Prediction and identification method and device for restaurant meal making data and computer equipment

Abstract

The invention relates to a prediction and identification method and device for restaurant meal making data and computer equipment. The method comprises the following steps: obtaining meal making data information of each meal making mode of a store, and identifying meal making process information and material consumption information of each meal making mode based on the meal making data information of each meal making mode; according to a meal making data evaluation strategy, identifying meal making standard evaluation information of each meal making mode, and identifying consumption distribution information of each material type of the store; generating a meal making standard adjustment strategy of each meal making mode based on the meal making standard evaluation information of each meal making mode, and generating consumption prediction data of each material type through a material consumption prediction model based on the meal making standard adjustment strategy of each meal making mode and the consumption distribution information of each material type; and obtaining a meal making data identification result of the store. By adopting the method, the analysis and prediction accuracy of the meal data can be improved.

Description

Technical Field

[0001] The present application relates to the fields of big data analysis and artificial intelligence technology, and in particular to a method, device and computer equipment for predicting and identifying in-store dining data. Background Art

[0002] In the modern catering industry, intelligent and digital management has become a trend. Data analysis, intelligent control systems, and catering management technologies are key tools for achieving intelligent and digital catering. Data analysis, through analyzing catering data, can yield valuable information, providing decision support for catering management. Intelligent control systems, through automated control, can automate and intelligentize the catering process. Real-time acquisition, analysis, and prediction of restaurant standard cooking procedures and various material requirements are highly effective methods for improving catering data analysis. However, improving the accuracy of monitoring and predicting this data is a current research focus.

[0003] Traditional technical solutions rely on comprehensive analysis of meal preparation data, manual preparation data, and material consumption to understand a store's compliance with standard meal preparation specifications and the demand for various types of materials. However, the ambiguity and uncertainty of material requirements often lead to errors in forecasting individual material requirements. Furthermore, manual analysis is limited in efficiency and accuracy, potentially leading to slow data processing and inaccurate analysis results, resulting in poor accuracy in meal preparation data analysis and forecasting. Summary of the Invention

[0004] Based on this, it is necessary to provide a method, device, computer equipment, computer-readable storage medium and computer program product for predicting and identifying store dining data in response to the above technical problems.

[0005] In a first aspect, the present application provides a method for predicting and identifying restaurant meal data, comprising:

[0006] Acquire meal preparation data information of each meal preparation method of the store, and based on the meal preparation data information of each meal preparation method, identify meal preparation process information of each meal preparation method and material consumption information of each meal preparation method;

[0007] Based on the meal preparation process information of each meal preparation method, the meal preparation standard evaluation information of each meal preparation method is identified through a meal preparation data evaluation strategy, and based on the material consumption information of each meal preparation method, the consumption distribution information of each material type in the store is identified;

[0008] Based on the meal preparation standard evaluation information of each meal preparation method, a meal preparation standard adjustment strategy for each meal preparation method is generated; and based on the meal preparation standard adjustment strategy for each meal preparation method and the consumption distribution information of each material type, consumption forecast data for each material type is generated through a material consumption forecast model;

[0009] The meal preparation standard evaluation information of each meal preparation method, the meal preparation standard adjustment strategy of each meal preparation method, and the consumption forecast data of each material type are used as the meal preparation data recognition result of the store.

[0010] Optionally, the identifying of the meal preparation process information of each meal preparation method and the material consumption information of each meal preparation method based on the meal preparation data information of each meal preparation method includes:

[0011] For each meal preparation method, the meal preparation data information of the meal preparation method is split into sub-meal preparation data corresponding to each meal preparation task, and the meal preparation process extraction strategy corresponding to the meal preparation method is searched in the database;

[0012] Based on the sub-meal preparation data corresponding to each of the meal preparation tasks, identifying the consumption data of each material type of each meal preparation task, and using the consumption data of each material type of all meal preparation tasks as the material consumption information of the meal preparation method;

[0013] Based on the sub-meal data corresponding to each of the meal tasks, the actual task process of each meal task during the meal process is extracted separately through the meal process extraction strategy corresponding to the meal method, and the actual task process corresponding to all meal tasks is used as the meal process information of the meal method.

[0014] Optionally, the identifying of the meal preparation standard evaluation information of each meal preparation method based on the meal preparation process information of each meal preparation method through a meal preparation data evaluation strategy includes:

[0015] For each meal preparation method, based on the actual task flow corresponding to each meal preparation task of the meal preparation method, actual task feature data of each meal preparation task is extracted using the task standard feature extraction strategy of each meal preparation task;

[0016] In the task database, a standard evaluation strategy for each meal preparation task is collected, and based on actual task feature data of each meal preparation task, a standard evaluation value for each task standard type corresponding to each meal preparation task and a standard deviation value for each task standard type corresponding to each meal preparation task are evaluated using the standard evaluation strategy for each meal preparation task;

[0017] The standard evaluation values of each task standard type corresponding to all meal preparation tasks and the standard deviation values of each task standard type corresponding to all meal preparation tasks are used as the meal preparation standard evaluation information of the meal preparation method.

[0018] Optionally, identifying the consumption distribution information of each material type in the store based on the material consumption information of each meal preparation method includes:

[0019] Obtaining the meal frequency data of each meal task for each meal method at the store, and for each meal method, generating sub-consumption distribution information of each material type for each meal task of the meal method based on the consumption data of each material type for each meal task and the meal frequency data of each meal task;

[0020] Based on the sub-consumption distribution information of each material type for each meal preparation method, consumption distribution information of each material type is generated.

[0021] Optionally, generating a meal preparation standard adjustment strategy for each meal preparation method based on the meal preparation standard evaluation information of each meal preparation method includes:

[0022] For each meal preparation method, based on the standard evaluation value of each task standard type corresponding to each meal preparation task of the meal preparation method, filter out abnormal task standard types that are lower than the standard evaluation threshold of each task standard type corresponding to each meal preparation task;

[0023] For each meal preparation task, the task database is queried for the abnormal task process stage corresponding to each abnormal task standard type of the meal preparation task, and based on the standard deviation value of each abnormal task standard type of the meal preparation task and the abnormal task process stage corresponding to each abnormal task standard type of the meal preparation task, a task data adjustment strategy for each abnormal task process stage is generated through a data deviation identification strategy;

[0024] The task data adjustment strategies of each abnormal task process stage of each meal preparation task are used as the sub-meal preparation standard adjustment strategies of each meal preparation task, and the sub-meal preparation standard adjustment strategies of all meal preparation tasks are used as the meal preparation standard adjustment strategies of the meal preparation method.

