A cooking assisting method and device based on recommended recipes

Abstract

The present application relates to the technical field of recipe recommendation, and particularly relates to a cooking auxiliary method and device based on recommended recipes. The method comprises the following steps: in response to an operation instruction of a user for a recommended recipe, identifying the operation instruction to obtain instruction information, and inputting the instruction information into a pre-trained binary classification model to enable the binary classification model to judge the type of the instruction information; in the case that the instruction information belongs to inquiry information, inputting the instruction information into a pre-trained recipe question and answer language model to enable the recipe question and answer language model to generate a response matched with the instruction information; in the case that the instruction information belongs to correction information, inputting the instruction information into a pre-trained recipe correction model to enable the recipe correction model to determine a step to be corrected in the recommended recipe to which the instruction information is directed, and adjusting the step to be corrected according to correction information contained in the instruction information; and providing the generated response or the adjusted recommended recipe to the user.

Description

Technical Field

[0001] This invention relates to the field of cooking technology, and more specifically to a cooking assistance method and apparatus based on recommended recipes. Background Technology

[0002] Recipe recommendation refers to the intelligent recommendation of recipes to users based on their taste preferences, nutritional needs, and food contraindications. A recipe recommendation system is an application system built upon recipe recommendation technology.

[0003] In related technologies, recipe recommendation systems can select matching recipes from a recipe database based on user instructions and recommend them to the user. However, once a recipe is selected, it is often impossible to modify or change it, and users cannot adjust the recipe in real time. Furthermore, recipe recommendation systems cannot answer user questions about recipes, thus affecting the user's cooking process. Summary of the Invention

[0004] To address the aforementioned technical problems, this invention proposes a cooking assistance method and device based on recommended recipes. The aim is to make the recipes more tailored to users' habits and preferences, and to answer inquiries about the recipes and modify them according to user-suggested corrections. This increases the interactivity between the cooking assistance system and the user, ensuring a smooth cooking process.

[0005] Firstly, this application provides a cooking assistance method based on recommended recipes, including:

[0006] In response to a user's operation command for a recommended recipe, the operation command is identified to obtain command information, and the command information is input into a pre-trained binary classification model so that the binary classification model can determine the type of the command information;

[0007] If the instruction information is a query, the instruction information is input into a pre-trained recipe question-answering language model so that the recipe question-answering language model generates a response that matches the instruction information.

[0008] If the instruction information is correction information, the instruction information is input into a pre-trained recipe correction model so that the recipe correction model can determine the steps to be corrected in the recommended recipe targeted by the instruction information, and adjust the steps to be corrected according to the correction information contained in the instruction information.

[0009] The generated response or the adjusted recommended recipe will be provided to the user.

[0010] In some embodiments, the operation instructions are audio data or operation requests sent from the user's mobile device.

[0011] In some embodiments, providing the generated response or adjusted recommended recipe to the user includes:

[0012] The generated response or adjusted recommended recipe will be provided to the user via voice broadcast; or...

[0013] The generated response or the adjusted recommended recipe will be sent to the user's mobile device in the form of pictures and text for display.

[0014] In some embodiments, the recipe question-answering language model is a large-scale language model trained on training data in the culinary field, and the recipe correction model is a machine learning model built on natural language processing technology and generative adversarial networks.

[0015] Secondly, this application provides a training method for a binary classification model, including:

[0016] Obtain a training sample set, wherein each training sample in the training sample set includes: instruction information and the real type corresponding to the instruction information;

[0017] The training sample set is input into the model to be trained, so that the model to be trained outputs the prediction type corresponding to the instruction information in each training sample.

[0018] The true type and predicted type of each training sample are compared, and the model to be trained is optimized based on the comparison results until the fit between the true type and predicted type of each training sample reaches a preset threshold.

[0019] Thirdly, this application provides a method for training a recipe question-answering language model, including:

[0020] Obtain a training sample set, wherein each training sample in the training sample set includes: a query for a recipe and the actual response to the query;

[0021] The training sample set is input into the model to be trained, so that the model to be trained generates the predicted response corresponding to the query in each training sample.

[0022] The actual responses and predicted responses of each training sample are compared, and the model to be trained is optimized based on the comparison results until the fit between the actual responses and predicted responses of each training sample reaches a preset threshold.

