Intelligent induction cooker system

Abstract

The invention belongs to the technical field of intelligent household appliances, and discloses an intelligent induction cooker system which comprises an induction cooker main circuit, a monitoring module, a memory module, a voice interaction module and an AI interaction module. A main control chip in the induction cooker main circuit is used for monitoring whether cookware is placed or not and whether food materials are placed or not in the cooking process according to the energy information and cookware temperature collected by the monitoring module, and reporting the information to the AI interaction module; the AI interaction module is used for executing the following steps: calling a cloud AI large model to generate a corresponding menu according to food material information and taste information input by a user through the voice interaction module; menu information feedback and confirmation are carried out through the voice interaction module; guiding the user to cook step by step through the voice interaction module according to a menu confirmed by the user in combination with reported information, and updating personalized cooking information in the memory module according to cooking process information; therefore, the system has intelligent cooking guidance, high-precision state monitoring and personalized learning capabilities.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of intelligent household appliances, in particular to an intelligent induction cooker system. BACKGROUND

[0002] Induction cookers have become one of the core appliances in modern kitchens due to their efficient energy conversion characteristics through electromagnetic coupling. With the deep penetration of artificial intelligence technology, traditional induction cookers are transitioning from "functional heating devices" to "intelligent cooking centers". Although some induction cooker products have basic intelligent control functions, there are still many technical bottlenecks in actual application.

[0003] The intelligent induction cookers on the current market mainly have the following technical defects: First, their intelligent control functions are mostly based on preset programs, lacking true autonomous learning and adaptive capabilities. This fixed program control mode cannot dynamically adjust according to the user's actual cooking habits, resulting in deviations between the cooking effect and the user's expectations. Second, the existing systems lack accuracy in pot state monitoring, making it difficult to accurately identify the pot placement state and food material placement timing, affecting the precise control of the cooking process. Third, the human-computer interaction method of traditional induction cookers is single, mainly through keys or simple touch control, which cannot meet the needs of modern users for intelligent and convenient operation.

[0004] More critically, existing technologies lack the ability to learn and remember users' personalized cooking habits. Although some high-end products can store a small number of cooking programs, they cannot intelligently optimize based on users' actual operation adjustments, nor can they feed back personalized adjustments to subsequent cooking guidance. This technical defect requires users to repeatedly set up each time, severely affecting the user experience.

[0005] In addition, the power control module of existing induction cooker systems lacks in response speed and accuracy, especially in high-frequency switching control, which limits the system's ability to precisely control complex cooking processes. At the same time, traditional systems have single means of energy detection, making it difficult to comprehensively obtain energy change information during the cooking process, restricting the improvement of intelligent control effect.

[0006] In view of the above problems, existing technologies need to be improved. SUMMARY

[0007] The purpose of the present application is to provide an intelligent induction cooker system with intelligent cooking guidance, high-precision state monitoring, and personalized learning capabilities.

[0008] The present application provides an intelligent induction cooker system, comprising: an induction cooker main circuit, including a power supply circuit, a main control chip, a power module, and an LC resonance circuit composed of a coil disc and a resonance capacitor; a monitoring module including a temperature detection unit and an energy detection unit electrically connected to the master chip, the temperature detection unit being configured to detect a temperature of a pot, and the energy detection unit being configured to detect energy information of an LC resonant circuit; a memory module configured to store personalized cooking information of a user; a voice interaction module including a voice broadcast device and a voice receiving device; an AI interaction module supporting network communication and electrically connected to the master chip, the memory module, and the voice interaction module; the master chip being configured to monitor whether a pot is placed and whether food is placed in a cooking process according to the energy information and the temperature of the pot, and report the monitoring result and the temperature of the pot as reporting information to the AI interaction module; the AI interaction module being configured to perform: calling a cloud AI large model to generate a corresponding recipe according to food information and taste information input by a user through the voice interaction module; feeding back and confirming recipe information through the voice interaction module; step-by-step guiding the user to cook through the voice interaction module according to the recipe confirmed by the user and in combination with the reporting information, and updating personalized cooking information in the memory module according to cooking process information.

