A recipe management method and device, electronic equipment and storage medium

Abstract

This application discloses a recipe management method, apparatus, electronic device, and storage medium. The recipe management method is applied to a cooking equipment management system, which is communicatively connected to the cooking equipment and provides recipes to the cooking equipment. The method includes: acquiring a target cooking video carrying a cooking tag from a target network platform; extracting key image frames from the preprocessed target cooking video; identifying cooking-related visual features in the key image frames to obtain first key descriptive information; converting the audio of the preprocessed target cooking video into text, extracting textual descriptions related to the cooking process from the text to obtain second key descriptive information; and generating a recipe based on the key image frames, the first key descriptive information, and the second key descriptive information. This application achieves dynamic updating, accurate presentation, and convenient access to recipes.

Description

Technical Field

[0001] This application relates to the field of cooking equipment technology, and in particular to a recipe management method, device, electronic device and storage medium. Background Technology

[0002] In existing cooking equipment technology, users primarily rely on traditional information input and interaction methods to obtain recipe information and perform corresponding cooking operations. One common approach is to pre-set a certain number of fixed recipe programs within the cooking equipment. Users can select these programs through the equipment's interface, and the equipment then executes the corresponding operations based on the preset cooking parameters and procedures. However, due to the limited number and variety of built-in recipes, it is difficult to meet the increasingly diverse and personalized dietary needs of users, and it also cannot be flexibly updated to adapt to the development of emerging cuisines and cooking methods.

[0003] Another common method is for users to obtain recipes through mobile applications. Some smart cooking devices with internet connectivity can receive instructions from these apps, translating recipe steps into control commands that the device can execute. However, the recipes in these applications often rely on manual input by users or professionals, have long update cycles, and struggle to respond promptly to new cooking methods rapidly spreading on emerging media such as short video platforms. Furthermore, users often need to switch between multiple platforms or applications to find the recipes they need, making the process cumbersome and increasing the barrier to entry, thus impacting the convenience and user experience of smart cooking devices. Summary of the Invention

[0004] To address the problems of existing technologies, this application provides a recipe management method, apparatus, electronic device, and storage medium. The technical solution is as follows: On one hand, a recipe management method is provided, which is applied to a cooking equipment management system. The cooking equipment management system is communicatively connected to the cooking equipment and is used to provide recipes to the cooking equipment. The method includes: Obtain target cooking videos with cooking tags from the target online platform; Extract key image frames from the preprocessed target cooking video; Identify cooking-related visual features in the key image frames to obtain first key descriptive information; The audio of the preprocessed target cooking video is converted into text, and textual descriptions related to the cooking process are extracted from the text to obtain the second key descriptive information; A recipe is generated based on the key image frame, the first key description information, and the second key description information.

[0005] On the other hand, a recipe management device is provided, which is applied to a cooking equipment management system. The cooking equipment management system is communicatively connected to the cooking equipment and is used to provide recipes to the cooking equipment. The device includes: The video acquisition module is used to acquire target cooking videos with cooking tags from the target network platform; The image frame extraction module is used to extract key image frames from the preprocessed target cooking video; The image recognition module is used to identify cooking-related visual features in the key image frames to obtain first key descriptive information; The audio conversion module is used to convert the preprocessed audio of the target cooking video into text, extract text descriptions related to the cooking process from the text, and obtain second key description information; The recipe generation module is used to generate a recipe based on the key image frame, the first key description information, and the second key description information.

[0006] In one exemplary embodiment, the target cooking video further includes popular cooking videos; the video acquisition module includes: The ranking acquisition module is used to obtain the current popular ranking of the target network platform in response to the update of the current detection period; The candidate video module is used to identify candidate cooking videos with the cooking tag among the videos listed in the current popular list. The popular video module is used to identify popular cooking videos from the candidate cooking videos based on historical popular lists obtained from historical detection periods; the time when the popular cooking videos are listed is later than the update time of the previous detection period. The popular acquisition module is used to acquire the popular cooking videos.

[0007] In one exemplary implementation, the target cooking video includes a newly added cooking video; the video acquisition module includes: A new acquisition module is added to acquire the newly added cooking video carrying the cooking tag from the target network platform in response to the update of the current detection period; the publication time or editing time of the newly added cooking video is later than the update time of the previous detection period.

[0008] In one exemplary embodiment, the cooking equipment management system is further configured to manage a recipe database for storing recipes; the device also includes a recipe storage module configured to store the recipe in the recipe database if the recipe does not exist in the recipe database.

[0009] In one exemplary embodiment, the apparatus further includes an instruction control module for sending corresponding control instructions to the cooking device after determining the target recipe, the instruction control module comprising: The target recipe module is used to send candidate recipes that match the cooking device to the cooking device, so that the cooking device can determine the target recipe from the candidate recipes; The instruction sending module is used to send a control instruction corresponding to the target recipe to the cooking device in response to the cooking device's determination of the target recipe, so that the cooking device executes the control instruction.

