Electronic menu generation method and device, electronic equipment and storage medium

Abstract

The invention provides an electronic menu generation method and device, electronic equipment and a storage medium, and relates to the technical field of intelligent kitchen ware. According to the method, menu template information can be constructed, and menu parameters obtained by performing text standardization on an original menu are recorded in the menu template information; in response to a generation instruction of the electronic menu, performing association analysis on the menu input parameter and the menu template information to obtain a menu cooking process including the menu input parameter; and performing menu editing according to the menu cooking process containing the menu input parameters to obtain an electronic menu. According to the embodiment, the menu input parameters and the menu template information are subjected to correlation analysis to extract the menu cooking procedures with generality, menu editing is correspondingly carried out on the basis of the menu cooking procedures, electronic menus with different quantity requirements can be flexibly generated, the configuration time of cooking steps in the electronic menus is shortened, and the cooking efficiency of the electronic menus is improved. And the generation efficiency of the electronic menu is improved.

Description

Technical Field

[0001] The present application relates to the technical field of intelligent kitchenware, and particularly to a method and device for generating an electronic recipe, an electronic device, and a storage medium. Background Art

[0002] With the continuous development of intelligent catering, electronic recipes, as convenient kitchen assistants, have replaced paper recipes. In related technologies, users can generate electronic recipes by recording cooking steps or by describing cooking steps in natural language. However, these two methods of generating electronic recipes are usually for a single electronic recipe. When the client has a large demand for the number of electronic recipes, it takes a lot of time to configure cooking steps, resulting in low efficiency in generating electronic recipes. Summary of the Invention

[0003] In view of the above problems, the present application is proposed to provide a method and device for generating an electronic recipe, an electronic device, and a storage medium that overcome the above problems or at least partially solve the above problems. The technical solutions are as follows:

[0004] In a first aspect, a method for generating an electronic recipe is provided, including:

[0005] Constructing recipe template information, where recipe parameters obtained by text standardization of the original recipe are recorded in the recipe template information;

[0006] In response to a generation instruction of an electronic recipe, performing correlation analysis on recipe input parameters and the recipe template information to obtain a recipe cooking process including the recipe input parameters;

[0007] Editing a recipe according to the recipe cooking process including the recipe input parameters to obtain an electronic recipe.

[0008] In a possible implementation, the constructing of the recipe template information includes:

[0009] Pre-collecting original recipes;

[0010] Converting the original recipe into recipe information including different recipe parameters through text standardization processing to obtain a standard electronic recipe;

[0011] Entering the recipe information of different recipe parameters in the standard electronic recipe into a recipe table by using set recipe fields to obtain recipe template information.

[0012] In a possible implementation, the pre-collecting of the original recipes includes:

[0013] Use at least one pattern recognition method to identify recipes in different recipe platforms to obtain the original recipes, and the pattern recognition method includes one or more combinations of visual recognition method, speech recognition method, and / or character recognition method.

[0014] In a possible implementation, before, in response to the generation instruction of the electronic recipe, associating the recipe input parameters with the recipe template information to obtain the recipe cooking process containing the recipe input parameters, the method further includes:

[0015] Batch import the recipe parameters in the recipe template information into the recipe generation system at least once, and each batch import process includes at least the recipe parameters of one original recipe in the recipe template information;

[0016] Correspondingly, the recipe generation system stores the correspondingly batch-imported recipe parameters according to the set recipe format, so as to obtain the recipe template information with the set recipe format based on the recipe parameters batch-imported at least once.

[0017] In a possible implementation, the associating the recipe input parameters with the recipe template information to obtain the recipe cooking process containing the recipe input parameters includes:

[0018] Perform model training for big data analysis according to the recipe template information, so as to construct the association relationship between different recipe parameter combinations and the recipe cooking process through the trained big data model;

[0019] Process the recipe input parameters into a combined form and input them into the trained big data model, so as to perform association analysis on the combined recipe input parameters through the association relationship to obtain the recipe cooking process containing the recipe input parameters;

[0020] The performing model training for big data analysis according to the recipe template information, so as to construct the association relationship between different recipe parameter combinations and the recipe cooking process through the trained big data model includes:

[0021] Construct recipe sample data containing different recipe parameter combinations according to the recipe template information, and there is an association mark between different recipe parameter combinations and the recipe cooking process in the recipe sample data;

[0022] Input the recipe parameters in the recipe sample data into the big data model in a combined form for training, and learn the association relationship between different recipe parameter combinations and the recipe cooking process by using the association mark during the training process;

[0023] Obtain the trained big data model according to the learned association relationship between different recipe parameter combinations and the recipe cooking process.

[0024] In a possible implementation, before processing the recipe input parameters into a combined form and inputting them into the trained big data model to perform an association analysis on the recipe input parameters in the combined form through the association relationship to obtain a recipe cooking process containing the recipe input parameters, the method further includes:

[0025] Analyze the recipe input parameters according to the association relationship;

[0026] If the recipe input parameters are not recorded in the association relationship, then processing the recipe input parameters into a combined form and inputting them into the trained big data model to perform an association analysis on the recipe input parameters in the combined form through the association relationship to obtain a recipe cooking process containing the recipe input parameters includes:

[0027] Select recipe parameters with a similar effect to the recipe input parameters in the association relationship as substitute recipe parameters, process the substitute recipe parameters into a combined form and input them into the trained big data model to perform an association analysis on the substitute recipe parameters in the combined form through the association relationship to obtain a recipe cooking process containing the substitute recipe parameters.

[0028] In a possible implementation, the editing the recipe according to the recipe cooking process containing the recipe input parameters to obtain an electronic recipe includes:

[0029] Determine the ingredient specifications according to the recipe input parameters;

[0030] Determine the device information suitable for ingredient cooking according to the recipe cooking process containing the recipe input parameters;

[0031] On the basis of the recipe cooking process, aggregate the ingredient specifications and the device information suitable for ingredient cooking to obtain an electronic recipe with corresponding ingredient specifications.

[0032] In a possible implementation, after determining the device information suitable for ingredient cooking according to the recipe cooking process containing the recipe input parameters, the method further includes:

[0033] Determine the functional parameters suitable for the ingredient specifications according to the device information suitable for ingredient cooking;

[0034] Correspondingly, on the basis of the recipe cooking process, aggregate the ingredient specifications, the device information suitable for ingredient cooking, and the functional parameters suitable for the ingredient specifications to obtain an electronic recipe with corresponding ingredient specifications.

[0035] In a possible implementation, after editing a recipe according to the recipe cooking process including recipe input parameters to obtain an electronic recipe, the method further includes:

[0036] Processing the electronic recipe into a recipe table and / or swimlane information with standard specifications;

[0037] According to the device information associated with the electronic recipe, synchronously sending the recipe table and / or swimlane information to the cooking device associated with the electronic recipe, so that the cooking device cooks the recipe according to the recipe table and / or swimlane information.

[0038] In a second aspect, there is provided a device for generating an electronic recipe, including:

[0039] A construction module, configured to construct recipe template information, where the recipe template information records recipe parameters obtained by text standardization of the original recipe;

[0040] An analysis module, configured to perform an association analysis on the recipe input parameters and the recipe template information in response to a generation instruction of the electronic recipe, to obtain a recipe cooking process including the recipe input parameters;

[0041] A generation module, configured to edit a recipe according to the recipe cooking process including the recipe input parameters to obtain an electronic recipe.

[0042] In a possible implementation, the construction unit includes:

[0043] A collection unit, configured to pre-collect the original recipe;

[0044] A conversion unit, configured to convert the original recipe into recipe information including different recipe parameters through text standardization processing to obtain a standard electronic recipe;

[0045] An input unit, configured to input the recipe information of different recipe parameters in the standard electronic recipe into a recipe table by using set recipe fields to obtain recipe template information.

[0046] In a possible implementation, the collection unit is specifically configured to:

[0047] Perform recipe recognition in different recipe platforms by using at least one pattern recognition method, where the pattern recognition method includes one or a combination of a visual recognition method, a voice recognition method, and / or a character recognition method.

