Menu video processing method, device and system based on kitchen scene and medium
By receiving and processing the images of ingredients in the kitchen, and using the recipe video production model to automatically obtain and push recipe videos, the problem of low efficiency in obtaining traditional recipes is solved, and the convenience of users in selecting ingredients and obtaining recipes is improved.
Patent Information
- Application Number
- CN202411212227.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-30
- Publication Date
- 2024-12-31
AI Technical Summary
In traditional solutions, the efficiency of obtaining recipe-making videos is too low. When users select ingredients in the kitchen, they need to cumbersomely enter ingredients information and search for recipes. Many recipes do not have corresponding videos, resulting in inefficiency.
Provide a recipe video processing method based on kitchen scenes. By receiving food images, entering the trained recipe video to make a model, obtaining matching target recipes, and automatically pushing recipes to kitchen TV, without the need for users to search and select ingredients manually.
It improves the efficiency of obtaining recipe videos, simplifies the process of users selecting ingredients and obtaining recipes, improves the user experience, and allows users to quickly choose food in the kitchen to cook.
Smart Images
Figure CN119232982A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of big data, and in particular to a recipe video processing method, device, system and medium based on a kitchen scene. Background Art
[0002] Users often have this kind of distress: when they open the refrigerator and look at the vast amount of food, they don't know what to choose to cook. The general solution is that users use the recipe application or search engine on mobile phones and other terminals to input some ingredients currently in the refrigerator without any clue. There are so many ingredients in the refrigerator that it is difficult to choose. Then they have to search and select recipes; then based on the recipes, they choose to click on the corresponding recipe making video. Some satisfactory recipes searched out do not have corresponding recipe making videos. The above process is cumbersome and inefficient. Summary of the invention
[0003] The present application provides a recipe video processing method, device, system and medium based on a kitchen scene to solve the technical problem of low efficiency in obtaining recipe making videos in traditional solutions.
[0004] In a first aspect, a recipe video processing method based on a kitchen scene is provided, comprising:
[0005] Receiving a food image, where the food image is an image corresponding to the food stored in a refrigerator in a kitchen;
[0006] Inputting the ingredient image into the trained recipe video production model to obtain a target recipe matching the ingredient image;
[0007] According to the target recipe, obtain a corresponding recipe making video;
[0008] The recipe making video is pushed to a kitchen TV in the kitchen, so that the kitchen TV automatically plays the recipe making video.
[0009] Furthermore, the target recipe matched with the ingredient image includes at least two recipes, and acquiring corresponding recipe making videos according to the target recipes includes:
[0010] In response to the recipe selection instruction, selecting a corresponding target recipe from the at least two recipes;
[0011] According to the corresponding target recipe, a corresponding recipe making video is obtained.
[0012] Furthermore, the food image includes images corresponding to the food stored in one or more refrigerators in the kitchen.
[0013] Furthermore, the receiving of the food image includes:
[0014] The food image photographed by the user using a handheld terminal is received.
[0015] Furthermore, the receiving of the food image includes:
[0016] Receive the food image captured by the built-in camera of the refrigerator.
[0017] In a second aspect, a recipe video processing device based on a kitchen scene is provided, comprising:
[0018] A receiving module, used to receive food images, where the food images are images corresponding to food stored in a refrigerator in a kitchen;
[0019] An input module, used for inputting the ingredient image into the trained recipe video production model to obtain a target recipe matching the ingredient image;
[0020] An acquisition module, used to acquire a corresponding recipe making video according to the target recipe;
[0021] The push module is used to push the recipe making video to the kitchen TV in the kitchen, so that the kitchen TV automatically plays the recipe making video.
[0022] In a third aspect, a recipe video processing system based on a kitchen scene is provided, the recipe video processing system comprising a server, a refrigerator and a kitchen TV arranged in the kitchen, the refrigerator being provided with a built-in camera, and:
[0023] The refrigerator captures food images corresponding to the food stored in the refrigerator through a built-in camera, and sends the food images to the server;
[0024] The server inputs the food image into the trained recipe video production model to obtain a target recipe matching the food image; obtains a corresponding recipe production video according to the target recipe; and pushes the recipe production video to a kitchen TV in the kitchen;
[0025] The kitchen TV automatically plays the received recipe making video.