[0010] In one exemplary embodiment, the apparatus further includes an instruction generation module for generating control instructions corresponding to the recipe, the instruction generation module comprising: The keyword extraction module is used to extract keywords from the text information of the recipe; The equipment keyword module is used to determine equipment keywords from the keywords based on a preset keyword mapping rule; the preset keyword mapping rule defines the correspondence between the equipment keywords and the cooking equipment. The target device module is used to map the device keywords to target cooking devices based on the preset keyword mapping rules; The template acquisition module is used to acquire a preset instruction template corresponding to the target cooking device; the preset instruction template includes control parameters required to control the target cooking device; The parameter conversion module is used to convert the keywords into control parameter values ​​corresponding to the control parameters based on preset parameter conversion rules; the preset parameter conversion rules define the correspondence between the keywords and the control parameter values. The parameter filling module is used to fill the preset instruction template based on the control parameter values ​​to generate the control instructions corresponding to the recipe.

[0011] On the other hand, an electronic device is provided, including a processor and a memory, wherein the memory stores at least one instruction or at least one program, the at least one instruction or the at least one program being loaded and executed by the processor to implement the recipe management method of any of the above aspects.

[0012] On the other hand, a computer-readable storage medium is provided, wherein at least one instruction or at least one program is stored therein, the at least one instruction or the at least one program being loaded and executed by a processor to implement the recipe management method as described above.

[0013] On the other hand, a computer program product or computer program is provided, which includes computer instructions stored in a computer-readable storage medium. A processor of an electronic device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the electronic device to perform the recipe management method of any of the above aspects.

[0014] This application embodiment obtains target cooking videos carrying cooking tags from a target network platform, extracts key image frames from the video to capture the core cooking scene, identifies cooking-related visual features and converts them into first key descriptive information, and simultaneously converts the video audio into text and extracts second key descriptive information related to the cooking process. Then, a recipe is generated based on these key elements, transforming the dynamic and intuitive cooking content in the video into structured and executable recipe information. This ensures that the generated recipe accurately reflects the actual cooking steps, ingredient status, and operational details. It not only breaks through the limitations of the fixed number and types of recipes built into cooking devices, but also incorporates novel cooking methods from short videos to meet the diverse dietary needs of users. It also avoids the problem of slow recipe updates caused by manual input, and saves users the tedious operation of repeatedly searching in multiple applications, reducing usage costs and realizing dynamic updates, accurate presentation, and convenient access to recipes. Attached Figure Description

[0015] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0016] Figure 1 This is a flowchart illustrating a recipe management method provided in an embodiment of this application; Figure 2 This is a flowchart illustrating a control method for a cooking device provided in an embodiment of this application; Figure 3 This is a flowchart illustrating a recipe management and equipment control method provided in an embodiment of this application; Figure 4 This is a structural block diagram of a recipe management device provided in an embodiment of this application; Figure 5 This is a hardware structure block diagram of an electronic device provided in an embodiment of this application. Detailed Implementation

[0017] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of this application.

[0018] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or server that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or devices.

[0019] It is understood that in the specific embodiments of this application, data such as user information are involved. When the above embodiments of this application are applied to specific products or technologies, user permission or consent is required, and the collection, use and processing of related data must comply with the relevant laws, regulations and standards of the relevant countries and regions.

[0020] In existing technologies, the number and types of recipes built into cooking devices are fixed and limited, making it difficult to keep up with the rapid changes in food trends. This fails to meet users' demands for diverse and novel dishes and makes it difficult for users to access the latest cooking methods through the devices, resulting in a shortage of recipe resources. At the same time, recipes that rely on manual input by users or professionals are updated very slowly in applications, lagging far behind the development of actual cooking trends. They cannot reflect current popular cooking methods, ingredient combinations, and innovative dishes in a timely manner, and are even less likely to incorporate new cooking methods that are rapidly spread through emerging media such as short videos. This prevents users from quickly accessing the latest food information and cooking techniques. In addition, users often need to switch repeatedly between multiple different recipe applications or platforms to find the recipes they need, and then manually convert the recipes into commands that the cooking device can recognize. The operation process is cumbersome, which not only increases the user's time and energy costs, but also brings many inconveniences.

[0021] In view of this, this application provides a recipe management method, which builds a data acquisition and processing system to capture cooking-related videos from major short video platforms, uses video and voice recognition technology to deeply mine the image and voice information in the videos, constructs a recipe database, and provides cooking equipment with a continuous stream of rich recipe resources, thereby effectively solving the problems of scarce recipe resources, delayed updates and cumbersome operation, and improving the convenience and user experience of intelligent cooking equipment.