[0009] Beneficial effects: The intelligent induction cooker system provided by the present application realizes intelligent cooking guidance, precise state monitoring, and personalized learning by integrating an AI interaction module and a monitoring module, and has the intelligent cooking guidance, high-precision state monitoring, and personalized learning capabilities. BRIEF DESCRIPTION OF DRAWINGS

[0010] Figure 1 FIG. 1 is a structural schematic diagram of an intelligent induction cooker system provided by the present application.

[0011] Figure 2 FIG. 4 is a flowchart of calling a cloud AI large model to generate a recipe.

[0012] Figure 3 FIG. 6 is a flowchart of guiding a user to cook.

[0013] Figure 4 FIG. 7 is a flowchart of step-by-step guiding a user to cook.

[0014] Figure 5 FIG. 8 is a flowchart of monitoring whether a pot is placed.

[0015] Figure 6 FIG. 9 is a flowchart of monitoring whether food is placed.

[0016] Brief description of drawings: 1, the main circuit of the induction cooker; 101, power supply circuit; 102, main control chip; 103, power module; 104, coil disc; 105, resonance capacitor; 106, LC resonance circuit; 107, silicon carbide MOSFET; 108, drive module; 2, monitoring module; 201, temperature detection unit; 202, energy detection unit; 3, memory module; 301, temporary storage unit; 302, local storage unit; 4, voice interaction module; 401, voice broadcast device; 402, voice receiving device; 5, AI interaction module. DETAILED DESCRIPTION

[0017] The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all the embodiments. The components of the embodiments of the present application described and shown in the drawings can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the claimed application, but only represents selected embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present application.

[0018] It should be noted that: similar labels and letters represent similar items in the following drawings, so once an item is defined in one drawing, it does not need to be further defined and explained in subsequent drawings. At the same time, in the description of the present application, the terms "first", "second" and the like are only used to distinguish the description, and cannot be understood as indicating or implying relative importance.

[0019] Please refer to Figure 1 The intelligent induction cooker system in some embodiments of the present application comprises: The main circuit of the induction cooker 1 comprises a power supply circuit 101, a main control chip 102, a power module 103, and an LC resonance circuit 106 composed of a coil disc 104 and a resonance capacitor 105; The monitoring module 2 comprises a temperature detection unit 201 and an energy detection unit 202 electrically connected to the main control chip 102, the temperature detection unit 201 is used to detect the temperature of the pot, and the energy detection unit 202 is used to detect the energy information of the LC resonance circuit 106; The memory module 3 is used to store the user's personalized cooking information; The voice interaction module 4 comprises a voice broadcast device 401 and a voice receiving device 402; The AI interaction module 5 supports network communication and is electrically connected to the main control chip 102, the memory module 3 and the voice interaction module 4. The master chip 102 is used to monitor whether the pot is put in and whether the food is put in during the cooking process according to the energy information and the pot temperature, and report the monitoring result and the pot temperature as the reporting information to the AI interaction module 5; The AI interaction module 5 is used to perform: According to the food information and the taste information input by the user through the voice interaction module 4, the cloud AI large model is called to generate the corresponding recipe; The recipe information feedback and confirmation are performed through the voice interaction module 4; According to the recipe confirmed by the user, the reporting information is combined to guide the user to cook step by step through the voice interaction module 4, and the personalized cooking information in the memory module 3 is updated according to the cooking process information.

[0020] The system realizes the self-learning ability by integrating the AI interaction module 5, the memory module 3 and the voice interaction module 4, thereby avoiding the dependence on the preset code and realizing the adaptive optimization.

[0021] Specifically, the intelligent induction cooker system includes an induction cooker main circuit 1, which is composed of a power supply circuit 101, a master chip 102, a power module 103, and an LC resonance circuit 106 composed of a coil disc 104 and a resonance capacitor 105. The power supply circuit 101 provides stable power for the whole system, and the master chip 102 serves as the core controller, responsible for coordinating the work of each component. The power module 103 converts electrical energy into high-frequency alternating magnetic field to drive the LC resonance circuit 106 to inductively heat the pot. For example, the power module 103 can adopt a traditional IGBT (Insulated Gate Bipolar Transistor) scheme, which adjusts the output power by controlling the switching frequency and duty cycle of IGBT, thereby realizing the energy transmission control of the LC resonance circuit 106.