[0048] In a possible implementation, the device further includes:

[0049] An import module is used to batch import the recipe parameters in the recipe template information into the recipe generation system at least once before associating the recipe entry parameters with the recipe template information in response to the generation instruction of the electronic recipe, and each batch import process includes at least the recipe parameters of one original recipe in the recipe template information; correspondingly, the recipe generation system stores the correspondingly batch-imported recipe parameters according to the set recipe format, so as to obtain the recipe template information with the set recipe format based on the recipe parameters batch-imported at least once.

[0050] For the recipe pictures in different recipe platforms, use the visual recognition method to perform recipe recognition on the recipe pictures to obtain recipe ingredients, recipe text descriptions, and recipe visual clues.

[0051] Using the recipe visual clues as the visual reference conditions for determining the recipe cooking progress and / or recipe cooking status, split the recipe text description into ordered recipe cooking steps.

[0052] Combine the recipe ingredients with the ordered recipe cooking steps to obtain the original recipe.

[0053] In a possible implementation manner, the analysis module includes:

[0054] A construction unit is used to train the big data analysis model according to the recipe template information, so as to construct the association relationship between different recipe parameter combinations and recipe cooking procedures through the trained big data model.

[0055] A first analysis unit is used to process the recipe entry parameters into a combined form and input them into the trained big data model, so as to perform association analysis on the combined recipe entry parameters through the association relationship to obtain the recipe cooking procedures containing the recipe entry parameters.

[0056] The construction unit is specifically used for:

[0057] Construct recipe sample data containing different recipe parameter combinations according to the recipe template information, and there is an association mark between different recipe parameter combinations and recipe cooking procedures in the recipe sample data.

[0058] Input the recipe parameters in the recipe sample data into the big data model in a combined form for training, and use the association mark to learn the association relationship between different recipe parameter combinations and recipe cooking procedures during the training process.

[0059] According to the learned association relationship between different recipe parameter combinations and recipe cooking procedures, obtain the trained big data model.

[0060] In a possible implementation, the analysis module further includes:

[0061] A second analysis unit, configured to analyze the recipe input parameters according to the association relationship before inputting the recipe input parameters processed into a combined form into the trained big data model to perform association analysis on the combined recipe input parameters through the association relationship to obtain a recipe cooking process including the recipe input parameters;

[0062] If the recipe input parameters are not recorded in the association relationship, the first analysis unit is specifically configured to select recipe parameters having a similar effect to the recipe input parameters in the association relationship as alternative recipe parameters, process the alternative recipe parameters into a combined form and input them into the trained big data model to perform association analysis on the combined alternative recipe parameters through the association relationship to obtain a recipe cooking process including the alternative recipe parameters.

[0063] In a possible implementation, the generating module is specifically configured to:

[0064] Determine the ingredient specifications according to the recipe input parameters;

[0065] Determine the device information suitable for ingredient cooking according to the recipe cooking process including the recipe input parameters;

[0066] On the basis of the recipe cooking process, aggregate the ingredient specifications and the device information suitable for ingredient cooking to obtain an electronic recipe with corresponding ingredient specifications.

[0067] In a possible implementation, the generating module is specifically further configured to:

[0068] After determining the device information suitable for ingredient cooking according to the recipe cooking process including the recipe input parameters, determine the functional parameters suitable for the ingredient specifications according to the device information suitable for ingredient cooking;

[0069] Correspondingly, on the basis of the recipe cooking process, aggregate the ingredient specifications, the device information suitable for ingredient cooking, and the functional parameters suitable for the ingredient specifications to obtain an electronic recipe with corresponding ingredient specifications.

[0070] In a possible implementation, the device further includes:

[0071] A processing module, configured to process the electronic recipe into a recipe table and / or swimlane information with standard specifications after editing the recipe according to the recipe cooking process including the recipe input parameters to obtain an electronic recipe;

[0072] A sending unit, configured to synchronously send the recipe table and / or the lane information to a cooking device associated with the electronic recipe according to the device information associated with the electronic recipe, so that the cooking device performs recipe cooking according to the recipe table and / or the lane information.

[0073] In a third aspect, an electronic device is provided. The electronic device includes a processor and a memory. Among them, a computer program is stored in the memory, and the processor is configured to run the computer program to execute the method for generating an electronic recipe according to any one of the above.

[0074] In a fourth aspect, a storage medium is provided. The storage medium stores a computer program, and the computer program is configured to execute the method for generating an electronic recipe according to any one of the above when running.

[0075] By means of the above technical solutions, the method and device for generating an electronic recipe, the electronic device and the storage medium provided by the embodiments of the present application can construct recipe template information, in which recipe parameters obtained by text standardization of the original recipe are recorded; in response to a generation instruction of the electronic recipe, perform correlation analysis on the recipe entry parameters and the recipe template information to obtain a recipe cooking process including the recipe entry parameters; perform recipe editing according to the recipe cooking process including the recipe entry parameters to obtain an electronic recipe. It can be seen that by performing correlation analysis on the recipe entry parameters and the recipe template information, the embodiments of the present application can extract common recipe cooking processes, and perform recipe editing on the basis of the recipe cooking processes, so as to flexibly generate electronic recipes with different quantity requirements, thereby reducing the configuration time of cooking steps in the electronic recipe and improving the generation efficiency of the electronic recipe. Description of the Drawings

[0076] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for description in the embodiments of the present application will be briefly introduced below.

[0077] Figure 1 Shows a flowchart of the method for generating an electronic recipe provided by an embodiment of the present application;

[0078] Figure 2 Shows a schematic diagram of a recipe table corresponding to recipe template information provided by an embodiment of the present application;

[0079] Figure 3 Shows a schematic diagram of a recipe table corresponding to a recipe cooking process provided by an embodiment of the present application;

[0080] Figure 4 Shows a flowchart of the method for generating an electronic recipe provided by an embodiment of the present application;

[0081] Figure 5Shows the structural diagram of the electronic recipe creation device provided by the embodiments of the present application;

[0082] Figure 6 Shows the structural diagram of an electronic device provided by the embodiments of the present application. Detailed implementation manners

[0083] The exemplary embodiments of the present application will be described in more detail below with reference to the accompanying drawings. Although the exemplary embodiments of the present application are shown in the drawings, it should be understood that the present application can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided so that the present application can be more thoroughly understood and the scope of the present application can be fully conveyed to those skilled in the art.

[0084] It should be noted that the terms "first", "second", etc. in the description and claims of the present application and the above-mentioned drawings are used to distinguish similar objects and do not necessarily have to be used to describe a specific order or sequence. It should be understood that such use can be interchanged under appropriate circumstances so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the term "including" and its variants should be interpreted as open-ended terms meaning "including but not limited to".

[0085] As introduced above, the user can generate an electronic recipe by recording cooking steps or by describing cooking steps in natural language. However, these two ways of generating electronic recipes are usually for a single electronic recipe. When the client has a large demand for the number of electronic recipes, it takes a lot of time to configure the cooking steps, resulting in a low efficiency of generating electronic recipes. To solve this technical problem, the embodiments of the present application provide a method for generating an electronic recipe. This method can be applied to a configuration terminal, such as a smart phone, a tablet computer, a personal computer, etc., and can also be applied to other intelligent kitchen devices. This embodiment does not limit this. As Figure 1 shown, the method for generating an electronic recipe may include the following steps S101 to S103:

[0086] Step S101, construct recipe template information.

[0087] In this embodiment, the recipe template information records the recipe parameters obtained by text standardization of the original recipe. The original recipe here can be recipe data obtained from different recipe platforms. The specific source of the original recipe can be various food websites, internal data of catering institutions, or specialized recipe software. After obtaining the original recipe, in order to ensure the accuracy and integrity of the recipe data, data processing can be performed on the original recipe to remove duplicate, incorrect, or incomplete recipe records. For example, unifying the unit of cooking time, correcting typos in ingredient names, adjusting unreasonable ingredient amounts, or illogical cooking steps.