[0025] Optionally, the generation of consumption forecast data for each material type through a material consumption forecast model based on the meal preparation standard adjustment strategy for each meal preparation method and the consumption distribution information for each material type includes:

[0026] For each meal mode, based on the meal standard adjustment strategy of the meal mode, identify the material consumption adjustment amount of each material type corresponding to each meal task, and adjust the sub-consumption distribution information of each material type for the meal mode based on the material consumption adjustment amount of each material type corresponding to each meal task, to obtain new sub-consumption distribution information of each material type;

[0027] Based on the new sub-consumption distribution information of each material type for each meal preparation method, new consumption distribution information of each material type is regenerated, and based on the new consumption distribution information of each material type, a consumption distribution feature of each material type and a consumption trend feature of each material type are extracted through a feature extraction network of a material consumption prediction model;

[0028] Based on the consumption distribution characteristics of each material type and the consumption trend characteristics of each material type, the consumption forecast value of each material type in a preset time period is identified through the consumption forecast network of the material consumption forecast model, and the consumption forecast value of each material type in the preset time period is used as the consumption forecast data of each material type.

[0029] In a second aspect, the present application also provides a device for predicting and identifying restaurant meal data, comprising:

[0030] An acquisition module is used to acquire the meal preparation data information of each meal preparation method in the store, and based on the meal preparation data information of each meal preparation method, identify the meal preparation process information of each meal preparation method and the material consumption information of each meal preparation method;

[0031] an identification module for identifying, based on the meal preparation process information of each meal preparation method and a meal preparation data evaluation strategy, meal preparation standard evaluation information of each meal preparation method, and identifying, based on the material consumption information of each meal preparation method, consumption distribution information of each material type in the store;

[0032] a generation module for generating a meal specification adjustment strategy for each meal preparation method based on the meal specification evaluation information for each meal preparation method, and generating consumption forecast data for each material type using a material consumption forecast model based on the meal specification adjustment strategy for each meal preparation method and the consumption distribution information for each material type;

[0033] The display module is used to use the meal preparation standard evaluation information of each meal preparation method, the meal preparation standard adjustment strategy of each meal preparation method, and the consumption forecast data of each material type as the meal preparation data identification result of the store.

[0034] Optionally, the acquisition module is specifically configured to:

[0035] For each meal preparation method, the meal preparation data information of the meal preparation method is split into sub-meal preparation data corresponding to each meal preparation task, and the meal preparation process extraction strategy corresponding to the meal preparation method is searched in the database;

[0036] Based on the sub-meal preparation data corresponding to each of the meal preparation tasks, identifying the consumption data of each material type of each meal preparation task, and using the consumption data of each material type of all meal preparation tasks as the material consumption information of the meal preparation method;

[0037] Based on the sub-meal data corresponding to each of the meal tasks, the actual task process of each meal task during the meal process is extracted separately through the meal process extraction strategy corresponding to the meal method, and the actual task process corresponding to all meal tasks is used as the meal process information of the meal method.

[0038] Optionally, the identification module is specifically configured to:

[0039] For each meal preparation method, based on the actual task flow corresponding to each meal preparation task of the meal preparation method, actual task feature data of each meal preparation task is extracted using the task standard feature extraction strategy of each meal preparation task;

[0040] In the task database, a standard evaluation strategy for each meal preparation task is collected, and based on actual task feature data of each meal preparation task, a standard evaluation value for each task standard type corresponding to each meal preparation task and a standard deviation value for each task standard type corresponding to each meal preparation task are evaluated using the standard evaluation strategy for each meal preparation task;

[0041] The standard evaluation values of each task standard type corresponding to all meal preparation tasks and the standard deviation values of each task standard type corresponding to all meal preparation tasks are used as the meal preparation standard evaluation information of the meal preparation method.

[0042] Optionally, the identification module is specifically configured to:

[0043] Obtaining the meal frequency data of each meal task for each meal method at the store, and for each meal method, generating sub-consumption distribution information of each material type for each meal task of the meal method based on the consumption data of each material type for each meal task and the meal frequency data of each meal task;

[0044] Based on the sub-consumption distribution information of each material type for each meal preparation method, consumption distribution information of each material type is generated.

[0045] Optionally, the generating module is specifically configured to:

[0046] For each meal preparation method, based on the standard evaluation value of each task standard type corresponding to each meal preparation task of the meal preparation method, filter out abnormal task standard types that are lower than the standard evaluation threshold of each task standard type corresponding to each meal preparation task;

[0047] For each meal preparation task, the task database is queried for the abnormal task process stage corresponding to each abnormal task standard type of the meal preparation task, and based on the standard deviation value of each abnormal task standard type of the meal preparation task and the abnormal task process stage corresponding to each abnormal task standard type of the meal preparation task, a task data adjustment strategy for each abnormal task process stage is generated through a data deviation identification strategy;

[0048] The task data adjustment strategies of each abnormal task process stage of each meal preparation task are used as the sub-meal preparation standard adjustment strategies of each meal preparation task, and the sub-meal preparation standard adjustment strategies of all meal preparation tasks are used as the meal preparation standard adjustment strategies of the meal preparation method.

[0049] Optionally, the generating module is specifically configured to:

[0050] For each meal mode, based on the meal standard adjustment strategy of the meal mode, identify the material consumption adjustment amount of each material type corresponding to each meal task, and adjust the sub-consumption distribution information of each material type for the meal mode based on the material consumption adjustment amount of each material type corresponding to each meal task, to obtain new sub-consumption distribution information of each material type;

[0051] Based on the new sub-consumption distribution information of each material type for each meal preparation method, new consumption distribution information of each material type is regenerated, and based on the new consumption distribution information of each material type, a consumption distribution feature of each material type and a consumption trend feature of each material type are extracted through a feature extraction network of a material consumption prediction model;

[0052] Based on the consumption distribution characteristics of each material type and the consumption trend characteristics of each material type, the consumption forecast value of each material type in a preset time period is identified through the consumption forecast network of the material consumption forecast model, and the consumption forecast value of each material type in the preset time period is used as the consumption forecast data of each material type.

[0053] In a third aspect, the present application provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of any one of the methods described in the first aspect when executing the computer program.

[0054] In a fourth aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the steps of any one of the methods in the first aspect.

[0055] In a fifth aspect, the present application provides a computer program product, wherein the computer program product comprises a computer program, and when the computer program is executed by a processor, the steps of any one of the methods in the first aspect are implemented.