[0026] Furthermore, the recipe video processing system further includes a handheld terminal of a user, the target recipes matching the ingredient images include at least two recipes, and the server is further used for:
[0027] The server pushes the at least two recipes to the handheld terminal;
[0028] The server selects a corresponding target recipe from the at least two recipes in response to the recipe selection instruction returned by the handheld terminal;
[0029] The server obtains a corresponding recipe making video according to the corresponding target recipe.
[0030] In a fourth aspect, a recipe video processing device based on a kitchen scene is provided, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the steps of the recipe video processing method as described in any one of the preceding items are implemented.
[0031] In a fifth aspect, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the recipe video processing method as described in any one of the above items are implemented.
[0032] In one of the solutions provided above, an image of ingredients can be received, and the image of ingredients is an image corresponding to the ingredients stored in the refrigerator in the kitchen; the image of ingredients is input into the trained recipe video production model to obtain a target recipe matching the image of ingredients; according to the target recipe, a corresponding recipe production video is obtained; the recipe production video is pushed to the kitchen TV in the kitchen, so that the kitchen TV automatically plays the recipe production video. In the above process, the user does not need to manually search and select the required recipe production video based on the refrigerator ingredients input, which improves the efficiency of obtaining recipe production videos. Secondly, through the above solution, when the user opens the refrigerator and looks at the vast amount of food, he can choose what food to cook, which provides a better user experience. BRIEF DESCRIPTION OF THE DRAWINGS
[0033] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the description of the embodiments of the present application will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.
[0034] Figure 1 It is a flowchart of a recipe video processing method based on a kitchen scene in one embodiment of the present application;
[0035] Figure 2 It is a structural schematic diagram of a recipe video processing method and device based on a kitchen scene in one embodiment of the present application;
[0036] Figure 3 It is a structural schematic diagram of a computer device in one embodiment of the present application. DETAILED DESCRIPTION
[0037] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.
[0038] like Figure 1 In one embodiment of the present application, a recipe video processing method based on a kitchen scene is provided, which can be implemented based on a server. The method includes:
[0039] S10: receiving a food image, where the food image is an image corresponding to food stored in a refrigerator in a kitchen;
[0040] S20: inputting the ingredient image into the trained recipe video production model to obtain a target recipe matching the ingredient image;
[0041] S30: According to the target recipe, obtain a corresponding recipe making video;
[0042] S40: Pushing the recipe making video to the kitchen TV in the kitchen, so that the kitchen TV automatically plays the recipe making video.
[0043] The recipe video production model is trained based on deep learning technology and a large amount of training data. For example, a large amount of training data includes sample ingredient images and corresponding recipe information. It can be trained in a supervised manner to obtain a trained recipe video production model.
[0044] The food images are images corresponding to various types of food stored in the refrigerator in the kitchen, including vegetables, pre-prepared dishes, meat, fish, seasonings, medicinal materials, etc., without specific limitation. As some other examples, the images corresponding to various types of food include quantity features of food, image features reflecting the freshness of food, etc., so that the recipe video production model can screen and output the corresponding recipe.
[0045] In addition, the ingredient image can be one or more, without specific limitation, and the recipe video production model can output one recipe or multiple recipes based on one or more ingredient images, without specific limitation.
[0046] In this embodiment, a recipe video processing method based on a kitchen scene is provided, wherein a server can receive an ingredient image, wherein the ingredient image is an image corresponding to the ingredient stored in the refrigerator in the kitchen; the ingredient image is input into a trained recipe video production model to obtain a target recipe matching the ingredient image; according to the target recipe, a corresponding recipe production video is obtained; the recipe production video is pushed to a kitchen TV in the kitchen, so that the kitchen TV automatically plays the recipe production video. In the above process, the user does not need to manually search and select the required recipe production video based on the refrigerator ingredient input, thereby improving the efficiency of obtaining the recipe production video. Secondly, through the above scheme, when the user opens the refrigerator and looks at the vast amount of food, he can choose what food to cook, which provides a better user experience.
[0047] Further, in one embodiment, the target recipe matched with the ingredient image includes at least two recipes, and step S30, that is, obtaining a corresponding recipe making video according to the target recipe, includes the following steps:
[0048] S31: responding to a recipe selection instruction, selecting a corresponding target recipe from the at least two recipes;
[0049] S32: According to the corresponding target recipe, a corresponding recipe making video is obtained.
