Cooking method for solving mutual promotion and mutual restraint relationship between multiple food ingredients on basis of large ai model, and intelligent cooking device therefor

Abstract

The present invention relates to a cooking method for solving a mutual promotion and mutual restraint relationship between multiple food ingredients on the basis of a large AI model, and an intelligent cooking device therefor. The cooking method is applied to an intelligent cooking device, and the intelligent cooking device is provided with a code scanning identification device, a processor and a wireless communication module; the code scanning identification device and the wireless communication module are electrically connected to the processor; the code scanning identification device scans identification codes on different food ingredient packages to identify food ingredient information and cooking parameters, unloads the food ingredient information and the cooking parameters to a large AI model of a cloud platform to determine a mutual promotion and mutual restraint relationship, and feeds information of the mutual promotion and mutual restraint relationship back to a user mobile terminal; and a user confirms by means of the user mobile terminal to enable the processor to execute cooking on the basis of the cooking parameters obtained by code scanning identification. The present invention implements application of a large AI model in the technical field of solving the problem of a mutual promotion and mutual restraint relationship when cooking multiple food ingredients; the intelligent cooking device scans identification codes on different food ingredient packages by means of the code scanning identification device to identify food ingredient information and cooking parameters, calls a mutual promotion and mutual restraint relationship-based cooking large AI model to determine whether multiple food ingredients have a mutual promotion and mutual restraint relationship, and reminds the user to confirm whether to continue cooking the food ingredients.

Description

A cooking method and intelligent cooking device based on AI big model to solve the mutual promotion and mutual restraint between multiple ingredients Technical Field

[0001] The present invention relates to a cooking method and a cooking device thereof, and in particular to a cooking method and an intelligent cooking device thereof that solves the mutual promotion and restraint between multiple ingredients based on an AI large model. Background Art

[0002] With the development of science and technology and the accelerated pace of life, smart cooking devices have emerged, which can realize automated cooking.

[0003] Regarding the combination of AI big models and smart cooking devices, the latest existing technologies include patent application number CN 116843510 A, published on October 3, 2023, entitled "Smart Cooking Machine Cloud Platform Data Management System and Method Based on AI Big Model," and application number 202310784823.7;

[0004] This invention application discloses a cloud platform data management system and method for intelligent cooking machines based on an AI big model, which relates to the technical field of data management systems. The management method includes the following steps: various parameter data of the cooking process are collected through the collection end, and the parameter data are transmitted to the cloud platform through the network to ensure real-time and stability. The processing end analyzes the stored parameter data through the AI ​​big model to analyze whether there is any abnormality in the intelligent cooking machine during the cooking process. When the intelligent cooking machine is analyzed to have an abnormality, it is determined that there is a deviation in the taste of the ingredients based on the analysis results. The management system sends a warning signal, and other intelligent cooking machines are replaced for cooking. The invention can determine whether there is a deviation in the taste of the dishes cooked this time based on the operating status of the intelligent cooking machine, so that timely warnings can be issued to ensure the quality and taste of the ingredients.

[0005] The role of applying AI big models to smart cooking machines in the existing technology is only for the processing end to analyze the stored parameter data through the AI ​​big model to analyze whether there is any abnormality in the smart cooking machine during the cooking process. When the smart cooking machine is analyzed to have an abnormality, it is determined based on the analysis results that there is a deviation in the taste of the ingredients, and other smart cooking machines need to be replaced to ensure the quality and taste of the ingredients. In fact, replacing other smart cooking machines for cooking may not necessarily ensure the quality and taste of the ingredients, because the other replaced smart cooking machines may also have abnormalities. In this way, users need to constantly replace smart cooking machines to ensure the quality and taste of the ingredients.

[0006] The present invention provides a cooking method and intelligent cooking device based on an AI big model to solve the mutual promotion and mutual restraint between multiple ingredients. The method uses a third-party AI big model to fine-tune a large amount of cooking data sets of mutual promotion and mutual restraint of ingredients. After the training is completed, an AI big model of mutual promotion and mutual restraint cooking with all relevant data of the cooking method is generated. The user inputs the ingredient information and cooking parameters by scanning the code, and the AI ​​big model of mutual promotion and mutual restraint cooking is called to determine whether multiple ingredients are mutually promoted or restrained, and remind the user whether to continue cooking the ingredients. Summary of the Invention

[0007] In order to solve the above-mentioned problems in the prior art, the present invention provides a cooking method based on an AI big model to solve the mutual promotion and mutual restraint between multiple ingredients. It is characterized by being applied to an intelligent cooking device, wherein the intelligent cooking device is provided with a code scanning and recognition device, a processor and a wireless communication module. The code scanning and recognition device and the wireless communication module are electrically connected to the processor. The code scanning and recognition device scans the identification codes on the packaging of different ingredients to identify the ingredient information and cooking parameters, and uploads the ingredient information to the AI ​​big model of the cloud platform for mutual promotion and mutual restraint judgment. The AI ​​big model includes constructing a mutual promotion and mutual restraint cooking AI big model and calling the mutual promotion and mutual restraint cooking AI big model. The specific process of cooking multiple ingredients is as follows:

[0008] In the first step, the intelligent cooking device uses the code scanning and recognition device to identify the identification code on the first ingredient packaging provided by the user, and identifies the first ingredient information and the first cooking parameters of the first ingredient. The intelligent cooking device transmits the first ingredient information and the first cooking parameters of the ingredient to the user mobile terminal and the cloud platform through the wireless communication module. The intelligent cooking device prompts the user to place the first ingredient in the corresponding operating station for cooking, and the user confirms the first cooking parameters through the user mobile terminal.

[0009] In the second step, after the intelligent cooking device receives the operation instruction confirmed by the user, the intelligent cooking device cooks the first ingredient according to the first cooking parameter.

[0010] In the third step, the intelligent cooking device uses the code scanning and recognition device to identify the identification code on the second ingredient package provided by the user, and identifies the second ingredient information and second cooking parameters of the second ingredient. The intelligent cooking device transmits the second ingredient information and the second cooking parameters to the user's mobile terminal and the cloud platform through the wireless communication module. The cloud platform pushes the first ingredient information and the second ingredient information to the mutual promotion and mutual restraint cooking AI big model. The mutual promotion and mutual restraint cooking AI big model compares the information to determine whether the first ingredient and the second ingredient are mutually promoting and restraining.

[0011] Step 4: When the AI ​​​​model for cooking with mutual promotion and mutual restraint compares and determines that the first ingredient and the second ingredient are mutually restraining, the AI ​​​​model for cooking with mutual promotion and mutual restraint will feedback this information to the user's mobile terminal and smart cooking device through the cloud platform, and prompt the user to cancel the cooking of the second ingredient;

[0012] Step 5: When the AI ​​cooking model determines that the first and second ingredients are mutually beneficial, the AI ​​cooking model feeds this information back to the user's mobile terminal and the smart cooking device via the cloud platform. The smart cooking device prompts the user to place the second ingredient at the corresponding operating station for cooking, and the user confirms the second cooking parameters through the user's mobile terminal.