[0056] The above-mentioned method, device and computer equipment for predicting and identifying store meal data obtain the meal data information of each meal method in the store, and identify the meal process information of each meal method and the material consumption information of each meal method based on the meal data information of each meal method; based on the meal process information of each meal method, identify the meal specification evaluation information of each meal method through a meal data evaluation strategy, and identify the consumption distribution information of each material type in the store based on the material consumption information of each meal method; based on the meal specification evaluation information of each meal method, generate a meal specification adjustment strategy for each meal method, and based on the meal specification adjustment strategy for each meal method and the consumption distribution information of each material type, generate consumption prediction data for each material type through a material consumption prediction model; use the meal specification evaluation information of each meal method, the meal specification adjustment strategy for each meal method and the consumption distribution information of each material type as the meal data identification result of the store. This solution comprehensively analyzes the cooking data information of various cooking methods to identify the evaluation information of cooking standards for different cooking methods and the cooking standard adjustment strategies for different cooking methods. This avoids the errors caused by the one-sidedness, ambiguity and uncertainty of manual analysis, thereby improving the accuracy of the evaluation of cooking standards for different cooking methods and the applicability of the adjustment of cooking standards. Then, this solution combines the material consumption information of different cooking methods and the cooking standard adjustment strategies for each of the aforementioned cooking methods to predict consumption data for different material types. When predicting the consumption of different material types, it can avoid the problem of abnormal material consumption caused by improper operation, which affects the accuracy of consumption prediction, thereby improving the accuracy and practicality of consumption prediction for different material types. Finally, this solution can not only evaluate and analyze the cooking specifications of different cooking methods and accurately predict the consumption of different material types, but also adjust the cooking specifications of different cooking methods and display them to users in real time, thereby effectively improving the evaluation efficiency of cooking specifications, the consumption prediction accuracy of material types, and the adjustment accuracy of cooking specifications for staff, thereby comprehensively improving the analysis and prediction accuracy of cooking data. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the following briefly introduces the drawings required for use in the embodiments or related technical descriptions. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0058] Figure 1 A flowchart of a method for predicting and identifying restaurant meal data in one embodiment is shown;

[0059] Figure 2 A flowchart of an example of predicting and identifying restaurant meal data in one embodiment;

[0060] Figure 3 This is a structural block diagram of a device for predicting and identifying restaurant meal data in one embodiment;

[0061] Figure 4 FIG. 1 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0062] In order to make the purpose, technical solutions and advantages of this application more clear, the following further describes this application in detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain this application and are not intended to limit this application.

[0063] The predictive identification method for in-store meal preparation data provided in the embodiments of this application can be applied to the integration of a constructed meal preparation standard evaluation model and a material demand forecasting model into an intelligent control system. The intelligent control system comprises a central processing unit (CPU), a data storage module, an output control module, and a user interaction module. The CPU utilizes an ARM Cortex-A7 processor, the data storage module utilizes 128GB of flash memory, the output control module utilizes solid-state relays, and the user interaction module utilizes a 7-inch touch screen. The intelligent control system automatically evaluates meal preparation standards and forecasts material demand based on real-time data. Based on the forecast results, it automatically adjusts the operating parameters of the liquid dispenser to ensure accurate material supply and adherence to meal preparation standards. The system's CPU can be used in a terminal, which can be, but is not limited to, various personal computers, laptops, mid-range computers, and the like. The terminal comprehensively analyzes meal preparation data from various meal preparation methods to identify meal preparation standard evaluation information and meal preparation standard adjustment strategies for each method. This avoids the errors caused by the one-sidedness, ambiguity, and uncertainty of manual analysis, thereby improving the accuracy of meal preparation standard evaluations and the adaptability of meal preparation standard adjustments for different meal preparation methods. Then, this solution combines the material consumption information of different meal preparation methods and the meal preparation specification adjustment strategy of each meal preparation method to predict the consumption forecast data of different material types, so that when predicting the consumption of different material types, it can avoid the problem of abnormal material consumption caused by improper operation, thereby affecting the accuracy of consumption forecast, thereby improving the accuracy of consumption forecast for different material types and the practicality of consumption forecast. Finally, this solution can not only evaluate and analyze the meal preparation specifications of different meal preparation methods and accurately predict the consumption of different material types, but also adjust the meal preparation specifications of different meal preparation methods and display them to users in real time, thereby effectively improving the evaluation efficiency of meal preparation specifications, the consumption forecast accuracy of material types, and the adjustment accuracy of meal preparation specifications for staff, thereby comprehensively improving the analysis and prediction accuracy of meal preparation data.

[0064] In an exemplary embodiment, Figure 1 As shown, a method for predicting and identifying restaurant meal data is provided, which is described by taking the application of the method to a terminal as an example, and includes the following steps S101 to S104.

[0065] in:

[0066] Step S101: Acquire meal preparation data information of each meal preparation method in the store, and based on the meal preparation data information of each meal preparation method, identify meal preparation process information of each meal preparation method and material consumption information of each meal preparation method.

[0067] In this embodiment, the terminal responds to the staff's information upload operation and the intelligent liquid dispensing machine's data upload operation to obtain meal preparation data information for different meal preparation methods. These meal preparation methods include, but are not limited to, intelligent liquid dispensing machine meal preparation methods and manual meal preparation methods. Each meal preparation data information includes, but is not limited to, material consumption data for different meal preparation tasks collected by various sensors, as well as meal preparation process record data for each meal preparation task. Then, based on the meal preparation data information for each meal preparation method, the terminal identifies the meal preparation process information and material consumption information for each meal preparation method. Each meal preparation task includes meal preparation tasks for different product types, different product specifications, and different product additional requirements. The material consumption data includes sub-consumption data for each material type, which refers to the material type of the basic material required to produce each product, such as pure milk material, black tea material, ice material, green tea material, syrup material, and various ingredient materials. The specific identification process will be described in detail later. Among them, the meal preparation process information of each meal preparation method and the material consumption information can be identified by using correlation analysis using the Pearson correlation coefficient method, and the correlation between the meal preparation data and the material consumption data is analyzed and identified.

[0068] Step S102: Based on the meal preparation process information of each meal preparation method, the meal preparation standard evaluation information of each meal preparation method is identified through the meal preparation data evaluation strategy, and based on the material consumption information of each meal preparation method, the consumption distribution information of each material type in the store is identified.

[0069] In this embodiment, the terminal identifies the meal preparation standard evaluation information of each meal preparation method based on the meal preparation process information of each meal preparation method through the meal preparation data evaluation strategy, and identifies the consumption distribution information of each material type in the store based on the material consumption information of each meal preparation method. Among them, the meal preparation standard evaluation information of each meal preparation method includes the standard evaluation value of each task standard type corresponding to all meal preparation tasks produced by the meal preparation method, and the standard deviation value of each task standard type corresponding to all meal preparation tasks. Among them, each task standard type includes but is not limited to a hygiene standard type, a behavior standard type, a step standard type, a use and placement standard type, and a time standard type. The specific identification process will be described in detail later.

[0070] Step S103: Based on the meal preparation standard evaluation information of each meal preparation method, a meal preparation standard adjustment strategy for each meal preparation method is generated; and based on the meal preparation standard adjustment strategy for each meal preparation method and the consumption distribution information of each material type, consumption forecast data for each material type is generated through a material consumption forecast model.