[0088] Considering that the original recipe covers recipe data of different cuisines, styles, and difficulty levels, for the convenience of subsequent recipe correlation analysis, the original recipe can be standardized according to the set recipe parameters to split the original recipe into the form of recipe parameters. Specifically, the original recipe can be split according to the recipe parameters in the form of word segmentation tags, and then the words after word segmentation are marked according to the set recipe parameters to split the original recipe into the form of recipe parameters. For example, for the recipe name "Sweet and Sour Pork Ribs", it is split into "sugar", "vinegar", and "pork ribs"; for the cooking process "Dice the chicken and marinate it with salt, cooking wine, and starch", it is split into "chicken", "dice", "salt", "cooking wine", "starch", and "marinate". The set recipe parameters here are equivalent to the key information of the electronic recipe, including but not limited to recipe name, ingredient name and amount, seasoning name and amount, etc., and can be increased or decreased according to actual needs.

[0089] It can be understood that the recipe template information can be updated according to actual needs or regularly. When a new recipe is entered, the recipe parameters of the new recipe can be obtained by text standardization of the new recipe, and then the recipe parameters of the new recipe are recorded in the recipe template information.

[0090] Furthermore, for the convenience of recipe recording, a recipe table can be set up, and the recipe parameters in the recipe template information are entered into the recipe table through the recipe table, and the key information of the original recipe is recorded accordingly through the recipe table. Exemplarily, as Figure 2 shown, Figure 2 the recipe template information corresponding to the recipe table records the recipe parameters obtained by text standardization of the original recipe, including recipe name, model, weight, ingredients, etc. It should be noted that the recipe table can add original recipes or batch import original recipes according to the actual situation, and enter the recipe parameters obtained by text standardization of the added original recipes accordingly.

[0091] Step S102, in response to the generation instruction of the electronic recipe, perform a correlation analysis on the recipe input parameters and the recipe template information to obtain a recipe cooking process containing the recipe input parameters.

[0092] In this step, the generation instruction of the electronic recipe can be triggered by the user through the client. Generally, the user can input at least one recipe parameter on the client, and through the generation instruction of the electronic recipe, at least one recipe parameter is combined and passed to the recipe generation system as the recipe input parameter. The recipe generation system performs an association analysis in the recipe template information according to the recipe input parameter to obtain the recipe cooking process containing the recipe input parameter. Here, the recipe cooking process has a time relationship, and each recipe cooking process corresponds to function parameters, time parameters, temperature parameters, etc. Among them, the function parameters include but are not limited to equipment function parameters, action function parameters, etc. Here, the equipment function can be the pot body work station, the pot body rotation parameter, and the action function parameter can be frying, stir-frying, steaming, boiling, frying, stirring, etc. The time parameter is the start execution time and / or execution duration corresponding to different function parameters in each recipe cooking process. For some function parameters that cannot be expressed by the time parameter, the corresponding function parameters do not have time parameters. The temperature parameter is the temperature requirement corresponding to different function parameters in each recipe cooking process. Similarly, for some that cannot be expressed by the temperature parameter, the corresponding function parameters do not have temperature parameters.

[0093] For the convenience of recipe recording, the recipe cooking process containing the recipe input parameter can also be recorded through a recipe table. Exemplarily, as Figure 3 shown, Figure 3 the recipe table in records the recipe cooking process and the corresponding function parameters, time parameters, temperature parameters, etc. for each recipe cooking process.

[0094] Specifically, in the process of associating and analyzing the recipe input parameter with the recipe template information, big data analysis technology can be used to establish an association database with the ability of association analysis, so as to construct a mapping relationship between the recipe parameter combination in the recipe template information and the corresponding cooking process through the association database. Based on the recipe input parameter, use the mapping relationship to search for the record with the highest matching degree with the recipe input parameter in the association database to obtain the recipe cooking process containing the recipe input parameter. For example, the recipe input parameter includes that the recipe name is "Kung Pao Chicken" and the ingredients include "chicken, peanuts, peppers". Accordingly, the recipe cooking process queried in the association database that matches the recipe input parameter includes "first dice and marinate the chicken, then fry the peanuts for later use, then stir-fry the chicken until it changes color, add peppers and other seasonings and stir-fry, and finally put the peanuts and mix well".

[0095] Considering the influence of ingredient proportions on the correlation analysis ability, it is also possible to optimize the recipe cooking process by analyzing the subtle influence of different ingredient proportions on the recipe cooking process in a large number of similar recipes on the basis of the recipe cooking process obtained through correlation analysis. At the same time, according to the user's feedback on the generated recipe cooking process, continuously adjust and improve the correlation analysis ability of the correlation database, so that it can more accurately match the appropriate recipe cooking process from the correlation database on the basis of the recipe input parameters.

[0096] Step S103, perform recipe editing according to the recipe cooking process containing the recipe input parameters to obtain an electronic recipe.

[0097] In this step, considering that the recipe cooking process is a general electronic recipe and does not have recipe applicability in actual applications, the recipe editing here can include unifying the format of the recipe parameters in the recipe cooking process. For example, convert the units such as weight and volume involved in the recipe parameters into standard units, and can also include standardizing the step expressions in the recipe cooking process. For example, modify the vague time description to a specific time node or a specific duration range. Then create a recipe document, and correspondingly mark the basic information such as the recipe name, cuisine, number of applicable people, etc. in the recipe document. After that, list the ingredient list in sequence, write down the name, quantity, and unit of each ingredient name, and then record the recipe cooking process item by item in detail, and correspondingly indicate the key elements such as actions, tools used, heat, time, etc. to generate an electronic recipe.

[0098] It can be understood that in order to facilitate the more intuitive display of the electronic recipe, ingredient pictures, cooking process step diagrams or finished product pictures can be generated according to the electronic recipe, and cooking tips such as key points for ingredient selection and special processing techniques can also be supplemented.

[0099] In the embodiment of the present application, by correlating and analyzing the recipe input parameters with the recipe template information to extract the common recipe cooking process, and correspondingly performing recipe editing on the basis of the recipe cooking process, electronic recipes with different quantity requirements can be flexibly generated, thereby reducing the configuration time of the cooking steps in the electronic recipe and improving the generation efficiency of the electronic recipe.

[0100] In actual applications, the recipe template information can be understood as the content framework that a recipe should contain, including recipe name, cuisine, ingredient list (main ingredients, auxiliary ingredients and seasonings), cooking equipment, cooking steps (including step numbers and detailed operations), cooking time and heat, finished product characteristics (taste, texture, appearance), and can also include nutritional information and applicable scenarios, etc. Specifically, the above step S101 constructs the recipe template information, which can specifically include the following steps A1 - A3:

[0101] Step A1: Collect original recipes in advance.

[0102] Step A2: Convert the original recipe into recipe information containing different recipe parameters through text standardization processing to obtain a standard electronic recipe.

[0103] Step A3: Use the set recipe fields to enter the recipe information of different recipe parameters in the standard electronic recipe into a recipe table to obtain recipe template information.

[0104] In this embodiment, the original recipes can be collected through various channels, including book collection, such as recipe monographs, lifestyle magazines, and food columns, and also including Internet platform collection, such as food websites, social media platforms, official websites and public accounts of catering brands, and also including offline channel collection, such as restaurant exchanges, cooking courses, and food events, etc. It should be noted that the examples here are only illustrative and do not limit this embodiment.

[0105] The above text standardization processing at least includes format cleaning, vocabulary standardization, structure adjustment, etc. Specifically, considering the different sources of the original recipes, such as pictures, paper documents, or voices of offline exchanges, etc., the text content can be first extracted from the original recipes through data extraction and cleaning, and then the description standardization processing is carried out on the original recipes in text form to obtain the original recipes with standardized text descriptions. Finally, the format of the original recipes with standardized text descriptions is converted using the standard recipe structure to obtain a standard electronic recipe.

