

[0027] if the relative order progress index is greater than the first threshold, the order progress status is an advanced state, and a raw material replenishment calculation program is started.

[0028] Optionally, in the intelligent noodle shop unmanned kitchen dispatching method described in the present application, further comprising:

[0029] obtain channel mode data of the customer order, and query a preset channel mode weight data list to obtain channel weight data;

[0030] obtain order condition data, including predicted delivery time, order complexity data, and order time sequence weight;

[0031] weight process the channel weight data, the order condition data, and the current time data to obtain order priority data;

[0032] sort the corresponding orders in descending order according to the order priority data to generate an order sequence queue.

[0033] Optionally, in the intelligent noodle shop unmanned kitchen dispatching method described in the present application, further comprising:

[0034] obtain historical noodle cooking data of the noodle shop, including a noodle taste category, a total cooking time data corresponding to each taste category, a stage heating time data, and a stage heating temperature data;

[0035] train a noodle taste heating database according to the historical noodle cooking data;

[0036] obtain noodle taste requirement data of the customer, and query the noodle taste heating database to obtain noodle stage heating parameters;

[0037] perform noodle cooking operation according to the noodle stage heating parameters.

[0038] In a second aspect, the present application provides a smart noodle shop unmanned back kitchen scheduling system, which comprises a memory and a processor, the memory comprising a smart noodle shop unmanned back kitchen scheduling method program, the smart noodle shop unmanned back kitchen scheduling method program being executed by the processor to implement the following steps:

[0039] Obtain historical order data in a preset time period of the noodle shop and order data of the same period, classify and calculate to obtain effective amplitude data;

[0040] Obtain amplitude influence data of the predicted date of the noodle shop, respectively query the preset amplitude influence weight data list to obtain item influence weight data, and calculate the corrected amplitude data according to the item influence weight data;

[0041] According to the corrected amplitude data and the effective amplitude data corresponding to the predicted date, the comprehensive amplitude data is calculated to obtain the predicted order data and the corresponding raw material data.

[0042] Optionally, in the smart noodle shop unmanned back kitchen scheduling system described in the present application, the historical order data in a preset time period of the noodle shop and the order data of the same period are obtained, classified and calculated to obtain effective amplitude data, which specifically comprises:

[0043] Obtain historical order data in a preset time period of the noodle shop, and classify to obtain historical stage order data, including historical working day order data and historical rest day order data;

[0044] Obtain order data of the same period of the noodle shop, and classify to obtain same period stage order data, including same period working day order data and same period rest day order data;

[0045] According to the historical stage order data and the same period stage order data, the amplitude data is calculated, and the arithmetic mean is obtained to obtain the effective amplitude data, including working day effective amplitude data and rest day effective amplitude data.

[0046] As can be seen from the above, the smart noodle shop unmanned back kitchen scheduling method and system provided by the present application. The method classifies and calculates the historical order data in a preset time period of the noodle shop and the order data of the same period to obtain effective amplitude data, queries the item influence weight data according to the amplitude influence data, processes to obtain corrected amplitude data, calculates the comprehensive amplitude data according to the corrected amplitude data and the effective amplitude data corresponding to the predicted date, and then obtains the predicted order data and the raw material data. Thus, through the calculation of the effective amplitude data, the corrected amplitude data and the comprehensive amplitude data, the precise prediction of the order data and the automatic inventory scheduling of the unmanned back kitchen are realized.

[0047] Other features and advantages of the present application will be set forth in the following specification, and in part will be apparent from the description, or can be learned by practice of the application. The objects and other advantages of the present application will be realized and attained by the structure particularly pointed out in the written description and claims hereof as well as the appended drawings. BRIEF DESCRIPTION OF DRAWINGS

[0048] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following will briefly introduce the drawings needed to be used in the embodiments of the present application. It should be understood that the following drawings only show some embodiments of the present application, and therefore should not be considered as limiting the scope. For those skilled in the art, other related drawings can also be obtained without creative labor on the basis of these drawings.

[0049] Figure 1 A flow chart of a smart noodle restaurant unmanned back kitchen scheduling method provided by the embodiments of the present application;

[0050] Figure 2 A flow chart of obtaining effective amplitude data of a smart noodle restaurant unmanned back kitchen scheduling method provided by the embodiments of the present application;

[0051] Figure 3 A flow chart of obtaining modified amplitude data of a smart noodle restaurant unmanned back kitchen scheduling method provided by the embodiments of the present application;

[0052] Figure 4 A flow chart of obtaining predicted order data and corresponding raw material procurement data of a smart noodle restaurant unmanned back kitchen scheduling method provided by the embodiments of the present application. DETAILED DESCRIPTION

[0053] The technical solutions in the embodiments of the present application will be described clearly and completely in the following with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only some of the embodiments of the present application, but not all the embodiments. The components of the embodiments of the present application described and shown in the drawings can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the claimed present application, but only represents selected embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of the present application.

[0054] It should be noted that: similar reference numerals and letters represent similar items in the following drawings, therefore, once an item is defined in one drawing, it does not need to be further defined and explained in the subsequent drawings. Meanwhile, in the description of the present application, the terms "first", "second", etc. are only used to distinguish the description, and cannot be understood as indicating or implying relative importance.