[0071] In this embodiment, the terminal generates a specific adjustment strategy for each meal type based on the evaluation information for each meal type. Furthermore, based on these adjustment strategies and the consumption distribution information for each material type, the terminal generates consumption forecast data for each material type using a material consumption forecast model. This material consumption forecast model is based on a convolutional neural network using reinforcement learning. The specific generation process will be described in detail later.

[0072] In step S104 , the meal preparation standard evaluation information of each meal preparation method, the meal preparation standard adjustment strategy of each meal preparation method, and the consumption forecast data of each material type are used as the meal preparation data recognition result of the store.

[0073] In this embodiment, the terminal uses the meal preparation evaluation information for each meal preparation method, the meal preparation adjustment strategy for each meal preparation method, and the consumption forecast data for each material type as the store's meal preparation data recognition results. Staff developed a user interface to facilitate human-computer interaction. Users can view the meal preparation evaluation results and material demand forecast results through the interface and make adjustments and settings as needed. The system also provides data visualization, allowing users to intuitively understand the data information corresponding to the data analysis and forecast results.

[0074] Based on the above scheme, by comprehensively analyzing the cooking data information of various cooking methods, the evaluation information of cooking standards for different cooking methods and the cooking standard adjustment strategies for different cooking methods are identified, avoiding the errors caused by the one-sidedness, ambiguity and uncertainty of manual analysis, thereby improving the accuracy of the evaluation of cooking standards for different cooking methods and the applicability of the adjustment of cooking standards. Then, this scheme combines the material consumption information of different cooking methods and the cooking standard adjustment strategies for each of the aforementioned cooking methods to predict consumption forecast data for different material types. When predicting the consumption of different material types, it is possible to avoid the problem of abnormal material consumption caused by improper operation, which affects the accuracy of consumption forecasts, thereby improving the accuracy of consumption forecasts for different material types and the practicality of consumption forecasts. Finally, this solution can not only evaluate and analyze the cooking specifications of different cooking methods and accurately predict the consumption of different material types, but also adjust the cooking specifications of different cooking methods and display them to users in real time, thereby effectively improving the evaluation efficiency of cooking specifications, the consumption prediction accuracy of material types, and the adjustment accuracy of cooking specifications for staff, thereby comprehensively improving the analysis and prediction accuracy of cooking data.

[0075] Optionally, based on the meal data information of each meal method, the meal process information of each meal method and the material consumption information of each meal method are identified, including: for each meal method, splitting the meal data information of the meal method into sub-meal data corresponding to each meal task, and querying the database for the meal process extraction strategy corresponding to the meal method; based on the sub-meal data corresponding to each meal task, identifying the consumption data of each material type of each meal task, and using the consumption data of each material type of all meal tasks as the material consumption information of the meal method; based on the sub-meal data corresponding to each meal task, extracting the actual task flow of each meal task in the meal process respectively through the meal process extraction strategy corresponding to the meal method, and using the actual task flow corresponding to all meal tasks as the meal process information of the meal method.

[0076] In this embodiment, for each meal preparation method, the terminal splits the meal preparation data information of the meal preparation method into sub-meal preparation data corresponding to each meal preparation task, and queries the database for the meal preparation process extraction strategy corresponding to the meal preparation method. Different meal preparation methods have different meal preparation process extraction strategies. For example, when the meal preparation method is an intelligent liquid dispensing machine, the meal preparation process extraction strategy corresponding to the meal preparation method is to extract the consumption value of each production step of each meal preparation task by the intelligent liquid dispensing machine, as well as each material type corresponding to each production step. The step content of each production step and the consumption value of each material type corresponding to each production step are then sorted in the order of each production step to obtain the meal preparation process corresponding to the meal preparation method. In the case where the dining method is a human working method, the dining process extraction strategy corresponding to the dining method is to extract the staff operation content in each step of the dining method through a semantic extraction network based on natural language processing technology, as the step content of each production step, and based on each staff operation content, extract the consumption value of each material type in the staff operation content, and sort the step content of each production step and the consumption value of each material type in each production step according to the order of each production step to obtain the dining process corresponding to the dining method.

[0077] Then, the terminal identifies the consumption data of each material type of each meal task based on the sub-meal data corresponding to each meal task, and uses the consumption data of each material type of all meal tasks as the material consumption information of the meal method.

[0078] Finally, based on the sub-meal data corresponding to each meal task and the meal process extraction strategy corresponding to the meal method, the terminal extracts the actual task process for each meal task during the meal process and uses the actual task process corresponding to all meal tasks as the meal process information for the meal method. This actual task process is the meal process actually applied by each meal method when executing the meal task.

[0079] Based on the above solution, by extracting different meal preparation processes according to different meal preparation methods, the actual task processes corresponding to each meal preparation task are extracted separately, and the consumption data of each material type is identified, thereby improving the comprehensiveness and accuracy of the meal preparation specification identification for different meal preparation methods.

[0080] Optionally, based on the dining process information of each dining method, the dining standard evaluation information of each dining method is identified through the dining data evaluation strategy, including: for each dining method, based on the actual task process corresponding to each dining task of the dining method, the actual task feature data of each dining task are extracted separately through the task standard feature extraction strategy of each dining task; in the task database, the standard evaluation strategy of each dining task is collected, and based on the actual task feature data of each dining task, the standard evaluation value of each task standard type corresponding to each dining task and the standard deviation value of each task standard type corresponding to each dining task are evaluated through the standard evaluation strategy of each dining task; the standard evaluation value of each task standard type corresponding to all dining tasks and the standard deviation value of each task standard type corresponding to all dining tasks are used as the dining standard evaluation information of the dining method.

[0081] In this embodiment, for each dining method, based on the actual task flow corresponding to each dining task of the dining method, the terminal extracts the actual task feature data of each dining task through the task standard feature extraction strategy of each dining task. Among them, the task standard feature extraction strategy of each dining task includes the task standard type that each dining task is concerned about. For example, the task standard type that the tea-drinking dining task is concerned about is the beverage ratio standard type corresponding to the ratio value between tea and water, and the material temperature standard type for tea temperature control, etc. The task standard feature extraction strategy is used to extract the task feature data of each task labeling type. For example, the task feature data extracted by the beverage ratio standard type is the ratio value between tea and water in the product. The task standard feature extraction strategy of each dining task is an extraction strategy preset by the staff in the terminal. In the actual task flow, the task feature data of each task standard type can be extracted through the trained text feature extraction network (a neural network built based on a large prediction model).