[0022] The monitoring module 2 includes a temperature detection unit 201 and an energy detection unit 202 electrically connected to the master chip 102. The temperature detection unit 201 is used to detect the pot temperature in real time, for example, the temperature data of the pot surface can be obtained through a thermistor or an infrared sensor. The energy detection unit 202 is used to detect the energy information of the LC resonance circuit 106, for example, the current data or voltage data of the LC resonance circuit 106 can be collected through a current transformer or a voltage transformer, or the resonance frequency data can be detected through a frequency meter. These detection units feed back real-time data to the master chip 102, providing basis for the master chip 102 to make state judgments.

[0023] The memory module 3 is used to store the user's personalized cooking information. This module can be an internal storage chip, such as EEPROM or NAND Flash, used to store the recipes the user has made and their personalized cooking process information. When the user cooks, the system can provide customized guidance based on the stored personalized information.

[0024] The voice interaction module 4 includes a voice broadcast device 401 and a voice receiving device 402. The voice broadcast device 401 can be a built-in speaker for playing system-generated voice prompts and guidance. The voice receiving device 402 can be a microphone array for receiving user voice instructions, ingredient information, and taste information. Through voice interaction, users can naturally communicate with the induction cooker system, improving operational convenience.

[0025] The AI interaction module 5 supports network communication and is electrically connected to the main control chip 102, the memory module 3, and the voice interaction module 4. This module is the core of intelligence and can be a separate microprocessor or embedded system with a built-in Wi-Fi or 4G communication module, allowing it to connect to the cloud platform. The AI interaction module 5 is responsible for processing user voice input, calling cloud AI large models, and controlling the induction cooker main circuit 1 and the voice interaction module 4 based on the returned results.

[0026] The main control chip 102 is used to monitor whether the pot is placed and whether the ingredients are placed during cooking based on energy information and pot temperature, and reports the monitoring results and pot temperature to the AI interaction module 5 as reporting information. For example, the main control chip 102 can preset a reference energy information, and when the monitored energy information significantly differs from the reference energy information, it is determined that the pot has been placed. Similarly, by monitoring the dynamic changes of the pot temperature and energy information, it can be determined whether the ingredients are placed.

[0027] The AI interaction module 5 is used to perform a series of intelligent cooking guidance functions. First, based on the ingredient information and taste information input by the user through the voice interaction module 4, the cloud AI large model is called to generate corresponding recipes. For example, the user can say "I have pork, shrimp, carrots, and celery in my fridge, and I want to eat Hunan cuisine," and the AI interaction module 5 sends this information to the cloud AI large model, which generates one or more matching recipes based on this information.

[0028] Second, the recipe information is fed back and confirmed through the voice interaction module 4. The AI interaction module 5 will inform the user of the generated recipe through the voice broadcast device 401 and wait for user confirmation. For example, the system will broadcast "OK, based on the ingredients and taste you reported, I recommend making a spicy hot pot, which requires shrimp, carrots, …", and then wait for the user to confirm whether to adopt it.

[0029] Finally, according to the user-confirmed recipe, combined with the reported information, the system guides the user to cook through the voice interaction module 4 step by step, and updates the personalized cooking information in the memory module 3 according to the cooking process information. During the cooking process, the AI interaction module 5 will adjust the cooking guidance in real time according to the pot temperature and food material state reported by the main control chip 102, such as prompting the user when to put oil, when to put food materials, when to stir-fry, etc. At the same time, the system will record the user's adjustments during the cooking process, such as the increase or decrease of food materials or seasonings, and use these information as cooking process information to update the personalized cooking information in the memory module 3, so as to realize the continuous learning and optimization of the system.

[0030] The intelligent induction cooker system of the present application realizes a complete closed loop from recipe generation to cooking guidance to personalized learning through the cooperative work of the AI interaction module 5, the memory module 3 and the voice interaction module 4. Unlike traditional induction cookers that rely on pre-set codes, the system of the present application can dynamically generate and adjust cooking schemes according to real-time user input and cooking process data, and continuously learn and optimize the user's personalized cooking information. This self-learning ability enables the system to provide truly customized cooking experience, significantly improving user satisfaction and the intelligence level of the induction cooker. In addition, by monitoring the pot temperature and energy information in real time, the system can accurately judge the cooking state and give timely operation prompts to ensure the safety and efficiency of the cooking process. This intelligent cooking guidance based on AI large model and real-time data feedback enables the induction cooker to transform from a "functional heating device" to a "smart cooking center", bringing users an unprecedented convenient and personalized experience.