[0055] Please refer to Figure 1 , Figure 1 is a flowchart of a smart noodle shop unmanned kitchen scheduling method in some embodiments of the present application. The smart noodle shop unmanned kitchen scheduling method is used in terminal equipment such as computers, mobile phones, etc. The smart noodle shop unmanned kitchen scheduling method includes the following steps:

[0056] S11, obtain historical order data in a preset time period of a noodle shop and contemporaneous order data, classify and calculate to obtain effective amplitude data;

[0057] S12, obtain amplitude influence data of a predicted date of the noodle shop, respectively query a preset amplitude influence weight data list to obtain item influence weight data, and calculate to obtain corrected amplitude data according to the item influence weight data;

[0058] S13, calculate to obtain comprehensive amplitude data according to the corrected amplitude data and the effective amplitude data corresponding to the predicted date, and calculate to obtain predicted order data and corresponding raw material procurement data according to the comprehensive amplitude data.

[0059] It should be noted that the stable operation of the noodle shop cannot be separated from the preparation of the kitchen materials, and the preparation of the materials benefits from the accurate prediction of the order, because only accurate prediction of the order can better know the quantity of the material preparation, so as to guarantee normal operation and avoid waste. The operation of the entity noodle shop is relatively stable, and the order quantity in the past has good reference significance, so the historical order data in a preset time period of a noodle shop and the contemporaneous order data are obtained, and the effective amplitude data corresponding to the categories is respectively obtained after classification in view of the great influence of rest days and working days on the order quantity. The noodle shop order is also affected by some external factors, called amplitude image data, the item influence weight data is obtained by querying the preset amplitude influence weight data list according to the amplitude influence data, so as to calculate the corrected amplitude data according to the item influence weight data, calculate the comprehensive amplitude data according to the corrected amplitude data and the effective amplitude data corresponding to the predicted date, and finally obtain the predicted order data and the corresponding raw material procurement data.

[0060] Please refer to Figure 2 , Figure 2 is a flowchart of a smart noodle shop unmanned kitchen scheduling method provided by an embodiment of the present application. According to the embodiment of the present application, the historical order data in a preset time period of a noodle shop and the contemporaneous order data are obtained, and the effective amplitude data is calculated after classification, which specifically includes:

[0061] S21, obtain historical order data in a preset time period of a noodle shop, and classify to obtain historical stage order data, including historical working day order data and historical rest day order data;

[0062] S22, obtain the order data of the same period of the noodle restaurant, and classify to obtain the same period stage order data, including the same period working day order data and the same period holiday order data;

[0063] S23, calculate the increase data according to the historical stage order data and the same period stage order data, and obtain the effective increase data by taking the arithmetic mean, including the working day effective increase data and the holiday effective increase data.

[0064] It should be noted that the preset time period can be customized according to user demand; in the catering industry, the passenger flow of working days and holidays changes greatly, for example, the noodle restaurant around the business office building, the meal quantity of working days is obviously greater than that of holidays, therefore, in order to realize more accurate prediction, the orders need to be classified according to working days and holidays; the historical stage order data refers to the order quantity data of the historical preset time period, the historical working day order data and the historical holiday order data respectively refer to the daily order quantity of the historical working day and the daily order quantity of the historical holiday in the preset time period; the same period working day order data and the same period holiday order data respectively refer to the daily order data of the same period working day and the daily order data of the same period holiday in the preset time period; taking the calculation of the working day effective increase data as an example, the calculation process is to subtract the historical working day order data from the same period working day order data to obtain the working day order growth data, then divide the working day order growth data by the historical working day order data to obtain the increase data, and take the arithmetic mean of the increase data of the working day in the preset time period to obtain the working day effective increase data, and the holiday effective increase data can be calculated in the same way; in this embodiment, the preset time period is set to 3 weeks, the order data of the same period refers to the daily order quantity data of the previous 3 weeks, and the historical order data refers to the daily order quantity data of the previous 3 weeks.

[0065] Please refer to Figure 3 , Figure 3 is a flowchart of a method for obtaining modified increase data of a smart noodle restaurant unmanned kitchen dispatching provided by the embodiment of the application. According to the embodiment of the application, the increase influence data of the prediction date of the noodle restaurant is obtained, the preset increase influence weight data list is queried to obtain the sub-item influence weight data, the modified increase data is calculated according to the sub-item influence weight data, and specifically includes:

[0066] S31, obtain the increase influence data of the prediction date of the noodle restaurant, including the temperature change data, the activity influence data and the member change data;

[0067] S32, obtain the sub-item influence weight data according to the increase influence data and the preset increase influence weight data list, including the temperature change weight data, the activity influence weight data and the member change weight data;

[0068] S33. Calculate the corrected increase data based on the weighted data of each component.

[0069] It should be noted that, based on historical data analysis, the noodle shop's customer traffic is also affected by some external and internal factors, including weather and temperature changes, promotional activities, and the number of members. Weather and temperature change data refers to the change between the predicted temperature and the temperature of the day before the prediction date; activity impact data refers to the type of activity held, such as a buy-one-get-one-half-price offer or a 20% discount, with different discount levels having different amplification effects; member change data refers to the change between the predicted number of members and the average number of members during the same period. Temperature change weight data, activity impact weight data, and member change weight data are obtained by querying a preset amplification impact weight data list based on weather and temperature change data, activity impact data, and member change data. This preset amplification impact weight data list is trained based on historical data and can retrieve a list of corresponding sub-item impact weight data based on known weather and temperature change data, activity impact data, and member change data. In this embodiment, a 5°C temperature drop corresponds to a 6% temperature change weight data, and a buy-one-get-one-half-price offer corresponds to a 13% activity impact weight data. The corrected amplification data is the sum of the temperature change weight data, activity impact weight data, and member change weight data.