[0082] In the task database, the terminal collects the standard evaluation strategy for each meal preparation task, and based on the actual task feature data of each meal preparation task, evaluates the standard evaluation value of each task standard type corresponding to each meal preparation task through the standard evaluation strategy of each meal preparation task, and obtains the standard deviation value of each task standard type corresponding to each meal preparation task. Among them, the standard evaluation strategy for each meal preparation task includes the correspondence between the range of each task feature data of each task standard type and the standard evaluation value. The terminal identifies the standard evaluation value of each task standard type through this correspondence, and then, based on the evaluation value threshold of each task standard type corresponding to each meal preparation task preset in the terminal, and the standard evaluation value of each task standard type corresponding to each meal preparation task, the terminal calculates the standard deviation value of each task standard type corresponding to each meal preparation task.

[0083] The terminal uses the standard evaluation values of each task standard type corresponding to all meal preparation tasks and the standard deviation values of each task standard type corresponding to all meal preparation tasks as meal preparation standard evaluation information of the meal preparation method.

[0084] Based on the above scheme, each meal preparation task of different meal preparation methods is evaluated separately by dividing it into different task standard types, thereby improving the recognition and evaluation accuracy of the meal preparation standards of each meal preparation task of different meal preparation methods.

[0085] Optionally, based on the material consumption information of each dining method, the consumption distribution information of each material type in the store is identified, including: obtaining the store's dining frequency data for each dining task of each dining method, and for each dining method, based on the consumption data of each material type for each dining task of the dining method and the dining frequency data of each dining task, generating sub-consumption distribution information of each material type for the dining method; based on the sub-consumption distribution information of each material type for each dining method, generating consumption distribution information of each material type.

[0086] In this embodiment, the terminal obtains the meal frequency data of each meal task for each meal mode in the store, and for each meal mode, the terminal identifies the task ranking information of each meal task at each time of the meal mode.

[0087] Then, the terminal calculates the average consumption data of each material type for each dining task based on the consumption data of each material type for each dining task and the dining frequency data of each dining task. Then, the terminal arranges the average consumption data of each material type for each dining task in sequence according to the task sorting information of each dining task at each moment of the dining mode, and obtains the sub-consumption distribution information of each material type for each dining mode.

[0088] Finally, the terminal uses the sub-consumption distribution information of each material type for all cooking methods as the consumption distribution information of each material type.

[0089] Based on the above scheme, by combining the meal frequency of the meal tasks and the consumption data of each material type of each meal task, the consumption distribution information of different material types is calculated, thereby improving the comprehensiveness and accuracy of the consumption distribution identification of each material type.

[0090] Optionally, based on the dining standard evaluation information of each dining method, a dining standard adjustment strategy for each dining method is generated, including: for each dining method, based on the standard evaluation value of each task standard type corresponding to each dining task of the dining method, screening out abnormal task standard types that are lower than the standard evaluation threshold of each task standard type corresponding to each dining task; for each dining task, querying the abnormal task process stage of the dining task corresponding to each abnormal task standard type through the task database, and based on the standard deviation value of each abnormal task standard type of the dining task and the abnormal task process stage of the dining task corresponding to each abnormal task standard type, generating a task data adjustment strategy for each abnormal task process stage through a data deviation identification strategy; using the task data adjustment strategy of each abnormal task process stage of each dining task as the sub-dining standard adjustment strategy of each dining task, and using the sub-dining standard adjustment strategy of all dining tasks as the dining standard adjustment strategy of the dining method.

[0091] In this embodiment, for each dining method, the terminal filters out abnormal task standard types that are lower than the standard evaluation threshold of each task standard type corresponding to each dining task based on the standard evaluation value of each task standard type corresponding to each dining task of the dining method.

[0092] Then, for each meal preparation task, the terminal queries the abnormal task process stage corresponding to each abnormal task standard type through the task database, and based on the standard deviation value of each abnormal task standard type of the meal preparation task and the abnormal task process stage corresponding to each abnormal task standard type of the meal preparation task, generates a task data adjustment strategy for each abnormal task process stage through the data deviation identification strategy. Among them, the task database stores the correspondence between the different task standard types concerned by each meal preparation task and the various task process stages (i.e., task steps) of the meal preparation task. For example, the task process stage of the tea preparation task corresponding to the beverage ratio standard type is the process stage of blending tea and water.

[0093] Specifically, for each abnormal task standard type, the terminal identifies the task feature data deviation value corresponding to the standard deviation value based on the standard deviation value of the abnormal task standard type, through a corresponding conversion program between the evaluation value of each abnormal task standard type and the task feature data preset in the terminal. Then, the terminal identifies the process data adjustment range of the abnormal task process stage based on the abnormal task process stage of the meal task corresponding to the abnormal task standard type and the task feature data deviation value corresponding to the standard deviation value, and uses the process data adjustment range of the abnormal task process stage corresponding to all abnormal task standard types as the task data adjustment strategy for the abnormal task process stage.

[0094] Finally, the terminal uses the task data adjustment strategy of each abnormal task process stage of each meal preparation task as the sub-meal preparation standard adjustment strategy of each meal preparation task, and uses the sub-meal preparation standard adjustment strategy of all meal preparation tasks as the meal preparation standard adjustment strategy of the meal preparation method.

[0095] Based on the above scheme, by adjusting the task process specifications of each meal preparation task for each meal preparation method according to the standard deviation value of the abnormal task standard type, the accuracy of process control of each meal preparation task is improved, and the accuracy of cost control of each material type can also be effectively improved.

[0096] Optionally, based on the meal standard adjustment strategy for each meal mode and the consumption distribution information of each material type, consumption forecast data for each material type is generated through a material consumption forecast model, including: for each meal mode, based on the meal standard adjustment strategy for the meal mode, identifying the material consumption adjustment amount of each material type corresponding to each meal task, and adjusting the sub-consumption distribution information of each material type for the meal mode based on the material consumption adjustment amount of each material type corresponding to each meal task to obtain new sub-consumption distribution information for each material type; based on the new sub-consumption distribution information of each material type for each meal mode, regenerating new consumption distribution information for each material type, and based on the new consumption distribution information of each material type, extracting the consumption distribution characteristics of each material type and the consumption trend characteristics of each material type through the feature extraction network of the material consumption forecast model; based on the consumption distribution characteristics of each material type and the consumption trend characteristics of each material type, identifying the consumption forecast value of each material type in a preset time period through the consumption forecast network of the material consumption forecast model, and using the consumption forecast value of each material type in the preset time period as the consumption forecast data for each material type.