[0013] Step 6: After the intelligent cooking device receives the operation instruction confirmed by the user, the intelligent cooking device cooks the second ingredient according to the second cooking parameter;

[0014] The construction of the AI ​​big model for cooking with ingredients that are mutually reinforcing and mutually restraining includes six steps: collecting cooking data on ingredients that are mutually reinforcing and mutually restraining, pre-processing the cooking data on ingredients that are mutually reinforcing and mutually restraining, selecting an AI big model that can be applied to cooking, training the AI ​​big model for cooking with ingredients that are mutually reinforcing and mutually restraining, verifying and testing the AI ​​big model for cooking with ingredients that are mutually reinforcing and mutually restraining, and deploying and maintaining the AI ​​big model for cooking with ingredients that are mutually reinforcing and mutually restraining on a cloud platform.

[0015] The calling of the mutual promotion and mutual restraint cooking AI big model includes assembling a query statement, the AI ​​big model performing an inference operation, and the AI ​​big model returning a result. The information on mutual promotion and mutual restraint is sent to the user's mobile terminal and the smart cooking device through the cloud platform after the inference operation of the mutual promotion and mutual restraint cooking AI big model is completed;

[0016] As an improvement of the present invention's cooking method for solving the mutual promotion and mutual restraint between multiple ingredients based on the AI ​​big model, the construction of the mutual promotion and mutual restraint cooking AI big model includes:

[0017] Step 1: Collect cooking data on ingredients that interact with each other: Collect all information on cooking methods for ingredients that interact with each other, presented through voice, video, text, images, or 3D models;

[0018] The second step is to pre-process the cooking data of ingredients that interact with each other: all the collected information on cooking methods of ingredients that interact with each other is processed to ensure the integrity and usability of the information. This includes converting information in different formats into text and editing the text information according to a specific format to facilitate the subsequent training of the AI ​​large model.

[0019] Step 3: Select AI models applicable to cooking: Select domestic and international third-party AI models, and measure them using accuracy, response speed, and diversity indicators;

[0020] Step 4: Train the AI ​​cooking model for mutual promotion and mutual restraint: After organizing the cooking dataset of mutual promotion and mutual restraint ingredients through the second step, fine-tune the cooking dataset with a third-party AI model. After the training is complete, the AI ​​cooking model for mutual promotion and mutual restraint with all the relevant data of cooking methods for mutual promotion and mutual restraint ingredients is generated;

[0021] Step 5: Verify and test the AI ​​cooking model based on mutual promotion and mutual restraint: Perform a specific task performance test on the AI ​​cooking model generated in step 4. If the performance fails, repeat steps 1, 2, 3, and 4, retraining until the performance passes. Generate the AI ​​cooking model based on mutual promotion and mutual restraint and store it on the cloud platform.

[0022] Step 6: Deploy and maintain the AI ​​cooking model: Deploy the newly generated AI cooking model to the cloud platform and continuously maintain and update it. Regularly update the data to ensure its timeliness and accuracy.

[0023] As an improvement to the cooking method of the present invention based on the AI ​​big model to solve the mutual promotion and mutual restraint between multiple ingredients, the third step selects an AI big model applicable to cooking. The selected AI big model is the Baichuan2-13B AI big model. The parameters of the AI ​​big model are as follows: hidden layer dimension: 5,120, number of layers: 40, number of attention heads: 40, vocabulary size: 64,000, total number of parameters: 13,264,901,120, training data (tokens): 1.4 trillion, position encoding: ALiBi, maximum length: 4,096;

[0024] As an improvement to the cooking method of the present invention based on the AI ​​large model to solve the mutual promotion and restraint of multiple ingredients, the training process of the fourth step of training the mutual promotion and restraint cooking AI large model is as follows: first, download the model weights of baichuan13b from huggingface, then download the belle dataset train_0.5M_CN to the local and put it in the dataset folder under the project directory, and finally run the sft_lora.py script. Then, quantize Baichuan LLM using Qlora's nf4 and double quantization methods, and finally, use Lora to fine-tune the instructions.

[0025] As an improvement of the present invention's cooking method for solving the mutual promotion and mutual restraint between multiple ingredients based on the AI ​​big model, the calling of the mutual promotion and mutual restraint cooking AI big model specifically includes the following steps:

[0026] The first step is to assemble query statements. Different ingredients are assembled into query statements that the AI ​​model can understand. The AI ​​model is required to determine whether different ingredients are incompatible and analyze the reasons.

[0027] The second step is for the AI ​​big model to perform inference operations: The query statement is passed to the AI ​​big model, which then performs inference operations. This involves the following steps:

[0028] 1) Understanding the input: Distributed semantic parsing first receives a text sequence and converts it into word vectors. This process is based on the distributed semantics assumption that the meaning of a word is determined by its context.

[0029] 2) Parameter association: context-focus chaining, inputting these word vectors into the Transformer Encoder to generate context representation;

[0030] 3) Generate Answers: Generative probabilistic modeling: The model initializes the Transformer's decoder and feeds the encoder output and the current output sequence into the decoder. The decoder generates a probability distribution for the next word and selects the word with the highest probability or another set probability distribution as the output. This word is then appended to the output sequence.

[0031] 4) Select the most appropriate answer: Dynamic word string evolution, repeat the above steps, adding new words to the output sequence each time, until a complete output sequence is generated;

[0032] Step 3: The AI ​​model returns the result: After the inference operation of the AI ​​cooking model is completed, it returns the result of whether there is incompatibility and the reason, including providing the user with content in text, picture, audio, video or 3D model format;

[0033] As an improvement to the cooking method of the present invention based on the AI ​​big model to solve the mutual promotion and mutual restraint between multiple ingredients, the AI ​​big model for mutual promotion and mutual restraint cooking determines that the interval between different ingredients is no more than 6 hours;

[0034] As an improvement to the cooking method of the present invention that solves the mutual promotion and mutual restraint between multiple ingredients based on the AI ​​big model, when the mutual promotion and mutual restraint cooking AI big model compares and determines that different ingredients are mutually restrained, the mutual promotion and mutual restraint cooking AI big model feeds back the information to the user's mobile terminal through the cloud platform and pushes the information of the mutually promoting ingredients and cooking parameters;

[0035] In order to solve the above-mentioned problems of the prior art, the present invention provides an intelligent cooking device that implements a cooking method based on an AI large model to solve the mutual promotion and restraint between multiple ingredients. The device is characterized in that it is provided with a code scanning and recognition device, a processor and a wireless communication module. The code scanning and recognition device is used to scan the identification codes on the packaging of different ingredients that the user needs to cook to obtain different ingredient information and different cooking parameters. The processor is connected to the cloud platform and the user mobile terminal through the wireless communication module. The processor is used to execute the user in claim 1 to confirm the first cooking parameter and the second cooking parameter through the user mobile terminal operation for cooking.