[0050] In this embodiment, the recipe video production model can output at least two recipes for the user to choose from. After the user makes a choice, the user responds to the recipe selection instruction and selects a corresponding target recipe from the at least two recipes. Then, according to the corresponding target recipe, a corresponding recipe production video is obtained so as to be pushed to the kitchen TV in the kitchen, so that the kitchen TV automatically plays the recipe production video. In this embodiment, the recipe video production model can be trained to output a variety of recipes for the user to choose from, thereby improving the flexibility and diversity of the recipe production video and enhancing the user experience.
[0051] Furthermore, in one embodiment, the food image includes images corresponding to the food stored in one or more refrigerators in the kitchen.
[0052] In this embodiment, the ingredient images include images corresponding to the ingredients stored in one or more refrigerators in the kitchen, so that decisions can be made on the ingredients in any one or more refrigerators in the kitchen. On the one hand, this ensures the utilization of various ingredients in the kitchen; on the other hand, it is also conducive to the recipe video production model to output diverse or appropriate recipe production videos.
[0053] Furthermore, in step S10, that is, receiving the food image, includes:
[0054] The food image photographed by the user using a handheld terminal is received.
[0055] In this embodiment, an application scenario is provided, that is, after opening the refrigerator in the kitchen, the user can use a mobile phone, a wristband or other handheld terminal to take a photo of the food in the refrigerator in the kitchen, and then use the handheld terminal to automatically send the taken food image to the server, so that the server outputs a recipe making video to the kitchen TV in the kitchen, and the kitchen TV automatically plays the recipe making video. This method allows users to participate in it, which is simple and convenient, and solves the problem of not knowing how to cook after opening the refrigerator. After opening the refrigerator, you can take a photo at will, which is simple, convenient, and has a good user experience.
[0056] Furthermore, in step S20, receiving the food image includes:
[0057] Receive the food image captured by the built-in camera of the refrigerator.
[0058] In this embodiment, an application scenario is provided, that is, the user does not need to open the refrigerator in the kitchen and take pictures casually, but the built-in camera in the refrigerator in the kitchen automatically takes pictures of the food in the refrigerator, so that the server outputs the recipe making video to the kitchen TV in the kitchen, and the kitchen TV automatically plays the recipe making video. This method is smarter and does not require the user to participate in shooting, which is smarter.
[0059] Among them, the built-in camera of the refrigerator in the kitchen can automatically take pictures based on some preconditions to obtain images of food in the refrigerator, which are not specifically limited. For example, the preconditions can be jointly determined based on the time interval and the type and quantity of the food images, which are not specifically limited.
[0060] In one embodiment, a recipe video processing system based on a kitchen scene is provided, the recipe video processing system comprising a server, a refrigerator and a kitchen TV arranged in the kitchen, the refrigerator being provided with a built-in camera, the:
[0061] The refrigerator captures food images corresponding to the food stored in the refrigerator through a built-in camera, and sends the food images to the server;
[0062] The server inputs the food image into the trained recipe video production model to obtain a target recipe matching the food image; obtains a corresponding recipe production video according to the target recipe; and pushes the recipe production video to a kitchen TV in the kitchen;
[0063] The kitchen TV automatically plays the received recipe making video.
[0064] The recipe video production model is trained based on deep learning technology and a large amount of training data. For example, a large amount of training data includes sample ingredient images and corresponding recipe information. It can be trained in a supervised manner to obtain a trained recipe video production model.
[0065] The food images are images corresponding to various types of food stored in the refrigerator in the kitchen, including vegetables, pre-prepared dishes, meat, fish, seasonings, medicinal materials, etc., without specific limitation. As some other examples, the images corresponding to various types of food include quantity features of food, image features reflecting the freshness of food, etc., so that the recipe video production model can screen and output the corresponding recipe.
[0066] In addition, the ingredient image can be one or more, without specific limitation, and the recipe video production model can output one recipe or multiple recipes based on one or more ingredient images, without specific limitation.
[0067] In this embodiment, a recipe video processing system based on a kitchen scene is provided, wherein a server can receive an image of ingredients, wherein the image of ingredients corresponds to an image of ingredients stored in a refrigerator in a kitchen; the image of ingredients is input into a trained recipe video production model to obtain a target recipe matching the image of ingredients; a corresponding recipe production video is obtained according to the target recipe; the recipe production video is pushed to a kitchen TV in the kitchen, so that the kitchen TV automatically plays the recipe production video. In the above process, there is no need for the user to manually search and select the required recipe production video based on the input of refrigerator ingredients, thereby improving the efficiency of obtaining recipe production videos. Secondly, through the above scheme, when the user opens the refrigerator and looks at the vast amount of food, he or she can choose what food to cook, which provides a better user experience.