[0023] Fourthly, this application provides a training method for a recipe correction model, including:

[0024] Obtain a training sample set, wherein each training sample in the training sample set includes: correction information for the recipe and actual steps after manually correcting the steps to be corrected in the recipe based on the correction information;

[0025] The training sample set is input into the model to be trained, so that the model to be trained generates the prediction steps corresponding to each training sample.

[0026] The actual steps and predicted steps of each training sample are compared, and the model to be trained is optimized based on the comparison results until the fit between the actual steps and predicted steps of each training sample reaches a preset threshold.

[0027] Fifthly, this application provides a cooking aid device based on a recommended recipe, comprising:

[0028] The recognition unit is used to respond to the user's operation command for the recommended recipe, recognize the operation command to obtain command information, and input the command information into a pre-trained binary classification model so that the binary classification model can determine the type of the command information;

[0029] The first input unit is used to input the instruction information into a pre-trained recipe question-answering language model when the instruction information belongs to the query type, so that the recipe question-answering language model generates a response that matches the instruction information;

[0030] The second input unit is used to input the instruction information into a pre-trained recipe correction model when the instruction information belongs to the correction type, so that the recipe correction model can determine the step to be corrected in the recommended recipe targeted by the instruction information, and adjust the step to be corrected according to the correction information contained in the instruction information.

[0031] The unit provides the generated response or the adjusted recommended recipe to the user.

[0032] Sixthly, this application provides a method for training a binary classification model, including:

[0033] An acquisition unit is used to acquire a training sample set, wherein each training sample in the training sample set includes: instruction information and the real type corresponding to the instruction information;

[0034] An input unit is used to input the training sample set into the model to be trained, so that the model to be trained outputs the prediction type corresponding to the instruction information in each training sample.

[0035] An optimization unit is used to compare the true type and predicted type of each training sample, and optimize the model to be trained based on the comparison results until the fit between the true type and predicted type of each training sample reaches a preset threshold.

[0036] Seventhly, this application provides a method for training a recipe question-answering language model, including:

[0037] The acquisition unit is used to acquire a training sample set, wherein each training sample in the training sample set includes: a query for a recipe and the actual response corresponding to the query;

[0038] An input unit is used to input the training sample set into the model to be trained, so that the model to be trained generates the predicted response corresponding to the query in each training sample.

[0039] An optimization unit is used to compare the actual response and the predicted response of each training sample, and optimize the model to be trained based on the comparison results until the fit between the actual response and the predicted response of each training sample reaches a preset threshold.

[0040] Eighthly, this application provides a method for training a recipe correction model, including:

[0041] An acquisition unit is used to acquire a training sample set, wherein each training sample in the training sample set includes: correction information for the recipe and actual steps after manually correcting the steps to be corrected in the recipe based on the correction information.

[0042] An input unit is used to input the training sample set into the model to be trained, so that the model to be trained generates prediction steps corresponding to each training sample.

[0043] The optimization unit is used to compare the actual steps and predicted steps of each training sample, and optimize the model to be trained based on the comparison results, until the fit between the actual steps and predicted steps of each training sample reaches a preset threshold.

[0044] Ninth aspect, an electronic device including a processor and a memory;

[0045] The processor is connected to the memory;

[0046] The memory is used to store executable program code;

[0047] The processor runs a program corresponding to the executable program code stored in the memory to perform the methods described in any one of the first, second, third, and fourth aspects.

[0048] A tenth aspect is a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method as described in any one of the first, second, third, and fourth aspects.

[0049] The beneficial technical effects of the present invention include at least the following: by adopting a cooking assistance method and device based on recommended recipes, the cooking assistance system can distinguish user instruction information, answer the distinguished inquiries, and modify the recipe according to the user's correction instructions, thereby increasing the interactivity between the cooking assistance system and the user, and ensuring the smoothness of the user's cooking process.

[0050] Other features and advantages of the present invention will be disclosed in detail in the following detailed description and accompanying drawings. Attached Figure Description

[0051] The invention will be further described below with reference to the accompanying drawings:

[0052] Figure 1 This is an architecture diagram of a cooking assistance system based on recommended recipes, as shown in an embodiment of the present invention.

[0053] Figure 2 This is a flowchart illustrating a cooking assistance method based on recommended recipes, as shown in an embodiment of the present invention.