[0031] In some preferred embodiments, the power module 103 includes a silicon carbide MOSFET 107 and its driving module 108; the driving module 108 can control the gate of the silicon carbide MOSFET 107 to generate a switching frequency higher than 20 kHz, and can provide the silicon carbide MOSFET 107 with a direct current driving voltage of 18V-22V, and can provide the silicon carbide MOSFET 107 with a direct current gate off voltage of -5V to -3V; the main control chip 102 can generate a control output frequency of 20kHz-250kHz, and the feedback response speed reaches above 150kHz.

[0032] Specifically, the silicon carbide MOSFET 107 in the power module 103 is a metal-oxide-semiconductor field-effect transistor based on silicon carbide semiconductor material. Compared with traditional silicon-based power devices, the silicon carbide MOSFET 107 has a higher bandgap, higher thermal conductivity, and lower on-resistance, enabling it to withstand higher voltage, current, and temperature, and achieve faster switching speed. Its implementation can choose mature silicon carbide MOSFET 107 devices on the market. The drive module 108 is a circuit for controlling the switching state of the silicon carbide MOSFET 107. It receives control signals from the master chip 102 and converts them into voltage and current signals suitable for gate drive of the silicon carbide MOSFET 107. The drive module 108 usually includes level conversion circuit, buffer circuit, isolation circuit, and overcurrent / undervoltage protection circuit, etc. Its implementation can choose mature silicon carbide MOSFET 107 drive chips on the market as needed, or build a drive circuit with discrete components.

[0033] The drive module 108 can control the gate of the silicon carbide MOSFET 107 to generate a switching frequency higher than 20 kHz. The switching frequency refers to the number of times the silicon carbide MOSFET 107 turns on and off in a unit of time. High switching frequency helps reduce the size and weight of passive components such as inductors and capacitors, improve power conversion efficiency, and reduce electromagnetic interference. The drive module 108 achieves high-frequency switching operation of the silicon carbide MOSFET 107 by precisely controlling the rising and falling edges of the gate voltage.

[0034] The drive module 108 can provide the silicon carbide MOSFET 107 with a direct current driving voltage of 18V-22V. The direct current driving voltage is the voltage applied between the gate and source of the silicon carbide MOSFET 107 to make it conduct. The appropriate driving voltage can ensure that the silicon carbide MOSFET 107 is fully on, reduce on-resistance, and improve device reliability. This voltage range is usually determined by the characteristics of the silicon carbide MOSFET 107 to ensure its optimal operating state.

[0035] The drive module 108 can provide the silicon carbide MOSFET 107 with a direct current gate off voltage of -5V to -3V. The direct current gate off voltage is a negative voltage applied between the gate and source of the silicon carbide MOSFET 107 to reliably turn it off. Providing a negative off voltage helps speed up the turn-off process of the silicon carbide MOSFET 107, effectively suppresses the Miller effect-induced false conduction, thereby reducing switching loss and improving system stability.

[0036] The master chip 102 is capable of generating control output frequencies ranging from 20 kHz to 250 kHz. The control output frequency is the frequency of the PWM (Pulse Width Modulation) signals sent by the master chip 102 to the drive module 108, used to control the switching of the silicon carbide MOSFET 107. This frequency range matches the operating frequency of the LC resonant circuit 106, ensuring that the induction cooker can efficiently perform induction heating. The master chip 102 generates these control signals through internal timers and PWM generators.

[0037] The feedback response speed of the master chip 102 reaches above 150 kHz. The feedback response speed refers to the speed at which the master chip 102 processes the data fed back by the monitoring module 2 (such as the temperature detection unit 201 and the energy detection unit 202) and adjusts the control output signal. A high feedback response speed means that the master chip 102 can quickly perceive changes in the cooking state (such as pot temperature, energy information) and timely adjust the power output, thereby achieving more accurate temperature control and more stable heating process. This is usually achieved by optimizing the algorithm of the master chip 102, improving its processing capability (for example, using a microcontroller with a higher clock frequency), and optimizing the interrupt handling mechanism.