[0070] Please refer to Figure 4 , Figure 4 This is a flowchart illustrating the process of obtaining predicted order data and corresponding raw material purchase data in a smart noodle restaurant unmanned kitchen scheduling method provided in this application embodiment. The step of calculating comprehensive growth data based on corrected growth data and effective growth data corresponding to the predicted date, and then calculating predicted order data and corresponding raw material purchase data based on the comprehensive growth data, specifically includes:

[0071] S41. Obtain the type data for the forecast date, including weekday data or rest day data;

[0072] S42. If the data of the aforementioned type is working day data, then the comprehensive increase data is calculated based on the corrected increase data and the effective increase data of working days.

[0073] S43. If the data of the type is rest day data, then the comprehensive increase data is calculated based on the corrected increase data and the effective increase data of rest days.

[0074] S44. Calculate the predicted order data and the corresponding raw material purchase data based on the comprehensive increase data.

[0075] It should be noted that selecting the appropriate effective growth rate data based on the type of forecast date is crucial for accurately reflecting the overall growth rate. The formula for calculating the overall growth rate is as follows:

[0076] The comprehensive increase data = the effective increase data * (1 + the correction increase data);

[0077] If the type data is working day data, the comprehensive increase data is multiplied by the average order value of working days in the same period to obtain predicted order data;

[0078] If the type data is holiday data, the comprehensive increase data is multiplied by the average order value of holidays in the same period to obtain predicted order data;

[0079] According to the predicted order data, a raw material purchase data is obtained in combination with a preset order material preparation relationship table, and the preset order material preparation relationship table is obtained according to past historical operation experience.

[0080] According to the embodiment of the present application, the method further comprises:

[0081] Obtaining current order progress data and historical order progress data corresponding to the current time progress;

[0082] Dividing the current order progress data by the historical order progress data to obtain a relative order progress index;

[0083] Comparing the relative order progress index with a preset order state evaluation threshold to obtain an order progress state;

[0084] According to the preset order state evaluation threshold, a first threshold and a second threshold are extracted, and the first threshold is greater than the second threshold;

[0085] If the relative order progress index is greater than the first threshold, the order progress state is an advanced state, and a raw material supplement calculation program is started.

[0086] It should be noted that the working time of the daily noodle restaurant is limited, the current time progress is the length of the current working time divided by the total working time, the historical order progress data refers to the proportion of the number of orders sold to the total number of orders when the current time progress is consistent with the time progress in recent days, and the current order progress data refers to the proportion of the number of orders sold to the predicted order number; if the relative order progress index is greater than or equal to the second threshold and less than or equal to the first threshold, the order progress state is a normal state, and the noodle restaurant is normally operated; if the relative order progress index is less than the second threshold, the order progress state is an abnormal state, and a warning is issued; after the warning is issued, it is reminded that there is a risk of having too much raw material left, and temporary activities need to be pushed according to the situation; in the embodiment, the preset order state evaluation threshold is set to (0, 0.75), the order progress state is an abnormal state; [0.75, 1.15], the order progress state is a normal state; greater than 1.15; the order progress state is an advanced state.

[0087] According to the embodiment of the present application, the method further comprises:

[0088] Channel mode data of a customer order is acquired, and channel weight data is obtained by querying a preset channel mode weight data list;

[0089] Order condition data is acquired, including expected delivery time, order complexity data, and order time sequence weight;

[0090] Order priority data is obtained by weighting processing according to the channel weight data, order condition data, and current time data;

[0091] According to the order priority data, corresponding orders are sorted in descending order to generate an order sequence queue.

[0092] It should be noted that the channel mode data refers to the channel mode of the customer order, including dine-in code scanning ordering, app remote ordering, or takeout platform ordering. Different modes can be set with different priority guarantee weight data by the noodle shop. For example, dine-in ordering indicates that the customer is waiting in the store, so it is relatively prioritized, and the priority guarantee weight data is slightly larger than that of other modes. The preset channel mode weight data list is a list defined by the noodle shop operator as needed. The order complexity data reflects the processing complexity of the order, which can be measured by a preset rule. For example, each additional ingredient is counted as 1 point, and each additional processing step (such as frying, frying, boiling, etc.) is counted as 2 points. The order complexity is evaluated by calculating the total score. The earlier the order time, the higher the order time sequence weight. The calculation formula of the order priority data is:

[0093] Order priority data = alpha x (expected delivery time - current time) + beta x order complexity + gamma x order time sequence weight (where alpha, beta, and gamma are weight coefficients, which are adjusted according to the actual operation of the operator).

[0094] According to the embodiment of the present application, it further comprises:

[0095] Historical noodle cooking data of the noodle shop is acquired, including the category of noodle taste, the total cooking time data of each category of noodle taste, the stage heating time data, and the stage heating temperature data;

[0096] A noodle taste heating database is trained and obtained according to the historical noodle cooking data;

[0097] Noodle taste requirement data of the customer is acquired, and noodle stage heating parameters are obtained by querying the noodle taste heating database;

[0098] Noodle cooking operation is performed according to the noodle stage heating parameters.