[0022] Please see Figure 1 The diagram illustrates a flowchart of a recipe management method provided in this application. It should be noted that while this specification provides method steps as shown in the embodiments or flowcharts, more or fewer steps may be included based on conventional or non-inventive methods. The order of steps listed in the embodiments is merely one possible execution order among many and does not represent the only possible execution order. In actual system or product execution, the method can be executed sequentially according to the embodiments or accompanying drawings, or in parallel (e.g., using parallel processors or a multi-threaded processing environment). Specifically, this method is applied to a cooking equipment management system, which is communicatively connected to the cooking equipment to provide recipes to the cooking equipment, such as... Figure 1 As shown, the method may include: S101, Obtain the target cooking video carrying the cooking tag from the target network platform.

[0023] The cooking equipment management system is used for data acquisition and processing. Specifically, it automatically searches for and collects video resources with cooking tags on target network platforms, and uses video recognition technology to preprocess the acquired videos.

[0024] The cooking labels include, but are not limited to, labels related to cooking such as "food tutorials", "home-style dishes", "baking", "Chinese food", and "Western food".

[0025] The target online platforms include short video platforms, food-related social media platforms, and other online service providers that support video sharing. In practice, the target online platforms are typically the major mainstream short video platforms.

[0026] The preprocessing includes format conversion, noise reduction, and frame rate standardization of the target cooking video, such as unifying it to MP4 format and adjusting it to 30 frames per second to ensure the accuracy of subsequent keyframe extraction.

[0027] The target cooking videos also include popular cooking videos. Specifically, in response to the update of the current detection period, the current popular list of the target network platform is obtained; candidate cooking videos with cooking tags are identified among the videos listed in the current popular list; popular cooking videos are identified from the candidate cooking videos based on the historical popular list obtained in previous detection periods; the popular cooking videos were listed after the update time of the previous detection period; and the popular cooking videos are then obtained.

[0028] The current detection cycle can be set according to the content update frequency of the target network platform, such as updating at 3 am every day, with a cycle of 24 hours.

[0029] In practice, the current trending list is obtained by calling the target platform's open API, and list data, including video ID, title, tags, and listing time, is extracted. Candidate cooking videos are identified through tag matching, such as cooking tags including "food tutorials," "home-style dishes," and "cooking techniques." The listing time of the current candidate videos is compared with the update time of the previous detection period. For example, if the current detection period starts at 3:00 AM on July 28, 2025, and the previous detection period started at 3:00 AM on July 27, then cooking videos newly listed between 3:00 AM on July 27 and 3:00 AM on July 28 are selected to ensure that the obtained content is trending content that has not been processed in previous periods.

[0030] The target cooking videos also include newly added cooking videos. Specifically, in response to the update of the current detection cycle, new cooking videos carrying cooking tags are retrieved from the target online platform; the publication or editing time of the new cooking videos is later than the update time of the previous detection cycle.

[0031] In practice, newly added cooking videos are obtained through the content update interface of the target network platform. Simultaneously, metadata of videos tagged with "cooking" is collected, including publication and editing times. The timestamps in the video metadata are extracted and compared with the previous update time (e.g., 3:00 AM on July 27, 2025), retaining videos with the larger timestamps. For example, if a video was published at 10:00 AM on July 27, 2025, and edited at 3:00 PM on July 27, both later than the previous update time (3:00 AM on July 27), it is determined to be a newly added cooking video.

[0032] The determination of the publication time or editing time is based on the video metadata returned by the platform. If the video has been edited multiple times, the latest editing time will be used as the basis for judgment. For example, if a video is published on July 20, 2025, and edited again at 10:00 on July 27, 2025, then 10:00 on July 27 will be used as the timestamp.

[0033] Specifically, the cooking equipment management system includes a real-time monitoring module for updating recipes in real time. This module periodically scans the trending video lists and newly published video areas of the target online platform according to a set detection cycle, continuously tracking the platform's trending topics and new content. Once these trending and newly added cooking videos are detected, the data collection and processing process is immediately triggered.

[0034] Through real-time monitoring and automatic updating mechanisms, the recipes provided by the cooking equipment always keep up with the latest food trends. This solves the problem that traditional built-in recipes cannot respond in a timely manner to new cooking methods that are rapidly spreading on current short video platforms. Users can access the latest cooking trends and popular dishes at any time without manual operation, adding freshness to their cooking life, satisfying their pursuit of novel food, and enabling recipes to keep up with and be updated in real time to the popular trends in short videos.

[0035] S103, extract key image frames from the preprocessed target cooking video.

[0036] In practice, frames with significant changes in the image are selected using an inter-frame difference algorithm. For example, the pixel difference between adjacent frames is calculated to select key action frames such as food processing and changes in cooking temperature, and 1-3 key frames are retained every 10 to 30 seconds.

[0037] S105, Identify cooking-related visual features in key image frames to obtain first key descriptive information.