[0106] In an application scenario, if the original recipe is in the form of a picture, optical character recognition technology can be used to convert the text in the picture into an editable text form of the original recipe. Then, the recipe description in the text form of the original recipe is standardized. Here, standardization includes ingredient standardization and step standardization. Ingredient standardization includes unifying the names and common names of various ingredients in the original recipe into standard names. For example, converting "potato" and "sweet potato" to "potato", and converting "tomato" and "love apple" to "tomato". Here, the conversion of the recipe description can be achieved through database query or text matching algorithms. Ingredient standardization also includes the specification of dosage and unit. Converting vague dosage expressions (such as "a little" or "appropriate amount") into precise or estimated numerical values and units to standardize the representation of ingredient dosage. For example, converting "a little salt" to "2 grams of salt" according to experience. At the same time, unifying the expression form of units also includes standardizing the specifications. For example, converting "1 catty" to "500 grams", and converting "1 tael" to "50 grams", etc. Step standardization includes unifying the verbs in the original recipe into verb specifications. Here, unifying verb specifications includes merging verbs with similar semantics to standardize the description of cooking actions. For example, unifying verbs such as "stir-fry", "stir-fry for a while", and "quick-fry" into "stir-fry", and unifying verbs such as "simmer slowly over low heat" and "braise over low heat" into "simmer over low heat". Step standardization also includes splitting the continuous cooking step text according to the logical order and numbering each step to clearly present the operation of each cooking step. For example, for the original recipe "First, wash and cut the chicken into pieces, put it into the pot and add water to cook until done, take it out and drain the water, then add oil, ginger and garlic and stir-fry until fragrant", after standardization, the cooking step text is "1. Wash and cut the chicken into pieces. 2. Add water to the pot and put the chicken into it to cook until done. 3. Take out the chicken and drain the water. 4. Add oil to the pot and put ginger and garlic into it to stir-fry until fragrant.". Finally, construct the standard recipe structure, including fields such as recipe name, ingredient list (including ingredient name, dosage, unit, category), cooking steps (including step number, detailed steps, time, heat), taste characteristics, applicable scenarios, etc. Fill the standardized recipe information into the standard recipe structure and store it in a database or file system. Here, a relational database (such as MySQL, PostgreSQL) or a non-relational database (such as MongoDB) can be selected to store the original recipe for subsequent query, retrieval, modification and management. For example, fill the original recipe with the standardized text description of "stewed beef with potatoes" into the above standard recipe structure to obtain a standard electronic recipe. In this way, the original recipe can be converted into a standard electronic recipe containing different recipe parameters, which is convenient for use in application scenarios such as smart kitchen appliances.

[0107] In this embodiment, the set recipe fields can be partial recipe parameters, usually the more critical recipe parameters in the electronic recipe, such as the dish name, cuisine type, ingredient list, cooking steps, time and heat, etc. Based on the set recipe fields, the process of entering the standard electronic recipe information into the recipe table requires extracting the corresponding information in the standard electronic recipe one by one, and then entering the corresponding information in the standard electronic recipe into the corresponding fields to form the complete recipe template information. Specifically, the dish name is accurately filled into the dish name field, the corresponding field of the cuisine type is entered, the main ingredients, dosages, auxiliary ingredients, and seasonings are filled in their respective ingredient fields as required, and for the cooking steps, the step numbers and detailed operation contents are filled into the corresponding step fields in sequence. The time and heat information are also filled into the total time and the time and heat fields of each step according to the actual situation. If there is information such as nutritional components and taste characteristics, they are also entered into the corresponding fields.

[0108] In an embodiment of the present application, a possible implementation manner is provided. In the above step A1, the original recipes are collected in advance. Specifically, at least one pattern recognition method can be used to recognize recipes in different recipe platforms to obtain the original recipes.

[0109] In the above steps, the pattern recognition methods include one or a combination of more of visual recognition method, speech recognition method, and / or text recognition method. For the text recognition method, keywords related to the recipe type can be determined first, such as ingredients including "potato" and "beef", cooking methods including "stew" or "fry", cuisine types including "Sichuan cuisine" or "Cantonese cuisine", etc. Then, the recipes in the recipe platform are recognized according to the keyword combination, and the original recipes are obtained through the recognition results. For the visual recognition method, the recipe pictures and / or dish pictures in the recipe platform are recognized according to the appearance of the dish (visual impression of color, shape, and ingredient combination), and the original recipes are obtained through the recognition results. For the speech recognition method, the original recipes can be entered through the speech function, and the recipe keywords can also be entered in the recipe platform through the speech function. The recipes in the recipe platform are recognized according to the recipe keywords, and the original recipes are obtained through the recognition results. It should be noted that combining multiple pattern recognition methods can recognize the original recipes more efficiently. For example, the recipe requirements are entered first through the speech recognition method, and then the original recipes are screened and determined through the text recognition method.

[0110] Since the visual recognition mode is usually applicable to recipe platforms with recipe pictures and has certain quality requirements for recipe pictures, such as clarity, resolution, and size, etc., the above steps use at least one pattern recognition method to perform recipe recognition in different recipe platforms to obtain the original recipe. Specifically, for the recipe pictures in different recipe platforms, the visual recognition method can be used to perform recipe recognition on the recipe pictures to obtain recipe ingredients, recipe text descriptions, and recipe visual clues; then, using the recipe visual clues as the visual reference conditions for determining the cooking progress and / or cooking status of the recipe, the recipe text description is split into ordered recipe cooking steps; the recipe ingredients are combined with the ordered recipe cooking steps to obtain the original recipe.

[0111] In this embodiment, for recipe ingredients, the visual recognition mode can accurately locate and label various ingredients in the recipe picture, such as identifying broccoli, shrimps, etc. in the plate, and can also judge the freshness of the ingredients according to their appearance as intact or processed, for example, sliced mushrooms or minced meat. Correspondingly, after identifying various ingredients, for the recipe text description, if the recipe picture records the text description, the recognized text description can be used as the recipe text description. If the recipe picture does not contain the recipe text description, the overall characteristics of the dish recognized from the recipe picture can be matched with the database to obtain the recipe name, and then the corresponding recipe text description can be searched on the recipe platform using the recipe name to obtain content such as the amount of ingredients used and precise cooking steps. Additionally, by analyzing the actions of the people and the changes in the state of the ingredients in the recipe picture, some cooking steps can be pieced together. For example, if there is oil in the pan and scallions in the recipe picture, it can be inferred that the cooking step is "pour oil into the pan and stir-fry scallions until fragrant".

[0112] The above recipe visual clues are visual clues extracted from aspects such as the appearance of the dish, the ingredient processing situation, and the kitchenware usage situation in the recipe picture. Common dish appearances include color, texture, and shape. Color includes the cooking degree, for example, the outer skin of fried chicken wings shows an attractive golden color, and also includes the freshness of the ingredients, such as bright red tomatoes. Texture and shape include the ingredient processing method, for example, shredded potatoes are suitable for quick frying, and the smooth texture of the meat slices indicates that they have been marinated with starch and egg white before cooking. It also includes the plasticity of the finished product, such as a multi-layer cake. Common ingredient processing situations include cutting forms, such as large pieces for stewing, thin slices for quick cooking, etc. Common kitchenware usage situations include kitchenware types, cooking environments, etc. The kitchenware type can imply the cooking method. For example, pancakes are made with a flat pan. The cooking environment, as a clue supplement to the cooking process, helps to improve the understanding of the cooking process. For example, the placement of seasoning bottles on the stove can prompt the use of these seasonings during the cooking process.

[0113] In the actual application scenario, the above process of generating the electronic recipe can be applied to a recipe generation system. Correspondingly, before step 102, the method can further include the following steps B1 - B2:

[0114] Step B1: Import the recipe parameters in the recipe template information into the recipe generation system in at least one batch. Each batch import process includes at least the recipe parameters of one original recipe in the recipe template information.

[0115] Step B2: The recipe generation system stores the corresponding batch-imported recipe parameters according to the set recipe format, so as to obtain recipe template information with the set recipe format based on the recipe parameters imported at least once.

[0116] In this embodiment, the recipe parameters in the recipe template information can be imported into the recipe generation system in one batch, or can be imported into the recipe generation system in multiple batches. The recipe parameters imported each time can be set by the user. For example, import the recipe parameters corresponding to 100 original recipes, or can be automatically imported by triggering at time intervals. For example, during the recipe collection process, automatically import the recipe parameters corresponding to the collected original recipes every 2 hours.

[0117] It can be understood that the recipe generation system has its own storage format. Usually, after receiving the recipe parameters, the recipe template generation system can store the imported recipe parameters according to its own storage format. Here, the storage format of the recipe generation system itself can include multiple data tables, such as recipe table, user table, favorite table, and date record table, etc. Further, the imported recipe fields are automatically inserted into the corresponding data tables by means of field recognition to obtain recipe template information with the set recipe format.