[0068] Further, in one embodiment, the recipe video processing system further includes a handheld terminal of a user, and the target recipes matched with the ingredient image include at least two recipes;
[0069] The server pushes the at least two recipes to the handheld terminal;
[0070] The server selects a corresponding target recipe from the at least two recipes in response to the recipe selection instruction returned by the handheld terminal;
[0071] The server obtains a corresponding recipe making video according to the corresponding target recipe.
[0072] In the system provided in this embodiment, the recipe video production model can output at least two recipes for the user to choose from. After the user makes a choice, the user responds to the recipe selection instruction and selects a corresponding target recipe from the at least two recipes. Then, according to the corresponding target recipe, a corresponding recipe production video is obtained so as to be pushed to the kitchen TV in the kitchen, so that the kitchen TV automatically plays the recipe production video. In this embodiment, the recipe video production model can be trained to output a variety of recipes for the user to choose from, thereby improving the flexibility and diversity of the recipe production video and enhancing the user experience.
[0073] Furthermore, in one embodiment, the server is used to receive the food image taken by the user using a handheld terminal.
[0074] In this embodiment, an application scenario is provided, that is, after opening the refrigerator in the kitchen, the user can use a mobile phone, a wristband or other handheld terminal to take a photo of the food in the refrigerator in the kitchen, and then use the handheld terminal to automatically send the taken food image to the server, so that the server outputs a recipe making video to the kitchen TV in the kitchen, and the kitchen TV automatically plays the recipe making video. This method allows users to participate in it, which is simple and convenient, and solves the problem of not knowing how to cook after opening the refrigerator. After opening the refrigerator, you can take a photo at will, which is simple, convenient, and has a good user experience.
[0075] Furthermore, in one embodiment, the server is used to receive the food image taken by the built-in camera of the refrigerator.
[0076] In this embodiment, an application scenario is provided, that is, the user does not need to open the refrigerator in the kitchen and take pictures casually, but the built-in camera in the refrigerator in the kitchen automatically takes pictures of the food in the refrigerator, so that the server outputs the recipe making video to the kitchen TV in the kitchen, and the kitchen TV automatically plays the recipe making video. This method is smarter and does not require the user to participate in shooting, which is smarter.
[0077] It should be understood that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.
[0078] In one embodiment, a recipe video processing device based on a kitchen scene is provided, and the recipe video processing device corresponds to the recipe video processing device method in the above embodiment. Figure 2 As shown, the recipe video processing device includes a receiving module 101, an input module 102, an acquisition module 103 and a push module 104. The functional modules are described in detail as follows:
[0079] A receiving module 101 is used to receive food images, where the food images are images corresponding to food stored in a refrigerator in a kitchen;
[0080] An input module 102, for inputting the ingredient image into the trained recipe video production model to obtain a target recipe matching the ingredient image;
[0081] An acquisition module 103 is used to acquire a corresponding recipe making video according to the target recipe;
[0082] The push module 104 is used to push the recipe making video to the kitchen TV in the kitchen, so that the kitchen TV automatically plays the recipe making video.
[0083] The recipe video production model is trained based on deep learning technology and a large amount of training data. For example, a large amount of training data includes sample ingredient images and corresponding recipe information. It can be trained in a supervised manner to obtain a trained recipe video production model.
[0084] The food images are images corresponding to various types of food stored in the refrigerator in the kitchen, including vegetables, pre-prepared dishes, meat, fish, seasonings, medicinal materials, etc., without specific limitation. As some other examples, the images corresponding to various types of food include quantity features of food, image features reflecting the freshness of food, etc., so that the recipe video production model can screen and output the corresponding recipe.
[0085] In addition, the ingredient image can be one or more, without specific limitation, and the recipe video production model can output one recipe or multiple recipes based on one or more ingredient images, without specific limitation.
[0086] In this embodiment, a recipe video processing device based on a kitchen scene is provided, which can receive an image of ingredients, wherein the image of ingredients is an image corresponding to the ingredients stored in the refrigerator in the kitchen; the image of ingredients is input into a trained recipe video production model to obtain a target recipe matching the image of ingredients; according to the target recipe, a corresponding recipe production video is obtained; the recipe production video is pushed to a kitchen TV in the kitchen, so that the kitchen TV automatically plays the recipe production video. In the above process, the user does not need to manually search and select the required recipe production video based on the input of refrigerator ingredients, which improves the efficiency of obtaining recipe production videos. Secondly, through the above scheme, when the user opens the refrigerator and looks at the vast amount of food, he can choose what food to cook, which provides a better user experience.