[0099] It should be noted that the category of the taste of noodles includes soft, moderate and hard. In order to have different tastes, the noodles are often heated in stages during cooking. Different time stages adopt different temperatures. The noodle taste requirement data refers to the requirement for the taste of the noodles. The noodle stage heating parameter refers to the heating of the noodles into several stages, how long each stage lasts, and what temperature each stage is heated at.

[0100] It is worth mentioning that it also includes:

[0101] Obtain the order placement time period data and query the preset time period correction weight list to obtain the time period correction weight coefficient;

[0102] Obtain the member level weight coefficient of the ordering customer, and process the time period correction weight coefficient and the member level weight coefficient to obtain the comprehensive correction weight coefficient;

[0103] Process the order priority data and the comprehensive correction weight coefficient to obtain updated order priority data;

[0104] According to the updated order priority data, the corresponding orders are processed in order.

[0105] It should be noted that the business hours of the noodle restaurant are generally concentrated in breakfast time, lunch time and dinner time. The breakfast time is generally more nervous and requires a higher time. Therefore, the weight coefficient corresponding to the time item can be increased, that is, the time period correction weight coefficient is obtained by querying the preset time period correction weight list. The preset time period correction weight list is self-defined by the operator according to actual needs, and the value range is a decimal between (0, 1). The member level weight coefficient is determined according to the member level. The higher the member level, the greater the corresponding weight coefficient. The comprehensive correction weight coefficient is the sum of the time period correction weight coefficient and the member level weight coefficient. The updated order priority data = order priority data * (1 + comprehensive correction weight coefficient).

[0106] It is worth mentioning that it also includes:

[0107] Obtain the health status data of the customer, including blood sugar status history data and blood pressure status history data;

[0108] Obtain the noodle requirement data and the expected start processing time of the customer order. The noodle requirement data includes flour type data and salt content state data;

[0109] The health status data is checked for adaptability with the noodle requirement data at a preset fixed time before the expected start processing time;

[0110] If the adaptability is consistent, processing is performed according to the expected start processing time;

[0111] If the adaptability is inconsistent, inconsistent prompt information is sent and the customer is required to confirm;

[0112] Processing is performed according to the customer confirmation information.

[0113] It should be noted that the blood glucose condition history data refers to whether the user has a history of hyperglycemia; the blood pressure condition history data refers to whether the user has a history of hypertension; the flour type data includes normal flour or low-sugar flour; the salt content state data includes moderate salt content or low salt; the blood glucose condition history data and the flour type data are checked for adaptability, and if the health requirements are met, the flour adaptability is consistent, otherwise the flour adaptability is inconsistent; the blood pressure condition history data and the salt content state data are checked for adaptability, and if the health requirements are met, the salt content adaptability is consistent, otherwise the salt content adaptability is inconsistent; when one of the flour type data and the salt content state data is inconsistent, the adaptability is inconsistent; after the customer receives the prompt, if the order is selected incorrectly, it can be changed, and after the change, the new execution is performed; if there is no feedback within 2 minutes, the order is executed according to the original state. In this embodiment, the preset fixed time is 3 minutes, and after the expected start processing time is obtained, the health condition data is checked for adaptability with the noodle requirement data 3 minutes before the expected start processing time.

[0114] It is worth mentioning that when the customer order enters the processing link, it also includes:

[0115] The intelligent noodle cooking device sends a request connection information to the order corresponding client;

[0116] After the client is verified by a preset verification method, the intelligent noodle cooking device and the client establish a connection and authorize corresponding operation permissions;

[0117] Real-time noodle cooking video and real-time noodle cooking parameters are obtained and synchronously transmitted to the client;

[0118] The customer adjusts the noodle cooking parameters according to real-time needs.

[0119] It should be noted that in order to increase the transparency of the kitchen, meet the customer's requirements for food safety supervision, and realize the customer's personalized operation appeal, the client will receive a connection request from the intelligent noodle cooking device when the customer's order enters the processing link; the preset verification method can be set according to needs, which can be a fingerprint, a password, or face recognition; the authorized operation permission means that the customer can adjust within a certain range under the condition of automatically setting the noodle cooking parameters corresponding to the order, such as adjusting the original temperature of 100 degrees for 5 minutes to 90 degrees for 4 minutes in one heating stage.

[0120] The application also discloses a smart noodle restaurant unmanned back kitchen dispatching system.

[0121] The historical order data and the order data of the same period in a preset time period of the noodle restaurant are acquired, classified, and used to calculate effective increase data;

[0122] The increase influence data of a predicted date of the noodle restaurant is acquired, and sub-item influence weight data is acquired by respectively querying a preset increase influence weight data list, and the corrected increase data is calculated according to the sub-item influence weight data;

[0123] The comprehensive increase data is calculated according to the corrected increase data and the effective increase data corresponding to the predicted date, and the predicted order data and the corresponding raw material purchase data are calculated according to the comprehensive increase data.