[0038] Specifically, through in-depth analysis of key image frames, information such as ingredients, kitchen utensils, and various cooking actions can be identified.

[0039] In practice, deep learning models are used to identify ingredients (such as pork belly and green peppers), kitchen utensils (such as woks and ovens), and actions (such as stir-frying and flipping), and then convert them into structured text.

[0040] S107, convert the audio of the pre-processed target cooking video into text, extract text descriptions related to the cooking process from the text, and obtain the second key description information.

[0041] Specifically, speech recognition technology is used to convert the audio in the video into text, and then natural language processing technology is used to extract key descriptive information such as the sequence of steps (e.g., "stir-fry the meat first, then add the vegetables") and the amount of seasonings (e.g., "appropriate amount of salt").

[0042] S109, Generate a recipe based on key image frames, first key description information and second key description information.

[0043] Specifically, the extracted image and text information is organically integrated and stored. In particular, key image frames are used as illustrations for each step. By integrating key image frames, first key description information, and second key description information, a structured recipe containing "ingredient list - step breakdown - illustration description" is generated.

[0044] Specifically, the cooking equipment management system also manages a recipe database, which stores recipes. For example, when it detects ingredients such as pork belly and green peppers in a video keyframe, and the voice message mentions steps like "first stir-fry the pork belly until the oil is rendered, then add the green peppers and stir-fry, adding appropriate amounts of salt and light soy sauce for seasoning," this detailed information is compiled into a complete recipe record and stored in the recipe database. The cooking equipment can access this recipe database at any time via a network connection, thereby obtaining a rich and diverse range of recipe resources.

[0045] In practice, the recipe database can be a relational database, storing fields such as recipe ID, title, ingredient list, step text, keyframe image path, and generation time.

[0046] Specifically, if a recipe does not exist in the recipe database, it will be stored there. More specifically, the generated recipe is meticulously compared with all existing recipe records in the database. If it is determined to be a new dish or a unique cooking method, it is added to the database as a new recipe and promptly pushed to the connected cooking device via the network. In practice, the hash values ​​of the recipe title, core ingredients (e.g., tomatoes and eggs for "tomato and egg stir-fry"), and key steps are calculated and compared with the hash values ​​of existing recipes in the database. If the similarity is below a certain threshold, it is considered a new recipe. For example, if the database already contains "tomato and egg stir-fry (with sugar)," a newly generated "tomato and egg stir-fry (without sugar)" will have a hash value similarity below the threshold due to differences in steps, and will be stored as a new recipe.

[0047] For example, when an innovative short video of making a trendy cake quickly goes viral on the platform, the real-time monitoring module can immediately capture the video, quickly extract and process the information, update the new recipe to the database, and promptly push it to the user's cooking equipment, so that the user can obtain the recipe for making the trendy cake as soon as possible.

[0048] Specifically, by managing the recipe database, the system selectively stores newly added recipes, avoiding duplicate content in the database, saving storage space, optimizing the database structure, improving system efficiency, ensuring that users only receive new or unique recipes, avoiding duplicate pushes, and improving the efficiency of users obtaining effective information. At the same time, centralized database management provides a stable and abundant source of recipes for cooking equipment, enhancing the system's usability.

[0049] As can be seen from the above technical solutions of the embodiments of this application, the embodiments of this application comprehensively utilize video recognition and speech recognition technologies to fully and deeply mine various rich cooking information from massive short videos. Compared with traditional built-in recipes or manual recipe input methods, this greatly expands the number and types of recipes available for cooking devices, significantly enriching the source of recipes. Therefore, cooking devices can cover diverse recipes based on massive short video content, thereby meeting users' cooking needs for various dishes with different regional characteristics and styles, providing users with more diverse cooking options. Furthermore, by integrating visual and audio information from the video, the state of ingredients, operating steps, and details (such as ingredient processing methods and heat changes) during the cooking process can be accurately captured, resulting in recipes that are more closely aligned with actual cooking scenarios.

[0050] In one exemplary embodiment, after generating a recipe, to further enhance the automation level and user convenience of the intelligent cooking equipment, and to solve the cumbersome problem in the prior art where users need to manually convert recipe steps into executable commands for the equipment, this application also provides a technical solution for sending corresponding control instructions to the cooking equipment based on the recipe items, so as to achieve seamless connection from recipe information to automatic execution of operations by the cooking equipment. For example... Figure 2 As shown, it includes the following steps: S201, send candidate recipes that match the cooking device to the cooking device so that the cooking device can determine the target recipe from the candidate recipes.

[0051] Specifically, recipes are filtered based on the type of cooking equipment (such as oven or microwave) and its functional parameters (such as the oven's maximum temperature of 300°C), and matching candidate recipes are sent to the cooking equipment. For example, only recipes containing "baking" or "roasting" steps are sent to the oven, while recipes related to "heating" or "defrosting" are sent to the microwave.