[0054] Figure 3 This is a flowchart illustrating a training method for a binary classification model according to an embodiment of the present invention.

[0055] Figure 4 This is a flowchart illustrating a training method for a recipe question-and-answer language model, as shown in an embodiment of the present invention.

[0056] Figure 5 This is a flowchart illustrating a training method for a recipe correction model, as shown in an embodiment of the present invention.

[0057] Figure 6 This is a block diagram illustrating a cooking aid device based on a recommended recipe, as shown in an embodiment of the present invention.

[0058] Figure 7 This is a block diagram illustrating a training device for a binary classification model according to an embodiment of the present invention.

[0059] Figure 8 This is a block diagram illustrating a training device for a recipe question-and-answer language model, as shown in an embodiment of the present invention.

[0060] Figure 9 This is a block diagram illustrating a training device for a recipe correction model according to an embodiment of the present invention.

[0061] Figure 10This is a schematic diagram of the structure of an electronic device according to an embodiment of the present invention. Detailed Implementation

[0062] The technical solutions of the embodiments of the present invention will be explained and described below with reference to the accompanying drawings. However, the following embodiments are only preferred embodiments of the present invention and not all of them. Other embodiments obtained by those skilled in the art based on the embodiments in the implementation methods without creative effort are all within the protection scope of the present invention.

[0063] In the following description, terms such as “inner,” “outer,” “upper,” “lower,” “left,” and “right” are used only to indicate orientation or positional relationship for the convenience of describing the embodiments and simplifying the description, and are not intended to indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation, and therefore should not be construed as a limitation of the present invention.

[0064] This application provides a cooking assistance system based on recommended recipes. Please refer to the appendix. Figure 1 ,like Figure 1 As shown, the recipe-based cooking assistance system 10 includes a binary classification model 11, a recipe question-and-answer language model 12, and a recipe correction model 13.

[0065] Binary classification models are a type of machine learning model used to classify input data into two mutually exclusive categories. These models are widely used in various scenarios, such as spam detection (classifying emails as spam or non-spam), sentiment analysis (classifying text as positive or negative comments), and disease diagnosis (classifying disease states as active or inactive). In a binary classification model, there is typically a target variable, which is binary and can be either 0 or 1, representing two distinct categories. The model's task is to predict the value of the target variable by analyzing the feature vectors of the input data. During the training phase, the model learns the relationship between the input features and the target variable, thereby establishing a classification boundary that enables it to correctly classify new input data during the testing phase. The binary classification model described in this specification can be any of the following: logistic regression, support vector machine (SVM), decision tree, random forest, or neural network; this specification does not impose any restrictions on this.

[0066] The recipe question-answering language model 122 is a large-scale language model trained on training data in the culinary field, while the recipe correction model 123 is a machine learning model built on natural language processing technology and generative adversarial networks.

[0067] In this embodiment, the cooking assistance system can distinguish user instructions, answer distinguished inquiries, and modify recipes according to user correction instructions, thereby increasing the interactivity between the cooking assistance system and the user and ensuring the smoothness of the user's cooking process.

[0068] Please see Figure 2 , Figure 2 The application provides a flowchart of a cooking assistance method based on recommended recipes, such as... Figure 2 As shown, the method includes at least the following steps:

[0069] Step 202: In response to the user's operation command for the recommended recipe, the operation command is identified to obtain command information, and the command information is input into a pre-trained binary classification model so that the binary classification model can determine the type of the command information.

[0070] In one embodiment, the operation instruction can be audio data or an operation request sent by the user's mobile device. The cooking assistance system may include an audio device that can acquire audio signals emitted by the user and then identify the audio signals to obtain instruction information; alternatively, the cooking assistance system may include the user's mobile device, which may have a client program for the cooking assistance system installed. This client program can receive user operation requests (e.g., user-inputted commands or button clicks, which are not limited herein) and identify the operation instructions to obtain instruction information.

[0071] Step 204: If the instruction information is a query type, input the instruction information into a pre-trained recipe question-answering language model so that the recipe question-answering language model generates a response that matches the instruction information.

[0072] Step 206: If the instruction information is correction information, input the instruction information into the pre-trained recipe correction model so that the recipe correction model can determine the step to be corrected in the recommended recipe targeted by the instruction information, and adjust the step to be corrected according to the correction information contained in the instruction information.