[0124] It should be noted that the stable operation of the noodle restaurant cannot be achieved without the preparation of back kitchen materials, and the preparation of materials benefits from the accurate prediction of orders, because only accurate prediction of orders can better know the quantity of materials, and can guarantee normal operation and avoid waste. The operation of the entity noodle restaurant is relatively stable, and the order quantity in the past has good reference significance, so the historical order data and the order data of the same period in a preset time period of the noodle restaurant are acquired, classified, and used to calculate effective increase data. The order of the noodle restaurant is also affected by some external factors, which are called increase image data. The sub-item influence weight data is acquired by querying the preset increase influence weight data list according to the increase influence data, so as to calculate the corrected increase data according to the sub-item influence weight data, calculate the comprehensive increase data according to the corrected increase data and the effective increase data corresponding to the predicted date, and finally obtain the predicted order data and the corresponding raw material purchase data.

[0125] According to the embodiment of the application, the historical order data and the order data of the same period in a preset time period of the noodle restaurant are acquired, classified, and used to calculate effective increase data, and specifically include:

[0126] The historical order data in a preset time period of the noodle restaurant is acquired, and historical stage order data, including historical working day order data and historical rest day order data, is obtained by classification;

[0127] The order data of the same period of the noodle restaurant is acquired, and same period stage order data, including same period working day order data and same period rest day order data, is obtained by classification;

[0128] The growth data is calculated according to historical stage order data and same period stage order data, and the effective growth data is obtained by taking an arithmetic mean, including working day effective growth data and rest day effective growth data.

[0129] It should be noted that the preset time period can be customized according to user requirements; in the catering industry, the passenger flow of working days and rest days has a large change, for example, the noodle shop around the business office building, the meal quantity of working days is obviously larger than that of rest days, therefore, in order to realize more accurate prediction, orders need to be classified according to working days and rest days; the historical stage order data refers to the order quantity data of the historical preset time period, the historical working day order data and the historical rest day order data respectively refer to the daily order quantity of the historical working day and the daily order quantity of the historical rest day in the preset time period; the same period working day order data and the same period rest day order data respectively refer to the daily order data of the same period working day and the daily order data of the same period rest day in the preset time period; taking the calculation of the working day effective growth data as an example, the calculation process is that the same period working day order data is subtracted from the historical working day order data to obtain working day order growth data, and then the working day order growth data is divided by the historical working day order data to obtain growth data, and the growth data of the working day in the preset time period is taken to obtain the working day effective growth data, and the rest day effective growth data can be calculated in the same way; in the embodiment, the preset time period is set to 3 weeks, the order data of the same period refers to the daily order quantity data of the previous 3 weeks, and the historical order data refers to the daily order quantity data of the previous 3 weeks.

[0130] According to the embodiment of the application, the growth influence data of the noodle shop prediction date is obtained, the sub-item influence weight data is obtained by querying the preset growth influence weight data list, and the corrected growth data is calculated according to the sub-item influence weight data, specifically including:

[0131] The growth influence data of the noodle shop prediction date is obtained, including weather temperature change data, activity influence data and member change data;

[0132] The sub-item influence weight data is obtained by querying the preset growth influence weight data list according to the growth influence data, including temperature change weight data, activity influence weight data and member change weight data;

[0133] The corrected growth data is calculated according to the sub-item influence weight data.

[0134] It should be noted that according to the analysis of historical data, the customer flow of the noodle restaurant is also affected by some external and internal factors, including temperature change of weather, holding promotional activities and member quantity; the temperature change of weather data refers to the change value of the temperature of the prediction day and the temperature of the day before the prediction day; the activity influence data refers to the type data of the activities held, such as half price for the second bowl, 80% discount, etc., different discount strength will have different increasing influence, and the member change data refers to the change amount of the member quantity of the prediction day and the average number of members at the same time; the temperature change weight data, the activity influence weight data and the member change weight data are obtained by querying the preset increasing influence weight data list according to the weather temperature change data, the activity influence data and the member change data; the preset increasing influence weight data list is obtained by training according to historical data, and the corresponding item influence weight data list can be obtained by querying the known weather temperature change data, the activity influence data and the member change data; in this embodiment, the temperature change weight data corresponding to the temperature drop of 5℃ is 6%, and the activity influence weight data corresponding to the second bowl half price is 13%; the correction increasing data is the sum of the temperature change weight data, the activity influence weight data and the member change weight data.

[0135] The comprehensive increasing data is calculated according to the correction increasing data and the effective increasing data corresponding to the prediction date, and the predicted order data and the corresponding raw material preparation data are calculated according to the comprehensive increasing data, which specifically includes:

[0136] Type data of the prediction date is obtained, including working day data or rest day data;

[0137] If the type data is working day data, the comprehensive increasing data is calculated according to the correction increasing data and the working day effective increasing data;

[0138] If the type data is rest day data, the comprehensive increasing data is calculated according to the correction increasing data and the rest day effective increasing data;

[0139] The predicted order data and the corresponding raw material preparation data are calculated according to the comprehensive increasing data.

[0140] It should be noted that the corresponding effective increasing data is selected according to the type of the prediction date to more reasonably reflect the comprehensive increasing data, and the calculation formula of the comprehensive increasing data is:

[0141] Comprehensive increasing data = effective increasing data * (1 + correction increasing data);

[0142] If the type data is working day data, the comprehensive increasing data is multiplied by the working day order average value in the same time period to obtain the predicted order data;

[0143] If the type data is holiday data, the comprehensive increase data is multiplied by the average order data in the same period to obtain predicted order data;

[0144] According to the predicted order data, raw material purchase data is obtained in combination with a preset order material preparation relationship table.