[0036] As an improvement to the intelligent cooking device of the present invention, the intelligent cooking device is provided with operating stations for stir-frying, stir-frying, deep-frying, cooking, frying, sticking, burning, braising, stewing, steaming, blanching, boiling, stewing, sautéing, mixing, pickling, roasting, braising, freezing, pulling out silk, honey sauce, smoking, rolling, sliding or baking. The operating stations for stir-frying, stir-frying, deep-frying, cooking, frying, sticking, burning, braising, stewing, steaming, blanching, boiling, stewing, sautéing, mixing, pickling, roasting, braising, freezing, pulling out silk, honey sauce, smoking, rolling, sliding or baking are provided with corresponding detection modules, and the detection module is used to detect whether the cooking operation performed by the user on the intelligent cooking device meets the requirements of the cooking method based on the AI ​​large model to solve the mutual promotion and restraint between multiple ingredients;

[0037] As an improvement of the intelligent cooking device of the present invention, the intelligent cooking device is provided with a human-computer interaction system, which is used for information exchange between the intelligent cooking device and the user, including the user operating the user mobile terminal to confirm cooking parameters and start cooking operation instructions.

[0038] The present invention provides a cooking method and intelligent cooking device based on an AI big model to solve the mutual promotion and mutual restraint between multiple ingredients, and its beneficial effects are as follows: the present invention provides a cooking method and intelligent cooking device based on an AI big model to solve the mutual promotion and mutual restraint between multiple ingredients, collects all information on cooking methods of mutual promotion and mutual restraint between ingredients from people of all countries and regions, all races, and all ages around the world presented through voice, video, text, pictures or 3D models, and uses a third-party AI big model for fine-tuning training. After the training is completed, a mutual promotion and mutual restraint cooking AI big model with all relevant data of cooking methods of massive mutual promotion and mutual restraint between ingredients is generated. The user inputs the ingredient information and cooking parameters by scanning the code, and the intelligent cooking device executes the user's call to the mutual promotion and mutual restraint cooking AI big model. By calling the mutual promotion and mutual restraint cooking AI big model, it determines whether multiple ingredients are mutually promoting and restraining each other, reminds the user whether to continue cooking the ingredients, and cooks food that meets the safety needs of different users. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] Figure 1 is a flow chart of the AI ​​big model for cooking based on the present invention to solve the mutual promotion and mutual restraint between multiple ingredients and a preferred embodiment of its intelligent cooking device.

[0040] Figure 2 is a flow chart of calling the AI ​​big model for cooking based on the AI ​​big model to solve the mutual promotion and mutual restraint between multiple ingredients, and a preferred embodiment of the intelligent cooking device of the present invention.

[0041] FIG3 is a workflow diagram of a preferred embodiment of a cooking method and intelligent cooking device of the present invention for solving the mutual promotion and restraint between multiple ingredients based on an AI large model.

[0042] FIG4 is a workflow diagram of one of other embodiments of the cooking method and intelligent cooking device of the present invention for solving the mutual promotion and restraint between multiple ingredients based on the AI ​​big model.

[0043] FIG5 is a workflow diagram of another embodiment of the cooking method and intelligent cooking device of the present invention for solving the mutual promotion and restraint between multiple ingredients based on the AI ​​big model.

[0044] FIG6 is a workflow diagram of another embodiment of the cooking method and intelligent cooking device for solving the mutual promotion and restraint between multiple ingredients based on the AI ​​big model of the present invention.

[0045] FIG7 is a workflow diagram of another fourth embodiment of the cooking method and intelligent cooking device for solving the mutual promotion and restraint between multiple ingredients based on the AI ​​big model of the present invention.

[0046] FIG8 is a flowchart of the fifth embodiment of the cooking method and intelligent cooking device for solving the mutual promotion and restraint between multiple ingredients based on the AI ​​big model of the present invention. DETAILED DESCRIPTION

[0047] The present invention is further described below in conjunction with Figures 1-8 and specific implementation methods and other embodiments. It should be noted that, under the premise of no conflict, the various technical features described below can be arbitrarily combined to form new embodiments.

[0048] In a preferred embodiment, referring to Figures 1-3, the present invention provides a cooking method based on an AI large model to solve the mutual promotion and mutual restraint between multiple ingredients, characterized in that it is applied to an intelligent cooking device, the intelligent cooking device is provided with a code scanning and recognition device 6, a processor 7 and a wireless communication module 8, and the code scanning and recognition device 6 and the wireless communication module 8 are electrically connected to the processor 7;

[0049] In a preferred embodiment, the cooking parameters include operating stations, cooking steps, cooking time, cooking temperature, cooking power, or cooking operation instructions requiring user cooperation;

[0050] In a preferred embodiment, the code scanning and recognition device 6 scans the identification codes on the packaging of different ingredients to identify the ingredient information and cooking parameters, and uploads the ingredient information to the AI ​​big model of the cloud platform for determination of mutual promotion and mutual restraint. The AI ​​big model includes constructing the mutual promotion and mutual restraint cooking AI big model 5 and calling the mutual promotion and mutual restraint cooking AI big model 4. The specific process of cooking multiple ingredients is as follows:

[0051] In the first step, the intelligent cooking device uses the code scanning and recognition device 6 to identify the identification code on the first ingredient packaging provided by the user, and identifies the first ingredient information and the first cooking parameters of the first ingredient. The intelligent cooking device transmits the first ingredient information and the first cooking parameters of the ingredient to the user mobile terminal 2 and the cloud platform 3 through the wireless communication module 8. The intelligent cooking device prompts the user to place the first ingredient in the corresponding operating station for cooking, and the user confirms the first cooking parameters through the user mobile terminal 2.

[0052] In the second step, after the intelligent cooking device receives the operation instruction confirmed by the user, the intelligent cooking device cooks the first ingredient according to the first cooking parameter.

[0053] In the third step, the intelligent cooking device uses the code scanning and recognition device 6 to identify the identification code on the second ingredient package provided by the user, and identifies the second ingredient information and second cooking parameters of the second ingredient. The intelligent cooking device transmits the second ingredient information and the second cooking parameters to the user mobile terminal 2 and the cloud platform 3 through the wireless communication module 8. The cloud platform 3 pushes the first ingredient information and the second ingredient information to the mutual promotion and mutual restraint cooking AI big model. The mutual promotion and mutual restraint cooking AI big model compares the information to determine whether the first ingredient and the second ingredient are mutually promoting and restraining.