[0052] S203, in response to the cooking device determining the target recipe, a control command corresponding to the target recipe is sent to the cooking device so that the cooking device executes the control command.

[0053] Specifically, the cooking equipment displays candidate recipes through its own display screen or a related APP. After the user selects the target recipe by touch or voice, the system immediately retrieves the corresponding control instructions for the recipe (such as the oven's preheating temperature and duration) and sends them to the cooking equipment via Wi-Fi or Bluetooth. After receiving the instructions, the cooking equipment automatically executes them (such as starting the preheating program).

[0054] Specifically, by automatically matching recipes with cooking equipment and automatically sending control commands, the entire process of recipe acquisition and equipment execution is automated. Users no longer need to switch between multiple platforms to search for recipes, nor do they need to manually convert recipe steps into equipment commands. They only need to select the target recipe from the matching candidate recipes provided by the equipment, and the system can automatically send control commands. This greatly simplifies the operation process, lowers the threshold for use, and solves the problems of cumbersome operation and poor user experience in existing technologies, thus improving the convenience and user experience of smart cooking equipment.

[0055] The control instructions are generated based on the text information of the recipe. Specifically, this includes the following steps: Keyword extraction is performed on the recipe text. Specifically, natural language preprocessing is applied to the recipe text extracted from short videos, including word segmentation, part-of-speech tagging, and named entity recognition. For example, for the recipe text "Preheat the oven to 200 degrees and bake the cake for 30 minutes," word segmentation yields "will," "oven," "preheat," "to," "200 degrees," "bake," "cake," and "30 minutes." Part-of-speech tags are then used to identify "oven" as a cooking appliance, "200 degrees" as a temperature entity, and "30 minutes" as a time entity.

[0056] Device keywords are determined from the keywords based on preset keyword mapping rules; the preset keyword mapping rules define the correspondence between device keywords and cooking devices. For example, "oven" maps to "electric oven", and "pressure cooker" maps to "electric pressure cooker".

[0057] Based on preset keyword mapping rules, device keywords are mapped to target cooking devices, and preset instruction templates corresponding to the target cooking devices are obtained. These preset instruction templates include the control parameters required to control the target cooking device. Specifically, the preset instruction templates are customized for different types of cooking devices (such as ovens, microwave ovens, rice cookers, etc.). For example, an oven instruction template might be "PREHEAT:<temperature value>, TIME:<total time value>, MODE1:<mode 1>, DURATION1:<mode 1 duration>, MODE2:<mode 2>, DURATION2:<mode 2 duration>..."; a microwave oven instruction template might be "POWER:<power value>, TIME:<heating time>, MODE:<heating mode>", etc. In practice, an empty instruction set is initialized, the preprocessed word sequence is traversed, and keywords are matched according to the rule base. When a cooking device keyword (such as "oven" or "microwave oven") is matched, the corresponding instruction template is determined.

[0058] Based on preset parameter conversion rules, keywords are converted into corresponding control parameter values. These preset rules define the correspondence between keywords and control parameter values. Specifically, the preset parameter conversion rules include the correspondence between keywords such as cooking actions, ingredients, time, and temperature, and instruction parameters. For example, "baking" corresponds to the heating operation of an oven, "high power" corresponds to a higher power range of a microwave oven, "a little salt" is converted to "2g," and "appropriate amount of water" is converted proportionally according to the weight of the ingredients, such as 1kg of ingredients corresponding to 500ml of water.

[0059] The system generates control instructions corresponding to the recipe by filling a preset instruction template with control parameter values. In practice, if any parameters are missing, the device's default values ​​are used to ensure the completeness of the instructions. For example, if the temperature is not mentioned, the oven's default preheating temperature is used to fill the preset instruction template.

[0060] Specifically, the word sequence continues to be traversed. When a keyword related to the instruction template parameter is encountered (e.g., "preheat" corresponds to the preheating operation in the oven instruction template, and "temperature value" corresponds to "200 degrees"), the corresponding parameter value is extracted and filled into the instruction template. For example, if "preheat to 200 degrees" is matched, then "200 degrees" is filled into the "PREHEAT:<temperature value>" position in the oven instruction template. For other parameters such as time and mode, matching and extraction are performed according to the rule base to gradually improve the instruction template. For example, if "baking cake for 30 minutes" is matched, then "30 minutes" is filled into the "TIME:<total time value>" position. When the word sequence traversal is completed, a complete set of executable control instructions for the cooking equipment is generated.

[0061] In practice, the generated control commands are verified and optimized. Specifically, the generated control commands are verified to check whether the parameters are within a reasonable range (e.g., whether the oven temperature is between 50 and 300 degrees Celsius) and whether the command format is correct. If problems are found, optimization and adjustments are made according to preset correction rules to ensure that the generated commands can be accurately executed by the cooking equipment.