[0145] According to the embodiment of the present application, it further comprises:

[0146] Current order progress data and historical order progress data corresponding to the current time progress are obtained.

[0147] The current order progress data is divided by the historical order progress data to obtain a relative order progress index.

[0148] The relative order progress index is compared with a preset order state evaluation threshold to obtain an order progress state.

[0149] According to the preset order state evaluation threshold, a first threshold and a second threshold are extracted, and the first threshold is greater than the second threshold.

[0150] If the relative order progress index is greater than the first threshold, the order progress state is an advanced state, and a raw material supplement calculation program is started.

[0151] It should be noted that the working time of a daily noodle shop is limited, the current time progress is the length of the current working time divided by the total working time, the historical order progress data refers to the proportion of the number of orders sold to the total number of orders at the same time progress in recent days, and the current order progress data refers to the proportion of the number of orders sold to the predicted number of orders; if the relative order progress index is greater than or equal to the second threshold and less than or equal to the first threshold, the order progress state is a normal state, and the noodle shop is normally running, and if the relative order progress index is less than the second threshold, the order progress state is an abnormal state, and a warning is issued; after the warning is issued, it is reminded that there is a risk of having too much raw material left, and temporary activities need to be pushed according to the situation; in the embodiment, the preset order state evaluation threshold is set to (0, 0.75), the order progress state is an abnormal state; [0.75, 1.15], the order progress state is a normal state; greater than 1.15; the order progress state is an advanced state.

[0152] According to the embodiment of the present application, it further comprises:

[0153] Channel mode data of a customer order is obtained, and channel weight data is obtained by querying a preset channel mode weight data list.

[0154] Order condition data is obtained, including predicted delivery time, order complexity data and order time sequence weight.

[0155] According to the channel weight data, order condition data and current time data, order priority data is obtained through weighted processing;

[0156] According to the order priority data, corresponding orders are sorted in descending order to generate an order sequence queue.

[0157] It should be noted that the channel mode data refers to the channel mode of the customer's order, including dine-in code scanning ordering, app remote ordering or takeout platform ordering; For different modes, the noodle shop can set different priority guarantee weight data, such as dine-in ordering indicating that the customer has already waited in the store, which is relatively priority guarantee, so the priority guarantee weight data is slightly larger than that of other modes; The preset channel mode weight data list is a list defined by the noodle shop operator according to needs; The order complexity data reflects the processing complexity of the order, which can be measured by a preset rule, such as counting 1 point for each additional ingredient and 2 points for each additional processing step (such as frying, frying, boiling, etc.), and the order complexity is evaluated by calculating the total score; The earlier the order time, the higher the order time sequence weight; The calculation formula of the order priority data is:

[0158] Order priority data = α × (estimated delivery time - current time) + β × order complexity + γ × order time sequence weight (where α, β, γ are weight coefficients, which are adjusted according to the actual operation of the operator).

[0159] According to the embodiment of the application, it also includes:

[0160] Obtain historical noodle cooking data of the noodle shop, including the category of noodle taste, the total cooking time data of each category of noodle taste, the stage heating time data and the stage heating temperature data;

[0161] According to the historical noodle cooking data, a noodle taste heating database is trained and obtained;

[0162] Obtain the noodle taste requirement data of the customer, and query the noodle taste heating database to obtain the noodle stage heating parameters;

[0163] According to the noodle stage heating parameters, the noodle cooking operation is performed.

[0164] It should be noted that the category of noodle taste includes soft, moderate and hard, and in the noodle cooking process, the noodles are often heated in stages in order to have different tastes, different temperatures are used in different time stages, the noodle taste requirement data refers to the requirement for the taste of the noodles, and the noodle stage heating parameters refer to the heating of the noodles into several stages, how long each stage lasts, and what temperature each stage is heated at.

[0165] It is worth mentioning that it also includes:

[0166] Obtain the order placement time period data, and query the preset time period correction weight list to obtain the time period correction weight coefficient;

[0167] Obtain the member level weight coefficient of the order placement customer, and process the time period correction weight coefficient and the member level weight coefficient to obtain the comprehensive correction weight coefficient;

[0168] Process the order priority data and the comprehensive correction weight coefficient to obtain the updated order priority data;

[0169] According to the updated order priority data, process the corresponding order in sequence.

[0170] It should be noted that the business hours of the noodle restaurant are generally concentrated in the breakfast time, lunch time and dinner time. The breakfast time is generally more nervous and requires a higher time requirement, so the weight coefficient corresponding to the time item can be increased, i.e. querying the preset time period correction weight list to obtain the time period correction weight coefficient; the preset time period correction weight list is self-defined by the operator according to the actual demand, and the value range is a decimal between (0, 1); the member level weight coefficient is determined according to the member level, and the higher the member level, the greater the corresponding weight coefficient; the comprehensive correction weight coefficient is the sum of the time period correction weight coefficient and the member level weight coefficient; the updated order priority data = order priority data * (1 + comprehensive correction weight coefficient).