[0118] The above step 102 performs correlation analysis on the recipe input parameters and the recipe template information to obtain a recipe cooking process including the recipe input parameters, which can specifically include the following steps C1 - C3:

[0119] Step C1: Perform model training for big data analysis according to the recipe template information, so as to construct the correlation relationship between different recipe parameter combinations and recipe cooking processes through the trained big data model.

[0120] Step C2: Process the recipe input parameters into a combined form and input them into the trained big data model, so as to perform correlation analysis on the combined recipe input parameters through the correlation relationship to obtain a recipe cooking process including the recipe input parameters.

[0121] In the above steps, during the process of model training for big data analysis according to the recipe template information, big data analysis can be performed on the recipe template information to determine the correlation rules, establish a correlation matrix or table according to the correlation rules, and use the correlation matrix or correlation table to construct the correlation relationship between different recipe parameter combinations and recipe cooking processes during the model training process.

[0122] Specifically, the recipe template information analyzed through big data mainly includes two aspects. On the one hand, based on the association between ingredients and recipe cooking procedures, the characteristics and cooking requirements of the ingredients in the recipe template information are analyzed and associated with the cooking methods, times, cooking temperatures, etc. in the recipe input parameters. For example, for vegetable ingredients with high water content, in the recipe input parameters for stir-frying, the cooking time is usually shorter, and the cooking temperature is mainly high heat for quick stir-frying. The specific cooking procedure associated is "High heat, pour oil into the pan, when the oil is hot, put in the sliced cucumber, and stir-fry quickly for 2 - 3 minutes". On the other hand, based on the association between cooking equipment and recipe cooking procedures, according to the type of cooking equipment in the recipe input parameters, the corresponding recipe cooking procedures are determined. Taking the oven as an example, if the recipe input parameters specify the use of an oven and the ingredient is cake batter, the corresponding recipe cooking procedure is "Preheat the oven to the set temperature, place the mold containing the cake batter in the middle layer of the oven, bake for 30 - 40 minutes, and observe the color and swelling of the cake surface during baking". Then, according to the association rules, a two-dimensional association matrix is created, with the recipe input parameters as rows and the specific content in the recipe template information as columns, and the association relationship between the two is filled in the matrix. For example, in the cross-cell of the row "Ingredient - Chicken" and the column "Cooking Method - Deep-frying", fill in "Cut the chicken into uniform pieces, coat with flour or starch, and deep-fry in an oil pan at about 180°C until golden brown, for about 5 - 7 minutes". Then, the two-dimensional association matrix is refined using the association table, where the association table includes each item of the recipe input parameters, the key content of the recipe template information, and the description of the cooking procedure after association. For example, for the "Braised Pork" e-recipe, list the recipe input parameters in the recipe table, then list the pre-treatment steps, main cooking steps, time and cooking temperature, etc. information correspondingly, and the last column gives the recipe cooking procedure after association.

[0123] Specifically, in the process of performing association analysis on the combined recipe input parameters through the association relationship, first, the recipe input parameters are integrated. For example, information such as ingredient types, usage amounts, cooking methods, equipment, etc. are combined into a specific data format, such as a vector or a structured data form. Then, the recipe parameters are input into a pre-trained big data model in a combined form. The big data model, based on the association relationships learned from numerous recipe data, such as the connection between a certain ingredient and a specific cooking method, time, and cooking temperature, performs association analysis on the combined recipe input parameters. Through this association relationship, matching and reasoning are carried out to obtain the recipe cooking procedures containing the recipe input parameters, such as the detailed step sequence, time setting for each step, cooking temperature control, etc., thus completing the generation process from recipe input parameters to cooking procedures.

[0124] Correspondingly, the above step C1 performs model training for big data analysis according to the recipe template information, so as to construct the association relationship between different recipe parameter combinations and recipe cooking procedures through the trained big data model. Specifically, it may include the following steps D1-D2:

[0125] Step D1: Construct recipe sample data containing different recipe parameter combinations according to the recipe template information.

[0126] Step D2: Input the recipe parameters in the recipe sample data in combination form into the big data model for training, and utilize the association markers during the training process to learn the association relationship between different recipe parameter combinations and recipe cooking procedures.

[0127] Step D3: Obtain the trained big data model according to the learned association relationship between different recipe parameter combinations and recipe cooking procedures.

[0128] In the above steps, there are association markers between different recipe parameter combinations and recipe cooking procedures in the recipe sample data. In the recipe sample data, the association relationship is used to record the association relationship between different recipe parameter combinations (such as different combination situations in aspects like the selection and combination of ingredients, cooking methods, tools used, expected taste characteristics, etc.) and the corresponding recipe cooking procedures (including detailed processes from ingredient pre-treatment, cooking operations at each stage to the final finishing steps).

[0129] For example, for the recipe parameter combination "ingredients include tomatoes and eggs, cooking method is stir-frying, and a wok is used", the associated cooking procedures are as follows: "1. Wash the tomatoes and cut them into pieces for later use; 2. Crack the eggs into a bowl, add a small amount of salt and stir well; 3. Pour oil into the pan, pour in the egg mixture after the oil is hot, stir-fry until cooked and remove; 4. Pour a little more oil into the pan, sauté the scallions until fragrant, add the tomato pieces and stir-fry, add an appropriate amount of salt for seasoning after the juice is out; 5. Finally, pour in the fried eggs and stir-fry evenly before taking out of the pan". Here, the recipe name or recipe number of "scrambled eggs with tomatoes" can be used as the association marker and associated with the cooking procedures.

[0130] For the selection of big data models, neural networks such as Recurrent Neural Network (RNN), Long Short-Term Memory Network (LSTM), Convolutional Neural Network (CNN), or other machine learning models such as decision trees and support vector machines can be used. If the cooking process of a recipe consists of multiple cooking steps with a sequential order, considering the need for long-term dependencies in processing sequences, it is preferred to use RNN or LSTM. If classifying or regressing based on the features of recipe parameter combinations to predict the cooking process of a recipe, models such as decision trees or support vector machines are preferred. Specifically, the input of the big data model is a recipe parameter combination vector, and the output is a recipe cooking process vector, which can be a predicted cooking step sequence or the category of steps, etc. When constructing the model, considering the role of the association markers during model training, the association markers can be used as additional input features, or the data can be grouped and trained according to the association markers during model training. Correspondingly, within each group, the big data model is trained separately so that the big data model can learn the specific association relationship between the recipe parameter combinations and the cooking process within the group. For example, in the "stewed dishes" group, the big data model focuses on learning the relationship between the ingredient combinations of stewed dishes and the cooking process of recipes with long-term stewing.

[0131] Before inputting the recipe entry parameters processed into a combined form into the trained big data model in step 103 above to perform association analysis on the combined recipe entry parameters through the association relationship and obtain the recipe cooking process containing the recipe entry parameters, the recipe entry parameters can be analyzed according to the association relationship.

[0132] If the recipe entry parameters are not recorded in the association relationship, in step 102 above, the recipe entry parameters are processed into a combined form and input into the trained big data model to perform association analysis on the combined recipe entry parameters through the association relationship and obtain the recipe cooking process containing the recipe entry parameters. Specifically, recipe parameters with similar effects to the recipe entry parameters can be selected as substitute recipe parameters in the association relationship, and the substitute recipe parameters are processed into a combined form and input into the trained big data model to perform association analysis on the combined substitute recipe parameters through the association relationship and obtain the recipe cooking process containing the substitute recipe parameters.