[0038] In this scheme, the power module 103 is designed to contain a silicon carbide MOSFET 107 and its driving module 108. The silicon carbide MOSFET 107, as the core switching device, can achieve faster switching speed and lower on-state loss than traditional silicon-based devices due to its excellent physical properties. The driving module 108 is specifically optimized for the characteristics of the silicon carbide MOSFET 107 and can control its gate to generate a switching frequency higher than 20 kHz. This high-frequency switching operation enables the LC resonant circuit 106 in the electromagnetic oven main circuit 1 to work at a higher frequency, effectively improving energy conversion efficiency, reducing the size of passive components, and reducing electromagnetic interference. To ensure the reliable conduction and rapid turn-off of the silicon carbide MOSFET 107, the driving module 108 is configured to provide a DC driving voltage of 18V-22V and a DC gate turn-off voltage of -5V to -3V. Precise driving voltage ensures that the MOSFET can be fully saturated when conducting, reducing on-state loss; while the negative turn-off voltage accelerates the turn-off process of the device, effectively suppressing the Miller effect, thereby significantly reducing switching loss and improving the overall efficiency and stability of the system. The main control chip 102, as the control core of the entire system, is designed to be able to generate a control output frequency of 20kHz-250kHz. This frequency range matches the working frequency of the LC resonant circuit 106, allowing the main control chip 102 to accurately adjust the power output to adapt to different cooking needs. More importantly, the feedback response speed of the main control chip 102 reaches more than 150kHz. This means that the main control chip 102 can quickly receive and process the reported information from the monitoring module 2 (including the temperature detection unit 201 and the energy detection unit 202), such as the temperature of the pot and the energy information of the LC resonant circuit 106. Based on these real-time feedback data, the main control chip 102 can quickly adjust its control output frequency and duty cycle, thereby achieving real-time and accurate regulation of the power of the LC resonant circuit 106. Through the above technical scheme, the high-frequency and high-efficiency switching characteristics of the silicon carbide MOSFET 107 are combined with the optimized design of the driving module 108, providing the main control chip 102 with a wider control range and more precise adjustment capability. The main control chip 102, with its powerful control output frequency and fast feedback response speed, can monitor the pot state and cooking process in real time, and accurately control the heating power according to the instructions of the AI interaction module 5 or the preset recipe. For example, when the AI interaction module 5 guides the user step by step to cook, the main control chip 102 can quickly adjust the power according to the pot temperature and energy information to ensure that the food is cooked at the optimal temperature, avoiding overheating or insufficient heating. This close cooperation enables the intelligent electromagnetic oven system to achieve fine control of the cooking process, significantly improving heating efficiency, reducing energy consumption, and ensuring the accuracy and safety of cooking, thereby effectively solving the deficiencies of traditional electromagnetic ovens in heating efficiency, response speed, and control accuracy.

[0039] In some embodiments, with reference to Figure 2 , the AI interaction module 5, when invoking a cloud AI large model to generate a corresponding recipe according to the food material information and taste information input by the user through the voice interaction module 4, performs: Monitoring the surrounding sound information through the voice interaction module 4, and analyzing whether the sound information contains a wake-up instruction; When the sound information contains a wake-up instruction, obtaining the food material information and taste information input by the user through the voice interaction module 4; Generating a requirement instruction according to the food material information and the taste information and sending it to a cloud platform to invoke a cloud AI large model, and obtaining at least one recipe and its standard production process information matched with the food material information and the taste information fed back by the cloud AI large model.

[0040] Specifically, monitoring the surrounding sound information means that the intelligent induction cooker system continuously collects audio data in the environment. This can be achieved by allowing the audio front-end (voice receiving device 402) of the voice interaction module 4 to continuously sample the ambient sound in a low-power mode, or by periodically activating the main audio processing unit to buffer and analyze the audio data; or by the user triggering the voice interaction module 4 to collect audio data in the environment through the keys on the induction cooker panel.