[0062] As can be seen from the above technical solutions of the embodiments of this application, the embodiments of this application significantly simplify user operation and reduce the difficulty of using cooking equipment by automatically extracting recipes from short video content and generating cooking commands that can be directly executed by cooking equipment. This effectively improves the convenience of user operation, the accuracy of equipment control, and the overall user experience. Specifically, the algorithm based on natural language processing and rule matching automatically converts the natural language information of the recipes extracted from short videos into control commands that cooking equipment can recognize, thus automating and simplifying the operation process. It does not rely on complex machine learning model training, consumes low computational resources, and has a fast response speed. It can efficiently and accurately complete the conversion from natural language recipes to executable commands, greatly simplifying the conversion process from recipes to equipment instructions and reducing the complexity and maintenance costs of the system.

[0063] To facilitate a full understanding of the solution presented in this application, the process of recipe management and cooking equipment control is described below. Please refer to [link / reference needed]. Figure 3 The diagram shown is a flowchart illustrating a recipe management and equipment control method provided in an embodiment of this application, which may specifically include: Video resources tagged with cooking, such as "food tutorials" and "home-style dishes," are obtained from short video platforms like Douyin and Kuaishou using API calls or web scraping techniques. The acquired videos undergo format conversion, noise reduction, and frame rate standardization. A frame difference algorithm is then used to filter key image frames showing significant changes (such as frames depicting ingredient processing or temperature variations). Simultaneously, a speech recognition engine converts the video audio into text, extracting information such as step sequence and ingredient quantities. The key frames (used as step illustrations), visual feature descriptions (such as structured information about ingredients, utensils, and actions), and audio / text information are integrated into a structured recipe database, completing the initial recipe database construction.

[0064] To ensure the timeliness of the recipe database, the system continuously monitors for newly published or edited cooking videos according to a set detection cycle, using the platform's content update interface or a scheduled crawling mechanism. If a new video is detected, the video processing and information extraction operations described above are repeated; otherwise, the system returns to the monitoring stage and continues to wait for new content. After obtaining the processed information from the new video, a similarity comparison is performed with existing recipes in the recipe database. If it is determined to be a new recipe, it is stored in the recipe database and pushed to the associated cooking devices via the network, allowing users to access the latest recipes on their devices.

[0065] When a user browses candidate recipes and selects a target recipe through the device's display screen or a linked app, triggering the instruction generation process, the recipe text undergoes natural language preprocessing. Based on preset keyword mapping rules and device-specific instruction templates, fuzzy parameters (such as "a little salt" converted to "2g" and "medium heat" converted to "150℃") are standardized and converted to generate control instructions that the device can recognize. If any parameters are missing, the device's default values ​​are used to ensure the completeness of the instructions.

[0066] To avoid command errors, the control commands undergo syntax validation and logical rationality verification, and are optimized and adjusted according to device parameters. Verified control commands are sent to the cooking device via Wi-Fi or Bluetooth. Upon receiving the commands, the device automatically parses and executes the corresponding operations, completing a closed loop from recipe selection to automatic cooking.

[0067] Corresponding to the recipe management methods provided in the above embodiments, this application also provides a recipe management device. Since the recipe management device provided in this application corresponds to the recipe management methods provided in the above embodiments, the implementation methods of the aforementioned recipe management methods are also applicable to the recipe management device provided in this embodiment, and will not be described in detail in this embodiment.

[0068] Please see Figure 4 The diagram shows a structural schematic of a recipe management device provided in an embodiment of this application. This device has the function of implementing the recipe management method described in the above-described method embodiments. This function can be implemented by hardware or by hardware executing corresponding software. The device is applied to a cooking equipment management system, which is communicatively connected to the cooking equipment and used to provide recipes to the cooking equipment; for example... Figure 4 As shown, the device may include: Video acquisition module 410 is used to acquire target cooking videos carrying cooking tags from the target network platform; Image frame extraction module 420 is used to extract key image frames from the preprocessed target cooking video; Image recognition module 430 is used to identify cooking-related visual features in key image frames to obtain first key descriptive information; The audio conversion module 440 is used to convert the audio of the pre-processed target cooking video into text, extract text descriptions related to the cooking process from the text, and obtain the second key description information. The recipe generation module 450 is used to generate recipes based on key image frames, first key description information, and second key description information.

[0069] In one exemplary embodiment, the target cooking video further includes popular cooking videos; the video acquisition module includes: The ranking acquisition module is used to retrieve the current popular rankings of the target network platform in response to the update of the current detection cycle. The candidate video module is used to identify candidate cooking videos with the cooking tag among the videos currently listed on the trending list. The popular videos module is used to identify popular cooking videos from candidate cooking videos based on historical popular lists obtained from historical detection periods; the time when popular cooking videos are listed is later than the update time of the previous detection period. The "Popular Videos" module is used to retrieve popular cooking videos.