[0073] Instruction messages can be divided into two categories: query messages and correction messages. Query messages can be questions users encounter while cooking with a recipe, such as "How many spoonfuls is 50 grams of salt?" or "Is Kung Pao Chicken spicy?" For this type of information, the system does not need to modify the recommended recipe; it only needs to provide a response to the query. Correction messages can be adjustment instructions from users regarding steps in the recommended recipe that need to be changed, such as "Remove Kung Pao Chicken from the recipe" or "Use steaming instead of stir-frying when cooking." For this type of information, the system needs to make adaptive modifications to the recommended recipe.

[0074] Step 208: Provide the generated response or the adjusted recommended recipe to the user.

[0075] In this embodiment, the cooking assistance system can distinguish user instructions, answer distinguished inquiries, and modify recipes according to user correction instructions, thereby increasing the interactivity between the cooking assistance system and the user and ensuring the smoothness of the user's cooking process.

[0076] In one embodiment, providing the generated response or adjusted recommended recipe to the user includes: providing the generated response or adjusted recommended recipe to the user in the form of voice broadcast; or, sending the generated response or adjusted recommended recipe to the user's mobile device in the form of pictures and text for display.

[0077] As mentioned earlier, users can issue operation commands via audio or mobile devices, and the system can respond in two ways. If the system includes an audio device, the generated response or recommended recipe can be played directly to the user in the form of a voice broadcast; if the system includes a mobile device, the generated response or recommended recipe can be sent directly to the user's mobile device in the form of text and images for display.

[0078] In this embodiment, leveraging cutting-edge large-scale modeling and NLP technology, the system successfully achieved synchronized audiovisual interaction between mobile and audio devices, enhancing the user experience. With the powerful support of the cooking assistance system, it can accurately and intelligently recommend recipes that match individual tastes, allowing users to easily master the techniques for preparing various dishes. The recipe correction system dynamically adjusts based on real-time user feedback, ensuring that every step of every dish precisely meets user expectations, making the cooking process more refined and personalized. This system not only optimizes the cooking process but also significantly enhances user engagement and satisfaction through intelligent interaction.

[0079] In one embodiment, the recipe question-answering language model is a large-scale language model trained on training data in the culinary field, and the recipe correction model is a machine learning model built on natural language processing technology and generative adversarial networks.

[0080] In this embodiment, the cooking assistance system can distinguish user instructions, answer distinguished inquiries, and modify recipes according to user correction instructions, thereby increasing the interactivity between the cooking assistance system and the user and ensuring the smoothness of the user's cooking process.

[0081] This application also proposes training methods for binary classification models, recipe question-answering language models, and recipe correction models.

[0082] Please see Figure 3 , Figure 3 This is a flowchart of a training method for a binary classification model provided in this application. The method includes at least the following steps:

[0083] Step 302: Obtain the training sample set. Each training sample in the training sample set includes: instruction information and the real type corresponding to the instruction information.

[0084] Step 304: Input the training sample set into the model to be trained, so that the model to be trained outputs the prediction type corresponding to the instruction information in each training sample;

[0085] Step 306: Compare the true type and predicted type of each training sample, and optimize the model to be trained based on the comparison results until the fit between the true type and predicted type of each training sample reaches a preset threshold.

[0086] Please see Figure 4 , Figure 4 This is a flowchart of a training method for a recipe question-answering language model provided in this application. The method includes at least the following steps:

[0087] Step 402: Obtain a training sample set. Each training sample in the training sample set includes: a query for a recipe and the actual response to the query.

[0088] Step 404: Input the training sample set into the model to be trained so that the model to be trained can generate the predicted response corresponding to the query in each training sample;

[0089] Step 406: Compare the actual responses and predicted responses of each training sample, and optimize the model to be trained based on the comparison results until the fit between the actual responses and predicted responses of each training sample reaches a preset threshold.

[0090] Please see Figure 5 , Figure 5 This is a flowchart of a training method for a recipe correction model provided in this application, which includes at least the following steps:

[0091] Step 502: Obtain a training sample set. Each training sample in the training sample set includes: correction information for the recipe and the actual steps after manually correcting the steps to be corrected in the recipe based on the correction information.