[0171] It is worth mentioning that it also includes:

[0172] Obtain the health status data of the customer, including blood glucose status history data and blood pressure status history data;

[0173] Obtain the noodle requirement data and the expected start processing time of the customer order, the noodle requirement data including flour type data and salt content state data;

[0174] Adaptively check the health status data with the noodle requirement data respectively at a preset fixed time before the expected start processing time;

[0175] If the adaptability is consistent, process according to the expected start processing time;

[0176] If the adaptability is inconsistent, send an inconsistent reminder information and require the customer to confirm;

[0177] Process according to the customer confirmation information.

[0178] It should be noted that the blood glucose condition history data refers to whether the user has a history of hyperglycemia; the blood pressure condition history data refers to whether the user has a history of hypertension; the flour type data includes normal flour or low-sugar flour; the salt content state data includes moderate salt content or low salt; the blood glucose condition history data and the flour type data are subjected to adaptability checking, if the health requirements are met, the flour adaptation is consistent, otherwise the flour adaptation is inconsistent; the blood pressure condition history data and the salt content state data are subjected to adaptability checking, if the health requirements are met, the salt content adaptation is consistent, otherwise the salt content adaptation is inconsistent; when the flour type data and the salt content state data are inconsistent, the adaptability is inconsistent; after the customer receives the reminder, if the order is selected incorrectly, it can be changed, and after the change, the new execution is performed; if there is no feedback within 2 minutes, the original order state is executed. In this embodiment, the preset fixed time is 3 minutes, after the expected start processing time is obtained, the health condition data is subjected to adaptability checking with the noodle requirement data respectively before 3 minutes.

[0179] It is worth mentioning that when the customer order enters the processing link, it also includes:

[0180] The intelligent noodle cooking device sends a request connection information to the order corresponding client;

[0181] After the client is verified by the preset verification method, the intelligent noodle cooking device and the client establish a connection and authorize the corresponding operation permission;

[0182] Real-time noodle cooking video and real-time noodle cooking parameters are obtained and synchronously transmitted to the client;

[0183] The customer adjusts the noodle cooking parameters according to the real-time requirements.

[0184] It should be noted that in order to increase the transparency of the kitchen, meet the customer's requirements for food safety supervision and realize the personalized operation appeal, when the customer's order enters the processing link, the client will receive the connection request of the intelligent noodle cooking device; the preset verification method is set according to the needs, which can be fingerprint, password or face recognition; the authorized operation permission means that the customer can adjust within a certain range under the condition of the order corresponding automatic setting noodle cooking parameters, such as adjusting the original temperature of 100 degrees for 5 minutes to 90 degrees for 4 minutes in one heating stage.

[0185] The application discloses a smart noodle shop unmanned kitchen scheduling method and system, and the effective increase data is obtained by classifying and calculating the historical order data in the preset time period of the noodle shop and the order data in the same period, the sub-item influence weight data is obtained by querying the increase influence data, the corrected increase data is obtained by processing, the comprehensive increase data is obtained by calculating the corrected increase data and the effective increase data corresponding to the predicted date, and then the predicted order data and the raw material procurement data are obtained; therefore, the accurate prediction of the order data and the automatic inventory scheduling of the unmanned kitchen are realized by calculating the effective increase data, the corrected increase data and the comprehensive increase data.

[0186] In several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other manners. The above described device embodiments are merely schematic. For example, the division of the units is only a logical function division. There can be another division manner for the actual implementation. For example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the various components shown or discussed can be indirect coupling or communication connection through some interfaces, and can be electrical, mechanical or in other forms.

[0187] The units described as separate components can or can not be physically separate, and the components shown as units can or can not be physical units; they can be located in one place, or distributed on a plurality of network units; and part or all of the units can be selected according to actual needs to achieve the purpose of the embodiment.

[0188] In addition, each functional unit in each embodiment of the present application can be integrated into one processing unit, or each unit can be a separate unit, or two or more units can be integrated into one unit; the integrated unit can be realized in the form of hardware or in the form of hardware plus software functional unit.

[0189] Those skilled in the art can understand that all or part of the steps of the above method embodiments can be completed by program instruction related hardware, and the foregoing program can be stored in a readable storage medium, and the program is executed to perform the steps of the above method embodiments; and the foregoing storage medium includes mobile storage equipment, read-only memory (ROM), random access memory (RAM), magnetic disk or optical disk and various storage program codes.

[0190] Alternatively, the above-mentioned integrated unit of the present application, if realized in the form of a software function module and sold or used as an independent product, can also be stored in a readable storage medium. Based on such understanding, the technical solutions of the embodiments of the present application can be embodied in the form of a software product, which is stored in a storage medium, includes several instructions to make a computer device (which can be a personal computer, a server, or a network device, etc.) execute all or part of the methods described in the various embodiments of the present application. The aforementioned storage medium includes: mobile storage devices, ROM, RAM, magnetic or optical disks, and various media that can store program codes.