[0087] In one embodiment, the target recipe matching the ingredient image includes at least two recipes, and according to the target recipe, the acquisition module 103 is used to:
[0088] In response to the recipe selection instruction, selecting a corresponding target recipe from the at least two recipes;
[0089] According to the corresponding target recipe, a corresponding recipe making video is obtained.
[0090] In the system provided in this embodiment, the recipe video production model can output at least two recipes for the user to choose from. After the user makes a choice, the user responds to the recipe selection instruction and selects a corresponding target recipe from the at least two recipes. Then, according to the corresponding target recipe, a corresponding recipe production video is obtained so as to be pushed to the kitchen TV in the kitchen, so that the kitchen TV automatically plays the recipe production video. In this embodiment, the recipe video production model can be trained to output a variety of recipes for the user to choose from, thereby improving the flexibility and diversity of the recipe production video and enhancing the user experience.
[0091] In one embodiment, the food image includes images corresponding to the food stored in one or more refrigerators in the kitchen.
[0092] In one embodiment, the receiving module 101 is used to receive the food image taken by the user using a handheld terminal.
[0093] In this embodiment, an application scenario is provided, that is, after opening the refrigerator in the kitchen, the user can use a mobile phone, a wristband or other handheld terminal to take a photo of the food in the refrigerator in the kitchen, and then use the handheld terminal to automatically send the taken food image to the server, so that the server outputs a recipe making video to the kitchen TV in the kitchen, and the kitchen TV automatically plays the recipe making video. This method allows users to participate in it, which is simple and convenient, and solves the problem of not knowing how to cook after opening the refrigerator. After opening the refrigerator, you can take a photo at will, which is simple, convenient, and has a good user experience.
[0094] In one embodiment, the receiving module 101 is used to receive the food image taken by the built-in camera of the refrigerator.
[0095] In this embodiment, an application scenario is provided, that is, the user does not need to open the refrigerator in the kitchen and take pictures casually, but the built-in camera in the refrigerator in the kitchen automatically takes pictures of the food in the refrigerator, so that the server outputs the recipe making video to the kitchen TV in the kitchen, and the kitchen TV automatically plays the recipe making video. This method is smarter and does not require the user to participate in shooting, which is smarter.
[0096] In this embodiment, a recipe video device based on a kitchen scene is provided, which can receive an image of ingredients, wherein the image of ingredients is an image corresponding to the ingredients stored in the refrigerator in the kitchen; the image of ingredients is input into a trained recipe video production model to obtain a target recipe matching the image of ingredients; according to the target recipe, a corresponding recipe production video is obtained; the recipe production video is pushed to a kitchen TV in the kitchen, so that the kitchen TV automatically plays the recipe production video. In the above process, the user does not need to manually search and select the required recipe production video based on the input of refrigerator ingredients, which improves the efficiency of obtaining recipe production videos. Secondly, through the above scheme, when the user opens the refrigerator and looks at the vast amount of food, he can choose what food to cook, which provides a better user experience.
[0097] For the specific definition of the recipe video processing device, please refer to the definition of the recipe video processing method above, which will not be repeated here. Each module in the above-mentioned recipe video processing device can be implemented in whole or in part by software, hardware and a combination thereof. The above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.
[0098] In one embodiment, a computer device is provided, whose internal structure diagram can be as follows: Figure 3 As shown. The computer device includes a processor, a memory, and a network interface connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the processor is used to communicate with a refrigerator or a kitchen TV through a network connection. When the computer program is executed by the processor, a recipe video processing method is implemented.
[0099] In one embodiment, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the following steps when executing the computer program:
[0100] Receiving a food image, where the food image is an image corresponding to the food stored in a refrigerator in a kitchen;
[0101] Inputting the ingredient image into the trained recipe video production model to obtain a target recipe matching the ingredient image;
[0102] According to the target recipe, obtain a corresponding recipe making video;
[0103] The recipe making video is pushed to a kitchen TV in the kitchen, so that the kitchen TV automatically plays the recipe making video.