[0054] Step 4: When the AI ​​​​model for cooking with mutual promotion and mutual restraint compares and determines that the first ingredient and the second ingredient are mutually restraining, the AI ​​​​model for cooking with mutual promotion and mutual restraint feeds back the information to the user's mobile terminal 2 and the intelligent cooking device through the cloud platform 3, and prompts the user to cancel the cooking of the second ingredient;

[0055] Step 5: When the AI ​​large-scale cooking model determines that the first ingredient and the second ingredient are mutually beneficial, the AI ​​large-scale cooking model feeds back the information to the user mobile terminal 2 and the intelligent cooking device via the cloud platform 3. The intelligent cooking device prompts the user to place the second ingredient at the corresponding operation station for cooking. The user confirms the second cooking parameters through the user mobile terminal 2.

[0056] Step 6: After the intelligent cooking device receives the operation instruction confirmed by the user, the intelligent cooking device cooks the second ingredient according to the second cooking parameter;

[0057] With reference to FIG. 2 , in a preferred embodiment, the present invention solves the cooking method of the mutual promotion and mutual restraint between multiple ingredients based on the AI ​​big model, and the process of constructing the mutual promotion and mutual restraint cooking AI big model 5 is as follows:

[0058] 201. Collect cooking data on ingredients that are mutually beneficial or mutually destructive: Collect all information on cooking methods for ingredients that are mutually beneficial or mutually destructive, presented through voice, video, text, images, or 3D models;

[0059] 202. Preprocessing of cooking data on ingredients that interact with each other: Process all collected information on cooking methods for ingredients that interact with each other to ensure its integrity and usability. This includes converting information in different formats into text and editing the text according to a specific format to facilitate subsequent training of the AI ​​model.

[0060] 203. Select AI big models that can be applied to cooking: Select domestic and foreign third-party AI big models and measure them using accuracy, response speed, and diversity indicators;

[0061] 204. Training a large AI cooking model for mutual promotion and mutual restraint: After the second step, organize the cooking dataset of mutual promotion and mutual restraint ingredients. Then, fine-tune the cooking dataset of mutual promotion and mutual restraint ingredients using a third-party AI large model. After the training is completed, a large AI cooking model for mutual promotion and mutual restraint with all relevant data on cooking methods for mutual promotion and mutual restraint ingredients is generated.

[0062] 205. Verify and test the AI ​​cooking model based on mutual promotion and mutual restraint: Perform a specific task performance test on the AI ​​cooking model generated in step 4. If the performance fails, repeat steps 1, 2, 3, and 4, retraining until the performance passes. Generate the AI ​​cooking model based on mutual promotion and mutual restraint and store it on the cloud platform.

[0063] 206. Deploy and maintain the AI ​​cooking model for mutual growth and mutual restraint: Deploy the newly generated AI cooking model to the cloud platform and continuously maintain and update it. Regularly update data to ensure timeliness and accuracy.

[0064] In this embodiment, in the process 203 of constructing the mutual promotion and mutual restraint cooking AI big model 5 for solving the mutual promotion and mutual restraint cooking method of the present invention based on the AI ​​big model, the AI ​​big model applied to cooking is specifically selected as the Baichuan2-13B AI big model. The parameters of the AI ​​big model are as follows: hidden layer dimension: 5,120, number of layers: 40, number of attention heads: 40, vocabulary size: 64,000, total number of parameters: 13,264,901,120, training data (tokens): 1.4 trillion, position encoding: ALiBi, maximum length: 4,096;

[0065] In this embodiment, the present invention solves the cooking method of the mutual promotion and mutual restraint between multiple ingredients based on the AI ​​big model. The training process of the mutual promotion and mutual restraint cooking AI big model 5 is as follows: first, download the model weights of baichuan13b from huggingface, then download the belle dataset train_0.5M_CN to the local and put it in the dataset folder under the project directory, and finally run the sft_lora.py script. Then, quantize Baichuan LLM using qlora's nf4 and double quantization methods, and finally, use lora to fine-tune the instructions.

[0066] The ingredients include pre-prepared dishes and clean vegetables, the identification codes on the food packaging include QR codes and bar codes, and the cooking parameters include relevant operating stations, cooking steps, cooking time, cooking temperature, cooking power or cooking operation instructions that require user cooperation.

[0067] Referring to FIG. 3 , in this embodiment, the present invention solves the cooking method of the mutual promotion and mutual restraint between multiple ingredients based on the AI ​​big model, and the calling of the mutual promotion and mutual restraint cooking AI big model 4 specifically includes the following steps:

[0068] 301. Assemble query statements. Assemble different ingredients into query statements that the AI ​​model can understand. The AI ​​model is required to determine whether different ingredients are incompatible and analyze the reasons.

[0069] 302. AI big model performs reasoning operations: The query statement is passed to the AI ​​big model, which performs reasoning operations. This includes the following four steps:

[0070] 302-1. Understanding Input: Distributed semantic parsing first receives a text sequence and converts it into a word vector. This process is based on the distributed semantics assumption that the meaning of a word is determined by its use in context.

[0071] 302-2. Parameter association: context-focus chaining, inputting these word vectors into the Transformer Encoder to generate context representation;

[0072] 302-3. Generate answers: Generative probabilistic modeling. The model initializes the decoder part of the Transformer and inputs the encoder output and the current output sequence into the decoder. The decoder generates a probability distribution for the next word and selects the word with the highest probability or other set probability distribution as the output. This word will be added to the output sequence.

[0073] 302-4. Choose the most appropriate answer: Dynamic word string evolution, repeating the above steps, adding new words to the output sequence each time, until a complete output sequence is generated;

[0074] 303. AI big model return result: After the inference operation of the mutual promotion and mutual restraint cooking AI big model is completed, the result of whether there is mutual restraint and the reason are returned, including the content provided to the user in text, picture, audio, video or 3D model format;

[0075] In a preferred embodiment, the AI ​​large model for cooking that mutually promotes and restrains each other determines that the interval between different ingredients is 6 hours;

[0076] In a preferred embodiment, when the mutual promotion and mutual restraint cooking AI big model compares and determines that different ingredients are incompatible, the mutual promotion and mutual restraint cooking AI big model will feed back the information to the user's mobile terminal 2 through the cloud platform 3. At the same time, it can also collect all the ingredient information currently available to the user, and analyze and screen these ingredient information according to the Chinese medicine mutual promotion and mutual restraint recipes, and then push the screened out mutually promoting ingredient information to the user.