[0070] In one exemplary implementation, the target cooking video includes a newly added cooking video; the video acquisition module includes: A new acquisition module has been added to respond to updates in the current detection cycle by acquiring new cooking videos with cooking tags from the target network platform; the publication or editing time of the new cooking videos must be later than the update time of the previous detection cycle.

[0071] In one exemplary embodiment, the cooking equipment management system is further configured to manage a recipe database for storing recipes; the device also includes a recipe storage module for storing recipes in the recipe database if no recipe exists in the recipe database.

[0072] In one exemplary embodiment, the apparatus further includes an instruction control module for sending corresponding control instructions to the cooking device after determining the target recipe. The instruction control module includes: The target recipe module is used to send candidate recipes that match the cooking equipment to the cooking equipment, so that the cooking equipment can determine the target recipe from the candidate recipes; The instruction sending module is used to send control instructions corresponding to the target recipe to the cooking equipment in response to the cooking equipment's determination of the target recipe, so that the cooking equipment can execute the control instructions.

[0073] In one exemplary embodiment, the apparatus further includes an instruction generation module for generating control instructions corresponding to the recipe. The instruction generation module includes: The keyword extraction module is used to extract keywords from the text information of recipes; The equipment keyword module is used to determine equipment keywords from keywords based on preset keyword mapping rules; the preset keyword mapping rules define the correspondence between equipment keywords and cooking equipment. The target device module is used to map device keywords to target cooking devices based on preset keyword mapping rules; The template acquisition module is used to acquire the preset instruction template corresponding to the target cooking equipment; the preset instruction template includes the control parameters required to control the target cooking equipment; The parameter conversion module is used to convert keywords into control parameter values ​​corresponding to control parameters based on preset parameter conversion rules; the preset parameter conversion rules define the correspondence between keywords and control parameter values; The parameter filling module is used to fill preset instruction templates based on control parameter values ​​to generate control instructions corresponding to the recipe.

[0074] It should be noted that the apparatus provided in the above embodiments is only illustrated by the division of the above functional modules when implementing its functions. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above. In addition, the apparatus and method embodiments provided in the above embodiments belong to the same concept, and the specific implementation process can be found in the method embodiments, which will not be repeated here.

[0075] This application provides an electronic device, which includes a processor and a memory. The memory stores at least one instruction or at least one program, which is loaded and executed by the processor to implement any of the recipe management methods provided in the above method embodiments.

[0076] Memory is used to store software programs and modules. The processor executes these stored software programs and modules to perform various functional applications and data processing. Memory can primarily consist of a program storage area and a data storage area. The program storage area stores the operating system, application programs required for functionality, etc.; the data storage area stores data created based on device usage, etc. Furthermore, memory can include high-speed random access memory (RAM) and non-volatile memory, such as at least one disk storage device, flash memory device, or other volatile solid-state storage device. Accordingly, memory can also include a memory controller to provide the processor with access to the memory.

[0077] The method embodiments provided in this application can be executed in a computer terminal, server or similar computing device, that is, the above-mentioned electronic device may include a computer terminal, server or similar computing device. Figure 5 This is a hardware structure block diagram of a computer device for running a recipe management method provided in an embodiment of the present invention, such as... Figure 5 As shown, the internal structure of this computer device may include, but is not limited to, a processor, a network interface, and a memory. The processor, network interface, and memory within the computer device can be connected via a bus or other means, as illustrated in the embodiments of this specification. Figure 5 Taking the example of a connection between China and Israel via a bus.

[0078] The processor (or CPU, Central Processing Unit) is the computing and control core of the computer device. The network interface may optionally include a standard wired interface or a wireless interface (such as Wi-Fi, mobile communication interface, etc.). Memory is the storage device in the computer device used to store programs and data. It is understood that the memory here can be a high-speed RAM storage device, or a non-volatile storage device, such as at least one disk storage device; optionally, it can also be at least one storage device located remotely from the aforementioned processor. The memory provides storage space, which stores the operating system of the electronic device, including but not limited to: Windows (an operating system), Linux (an operating system), Android (a mobile operating system), iOS (a mobile operating system), etc., which are not limited in this invention; and the storage space also stores one or more instructions suitable for being loaded and executed by the processor, which can be one or more computer programs (including program code). In the embodiments of this specification, the processor loads and executes one or more instructions stored in the memory to implement the recipe management method provided in the above method embodiments.

[0079] The embodiments of this application also provide a computer-readable storage medium, which can be disposed in an electronic device to store at least one instruction or at least one program related to implementing a recipe management method. The at least one instruction or the at least one program is loaded and executed by the processor to implement any of the recipe management methods provided in the above-described method embodiments.

[0080] Optionally, in this embodiment, the storage medium may include, but is not limited to, various media capable of storing program code, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.