[0133] Specifically, when the system encounters unrecorded ingredients or seasonings, the recipe template information cannot analyze the recipe cooking process of the corresponding ingredients or seasonings. At this time, big data analysis technology can be used to search for ingredients or seasonings with similar effects in the existing huge database of ingredients and seasonings. Ingredients can be matched based on multi-dimensional features such as category, nutritional content, taste, texture, and appearance to find similar ingredients, and seasonings can be determined based on flavor attributes (such as removing fishy smell, enhancing fragrance, and enhancing freshness). The cooking processes of the recipes corresponding to these ingredients and seasonings with similar effects are then analyzed. The big data system will mine cooking cases involving these ingredients and seasonings with similar effects in numerous recipes to count the data patterns in preprocessing (such as washing, peeling, cutting, etc.), cooking methods (frying, stewing, steaming, boiling, etc.), cooking time, heat control, and pairing with other ingredients. Based on these data patterns, processing technology recommendations for unincluded ingredients or seasonings are generated. For example, if the unincluded ingredients are similar to a common vegetable in terms of nutritional components and taste texture, and the common vegetable is mostly cooked by quick stir-frying, a similar quick stir-frying processing technology can be recommended for the unincluded ingredients, including detailed processing technology information such as appropriate cutting shapes, stir-frying time range, and heat size, thereby realizing the association analysis of unincluded ingredients and seasonings based on recipe parameters with similar effects.

[0134] In an application scenario, the above step 103 edits the recipe according to the recipe cooking process including the recipe entry parameters to obtain an electronic recipe, which may specifically include the following steps E1-E3:

[0135] Step E1: Determine the specifications of ingredients according to the recipe entry parameters.

[0136] Step E2: Determine equipment information suitable for cooking ingredients according to the recipe cooking process including the recipe entry parameters.

[0137] Step E3: Based on the recipe cooking process, the ingredient specifications and the equipment information adapted for cooking the ingredients are aggregated to obtain an electronic recipe of corresponding ingredient specifications.

[0138] In this embodiment, different unit words such as units and quantities, including grams, liters, pieces, roots, and pieces, can be used as key clues to determine the specifications of ingredients. For example, 200 grams of pork can determine the weight specification as 200 grams; 3 potatoes can determine the quantity specification as 3. The shape and size description of ingredients, including length, width, height, thickness, and diameter, can also be used as key clues to determine the specifications of ingredients. For example, carrots (about 15 cm long and about 3 cm in diameter) can determine the length and diameter specifications; bread (cut into slices with a thickness of 2 cm) can determine the thickness specification.

[0139] Considering that cooking processes involve different cooking actions, such as frying, stir-frying, or deep-frying, etc., the corresponding cooking-adapted devices are wok and frying pan. Here, the device information suitable for cooking the ingredients can be determined based on the cooking actions extracted from the recipe cooking process. For example, in the recipe cooking process, there is "Pour oil into the pan, put the sliced potato chips into the pan, and stir-fry over medium-low heat until golden brown". Here, the "in the pan" combined with the "stir-fry" action can determine that the suitable device is a wok. If the device information is directly recorded in the recipe cooking process, the device information suitable for cooking the ingredients can be directly determined through the device description in the recipe cooking process. For example, in the recipe cooking process, there is "Crack the egg into a frying pan and fry over low heat until the egg white solidifies", and it can be directly determined that the suitable device is a frying pan.

[0140] Specifically, in the process of aggregating the ingredient specifications and the device information suitable for cooking the ingredients, it is necessary to standardize the ingredient specifications to unify the ingredient specifications and the specification descriptions, and then select the device information according to the ingredient specifications, such as device name, model, capacity range, etc. Finally, by designing a recipe template, the corresponding ingredient specifications and device information are inserted into the recipe cooking process to timely mention the ingredient specifications and the use of the device in the recipe cooking process. For example, in the cooking step of "Stir-fry over high heat until the color changes", add the ingredient specification of "200 grams of diced chicken breast with a side length of 1 cm" and the device information of "A wok with a diameter of 30 cm" to closely combine the ingredient specifications, device information, and cooking process, facilitating the user to understand the entire cooking process.

[0141] Furthermore, after determining the device information suitable for cooking the ingredients according to the recipe cooking process containing the recipe input parameters in step E2 above, the functional parameters suitable for the ingredient specifications can also be determined according to the device information suitable for cooking the ingredients;

[0142] Correspondingly, step E3 above is to aggregate the ingredient specifications, the device information suitable for cooking the ingredients, and the functional parameters suitable for the ingredient specifications on the basis of the recipe cooking process to obtain an electronic recipe for the corresponding ingredient specifications.

[0143] In this embodiment, considering that different device information has different cooking functions, the performance of the cooking device is determined here through the device information suitable for cooking the ingredients, and the functional parameters suitable for the ingredient specifications are determined according to the performance of the cooking device. For example, for ovens of different models, their performances such as heating power and temperature uniformity are different. If using an oven with a power of 2000 watts and good temperature uniformity to bake a 500-gram cake, the temperature can be set at 160 - 180 °C and baked for 30 - 40 minutes. However, if it is an oven with a lower power (such as 150 watts) and slightly worse temperature uniformity, the temperature may need to be appropriately reduced (such as 150 - 170 °C) and the baking time extended (such as 40 - 50 minutes).

[0144] The functional parameters adapted to the above food ingredient specifications include but are not limited to temperature parameters, time parameters, power parameters, and capacity parameters, etc. Here, the temperature parameter can be a temperature range, such as 180 - 200 °C, or the temperature control accuracy, such as making yogurt requires fermentation in a constant temperature environment of 40 - 45 °C, or the temperature uniformity, such as the internal temperature of the oven is evenly distributed. Here, the time parameter can be a time range, such as the stir-frying time is 5 minutes, or the time control accuracy, such as boiling in boiling water for 5 - 6 minutes. Here, the power parameter can be the heating power, such as the heating power of the oven is 2000 - 3000 watts, or the stirring power, such as the stirring power of the chef machine or bread machine when making dough is 300 - 500 watts. Here, the capacity parameter can be the capacity adapted to the volume of the food ingredients, such as using a stew pot of 6 - 8 liters for making large stews, and a small frying pan with a diameter within 18 cm for making small portions of fried eggs.

[0145] Correspondingly, specifically in the process of aggregating the food ingredient specifications, the device information adapted to food ingredient cooking, and the functional parameters adapted to food ingredient specifications, based on aggregating the food ingredient specifications and the device information adapted to food ingredient cooking to obtain an electronic recipe, the functional parameters adapted to food ingredient specifications can be inserted into the recipe cooking process by designing a recipe template, so as to mention the functional parameters adapted to the food ingredients in a timely manner during the recipe cooking process.

[0146] Furthermore, considering the associated execution of the electronic recipe, after generating the electronic recipe, the electronic recipe can be processed into a recipe table and / or swimlane information with standard specifications; according to the device information associated with the electronic recipe, the recipe table and / or swimlane information is synchronously sent to the cooking device associated with the electronic recipe, so that the cooking device cooks the recipe according to the recipe table and / or swimlane information. In the field of recipes, the swimlane information is equivalent to dividing different elements in the cooking process into different "swimlanes" or "zones" for display, such as time, food ingredient processing, device usage, etc., and can be specifically divided into a time swimlane, a food ingredient processing swimlane, and a device usage swimlane. The time swimlane is the most intuitive swimlane reflecting the cooking process sequence, and the entire time period from the start to the end of cooking can be divided into small intervals to determine the start time and duration of each cooking step. The food ingredient processing swimlane is used to reflect the state changes of the food ingredients, including steps such as preprocessing, marinating, operations during cooking, and final plating of the food ingredients. The device usage swimlane is used to record the usage of various kitchen devices during the cooking process, and indicates the operating parameters of the used devices according to the cooking sequence, such as temperature, power, and usage duration, etc.

[0147] In an actual application scenario, after generating a recipe table and / or swimlane information with standard specifications, the standard electronic recipe and / or swimlane information can be data-encapsulated, encoded according to the network communication protocol, and sent to the cooking device associated with the electronic recipe via a wired or wireless network. During the transmission process, the data may be compressed or transmitted in chunks according to the network bandwidth and device reception capabilities. For example, if the network environment is poor, the recipe data can be divided into multiple small packets, sent sequentially, and reassembled at the device end. At the same time, the data is encrypted to ensure the security of the recipe information during transmission and prevent it from being stolen or tampered with.