[0104] In one embodiment, the target recipes matched with the ingredient image include at least two recipes, and the processor further specifically implements the following steps when executing the computer program:
[0105] In response to the recipe selection instruction, selecting a corresponding target recipe from the at least two recipes;
[0106] According to the corresponding target recipe, a corresponding recipe making video is obtained.
[0107] In one embodiment, the food image includes images corresponding to the food stored in one or more refrigerators in the kitchen.
[0108] In one embodiment, when the processor executes the computer program, the processor further specifically implements the following steps:
[0109] The food image photographed by the user using a handheld terminal is received.
[0110] In one embodiment, when the processor executes the computer program, the processor further specifically implements the following steps:
[0111] Receive the food image captured by the built-in camera of the refrigerator.
[0112] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the recipe video processing method mentioned in any of the above embodiments is implemented, which will not be repeated here.
[0113] In this embodiment, a device or medium is provided, which can input the image of the ingredients into the trained recipe video production model to obtain a target recipe that matches the image of the ingredients; obtain the corresponding recipe production video according to the target recipe; and push the recipe production video to the kitchen TV in the kitchen so that the kitchen TV automatically plays the recipe production video. In the above process, the user does not need to manually search and select the required recipe production video based on the refrigerator ingredients input, which improves the efficiency of obtaining the recipe production video. Secondly, through the above solution, when the user opens the refrigerator and looks at the vast amount of food, he can choose what food to cook, which provides a better user experience.
[0114] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).
[0115] Those skilled in the art can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example. In actual applications, the above-mentioned functions can be distributed and completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above.
[0116] The embodiments described above are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, a person skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.
Claims
1. A recipe video processing method based on a kitchen scene, characterized in that: include: Receiving a food image, where the food image is an image corresponding to the food stored in a refrigerator in a kitchen; Inputting the ingredient image into the trained recipe video production model to obtain a target recipe matching the ingredient image; According to the target recipe, obtain a corresponding recipe making video; The recipe making video is pushed to a kitchen TV in the kitchen, so that the kitchen TV automatically plays the recipe making video.
2. The recipe video processing method according to claim 1, characterized in that: The target recipes matched with the ingredient images include at least two recipes, and acquiring corresponding recipe making videos according to the target recipes includes: In response to the recipe selection instruction, selecting a corresponding target recipe from the at least two recipes; According to the corresponding target recipe, a corresponding recipe making video is obtained.
3. The recipe video processing method according to claim 1, characterized in that: The food image includes images corresponding to the food stored in one or more refrigerators in the kitchen.
4. The recipe video processing method according to claim 1, characterized in that: The receiving of the food image comprises: The food image photographed by the user using a handheld terminal is received.
5. The recipe video processing method according to claim 1, characterized in that: The receiving of the food image comprises: Receive the food image captured by the built-in camera of the refrigerator.
6. A recipe video processing device based on a kitchen scene, characterized in that: include: A receiving module, used to receive food images, where the food images are images corresponding to food stored in a refrigerator in a kitchen; An input module, used for inputting the ingredient image into the trained recipe video production model to obtain a target recipe matching the ingredient image; An acquisition module, used to acquire a corresponding recipe making video according to the target recipe; The push module is used to push the recipe making video to the kitchen TV in the kitchen, so that the kitchen TV automatically plays the recipe making video.
7. A recipe video processing system based on kitchen scenes, characterized in that: The recipe video processing system includes a server, a refrigerator and a kitchen TV arranged in the kitchen, wherein the refrigerator is provided with a built-in camera, wherein: The refrigerator captures food images corresponding to the food stored in the refrigerator through a built-in camera, and sends the food images to the server; The server inputs the food image into the trained recipe video production model to obtain a target recipe matching the food image; obtains a corresponding recipe production video according to the target recipe; and pushes the recipe production video to a kitchen TV in the kitchen; The kitchen TV automatically plays the received recipe making video.
8. The recipe video processing system according to claim 7, characterized in that: The recipe video processing system further includes a user's handheld terminal, the target recipes matching the ingredient images include at least two recipes, and the server is further used for: The server pushes the at least two recipes to the handheld terminal; The server selects a corresponding target recipe from the at least two recipes in response to the recipe selection instruction returned by the handheld terminal; The server obtains a corresponding recipe making video according to the corresponding target recipe.
9. A recipe video processing device based on a kitchen scene, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the recipe video processing method according to any one of claims 1 to 5 are implemented.
10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the recipe video processing method according to any one of claims 1 to 5 are implemented.