[0077] In a preferred embodiment, referring to FIG3 , the present invention provides an intelligent cooking device that implements a cooking method based on an AI large model to solve the mutual promotion and mutual restraint between multiple ingredients, characterized in that it is provided with a code scanning and recognition device 6, a processor 7, and a wireless communication module 8. The code scanning and recognition device 6 is used to scan identification codes on different ingredient packages to identify ingredient information and cooking parameters. The processor 7 is connected to the cloud platform 3 and the user mobile terminal 2 via the wireless communication module 8 to transmit information to each other. The processor 7 is used to execute the cooking parameters according to claim 1 to control the relevant operating stations to cook the ingredients and issue cooking operation instructions requiring user cooperation. The AI ​​large model of mutual promotion and mutual restraint cooking is deployed on the cloud platform 3, and the transmission of information from the AI ​​large model of mutual promotion and mutual restraint cooking is completed through the cloud platform 3. The processor 7 can set relevant working parameters for the operating stations of frying 10, baking 12, boiling 13, air frying 9, steaming 11, and stir-frying 14 set in the intelligent cooking device, and control the execution of relevant instructions for each operating station, such as standby, start, stop, cleaning, and other working instructions. For example, when the user wants to cook "soft-shelled turtle", the barcode or QR code on the "soft-shelled turtle" package is scanned by the code scanning and recognition device 6. After the code scanning and recognition device 6 recognizes the "soft-shelled turtle" ingredient information and the "soft-shelled turtle" cooking parameters, it will issue a sound prompt to complete the code scanning. The code scanning and recognition device 6 sends the "soft-shelled turtle" ingredient information and cooking parameters to the user mobile terminal 2 and the cloud platform 3 through the processor 7 and the wireless communication module 8. The cloud platform 3 pushes the "soft-shelled turtle" ingredient information and cooking parameters to the mutual promotion and mutual restraint cooking AI large model. The model records the ingredient information and cooking parameters of "soft-shelled turtle". The user confirms the cooking parameters through the user mobile terminal 2. The user can customize the cooking parameters according to his or her own taste preferences, for example: the saltiness of the dish, such as strong, medium, and light; ingredients, such as chili sauce, soy sauce, and oyster sauce; side dishes, such as onions, garlic, and ginger; the heat of the dish, such as high, medium, and low; seasonings of the dish, such as MSG and chicken essence; cooking methods, such as steaming, braising, and stewing; users can also directly select according to the push menu, such as "steamed soft-shelled turtle", "braised soft-shelled turtle with chicken", "stewed soft-shelled turtle with meatballs", etc.For example, when the user confirms that the cooking parameter is "steamed soft-shelled turtle", the processor 7 receives the operation instruction confirmed by the user through the wireless communication module 8, and the processor 7 sets the parameters of the steaming operation station 11 according to the cooking parameters of "steamed soft-shelled turtle": add 1.7L of water; 2000W power continuously; work for another 30 minutes after the water temperature reaches 100 degrees. When the processor 7 detects that the water temperature of the steaming operation station 11 has reached 100 degrees, that is, steam is generated, it sends a message to the user's mobile terminal 2 through the wireless communication module 8, reminding the user to remove the package and put the ingredients on the corresponding operation station. At the same time, the processor 7 detects whether the user has performed the operation as required through the detection module 15. After 30 minutes, the processor 7 sends a message to the user's mobile terminal 2 through the wireless communication module 8, reminding the user to take out the cooked "steamed turtle". At the same time, the processor 7 detects whether the user has performed the operation as required through the detection module 15. When the user takes out the "steamed turtle", the processor 7 controls the steaming operation station 11 to perform self-cleaning and then enter the standby state. After the user finishes cooking the "steamed turtle", he plans to cook the "duck meat" (or he can cook the "duck meat" simultaneously when cooking the "steamed turtle"). The barcode or QR code on the "duck meat" package is scanned by the code recognition device 6, and the code recognition device 6 recognizes the "duck meat" ingredient information. After the code is scanned, a sound prompt is given to complete the code scanning. The code scanning and recognition device 6 sends the "duck meat" ingredient information and cooking parameters to the user mobile terminal 2 and the cloud platform 3 through the processor 7 and the wireless communication module 8. The cloud platform 3 pushes the "duck meat" ingredient information and cooking parameters to the mutual generation and mutual restraint cooking AI big model. The mutual generation and mutual restraint cooking AI big model analyzes the mutual generation and mutual restraint relationship between the "duck meat" ingredient information and the previously collected "soft-shelled turtle" ingredient information. After the mutual generation and mutual restraint cooking AI big model compares and determines that the "duck meat" and "soft-shelled turtle" ingredients are mutually restrained, the comparison and judgment results and the reasons for the mutual restraint are sent to the user mobile terminal 2 and the intelligent cooking device through the cloud platform 3. It is recommended that the user cancel the cooking of "duck meat". At the same time, the AI ​​big model of mutual generation and mutual restraint cooking pushes the information of ingredients and a list of dishes that are compatible with "soft-shelled turtle" to the customer based on the information of the cooked "soft-shelled turtle". When the user confirms the cancellation of the cooking of "duck meat" through the user mobile terminal 2, the user can also enter customized cooking requirements on the user mobile terminal 2, such as Cantonese cuisine, sweet, light, and steamed. The AI ​​big model of mutual generation and mutual restraint cooking will analyze and calculate according to the user's needs, and then push the relevant information of ingredients and a list of dishes that meet the user's needs and are compatible with "soft-shelled turtle" to the user, so that the user's diet meets the dietary requirements of Chinese medicine mutual generation and mutual restraint and satisfies his own taste preferences. In the above process, when the AI ​​big model of mutual generation and mutual restraint cooking determines that the current ingredient information is incompatible with the previously cooked ingredient information, if the comparison time between the ingredient information and the previously cooked ingredient information does not exceed 6 hours, it is recommended that the user do not cook the ingredient information currently input.

[0078] In this embodiment, the frying 10, baking 12, boiling 13, air frying 9, steaming 11 and stir-frying 14 operating stations of the intelligent cooking device of the present invention are provided with a common detection module 15, and the detection module 15 includes detection devices such as cameras, infrared detection, radar detection, magnetic detection, and weight detection, which are used to detect whether the cooking operation performed by the user on the intelligent cooking device meets the first cooking parameter and second cooking parameter requirements of the first ingredient or the second ingredient scanned and identified by the intelligent cooking device. For example, the first cooking parameter of the first ingredient scanned and identified by the intelligent cooking device is to place the first ingredient on the frying operation station, and the intelligent cooking device needs to When the user is asked to put the ingredients to be fried on the frying operation station, but the user does not put them or puts them in the wrong place, the detection module detects it through the camera and feeds this information back to the processor 7 of the intelligent cooking device. The processor 7 controls the operation station to pause the next operation and sends information to the user 17 for correction. When the user corrects it, the detection module detects it through the camera and feeds this information back to the processor 7. The processor 7 controls the operation station to perform the next operation. The above is just an example. In addition, infrared detection, radar detection, magnetic detection, and weight detection can be used alone or in combination for detection.