[0148] Correspondingly, after receiving the data, the cooking device first performs decryption and decoding operations to restore the recipe data to the format of the standard electronic recipe and / or swimlane information. Then, the control system of the cooking device analyzes the standard electronic recipe, extracts key information such as the dish name, ingredient list, cooking procedures, and equipment usage requirements, and stores this key information in the device's memory or local storage for easy access during the cooking process. For example, when a smart oven receives the recipe data for "baked chicken wings", it analyzes and obtains parameters such as preheating the oven to 200°C and baking for 20 - 25 minutes, and sets these parameters in the oven's control system. Further, based on the analyzed recipe information, the cooking device automatically starts the cooking program to achieve seamless connection from the recipe information to automatic cooking. During the cooking process, the control system of the cooking device precisely controls according to the information in the time swimlane, ingredient processing swimlane, and equipment usage swimlane. For example, according to the indication in the time swimlane, turn on or off devices such as the stove and oven at the predetermined time point; control the stirrer, frying device, etc. to process the ingredients according to the requirements of the ingredient processing swimlane; adjust the operating states such as the temperature, power, and rotation speed of the device according to the parameters in the equipment usage swimlane.

[0149] In an actual application scenario, the embodiment of the present application also provides a flowchart of another method for generating an electronic recipe. As Figure 4 shown, first write the pre-collected recipe parameters into the recipe generation system through the recipe template information. When receiving the recipe input parameters, the system extracts the associated recipe parameters according to the big data analysis of the recipe template information, generates the corresponding electronic recipe, and sends the electronic recipe to the cooking device associated with the electronic recipe.

[0150] Based on the method for generating an electronic recipe provided in the above embodiments, based on the same inventive concept, the embodiment of the present application also provides an apparatus for generating an electronic recipe.

[0151] Figure 5 is the structural diagram of the apparatus for generating an electronic recipe provided by the embodiment of the present application. As Figure 5As shown in the figure, the generating device of the electronic recipe may specifically include a construction module 510, an analysis module 520, and a generating module 530.

[0152] The construction module 510 is configured to construct recipe template information, where the recipe parameters obtained by text standardization of the original recipe are recorded in the recipe template information.

[0153] The analysis module 520 is configured to perform correlation analysis on the recipe input parameters and the recipe template information in response to a generating instruction of the electronic recipe, so as to obtain a recipe cooking process including the recipe input parameters.

[0154] The generating module 530 is configured to perform recipe editing according to the recipe cooking process including the recipe input parameters to obtain an electronic recipe.

[0155] In an embodiment of the present application, a possible implementation manner is provided. The construction unit includes:

[0156] A collection unit configured to collect original recipes in advance.

[0157] A conversion unit configured to convert the original recipe into recipe information including different recipe parameters through text standardization processing to obtain a standard electronic recipe.

[0158] An input unit configured to input the recipe information of different recipe parameters in the standard electronic recipe into a recipe table by using set recipe fields to obtain recipe template information.

[0159] In an embodiment of the present application, a possible implementation manner is provided. The collection unit is specifically configured to:

[0160] Perform recipe recognition in different recipe platforms by using at least one pattern recognition method to obtain an original recipe, where the pattern recognition method includes one or a combination of a visual recognition method, a voice recognition method, and / or a text recognition method.

[0161] In an embodiment of the present application, a possible implementation manner is provided. The device further includes:

[0162] An import module configured to, before performing correlation analysis on the recipe input parameters and the recipe template information in response to a generating instruction of the electronic recipe to obtain a recipe cooking process including the recipe input parameters, import the recipe parameters in the recipe template information into a recipe generation system in at least one batch, and each batch import process includes at least the recipe parameters of one original recipe in the recipe template information; correspondingly, the recipe generation system stores the correspondingly batch-imported recipe parameters according to a set recipe format to obtain recipe template information with a set recipe format based on the recipe parameters imported in at least one batch.

[0163] In an embodiment of the present application, a possible implementation manner is provided. The analysis module includes:

[0164] A construction unit, configured to perform model training for big data analysis according to the recipe template information, so as to construct an association relationship between different recipe parameter combinations and recipe cooking procedures through the trained big data model;

[0165] A first analysis unit, configured to process the recipe input parameters into a combined form and input them into the trained big data model, so as to perform association analysis on the combined recipe input parameters through the association relationship, and obtain a recipe cooking procedure including the recipe input parameters;

[0166] The construction unit is specifically configured to:

[0167] Construct recipe sample data including different recipe parameter combinations according to the recipe template information, and there is an association mark between different recipe parameter combinations and recipe cooking procedures in the recipe sample data;

[0168] Input the recipe parameters in the recipe sample data into the big data model in a combined form for training, and use the association mark to learn the association relationship between different recipe parameter combinations and recipe cooking procedures during the training process;

[0169] Obtain a trained big data model according to the learned association relationship between different recipe parameter combinations and recipe cooking procedures.

[0170] In an embodiment of the present application, a possible implementation manner is provided. The analysis module further includes:

[0171] A second analysis unit, configured to analyze the recipe input parameters according to the association relationship before processing the recipe input parameters into a combined form and inputting them into the trained big data model, so as to perform association analysis on the combined recipe input parameters through the association relationship and obtain a recipe cooking procedure including the recipe input parameters;

[0172] If the recipe input parameters are not recorded in the association relationship, the first analysis unit is specifically configured to select recipe parameters with a similar effect to the recipe input parameters in the association relationship as substitute recipe parameters, process the substitute recipe parameters into a combined form and input them into the trained big data model, so as to perform association analysis on the combined substitute recipe parameters through the association relationship, and obtain a recipe cooking procedure including the substitute recipe parameters.

[0173] In an embodiment of the present application, a possible implementation manner is provided. The generation module is specifically configured to:

[0174] Determine the ingredient specifications according to the recipe input parameters;

[0175] Determine the device information suitable for cooking the ingredients according to the recipe cooking process including the recipe input parameters;

[0176] Based on the recipe cooking process, aggregate the ingredient specifications and the device information suitable for cooking the ingredients to obtain an electronic recipe for the corresponding ingredient specifications.

[0177] In a possible implementation manner provided in the embodiments of the present application, the generating module is specifically further configured to:

[0178] After determining the device information suitable for cooking the ingredients according to the recipe cooking process including the recipe input parameters, determine the function parameters suitable for the ingredient specifications according to the device information suitable for cooking the ingredients;

[0179] Correspondingly, based on the recipe cooking process, aggregate the ingredient specifications, the device information suitable for cooking the ingredients, and the function parameters suitable for the ingredient specifications to obtain an electronic recipe for the corresponding ingredient specifications.

[0180] In a possible implementation manner provided in the embodiments of the present application, the device further includes:

[0181] A processing module, configured to process the electronic recipe into a recipe table and / or swimlane information with standard specifications after editing the recipe according to the recipe cooking process including the recipe input parameters to obtain the electronic recipe;

[0182] A sending unit, configured to synchronously send the recipe table and / or swimlane information to the cooking device associated with the electronic recipe according to the device information associated with the electronic recipe, so that the cooking device cooks the recipe according to the recipe table and / or swimlane information.

[0183] Based on the same inventive concept, the embodiments of the present application further provide an electronic device, including a processor and a memory, where a computer program is stored in the memory, and the processor is configured to run the computer program to execute the method for generating an electronic recipe in any one of the above embodiments.

[0184] In an exemplary embodiment, an electronic device is provided, as Figure 6 shown, Figure 6 The electronic device 600 shown includes: a processor 601 and a memory 603. Among them, the processor 601 and the memory 603 are connected, such as connected through a bus 602. Optionally, the electronic device 600 may further include a transceiver 604. It should be noted that in practical applications, the transceiver 604 is not limited to one, and the structure of the electronic device 600 does not constitute a limitation to the embodiments of the present application.

[0185] The processor 601 may be a CPU (Central Processing Unit), a general-purpose processor, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array), or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. It can implement or execute various exemplary logical blocks, modules, and circuits described in connection with the disclosure of this application. The processor 601 may also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, etc.

[0186] The bus 602 may include a path for transmitting information between the above components. The bus 602 may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus, etc. The bus 602 may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 6 only a thick line is shown in the figure, but it does not mean that there is only one bus or one type of bus.