[0097] In this embodiment, for each meal mode, the terminal identifies the material consumption adjustment amount of each material type corresponding to each meal task based on the meal standard adjustment strategy of the meal mode, and adjusts the sub-consumption distribution information of each material type of the meal mode based on the material consumption adjustment amount of each material type corresponding to each meal task, thereby obtaining new sub-consumption distribution information of each material type. The sub-consumption distribution information of each material type of each meal task is adjusted by replacing the average consumption data of each material type of each meal task with the material consumption amount of each material type of each meal task, and then returns to execute the step of sequentially arranging the task sorting information of each meal task at each moment of the meal mode to obtain the sub-consumption distribution information of each material type of each meal mode, thereby obtaining the new sub-consumption distribution information of each material type.

[0098] Based on the new sub-consumption distribution information for each material type for each meal preparation method, the terminal regenerates new consumption distribution information for each material type. Based on this new consumption distribution information for each material type, the terminal uses the feature extraction network of the material consumption prediction model to extract the consumption distribution characteristics and consumption trend characteristics of each material type. This feature extraction network is a linear feature extraction network that extracts features from linearly distributed data and is based on the feature extraction network architecture used in transfer learning.

[0099] Based on the consumption distribution characteristics and consumption trend characteristics of each material type, the terminal uses the consumption forecast network of the material consumption forecast model to identify the consumption forecast value of each material type during a preset time period and uses the consumption forecast value of each material type during the preset time period as the consumption forecast data for each material type. The material consumption forecast model is constructed using a linear regression method.

[0100] Based on the above scheme, consumption forecasts are performed on the adjusted new sub-consumption distribution information of each material type to obtain consumption forecast data for each material type. This allows us to avoid abnormal material consumption caused by improper operation when performing consumption forecasts on different material types, thereby affecting the accuracy of consumption forecasts. This improves the accuracy of consumption forecasts for different material types and the practicality of consumption forecasts.

[0101] The application also provides an example of predictive recognition of store meal data, such as Figure 2 As shown, the specific processing process includes the following steps:

[0102] Step S201: Acquire meal preparation data information of each meal preparation method of the store.

[0103] In step S202 , for each meal preparation method, the meal preparation data information of the meal preparation method is split into sub-meal preparation data corresponding to each meal preparation task, and a meal preparation process extraction strategy corresponding to the meal preparation method is searched in a database.

[0104] Step S203 : Based on the sub-meal preparation data corresponding to each meal preparation task, the consumption data of each material type of each meal preparation task is identified, and the consumption data of each material type of all meal preparation tasks is used as the material consumption information of the meal preparation method.

[0105] In step S204, based on the sub-meal data corresponding to each meal task, the actual task process of each meal task during the meal process is extracted through the meal process extraction strategy corresponding to the meal method, and the actual task process corresponding to all meal tasks is used as the meal process information of the meal method.

[0106] In step S205 , for each meal preparation method, based on the actual task flow corresponding to each meal preparation task of the meal preparation method, actual task feature data of each meal preparation task is extracted respectively through the task standard feature extraction strategy of each meal preparation task.

[0107] In step S206, the standard evaluation strategy for each meal preparation task is collected from the task database, and based on the actual task feature data of each meal preparation task, the standard evaluation value of each task standard type corresponding to each meal preparation task and the standard deviation value of each task standard type corresponding to each meal preparation task are evaluated through the standard evaluation strategy for each meal preparation task.

[0108] In step S207 , the standard evaluation values of the various task standard types corresponding to all meal preparation tasks and the standard deviation values of the various task standard types corresponding to all meal preparation tasks are used as meal preparation standard evaluation information of the meal preparation method.

[0109] Step S208: Obtain the store's meal frequency data for each meal task for each meal method, and for each meal method, generate sub-consumption distribution information for each material type of the meal method based on the consumption data of each material type for each meal task of the meal method and the meal frequency data of each meal task.

[0110] Step S209: generating consumption distribution information of each material type based on the sub-consumption distribution information of each material type for each cooking method.

[0111] Step S210 , for each meal preparation method, based on the standard evaluation value of each task standard type corresponding to each meal preparation task of the meal preparation method, screen out abnormal task standard types that are lower than the standard evaluation threshold of each task standard type corresponding to each meal preparation task.

[0112] In step S211, for each meal preparation task, the task database is queried to determine the abnormal task process stage of the meal preparation task corresponding to each abnormal task standard type, and based on the standard deviation value of each abnormal task standard type of the meal preparation task and the abnormal task process stage of the meal preparation task corresponding to each abnormal task standard type, a task data adjustment strategy for each abnormal task process stage is generated through a data deviation identification strategy.

[0113] In step S212, the task data adjustment strategies of each abnormal task process stage of each meal preparation task are used as the sub-meal preparation standard adjustment strategies of each meal preparation task, and the sub-meal preparation standard adjustment strategies of all meal preparation tasks are used as the meal preparation standard adjustment strategies of the meal preparation mode.

[0114] Step S213: For each meal preparation method, based on the meal preparation standard adjustment strategy of the meal preparation method, identify the material consumption adjustment amount of each material type corresponding to each meal preparation task, and adjust the sub-consumption distribution information of each material type of the meal preparation method based on the material consumption adjustment amount of each material type corresponding to each meal preparation task to obtain new sub-consumption distribution information of each material type.

[0115] In step S214, based on the new sub-consumption distribution information of each material type for each cooking method, new consumption distribution information of each material type is regenerated, and based on the new consumption distribution information of each material type, the consumption distribution characteristics of each material type and the consumption trend characteristics of each material type are extracted through the feature extraction network of the material consumption prediction model.

[0116] Step S215, based on the consumption distribution characteristics of each material type and the consumption trend characteristics of each material type, the consumption forecast value of each material type in the preset time period is identified through the consumption forecast network of the material consumption forecast model, and the consumption forecast value of each material type in the preset time period is used as the consumption forecast data of each material type.

[0117] It should be understood that, although the various steps in the flowcharts involved in the various embodiments described above are displayed in sequence according to the instructions of the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and these steps can be executed in other orders. Moreover, at least a portion of the steps in the flowcharts involved in the various embodiments described above can include multiple steps or multiple stages, and these steps or stages are not necessarily executed and completed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a portion of steps or stages in other steps.

[0118] Based on the same inventive concept, embodiments of the present application also provide a device for predicting and identifying in-store meal data, for implementing the aforementioned method for predicting and identifying in-store meal data. The solution provided by this device is similar to the solution described in the aforementioned method. Therefore, the specific limitations of one or more embodiments of the device for predicting and identifying in-store meal data provided below can be found in the aforementioned method for predicting and identifying in-store meal data, and will not be further elaborated here.