[0092] Step 504: Input the training sample set into the model to be trained so that the model to be trained generates prediction steps corresponding to each training sample.

[0093] Step 506: Compare the actual steps and predicted steps of each training sample, and optimize the model to be trained based on the comparison results until the fit between the actual steps and predicted steps of each training sample reaches a preset threshold.

[0094] It is understood that the technical concept of the training method for the binary classification model, recipe question-answering language model, and recipe correction model provided in this embodiment is similar to the technical concept of the aforementioned cooking assistance method based on recommended recipes, and will not be repeated here.

[0095] Please see Figure 6 , Figure 6 A block diagram of a cooking aid device based on recommended recipes, provided for embodiments of this specification. The device includes:

[0096] The recognition unit 602 is used to respond to the user's operation command for the recommended recipe, recognize the operation command to obtain command information, and input the command information into a pre-trained binary classification model so that the binary classification model can determine the type of the command information;

[0097] The first input unit 604 is used to input the instruction information into a pre-trained recipe question-answering language model when the instruction information belongs to the query type, so that the recipe question-answering language model generates a response that matches the instruction information;

[0098] The second input unit 606 is used to input the instruction information into a pre-trained recipe correction model when the instruction information belongs to the correction type information, so that the recipe correction model can determine the step to be corrected in the recommended recipe targeted by the instruction information, and adjust the step to be corrected according to the correction information contained in the instruction information.

[0099] Unit 608 is used to provide the generated response or the adjusted recommended recipe to the user.

[0100] Optionally, the operation instruction may be audio data or an operation request sent from the user's mobile device.

[0101] Optionally, the providing unit 608 is specifically used for:

[0102] The generated response or adjusted recommended recipe will be provided to the user via voice broadcast; or...

[0103] The generated response or the adjusted recommended recipe will be sent to the user's mobile device in the form of pictures and text for display.

[0104] Optionally, the recipe question-answering language model is a large-scale language model trained on training data in the culinary field, and the recipe correction model is a machine learning model built on natural language processing technology and generative adversarial networks.

[0105] Please see Figure 7 , Figure 7 A block diagram of a training device for a binary classification model provided in an embodiment of this specification. The device includes:

[0106] The acquisition unit 702 is used to acquire a training sample set, wherein each training sample in the training sample set includes: instruction information and the real type corresponding to the instruction information;

[0107] The input unit 704 is used to input the training sample set into the model to be trained, so that the model to be trained outputs the prediction type corresponding to the instruction information in each training sample.

[0108] The optimization unit 706 is used to compare the true type and predicted type of each training sample, and optimize the model to be trained according to the comparison results until the fit between the true type and predicted type of each training sample reaches a preset threshold.

[0109] Please see Figure 8 , Figure 8 A block diagram of a training device for a recipe question-answering language model provided in an embodiment of this specification. The device includes:

[0110] The acquisition unit 802 is used to acquire a training sample set, wherein each training sample in the training sample set includes: a query for a recipe and the actual response corresponding to the query;

[0111] The input unit 804 is used to input the training sample set into the model to be trained, so that the model to be trained generates the predicted response corresponding to the query in each training sample.

[0112] The optimization unit 806 is used to compare the real response and predicted response of each training sample, and optimize the model to be trained according to the comparison results until the fit between the real response and predicted response of each training sample reaches a preset threshold.

[0113] Please see Figure 9 , Figure 9 This is a block diagram of a training device for a recipe correction model provided in an embodiment of this specification. The device includes:

[0114] The acquisition unit 902 is used to acquire a training sample set, wherein each training sample in the training sample set includes: correction information for the recipe and actual steps after manually correcting the steps to be corrected in the recipe based on the correction information.

[0115] The input unit 904 is used to input the training sample set into the model to be trained, so that the model to be trained generates the prediction steps corresponding to each training sample.

[0116] The optimization unit 906 is used to compare the real steps and predicted steps of each training sample, and optimize the model to be trained according to the comparison results until the fit between the real steps and predicted steps of each training sample reaches a preset threshold.

[0117] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to interchangeably. Each embodiment focuses on its differences from other embodiments. In particular, the embodiment of the vibration-based wind turbine blade anomaly detection device is relatively simple in description because it is fundamentally similar to the embodiment of the cooking assistance method based on recommended recipes; relevant parts can be referred to in the description of the method embodiment.