[0079] In another embodiment 1, referring to FIG. 4 , the operating stations of the intelligent cooking device for stir-frying 14 , boiling 13 , baking 12 , frying 10 , and air frying 9 of the present invention are provided with a common detection module 15 , and the rest are the same as those in the preferred embodiment of the present invention;

[0080] In another embodiment 2, referring to FIG. 5 , the cooking 13 , baking 12 , steaming 11 , and frying 10 operating stations of the intelligent cooking device of the present invention are provided with a common detection module 15 , and the rest is the same as the preferred embodiment of the present invention;

[0081] In another third embodiment, referring to FIG6 , the stir-frying 14 and air frying 9 operating stations of the intelligent cooking device of the present invention are provided with a common detection module 15 , and the rest are the same as those of the preferred embodiment of the present invention;

[0082] In another fourth embodiment, referring to FIG. 7 , the stir-frying operation station 14 of the intelligent cooking device of the present invention is provided with a detection module 15 , and the rest is the same as the preferred embodiment of the present invention;

[0083] In another embodiment 5, referring to FIG8 , the intelligent cooking device of the present invention is not provided with the user mobile terminal 2 , and the rest is the same as the preferred embodiment of the present invention;

[0084] In this embodiment, the intelligent cooking device of the present invention is provided with a human-computer interaction system 16, which includes a touch screen, a sound input and output unit, an image input unit and a camera device. The human-computer interaction system 16 is electrically connected to the processor 7 for information interaction between the intelligent cooking device and the user 17. The user 17 can interact with the intelligent cooking device through the human-computer interaction system 16 in the form of voice, video, text, pictures or 3D models. The human-computer interaction system 15 can scan the identification codes on the packaging of different ingredients through the camera device to identify the ingredient information and cooking parameters, and send the ingredient information and cooking parameters to the processor 7. The processor 7 sends the ingredient information and cooking parameters to the cloud platform 4 via the wireless communication module 8. The ingredient information and cooking parameters are received by the cloud platform 4 and transmitted to the mutual generation and mutual restraint cooking AI large model of the cloud platform. The mutual generation and mutual restraint cooking AI large model will compare and determine the mutual generation and mutual restraint of the ingredient information with the information of the previously cooked ingredients, and then transmit the information to the cloud platform 4 via the wireless communication module 8. The communication module 8 feeds back the comparison judgment result and the reason to the processor 7, and the processor 7 feeds back the comparison judgment result and the reason to the user 17 through the human-computer interaction system 16 in the form of voice, video, text, picture or 3D model. The user 17 can confirm whether to execute the cooking instruction on the touch screen of the human-computer interaction system 16 or through sound. At the same time, the user 17 can set the cooking parameters, customize the cooking requirements and check the relevant cooking ingredients and dish information pushed by the mutual generation and mutual restraint cooking AI large model through the human-computer interaction system 16. During the cooking process, the processor 7 can send the cooking operation instructions that require the user's cooperation to the user 17 through the human-computer interaction system 16 in the form of voice, video, text, picture or 3D model. When the processor 7 detects through the detection module 15 that the cooking operation cooperated by the user does not meet the requirements, it will send a message to the user 17 through the human-computer interaction system 16 to help it correct it. When cooking is completed, the processor 7 sends a message to the user 17 through the human-computer interaction system 16 to let it take out the dish, and then the processor 7 controls the operating station to perform self-cleaning and enter the standby state.

[0085] In other embodiments, the smart cooking device is one or a combination of a cooker, an air fryer, an induction cooker, a microwave oven, an oven, a steam oven, an electric rice cooker, an electric pressure cooker, an electric stew pot, an integrated stove or a frying pan, and one or more smart cooking devices include one or more cooking functions of stir-frying, air frying, baking, frying, braising, stewing, steaming, boiling or baking to cook ingredients.

[0086] In other embodiments, the smart cooking device prompts the user to perform cooking operations at different operating stations on the smart cooking device when cooking different ingredients. For example, the stir-frying operation station is different from the steaming, air frying, and frying operation stations in the smart cooking device, and the user needs to be prompted to cook at the corresponding operation station; the cooking work steps include the cooking steps that the smart cooking device prompts the user to perform when cooking different ingredients; the cooking parameters include the cooking time, cooking temperature, and cooking power of the ingredients; the cooking operation instructions that require user cooperation include confirming the cooking parameters or confirming that the operation station and cooking work steps have been completed on the user mobile terminal 2.

[0087] In other embodiments, the smart cooking device is an integrated body of multiple cooking functions including stir-frying, air frying, baking, frying, braising, stewing, steaming, boiling or baking. For example, the smart cooking device is a cooking utensil that integrates functions such as air frying, baking, frying, and steaming, or a cooking utensil that integrates functions such as stir-frying, air frying, braising, stewing, and boiling, etc.

[0088] In other embodiments, the intelligent cooking device is provided with multiple cooking functions including one or more cooking functions of stir-frying, sautéing, deep-frying, cooking, frying, sticking, roasting, braising, stewing, steaming, blanching, boiling, stewing, sautéing, mixing, marinating, roasting, braising, freezing, candied food, honey sauce, smoking, rolling, sliding or baking. For example, the intelligent cooking device is a cooking utensil that integrates functions such as honey sauce, roasting, frying and steaming, or a cooking utensil that integrates functions such as stir-frying, air frying, braising, stewing and boiling, etc.

[0089] The present invention uses an AI large model to solve the problem of mutual promotion and mutual restraint between multiple ingredients. The specific implementation steps of the cooking method and its intelligent cooking device for cooking are as follows:

[0090] The present invention solves the cooking methods of multiple ingredients based on the AI ​​big model. The specific implementation process of the process 202 of constructing the mutual promotion and mutual restraint cooking AI big model for preprocessing the cooking data of the ingredients that promote and restrain each other is as follows: all the collected information on the cooking methods of the ingredients that promote and restrain each other is processed to ensure the integrity and availability of the information, including converting information in different formats into text in a unified manner, and editing the text information according to a certain format to facilitate the subsequent training of the AI ​​big model.

[0091] The data format is as follows:

[0092] instruction: Task instruction, cannot be empty.

[0093] input: Task input, can be empty. If not empty, when processing training data within the project, instruction and input will be concatenated together as the input of the task.

[0094] output: task output, cannot be empty

[0095] The data example is as follows:

[0096] {

[0097] "instruction": "Persimmons and crabs are incompatible",

[0098] "input": "",

[0099] According to traditional Chinese medicine, cooking persimmons and crabs together may cause incompatibility, so it is generally not recommended. Both persimmons and crabs are cold foods, and eating them together may cause stomach discomfort or digestive problems. Therefore, from a TCM perspective, cooking persimmons and crabs together is not recommended.