[0119] In an exemplary embodiment, Figure 3 As shown, a device for predicting and identifying restaurant meal data is provided, comprising: an acquisition module 310, an identification module 320, a generation module 330, and a display module 340, wherein:

[0120] An acquisition module 310 is configured to acquire meal preparation data information of each meal preparation method in the store, and based on the meal preparation data information of each meal preparation method, identify meal preparation process information of each meal preparation method and material consumption information of each meal preparation method;

[0121] an identification module 320 for identifying, based on the meal preparation process information of each meal preparation method and using a meal preparation data evaluation strategy, meal preparation standard evaluation information of each meal preparation method, and identifying, based on the material consumption information of each meal preparation method, consumption distribution information of each material type in the store;

[0122] A generation module 330 is configured to generate a meal standard adjustment strategy for each meal preparation method based on the meal standard evaluation information for each meal preparation method, and generate consumption forecast data for each material type using a material consumption forecast model based on the meal standard adjustment strategy for each meal preparation method and the consumption distribution information for each material type;

[0123] The display module 340 is used to use the meal preparation standard evaluation information of each meal preparation method, the meal preparation standard adjustment strategy of each meal preparation method, and the consumption forecast data of each material type as the meal preparation data identification result of the store.

[0124] Optionally, the acquisition module 310 is specifically configured to:

[0125] For each meal preparation method, the meal preparation data information of the meal preparation method is split into sub-meal preparation data corresponding to each meal preparation task, and the meal preparation process extraction strategy corresponding to the meal preparation method is searched in the database;

[0126] Based on the sub-meal preparation data corresponding to each of the meal preparation tasks, identifying the consumption data of each material type of each meal preparation task, and using the consumption data of each material type of all meal preparation tasks as the material consumption information of the meal preparation method;

[0127] Based on the sub-meal data corresponding to each of the meal tasks, the actual task process of each meal task during the meal process is extracted separately through the meal process extraction strategy corresponding to the meal method, and the actual task process corresponding to all meal tasks is used as the meal process information of the meal method.

[0128] Optionally, the identification module 320 is specifically configured to:

[0129] For each meal preparation method, based on the actual task flow corresponding to each meal preparation task of the meal preparation method, actual task feature data of each meal preparation task is extracted using the task standard feature extraction strategy of each meal preparation task;

[0130] In the task database, a standard evaluation strategy for each meal preparation task is collected, and based on actual task feature data of each meal preparation task, a standard evaluation value for each task standard type corresponding to each meal preparation task and a standard deviation value for each task standard type corresponding to each meal preparation task are evaluated using the standard evaluation strategy for each meal preparation task;

[0131] The standard evaluation values of each task standard type corresponding to all meal preparation tasks and the standard deviation values of each task standard type corresponding to all meal preparation tasks are used as the meal preparation standard evaluation information of the meal preparation method.

[0132] Optionally, the identification module 320 is specifically configured to:

[0133] Obtaining the meal frequency data of each meal task for each meal method at the store, and for each meal method, generating sub-consumption distribution information of each material type for each meal task of the meal method based on the consumption data of each material type for each meal task and the meal frequency data of each meal task;

[0134] Based on the sub-consumption distribution information of each material type for each meal preparation method, consumption distribution information of each material type is generated.

[0135] Optionally, the generating module 330 is specifically configured to:

[0136] For each meal preparation method, based on the standard evaluation value of each task standard type corresponding to each meal preparation task of the meal preparation method, filter out abnormal task standard types that are lower than the standard evaluation threshold of each task standard type corresponding to each meal preparation task;

[0137] For each meal preparation task, the task database is queried for the abnormal task process stage corresponding to each abnormal task standard type of the meal preparation task, and based on the standard deviation value of each abnormal task standard type of the meal preparation task and the abnormal task process stage corresponding to each abnormal task standard type of the meal preparation task, a task data adjustment strategy for each abnormal task process stage is generated through a data deviation identification strategy;

[0138] The task data adjustment strategies of each abnormal task process stage of each meal preparation task are used as the sub-meal preparation standard adjustment strategies of each meal preparation task, and the sub-meal preparation standard adjustment strategies of all meal preparation tasks are used as the meal preparation standard adjustment strategies of the meal preparation method.

[0139] Optionally, the generating module 330 is specifically configured to:

[0140] For each meal mode, based on the meal standard adjustment strategy of the meal mode, identify the material consumption adjustment amount of each material type corresponding to each meal task, and adjust the sub-consumption distribution information of each material type for the meal mode based on the material consumption adjustment amount of each material type corresponding to each meal task, to obtain new sub-consumption distribution information of each material type;

[0141] Based on the new sub-consumption distribution information of each material type for each meal preparation method, new consumption distribution information of each material type is regenerated, and based on the new consumption distribution information of each material type, a consumption distribution feature of each material type and a consumption trend feature of each material type are extracted through a feature extraction network of a material consumption prediction model;

[0142] Based on the consumption distribution characteristics of each material type and the consumption trend characteristics of each material type, the consumption forecast value of each material type in a preset time period is identified through the consumption forecast network of the material consumption forecast model, and the consumption forecast value of each material type in the preset time period is used as the consumption forecast data of each material type.

[0143] Each module in the aforementioned device for predicting and identifying in-store meal data may be implemented in whole or in part through software, hardware, or a combination thereof. Each module may be embedded in or independent of a processor within a computer device in the form of hardware, or may be stored in a computer device's memory in the form of software, so that the processor can call and execute the corresponding operations of each module.

[0144] In an exemplary embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as shown in FIG. Figure 4As shown. The computer device includes a processor, a memory, an input / output interface, a communication interface, a display unit and an input device. The processor, the memory and the input / output interface are connected via a system bus, and the communication interface, the display unit and the input device are connected to the system bus via the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, a mobile cellular network, NFC (near field communication) or other technologies. When the computer program is executed by the processor, a method for predicting and identifying restaurant meal data is implemented. The display unit of the computer device is used to form a visually visible picture, which can be a display screen, a projection device or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covering the display screen, or a button, trackball or touchpad set on the computer device casing, or an external keyboard, touchpad or mouse.

[0145] Those skilled in the art will understand that Figure 4 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement.

[0146] In an exemplary embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the steps of the method for predicting and identifying in-store meal data are implemented.

[0147] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps of the method for predicting and identifying in-store meal data are implemented.

[0148] In one embodiment, a computer program product is provided, comprising a computer program that, when executed by a processor, implements the steps of a method for predicting and identifying in-store meal data.

[0149] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0150] Those skilled in the art will appreciate that all or part of the processes in the above-mentioned embodiment methods can be implemented by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, database or other media used in the embodiments provided in this application may include at least one of non-volatile and volatile memory. Non-volatile memory may include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory may include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in the various embodiments provided herein may include at least one of a relational database and a non-relational database. Non-relational databases may include, but are not limited to, distributed databases based on blockchains. The processor involved in the various embodiments provided herein may be, but are not limited to, a general-purpose processor, a central processing unit, a graphics processing unit, a digital signal processor, a programmable logic unit, a data processing logic unit based on quantum computing, and the like.