[0118] Please see the appendix Figure 10 , Figure 10 This is a schematic diagram of an electronic device structure provided as another embodiment of this specification.

[0119] like Figure 10 As shown, the electronic device 1000 may include: at least one processor 1001, at least one network interface 1004, user interface 1003, memory 1005, and at least one communication bus 1002.

[0120] The communication bus 1002 can be used to realize the connection and communication of the above components.

[0121] The user interface 1003 may include buttons, and the optional user interface may also include a standard wired interface or a wireless interface.

[0122] The network interface 1004 may include, but is not limited to, Bluetooth modules, NFC modules, Wi-Fi modules, etc.

[0123] The processor 1001 may include one or more processing cores. The processor 1001 connects to various parts within the electronic device 1000 using various interfaces and lines. It executes various functions and processes data by running or executing instructions, programs, code sets, or instruction sets stored in the memory 1005, and by calling data stored in the memory 1005. Optionally, the processor 1001 may be implemented using at least one hardware form selected from DSP, FPGA, and PLA. The processor 1001 may integrate one or more of the following: CPU, GPU, and modem. The CPU primarily handles the operating system, user interface, and applications; the GPU is responsible for rendering and drawing the content required for display; and the modem handles wireless communication. It is understood that the modem may also not be integrated into the processor 1001 and may be implemented as a separate chip.

[0124] The memory 1005 may include RAM or ROM. Optionally, the memory 1005 may include a non-transitory computer-readable medium. The memory 1005 may be used to store instructions, programs, code, code sets, or instruction sets. The memory 1005 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for at least one function (such as touch function, sound playback function, image playback function, etc.), instructions for implementing the above-described method embodiments, etc.; the data storage area may store data involved in the above-described method embodiments, etc. Optionally, the memory 1005 may also be at least one storage device located remotely from the aforementioned processor 1001. As a computer storage medium, the memory 1005 may include an operating system, a network communication module, a user interface module, and application programs. The processor 1001 may be used to call the application programs stored in the memory 1005 and execute the methods in one or more of the above-described embodiments.

[0125] Another embodiment of this specification provides a computer-readable storage medium storing instructions that, when executed on a computer or processor, cause the computer or processor to perform one or more steps in the above embodiments. The constituent modules of the above-described electronic device, if implemented as software functional units and used as independent downstream task predictions or applications, can be stored in the computer-readable storage medium.

[0126] In the above embodiments, implementation can be achieved, in whole or in part, through software, hardware, firmware, or any combination thereof. When implemented using software, it can be implemented, in whole or in part, as a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of this specification are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in or transmitted through a computer-readable storage medium. The computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, Digital Subscriber Line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium accessible to a computer or a data storage device such as a server or data center that integrates one or more available media. The available media may be magnetic media (e.g., floppy disks, hard disks, magnetic tapes), optical media (e.g., Digital Versatile Discs (DVDs)), or semiconductor media (e.g., Solid State Disks (SSDs)).

[0127] The above description is merely a preferred embodiment disclosed in this application and an explanation of the technical principles employed. Those skilled in the art should understand that the scope of protection involved in this disclosure is not limited to technical solutions formed by specific combinations of the above-described technical features, but should also cover other technical solutions formed by arbitrary combinations of the above-described technical features or their equivalents without departing from the above-disclosed concept. For example, technical solutions formed by substituting the above features with (but not limited to) technical features with similar functions disclosed in this disclosure.

[0128] Furthermore, while the operations are described in a specific order, this should not be construed as requiring these operations to be performed in the specific order shown or in a sequential order. In certain environments, multitasking and parallel processing may be advantageous. Similarly, while several specific implementation details are included in the above discussion, these should not be construed as limiting the scope of this disclosure. Certain features described in the context of individual embodiments may also be implemented in combination in a single embodiment. Conversely, various features described in the context of a single embodiment may also be implemented individually or in any suitable sub-combination in multiple embodiments.