[0100] }

[0101] The cooking method based on the built-in AI big model of the present invention calls the built-in mutual promotion and mutual restraint cooking AI big model. The specific implementation process of step 303 of the built-in AI big model returning the result is as follows: after the mutual promotion and mutual restraint cooking AI big model reasoning operation is completed, it returns whether there is mutual restraint and the reason, including providing the user with content in text, picture, audio, video or 3D model format, and returns the Jason format content as follows:

[0102] {

[0103] "isOk": 0, / / 0 means no conflict, 1 means conflict,

[0104] “reasonText”:text / / The text content of the specific reason for the conflict,

[0105] "reasonPic":text / / Specific URL of the image of the reason for the conflict,

[0106] “reasonAudio”: audio_url / / The specific audio URL of the conflicting reason,

[0107] “reasonVideo”: video_url / / The video URL of the specific reason for the conflict,

[0108] “reason3D”:3D_url / / Specific 3D model URL of the reason for the conflict

[0109] }

[0110] The present invention uses an AI-based large-scale model to solve the problem of mutual promotion and mutual restraint between multiple ingredients. The cooking method and its intelligent cooking device are used to cook ingredient A, persimmon, and ingredient B, crab. The specific operation examples are as follows:

[0111] 1. Ingredient A: Persimmon and ingredient B: Crab were passed to the AI ​​model.

[0112] 2. Call the AI ​​big model through the Prompt query statement, and the AI ​​big model performs inference operations.

[0113] 3. After the AI ​​model performs inference operations, it returns the following results:

[0114] {

[0115] “isOk”: 1, / / 0 means no conflict, 1 means conflict

[0116] "reasonText": "Both persimmons and crabs are cold foods. Eating them together may cause stomach discomfort or digestive problems. Therefore, from the perspective of Traditional Chinese Medicine, it is not recommended to cook persimmons and crabs together." / / Specific text content of the reason for the incompatibility

[0117] "reasonPic": "None" / / None

[0118] "reasonAudio": "None" / / None

[0119] “reasonVideo”: “https: / / www.ixigua.com / 7289152022341747234?logTag=43fb2a078d33289b226b” / / Video URL of the specific reason for the conflict,

[0120] "reason3D": "None" / / None

[0121] }

[0122] The present invention provides a cooking method and intelligent cooking device based on an AI big model to solve the mutual promotion and mutual restraint between multiple ingredients. The beneficial effects are as follows: the present invention provides a cooking method and intelligent cooking device based on an AI big model to solve the mutual promotion and mutual restraint between multiple ingredients. The method collects all information on cooking methods of mutual promotion and mutual restraint between ingredients from people of all countries and regions, all races, and all ages around the world presented through voice, video, text, pictures or 3D models, and uses a third-party AI big model for fine-tuning training. After the training is completed, a mutual promotion and mutual restraint cooking AI big model with all relevant data of cooking methods of massive mutual promotion and mutual restraint between ingredients is generated. The user inputs the ingredient information and cooking parameters by scanning the code, and the intelligent cooking device executes and calls the mutual promotion and mutual restraint cooking AI big model to determine whether multiple ingredients are mutually promoting and restraining each other, and reminds the user whether to continue cooking the ingredients, so as to cook food that meets the safety needs of different users.

[0123] The present invention has been described in detail above. The above description is only a preferred embodiment of the present invention and should not limit the scope of implementation of the present invention. That is, all equivalent changes and modifications made within the scope of this application should still fall within the scope of the present invention.

Claims

1. A cooking method based on an AI big model to solve the mutual promotion and mutual restraint between multiple ingredients, characterized in that: Applied to an intelligent cooking device, the intelligent cooking device is provided with a code scanning and recognition device, a processor and a wireless communication module, the code scanning and recognition device, the wireless communication module and the processor are electrically connected, the code scanning and recognition device scans the identification codes on the packaging of different ingredients to identify the ingredient information and cooking parameters, and uploads the ingredient information and cooking parameters to the AI ​​big model of the cloud platform for determination of mutual promotion and mutual restraint, the AI ​​big model includes constructing a mutual promotion and mutual restraint cooking AI big model and calling a mutual promotion and mutual restraint cooking AI big model, the specific process of cooking multiple ingredients is as follows: In the first step, the intelligent cooking device recognizes the identification code on the first ingredient package provided by the user through the code scanning and recognition device, recognizes the first ingredient information and the first cooking parameter of the first ingredient, and transmits the first ingredient information and the first cooking parameter of the ingredient to the user mobile terminal and the cloud platform through the wireless communication module, and the intelligent cooking device prompts the user to place the first ingredient at the corresponding operation station for cooking, and the user confirms the first cooking parameter through the user mobile terminal operation; Step 2: After the intelligent cooking device receives the operation instruction confirmed by the user, the intelligent cooking device cooks the first food according to the first cooking parameter; Step 3: The intelligent cooking device identifies the identification code on the second ingredient package provided by the user through the code scanning and identification device, identifies the second ingredient information and the second cooking parameter of the second ingredient, and transmits the second ingredient information and the second cooking parameter to the user mobile terminal and the cloud platform through the wireless communication module. The cloud platform pushes the first ingredient information and the second ingredient information to the mutual promotion and mutual restraint cooking AI big model, and the mutual promotion and mutual restraint cooking AI big model compares and determines whether the first ingredient and the second ingredient are mutually promotion and mutual restraint information; Step 4: When the mutual promotion and mutual restraint cooking AI big model determines that the first ingredient and the second ingredient are mutually restrained, the mutual promotion and mutual restraint cooking AI big model feeds back the information to the user's mobile terminal and smart cooking device through the cloud platform, and prompts the user to cancel the cooking of the second ingredient; Step 5: When the mutual promotion and mutual restraint cooking AI big model determines that the first ingredient and the second ingredient are mutually promoting, the mutual promotion and mutual restraint cooking AI big model feeds back the information to the user mobile terminal and the intelligent cooking device via the cloud platform. The intelligent cooking device prompts the user to place the second ingredient at the corresponding operating station for cooking, and the user confirms the second cooking parameter through the user mobile terminal operation; Step 6: After the intelligent cooking device receives the operation instruction confirmed by the user, the intelligent cooking device cooks the second ingredient according to the second cooking parameter; The construction of the mutual growth and mutual restraint cooking AI big model includes six steps: collecting cooking data of mutual growth and mutual restraint ingredients, preprocessing cooking data of mutual growth and mutual restraint ingredients, selecting an AI big model that can be applied to cooking, training the mutual growth and mutual restraint cooking AI big model, verifying and testing the mutual growth and mutual restraint cooking AI big model, and deploying and maintaining the mutual growth and mutual restraint cooking AI big model on the cloud platform; The calling of the mutual promotion and mutual restraint cooking AI big model includes assembling query statements, the AI ​​big model performing reasoning operations and the AI ​​big model returning results. The information on mutual promotion and mutual restraint is sent to the user's mobile terminal and the intelligent cooking device through the cloud platform after the reasoning operation of the mutual promotion and mutual restraint cooking AI big model is completed.