[0151] The technical features of the above embodiments can be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0152] The above-described embodiments merely represent several implementation methods of the present application. While the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the present application. It should be noted that a person of ordinary skill in the art may make various modifications and improvements without departing from the spirit of the present application, and these modifications and improvements fall within the scope of protection of the present application. Therefore, the scope of protection of the present application shall be determined by the appended claims.

Claims

1. A method for predicting and identifying store dining data, characterized in that: The method comprises: Acquire meal preparation data information of each meal preparation method of the store, and based on the meal preparation data information of each meal preparation method, identify meal preparation process information of each meal preparation method and material consumption information of each meal preparation method; Based on the meal preparation process information of each meal preparation method, the meal preparation standard evaluation information of each meal preparation method is identified through a meal preparation data evaluation strategy, and based on the material consumption information of each meal preparation method, the consumption distribution information of each material type in the store is identified; Based on the meal preparation standard evaluation information of each meal preparation method, a meal preparation standard adjustment strategy for each meal preparation method is generated; and based on the meal preparation standard adjustment strategy for each meal preparation method and the consumption distribution information of each material type, consumption forecast data for each material type is generated through a material consumption forecast model; The meal preparation standard evaluation information of each meal preparation method, the meal preparation standard adjustment strategy of each meal preparation method, and the consumption forecast data of each material type are used as the meal preparation data recognition result of the store.

2. The method according to claim 1, characterized in that The identifying of the meal preparation process information of each meal preparation method and the material consumption information of each meal preparation method based on the meal preparation data information of each meal preparation method includes: For each meal preparation method, the meal preparation data information of the meal preparation method is split into sub-meal preparation data corresponding to each meal preparation task, and the meal preparation process extraction strategy corresponding to the meal preparation method is searched in the database; Based on the sub-meal preparation data corresponding to each of the meal preparation tasks, identifying the consumption data of each material type of each meal preparation task, and using the consumption data of each material type of all meal preparation tasks as the material consumption information of the meal preparation method; Based on the sub-meal data corresponding to each of the meal tasks, the actual task process of each meal task during the meal process is extracted separately through the meal process extraction strategy corresponding to the meal method, and the actual task process corresponding to all meal tasks is used as the meal process information of the meal method.

3. The method according to claim 2, characterized in that The method of identifying the meal preparation standard evaluation information of each meal preparation method based on the meal preparation process information of each meal preparation method through a meal preparation data evaluation strategy includes: For each meal preparation method, based on the actual task flow corresponding to each meal preparation task of the meal preparation method, actual task feature data of each meal preparation task is extracted using the task standard feature extraction strategy of each meal preparation task; In the task database, a standard evaluation strategy for each meal preparation task is collected, and based on actual task feature data of each meal preparation task, a standard evaluation value for each task standard type corresponding to each meal preparation task and a standard deviation value for each task standard type corresponding to each meal preparation task are evaluated using the standard evaluation strategy for each meal preparation task; The standard evaluation values of each task standard type corresponding to all meal preparation tasks and the standard deviation values of each task standard type corresponding to all meal preparation tasks are used as the meal preparation standard evaluation information of the meal preparation method.

4. The method according to claim 2, characterized in that The identifying of the consumption distribution information of each material type in the store based on the material consumption information of each meal preparation method includes: Obtaining the meal frequency data of each meal task for each meal method at the store, and for each meal method, generating sub-consumption distribution information of each material type for each meal task of the meal method based on the consumption data of each material type for each meal task and the meal frequency data of each meal task; Based on the sub-consumption distribution information of each material type for each meal preparation method, consumption distribution information of each material type is generated.

5. The method according to claim 3, characterized in that Generating a meal standard adjustment strategy for each meal preparation method based on the meal preparation standard evaluation information of each meal preparation method includes: For each meal preparation method, based on the standard evaluation value of each task standard type corresponding to each meal preparation task of the meal preparation method, filter out abnormal task standard types that are lower than the standard evaluation threshold of each task standard type corresponding to each meal preparation task; For each meal preparation task, the task database is queried for the abnormal task process stage corresponding to each abnormal task standard type of the meal preparation task, and based on the standard deviation value of each abnormal task standard type of the meal preparation task and the abnormal task process stage corresponding to each abnormal task standard type of the meal preparation task, a task data adjustment strategy for each abnormal task process stage is generated through a data deviation identification strategy; The task data adjustment strategies of each abnormal task process stage of each meal preparation task are used as the sub-meal preparation standard adjustment strategies of each meal preparation task, and the sub-meal preparation standard adjustment strategies of all meal preparation tasks are used as the meal preparation standard adjustment strategies of the meal preparation method.

6. The method according to claim 5, characterized in that The meal preparation standard adjustment strategy based on each meal preparation method and the consumption distribution information of each material type is used to generate consumption forecast data for each material type through a material consumption forecast model, including: For each meal mode, based on the meal standard adjustment strategy of the meal mode, identify the material consumption adjustment amount of each material type corresponding to each meal task, and adjust the sub-consumption distribution information of each material type for the meal mode based on the material consumption adjustment amount of each material type corresponding to each meal task, to obtain new sub-consumption distribution information of each material type; Based on the new sub-consumption distribution information of each material type for each meal preparation method, new consumption distribution information of each material type is regenerated, and based on the new consumption distribution information of each material type, a consumption distribution feature of each material type and a consumption trend feature of each material type are extracted through a feature extraction network of a material consumption prediction model; Based on the consumption distribution characteristics of each material type and the consumption trend characteristics of each material type, the consumption forecast value of each material type in a preset time period is identified through the consumption forecast network of the material consumption forecast model, and the consumption forecast value of each material type in the preset time period is used as the consumption forecast data of each material type.

7. A device for predicting and identifying restaurant meal data, characterized in that: The device comprises: An acquisition module is used to acquire the meal preparation data information of each meal preparation method in the store, and based on the meal preparation data information of each meal preparation method, identify the meal preparation process information of each meal preparation method and the material consumption information of each meal preparation method; an identification module for identifying, based on the meal preparation process information of each meal preparation method and a meal preparation data evaluation strategy, meal preparation standard evaluation information of each meal preparation method, and identifying, based on the material consumption information of each meal preparation method, consumption distribution information of each material type in the store; a generation module for generating a meal specification adjustment strategy for each meal preparation method based on the meal specification evaluation information for each meal preparation method, and generating consumption forecast data for each material type using a material consumption forecast model based on the meal specification adjustment strategy for each meal preparation method and the consumption distribution information for each material type; The display module is used to use the meal preparation standard evaluation information of each meal preparation method, the meal preparation standard adjustment strategy of each meal preparation method, and the consumption forecast data of each material type as the meal preparation data identification result of the store.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images