Claims

1. A cooking assistance method based on a recommended recipe, characterized in that, comprising: in response to a user's operation instruction for a recommended recipe, obtaining instruction information by identifying the operation instruction, and inputting the instruction information into a pre-trained binary classification model to make the binary classification model judge the type of the instruction information; in the case where the instruction information belongs to inquiry type information, inputting the instruction information into a pre-trained recipe question and answer language model to make the recipe question and answer language model generate a response matched to the instruction information; in the case where the instruction information belongs to correction type information, inputting the instruction information into a pre-trained recipe correction model to make the recipe correction model determine a step to be corrected in the recommended recipe to which the instruction information is directed, and adjust the step to be corrected according to correction information contained in the instruction information; providing the generated response or the adjusted recommended recipe to the user; the recipe question and answer language model is a large language model trained based on cooking field training data, and the recipe correction model is a machine learning model constructed based on natural language processing technology and a generative adversarial network.

2. The cooking assistance method based on a recommended recipe according to claim 1, characterized in that, the operation instruction is audio data or an operation request sent based on a user's mobile device.

3. The cooking assistance method based on a recommended recipe according to claim 1, characterized in that, the providing of the generated response or the adjusted recommended recipe to the user comprises: providing the generated response or the adjusted recommended recipe to the user in the form of voice broadcast; or sending the generated response or the adjusted recommended recipe to the user's mobile device in the form of text and image for display.

4. A training method of a binary classification model, applied to the cooking assistance method based on a recommended recipe according to any one of claims 1-3, characterized in that, comprising: obtaining a training sample set, each training sample in the training sample set comprising instruction information and a true type corresponding to the instruction information; inputting the training sample set into a to-be-trained model to make the to-be-trained model output a predicted type corresponding to the instruction information in each training sample; comparing the true type and the predicted type of each training sample respectively, and optimizing the to-be-trained model according to the comparison result until the fitting degree of the true type and the predicted type of each training sample reaches a preset threshold.

5. A training method of a recipe question and answer language model, applied to the cooking assistance method based on a recommended recipe according to any one of claims 1-3, characterized in that, comprising: obtaining a training sample set, each training sample in the training sample set comprising a question for a recipe and a true response corresponding to the question; inputting the training sample set into a to-be-trained model to make the to-be-trained model generate a predicted response corresponding to the question in each training sample; The real steps and the predicted steps of each training sample are compared respectively, and the to-be-trained model is optimized according to the comparison results until the fitting degree of the real steps and the predicted steps of each training sample reaches a preset threshold.

6. A training method of a recipe revision model, applied to the cooking assisting method based on a recommended recipe according to any one of claims 1-3, characterized in that, comprises: obtaining a training sample set, each training sample in the training sample set comprising revision information for a recipe and real steps obtained by manually revising a to-be-revised step of the recipe according to the revision information; inputting the training sample set into a to-be-trained model to enable the to-be-trained model to generate predicted steps corresponding to each training sample; The real steps and the predicted steps of each training sample are compared respectively, and the to-be-trained model is optimized according to the comparison results until the fitting degree of the real steps and the predicted steps of each training sample reaches a preset threshold.

7. A cooking assisting device based on a recommended recipe, characterized in that, comprises: an identification unit configured to, in response to an operation instruction of a user for a recommended recipe, identify the operation instruction to obtain instruction information, and input the instruction information into a pre-trained binary classification model to enable the binary classification model to judge the type of the instruction information; a first input unit configured to, in the case that the instruction information belongs to inquiry type information, input the instruction information into a pre-trained recipe question and answer language model to enable the recipe question and answer language model to generate a response matched to the instruction information; a second input unit configured to, in the case that the instruction information belongs to revision type information, input the instruction information into a pre-trained recipe revision model to enable the recipe revision model to determine a to-be-revised step in a recommended recipe to which the instruction information is directed, and adjust the to-be-revised step according to revision information contained in the instruction information; a providing unit configured to provide the generated response or the adjusted recommended recipe to the user; The recipe question and answer language model is a large language model trained based on cooking field training data, and the recipe revision model is a machine learning model constructed based on natural language processing technology and a generative adversarial network.

8. An electronic device, characterized in that, comprising a processor and a memory; the processor is connected with the memory; the memory is used for storing executable program codes; the processor runs a program corresponding to the executable program codes by reading the executable program codes stored in the memory, to execute the method according to any one of claims 1-6.

9. A computer readable storage medium, characterized in that, a computer program is stored thereon, and the computer program is executed by a processor to implement the method according to any one of claims 1-6.

Images