Claims

1. A method for unmanned kitchen scheduling in a smart noodle restaurant, characterized in that, include: Obtain historical order data from the noodle shop within a preset time period, and categorize it to obtain historical period order data, including historical weekday order data and historical weekend order data; Obtain the noodle shop's order data for the same period, and categorize it to obtain the order data for the same period, including weekday order data and weekend order data; The growth rate is calculated based on historical order data and order data from the same period, and the arithmetic mean is taken to obtain the effective growth rate, including the effective growth rate data for weekdays and the effective growth rate data for rest days. Obtain data on the impact of the predicted date on the noodle shop, including data on changes in weather and temperature, data on the impact of events, and data on changes in membership. Based on the increase impact data, query the preset increase impact weight data list to obtain the sub-item impact weight data, including temperature change weight data, activity impact weight data, and membership change weight data; The revised increase data is calculated based on the weighted data of each component's impact. The comprehensive growth rate data is calculated based on the revised growth rate data and the effective growth rate data corresponding to the forecast date. The forecast order data and the corresponding raw material purchase data are then calculated based on the comprehensive growth rate data. Also includes: Obtain historical noodle cooking data from noodle shops, including noodle texture categories, total cooking time for each texture category, stage heating time, and stage heating temperature. A noodle texture heating database was obtained by training based on historical noodle cooking data; Obtain customer data on noodle texture requirements and query the noodle texture heating database to obtain the heating parameters for each stage of noodle cooking. Cook the noodles according to the heating parameters for each stage of the noodle cooking process; Once a customer order enters the processing stage, it also includes: The intelligent noodle cooking device sends a connection request to the client corresponding to the order; After the client verifies the information using the preset verification method, the smart noodle cooking device establishes a connection with the client and authorizes the corresponding operation permissions; Acquire real-time noodle cooking video and real-time noodle cooking parameters and transmit them synchronously to the client; Customers adjust the noodle cooking parameters according to their real-time needs.

2. The unmanned kitchen scheduling method for smart noodle restaurants according to claim 1, characterized in that, The process of calculating the comprehensive growth rate data based on the corrected growth rate data and the effective growth rate data corresponding to the forecast date, and then calculating the forecast order data and corresponding raw material purchase data based on the comprehensive growth rate data, specifically includes: Obtain the type of data for the forecast date, including weekday data or rest day data; If the data type is working day data, then the comprehensive increase data is calculated based on the corrected increase data and the effective increase data of working days; If the data type is rest day data, then the comprehensive increase data is calculated based on the corrected increase data and the effective increase data of rest days; Based on the comprehensive increase data, the predicted order data and the corresponding raw material purchase data are calculated.

3. The unmanned kitchen scheduling method for smart noodle restaurants according to claim 2, characterized in that, Also includes: Retrieve the current order progress data and historical order progress data corresponding to the current time progress; The relative order progress index is obtained by dividing the current order progress data by the historical order progress data. The order progress status is obtained by comparing the relative order progress index with the preset order status evaluation threshold. Extract a first threshold and a second threshold based on a preset order status evaluation threshold, wherein the first threshold is greater than the second threshold; If the relative order progress index is greater than the first threshold, the order progress status is in the advanced state, and the raw material replenishment calculation program is started accordingly.

4. The unmanned kitchen scheduling method for smart noodle restaurants according to claim 3, characterized in that, Also includes: Obtain customer order channel data and query the preset channel weight data list to obtain channel weight data; Obtain order status data, including estimated delivery time, order complexity data, and the weight of order placement time order; Order priority data is obtained by weighting the channel weight data, order status data, and current time data; Based on the order priority data, the corresponding orders are sorted in descending order to generate an order sequence queue.

5. A smart noodle restaurant unmanned kitchen scheduling system, characterized in that, The system includes a memory and a processor. The memory contains a program for scheduling an unmanned kitchen in a smart noodle shop. When the processor executes the program, the program performs the following steps: Obtain historical order data from the noodle shop within a preset time period, and categorize it to obtain historical period order data, including historical weekday order data and historical weekend order data; Obtain the noodle shop's order data for the same period, and categorize it to obtain the order data for the same period, including weekday order data and weekend order data; The growth rate is calculated based on historical order data and order data from the same period, and the arithmetic mean is taken to obtain the effective growth rate, including the effective growth rate data for weekdays and the effective growth rate data for rest days. Obtain data on the impact of the predicted date on the noodle shop, including data on changes in weather and temperature, data on the impact of events, and data on changes in membership. Based on the increase impact data, query the preset increase impact weight data list to obtain the sub-item impact weight data, including temperature change weight data, activity impact weight data, and membership change weight data; The revised increase data is calculated based on the weighted data of each component's impact. The comprehensive growth rate data is calculated based on the revised growth rate data and the effective growth rate data corresponding to the forecast date. The forecast order data and the corresponding raw material purchase data are then calculated based on the comprehensive growth rate data. Also includes: Obtain historical noodle cooking data from noodle shops, including noodle texture categories, total cooking time for each texture category, stage heating time, and stage heating temperature. A noodle texture heating database was obtained by training based on historical noodle cooking data; Obtain customer data on noodle texture requirements and query the noodle texture heating database to obtain the heating parameters for each stage of noodle cooking. Cook the noodles according to the heating parameters for each stage of the noodle cooking process; Once a customer order enters the processing stage, it also includes: The intelligent noodle cooking device sends a connection request to the client corresponding to the order; After the client verifies the information using the preset verification method, the smart noodle cooking device establishes a connection with the client and authorizes the corresponding operation permissions; Acquire real-time noodle cooking video and real-time noodle cooking parameters and transmit them synchronously to the client; Customers adjust the noodle cooking parameters according to their real-time needs.

Images