[0187] The memory 603 may be a ROM (Read Only Memory) or other type of static storage device that can store static information and instructions, a RAM (Random Access Memory) or other type of dynamic storage device that can store information and instructions, or it may also be an EEPROM (Electrically Erasable Programmable Read Only Memory), a CD-ROM (Compact Disc Read Only Memory), or other optical disc storage, optical disc storage (including compact discs, laser discs, optical discs, digital versatile discs, Blu-ray discs, etc.), magnetic disk storage media, or any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto.

[0188] The memory 603 is used to store the computer program code for executing the solution of this application, and is controlled by the processor 601 for execution. The processor 601 is used to execute the computer program code stored in the memory 503 to implement the content shown in the foregoing method embodiments.

[0189] Among them, the electronic device includes but is not limited to: mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Tablet Computers), PMPs (Portable Multimedia Players), in-vehicle terminals (such as in-vehicle navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 6 The electronic device shown is only an example and should not impose any limitations on the functions and usage scope of the embodiments of this application.

[0190] Based on the same inventive concept, the embodiments of this application also provide a storage medium, in which a computer program is stored. Among them, the computer program is set to execute the method for generating an electronic recipe in any of the foregoing embodiments when running.

[0191] Those skilled in the art can clearly understand the specific working processes of the above-described systems, devices, and modules, and can refer to the corresponding processes in the foregoing method embodiments. For the sake of brevity, they will not be described in detail here.

[0192] Those of ordinary skill in the art can understand that the technical solution of this application, in essence, or all or part of this technical solution can be embodied in the form of a software product. This computer software product is stored in a storage medium, which includes several program instructions for causing an electronic device (such as a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the embodiments of this application when running the program instructions. The foregoing storage medium includes: various media that can store program code such as USB flash drives, mobile hard disks, read-only memories (ROMs), random access memories (RAMs), magnetic disks, or optical discs.

[0193] Alternatively, all or part of the steps of implementing the foregoing method embodiments can be completed by hardware related to program instructions (such as an electronic device such as a personal computer, a server, or a network device). The program instructions can be stored in a computer-readable storage medium. When the program instructions are executed by the processor of the electronic device, the electronic device executes all or part of the steps of the methods described in the embodiments of this application.

[0194] The above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it; although the present application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that within the spirit and principle of the present application, it is still possible to modify the technical solutions described in the foregoing embodiments, or to perform equivalent replacements on some or all of the technical features; and these modifications or replacements do not cause the corresponding technical solutions to deviate from the protection scope of the present application.

Claims

1. A method for generating an electronic recipe, characterized in that: include: Constructing recipe template information, wherein the recipe template information records recipe parameters obtained by text standardization of the original recipe; In response to the electronic recipe generation instruction, the recipe entry parameters are correlated and analyzed with the recipe template information to obtain a recipe cooking process including the recipe entry parameters; The recipe is edited according to the recipe cooking process including the recipe entry parameters to obtain an electronic recipe.

2. The method according to claim 1, characterized in that The recipe template information is constructed, including: Collect original recipes in advance; Converting the original recipe into recipe information containing different recipe parameters through text standardization processing to obtain a standard electronic recipe; The recipe information of different recipe parameters in the standard electronic recipe is entered into the recipe table by using the set recipe field to obtain the recipe template information.

3. The method according to claim 2, characterized in that The pre-collection of original recipes includes: Recipe recognition is performed on different recipe platforms using at least one pattern recognition method to obtain an original recipe, wherein the pattern recognition method includes a combination of one or more of a visual recognition method, a voice recognition method and / or a text recognition method.

4. The method according to claim 1, characterized in that Before the step of performing correlation analysis on the recipe input parameters and the recipe template information in response to the electronic recipe generation instruction to obtain the recipe cooking process including the recipe input parameters, the method further comprises: Importing the recipe parameters in the recipe template information into the recipe generation system in batches at least once, wherein each batch import process includes at least the recipe parameters of one original recipe in the recipe template information; Correspondingly, the recipe generation system stores the corresponding batch-imported recipe parameters according to the set recipe format, so as to obtain recipe template information having the set recipe format according to the recipe parameters imported in batch at least once.

5. The method according to any one of claims 1 to 4, characterized in that The step of performing correlation analysis on the recipe entry parameters and the recipe template information to obtain a recipe cooking process including the recipe entry parameters includes: Performing model training for big data analysis based on the recipe template information, so as to construct associations between different recipe parameter combinations and recipe cooking processes through the trained big data model; Processing the recipe entry parameters into a combined form and inputting them into the trained big data model, so as to perform association analysis on the combined recipe entry parameters through the association relationship, and obtain a recipe cooking process including the recipe entry parameters; The model training for big data analysis based on the recipe template information, so as to construct the association between different recipe parameter combinations and recipe cooking processes through the trained big data model, includes: Constructing recipe sample data including different recipe parameter combinations according to the recipe template information, wherein different recipe parameter combinations in the recipe sample data are associated with recipe cooking processes; Inputting the recipe parameters in the recipe sample data into the big data model in combination for training, and using the association tags to learn the association relationship between different recipe parameter combinations and recipe cooking processes during the training process; Based on the learned correlation between different recipe parameter combinations and recipe cooking processes, a trained big data model is obtained.

6. The method according to claim 5, characterized in that Before processing the recipe entry parameters into a combined form and inputting them into the trained big data model, so as to perform association analysis on the combined recipe entry parameters through the association relationship to obtain a recipe cooking process including the recipe entry parameters, the method further includes: Analyzing the recipe entry parameters according to the association relationship; If the recipe entry parameters are not recorded in the association relationship, the recipe entry parameters are processed into a combination form and input into the trained big data model, so as to perform association analysis on the combined recipe entry parameters through the association relationship to obtain a recipe cooking process containing the recipe entry parameters, including: In the association relationship, recipe parameters having similar effects to the recipe entry parameters are selected as substitute recipe parameters, and the substitute recipe parameters are processed into a combination form and input into the trained big data model, so as to perform association analysis on the substitute recipe parameters in the combination form through the association relationship to obtain the recipe cooking process containing the substitute recipe parameters.

7. The method according to any one of claims 1 to 4, characterized in that The step of editing a recipe according to the recipe cooking process including the recipe entry parameters to obtain an electronic recipe includes: Determine the specifications of ingredients according to the recipe input parameters; Determining equipment information suitable for cooking ingredients according to the recipe cooking process including the recipe entry parameters; On the basis of the recipe cooking process, the food specifications and the equipment information adapted for cooking the food are aggregated to obtain an electronic recipe with corresponding food specifications.

8. The method according to claim 7, characterized in that After determining the equipment information suitable for cooking the ingredients according to the recipe cooking process including the recipe entry parameters, the method further includes: Determine the function parameters suitable for the specifications of the ingredients according to the equipment information suitable for cooking the ingredients; Correspondingly, based on the recipe cooking process, the ingredient specifications, the equipment information adapted for the ingredient cooking, and the functional parameters adapted for the ingredient specifications are aggregated to obtain an electronic recipe of the corresponding ingredient specifications.

9. The method according to any one of claims 1 to 4, characterized in that After editing the recipe according to the recipe cooking process including the recipe entry parameters to obtain the electronic recipe, the method further includes: Processing the electronic recipe into a recipe table and / or lane information with standard specifications; According to the device information associated with the electronic recipe, the recipe table and / or lane information is synchronously sent to the cooking device associated with the electronic recipe, so that the cooking device performs recipe cooking according to the recipe table and / or lane information.

10. An electronic recipe generation device, characterized in that: include: A construction module, used to construct recipe template information, wherein the recipe template information records recipe parameters obtained by text standardization of the original recipe; An analysis module, for responding to an instruction for generating an electronic recipe, performing correlation analysis on the recipe input parameters and the recipe template information to obtain a recipe cooking process including the recipe input parameters; The generating module is used to edit the recipe according to the recipe cooking process including the recipe entry parameters to obtain an electronic recipe.

11. An electronic device, characterized in that: The invention comprises a processor and a memory, wherein a computer program is stored in the memory, and the processor is configured to run the computer program to execute the method for generating an electronic recipe according to any one of claims 1 to 9.

12. A storage medium, characterized in that: The storage medium stores a computer program, wherein the computer program is configured to execute the method for generating an electronic recipe according to any one of claims 1 to 9 when running.

Images