[0081] It should be noted that the order of the embodiments described above is merely for descriptive purposes and does not represent the superiority or inferiority of the embodiments. Furthermore, specific embodiments have been described above. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps described in the claims can be performed in a different order than that shown in the embodiments and still achieve the desired result. Additionally, the processes depicted in the drawings do not necessarily require a specific or sequential order to achieve the desired result. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0082] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, the apparatus embodiments are basically similar to the method embodiments, so the description is relatively simple; relevant parts can be referred to the descriptions of the method embodiments.

[0083] Those skilled in the art will understand that all or part of the steps of the above embodiments can be implemented by hardware or by a program instructing related hardware. The program can be stored in a computer-readable storage medium, such as a read-only memory, a disk, or an optical disk.

[0084] The above are merely preferred embodiments of this application and are not intended to limit this application. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the protection scope of this application.

Claims

1. A recipe management method, characterized in that, The method is applied to a cooking equipment management system, which is communicatively connected to the cooking equipment and used to provide recipes to the cooking equipment; the method includes: Obtain target cooking videos with cooking tags from the target online platform; Extract key image frames from the preprocessed target cooking video; Identify cooking-related visual features in the key image frames to obtain first key descriptive information; The audio of the preprocessed target cooking video is converted into text, and textual descriptions related to the cooking process are extracted from the text to obtain the second key descriptive information; A recipe is generated based on the key image frame, the first key description information, and the second key description information.

2. The recipe management method according to claim 1, characterized in that, The target cooking videos also include popular cooking videos; obtaining the target cooking videos with cooking tags from the target online platform includes: In response to the update of the current detection cycle, obtain the current hot list of the target network platform; Identify candidate cooking videos with the cooking tag among the videos listed in the current popular rankings; Based on the historical popular lists obtained from the historical detection period, popular cooking videos are determined from the candidate cooking videos; the time when the popular cooking videos are listed is later than the update time of the previous detection period. Get the popular cooking videos mentioned above.

3. The recipe management method according to claim 2, characterized in that, The target cooking video includes newly added cooking videos; obtaining the target cooking video with cooking tags from the target network platform includes: In response to the update of the current detection cycle, the newly added cooking video carrying the cooking tag is obtained from the target network platform; the publication time or editing time of the newly added cooking video is later than the update time of the previous detection cycle.

4. The recipe management method according to claim 2 or 3, characterized in that, The cooking equipment management system is also used to manage a recipe database, which stores the recipes; after generating the recipe based on the key image frame, the first key description information, and the second key description information, the method further includes: If the recipe does not exist in the recipe database, then the recipe will be stored in the recipe database.

5. The recipe management method according to claim 1, characterized in that, The method further includes: Send candidate recipes that match the cooking device to the cooking device, so that the cooking device can determine the target recipe from the candidate recipes; In response to the cooking device determining the target recipe, a control command corresponding to the target recipe is sent to the cooking device so that the cooking device executes the control command.

6. The recipe management method according to claim 5, characterized in that, The method further includes: Extract keywords from the text information of the recipe; Equipment keywords are determined from the keywords based on preset keyword mapping rules; the preset keyword mapping rules define the correspondence between the equipment keywords and the cooking equipment; Based on the preset keyword mapping rules, the device keywords are mapped to the target cooking device; Obtain a preset instruction template corresponding to the target cooking device; the preset instruction template includes control parameters required to control the target cooking device; The keywords are converted into control parameter values ​​corresponding to the control parameters based on preset parameter conversion rules; the preset parameter conversion rules define the correspondence between the keywords and the control parameter values. The preset instruction template is filled with the control parameter values ​​to generate the control instructions corresponding to the recipe.

7. A recipe generation device, characterized in that, The device is applied to a cooking equipment management system, which is communicatively connected to the cooking equipment and used to provide recipes to the cooking equipment; the device includes: The video acquisition module is used to acquire target cooking videos with cooking tags from the target network platform; The image frame extraction module is used to extract key image frames from the preprocessed target cooking video; The image recognition module is used to identify cooking-related visual features in the key image frames to obtain first key descriptive information; The audio conversion module is used to convert the preprocessed audio of the target cooking video into text, extract text descriptions related to the cooking process from the text, and obtain second key description information; The recipe generation module is used to generate a recipe based on the key image frame, the first key description information, and the second key description information.

8. An electronic device, characterized in that, The method includes a processor and a memory, wherein the memory stores at least one instruction or at least one program, and the at least one instruction or the at least one program is loaded and executed by the processor to implement the recipe management method as described in any one of claims 1 to 6.

9. A computer-readable storage medium storing at least one instruction or at least one program, the at least one instruction or the at least one program being loaded and executed by a processor to implement the recipe management method as described in any one of claims 1 to 6.

10. A computer program, characterized in that, When the computer program is executed by the processor, it implements the recipe management method according to any one of claims 1 to 6.

Images