2. The cooking method for solving the mutual promotion and mutual restraint between multiple ingredients based on the AI ​​big model according to claim 1 is characterized by: The construction of the mutual promotion and mutual restraint cooking AI model includes: Step 1: Collect cooking data of ingredients that are mutually reinforcing or mutually restraining: Collect all information about cooking methods of ingredients that are mutually reinforcing or mutually restraining, presented through voice, video, text, pictures or 3D models; Step 2: Preprocessing the cooking data of ingredients that are mutually reinforcing and mutually restraining: Process all the collected information on cooking methods of ingredients that are mutually reinforcing and mutually restraining to ensure the integrity and availability of the information, including converting information in different formats into text and editing the text information in a certain format to facilitate the subsequent training of the AI ​​large model; Step 3: Select AI big models that can be applied to cooking: Select domestic and foreign third-party AI big models and measure them by accuracy, response speed, and diversity indicators; Step 4: Train the AI ​​big model for cooking with mutually reinforcing and mutually restraining ingredients: After the second step, the cooking data set of mutually reinforcing and mutually restraining ingredients is sorted out, and then the cooking data set of mutually reinforcing and mutually restraining ingredients is fine-tuned using a third-party AI big model. After the training is completed, an AI big model for cooking with mutually reinforcing and mutually restraining ingredients with all relevant data on cooking methods is generated; Step 5: Verify and test the mutual promotion and mutual restraint cooking AI big model: Perform effect detection and evaluation of specific tasks on the mutual promotion and mutual restraint cooking AI big model generated in step 4. If the evaluation effect fails, continue to repeat the steps of step 1, step 2, step 3, and step 4, retrain until the effect evaluation passes, generate the mutual promotion and mutual restraint cooking AI big model and store it on the cloud platform; Step 6: Deploy and maintain the AI ​​big model of mutual promotion and mutual restraint cooking: Deploy the newly generated AI big model of mutual promotion and mutual restraint cooking to the cloud platform, and continuously maintain and update it. Update the data regularly to ensure the timeliness and accuracy of the data.

3. The cooking method for solving the mutual promotion and mutual restraint between multiple ingredients based on the AI ​​big model according to claim 2 is characterized by: The third step selects an AI big model that can be applied to cooking. The selected AI big model is Baichuan2-13B. The parameters of the AI ​​big model are as follows: hidden layer dimension: 5,120, number of layers: 40, number of attention heads: 40, vocabulary size: 64,000, total number of parameters: 13,264,901,120, training data (tokens): 1.4 trillion, Positional encoding: ALiBi, Maximum length: 4,096.

4. The cooking method for solving the mutual promotion and mutual restraint between multiple ingredients based on the AI ​​big model according to claim 2 is characterized by: The training process of the fourth step of training the mutual promotion and mutual restraint cooking AI large model is as follows: first, download the model weights of baichuan13b from huggingface, then download the belle dataset train_0.5M_CN to the local and put it in the dataset folder under the project directory, and finally run the sft_lora.py script. Then, quantize Baichuan LLM using qlora's nf4 and double quantization methods, and finally, use lora to fine-tune the instructions.

5. The cooking method for solving the mutual promotion and mutual restraint between multiple ingredients based on the AI ​​big model according to claim 1 is characterized by: The calling of the mutual promotion and mutual restraint cooking AI big model specifically includes the following steps: The first step is to assemble query statements. Different ingredients are assembled into query statements that the AI ​​big model can understand. The AI ​​big model is required to determine whether different ingredients are incompatible and analyze the reasons. The second step is that the AI ​​big model performs reasoning operations: the query statement is passed to the AI ​​big model, which performs reasoning operations. This includes the following processes: 1) Understanding input: Distributed semantic parsing first receives a text sequence and converts it into a word vector. This process is based on the distributed semantics assumption that the meaning of a word is determined by its use in context. 2) Parameter association: context focus linkage, input these word vectors into the Transformer Encoder to generate context representation; 3) Generate answers: Generative probability modeling. The model initializes the decoder part of the Transformer and inputs the encoder output and the current output sequence into the decoder. The decoder generates the probability distribution of the next word and selects the word with the largest probability or other set probability distribution as the output. This word will be added to the output sequence. 4) Select the most appropriate answer: Dynamic word string evolution, repeat the above steps, adding new words to the output sequence each time until a complete output sequence is generated; Step 3. The AI ​​big model returns the result: After the inference operation of the mutual promotion and mutual restraint cooking AI big model is completed, the mutual promotion and mutual restraint results and reasons are returned, including providing users with content in text, picture, audio, video or 3D model format.

6. The cooking method for solving the mutual promotion and mutual restraint between multiple ingredients based on the AI ​​big model according to claim 1 is characterized by: The AI ​​cooking model of mutual promotion and mutual restraint determines that the interval between different ingredients is no more than 6 hours.

7. The cooking method for solving the mutual promotion and mutual restraint between multiple ingredients based on the AI ​​big model according to claim 1 is characterized by: When the AI ​​big model of mutual promotion and mutual restraint cooking compares and determines that different ingredients are incompatible, the AI ​​big model of mutual promotion and mutual restraint cooking will feed back the information to the user's mobile terminal through the cloud platform and push the information of the compatible ingredients and cooking parameters.

8. An intelligent cooking device, characterized in that: A code scanning and recognition device, a processor and a wireless communication module are provided. The code scanning and recognition device is used to scan the identification codes on the packages of different ingredients that the user needs to cook to obtain different ingredient information and different cooking parameters. The processor is connected to the cloud platform and the user mobile terminal through the wireless communication module. The processor is used to execute the user in claim 1 to confirm the first cooking parameter and the second cooking parameter through the user mobile terminal operation to cook.

9. The intelligent cooking device according to claim 8, characterized in that: There are operating stations for stir-frying, sautéing, frying, cooking, frying, sticking, burning, braising, stewing, steaming, blanching, boiling, stewing, sautéing, mixing, pickling, roasting, braising, freezing, pulling out, honey, smoking, rolling, sliding or baking, and the operating stations for stir-frying, sautéing, frying, cooking, frying, sticking, burning, braising, stewing, steaming, blanching, boiling, stewing, sautéing, mixing, pickling, roasting, braising, freezing, pulling out, honey, smoking, rolling, sliding or baking are provided with corresponding detection modules. The detection module is used to detect whether the cooking operation performed by the user in the intelligent cooking device meets the requirements of the cooking method based on the AI ​​big model to solve the mutual generation and restraint between multiple ingredients.

10. The intelligent cooking device according to claim 8, characterized in that: A human-computer interaction system is provided, and the human-computer interaction system is used for information interaction between the intelligent cooking device and the user, including the user operating the user mobile terminal to confirm cooking parameters and start cooking operation instructions.

Images