[0041] Analyzing whether the sound information contains a wake-up instruction aims to intelligently identify whether the user has an explicit intention to interact with the system. This can be achieved by running a lightweight keyword recognition (KWS) model locally, which is trained to recognize specific wake-up phrases such as "Hello SiC" or "Hi SiC". Another way is to send the collected short-time audio clip to the cloud for keyword recognition, and the cloud service judges whether it contains a wake-up instruction and returns the result.

[0042] When the sound information contains a wake-up instruction, the voice interaction module 4 obtains the food material information and taste information input by the user through the voice, which means that the system only starts higher-level speech recognition and understanding functions after confirming the user's intention. This can be achieved by activating a complete local automatic speech recognition (ASR) engine to convert the user's continuous speech into text, and further extracting specific food materials and taste information through a natural language understanding (NLU) module. Alternatively, the system can stream the user's voice after waking up to the cloud's ASR / NLU service, and the cloud performs high-precision speech-to-text and semantic analysis.

[0043] The food material information refers to the types of food materials that the user informs the system through voice, such as "pork, prawns, carrots, celery", etc. The taste information refers to the user's description of the flavor preference of the dish, such as "Hunan cuisine" or "the taste can be heavier", etc.

[0044] The generation of the requirement instruction sent to the cloud platform to call the cloud AI large model refers to packaging the user's input of food material information and taste information according to the format required by the interface of the cloud AI large model. This can be constructing a structured data packet, such as a JSON or XML format API request, which contains parameters such as a list of food materials and taste preferences. Subsequently, the AI interaction module 5 sends the requirement instruction to the remote cloud platform through a network communication module (such as Wi-Fi, Ethernet MAC / PHY, or 4G / Bluetooth module).

[0045] The cloud platform is a remote server infrastructure that provides cloud computing services, used to host and run the cloud AI large model. The cloud AI large model refers to a large artificial intelligence model deployed on the cloud platform, such as deepseek or doubao, etc. These models have powerful natural language processing and knowledge reasoning capabilities, and can generate matching recipes according to the user's provided food materials and taste information.

[0046] The acquisition of at least one recipe and its standard making process information that matches the food material information and the taste information fed back by the cloud AI large model refers to the AI interaction module 5 receiving and analyzing the response data returned by the cloud AI large model. The response data usually contains the name of one or more recommended recipes, the list of required food materials (for example, the feedback recipe requires some or all of the food materials in the user's input through the voice interaction module 4), and detailed step-by-step making process information. The AI interaction module 5 will analyze these information for subsequent feedback to the user through the voice interaction module 4.

[0047] The scheme of the present application introduces a wake-up instruction mechanism, so that the intelligent induction cooker system can first determine whether the user has an explicit interaction intention when processing user voice input. Only when a specific wake-up instruction is detected, the system will further start the resource-intensive voice recognition and semantic understanding process to obtain the user's food material information and taste information, and call the cloud AI large model. This mechanism effectively avoids the mis-triggering of the system by environmental noise or non-intentional voice, thereby reducing unnecessary consumption of computing resources and cloud API calls, and improving the running efficiency of the system. At the same time, by ensuring that information collection and processing only occur when the user has an explicit intention, the accuracy of human-computer interaction and the smoothness of user experience are greatly improved.

[0048] In some embodiments, the personalized cooking information includes recipes that the user has made before and their personalized cooking process information; the personalized cooking process information has changes in ingredients and / or seasonings and / or substitutions compared to the standard cooking process information of the corresponding recipe; With reference to Figure 3 When the AI interaction module 5 guides the user to cook step by step through the voice interaction module 4 according to the user-confirmed recipe combined with the reported information, it performs: determines whether the personalized cooking information in the memory module 3 contains the user-confirmed recipe; If not, the standard cooking process information of the user-confirmed recipe is used as the effective cooking process information, otherwise, the corresponding personalized cooking process information is extracted from the recognition memory module 3 as the effective cooking process information; According to the effective cooking process information, combined with the reported information, the voice interaction module 4 guides the user to cook step by step.

[0049] The personalized cooking information refers to the records formed by the user's adjustments and modifications to the recipe during the cooking process according to their own preferences or actual situations. It can include the user's taste preferences for a particular dish, adjustments or substitutions of ingredients, and additions or substitutions of seasonings, etc. For example, the user may prefer a higher degree of spiciness for a certain dish, or choose to substitute due to an allergy to a certain ingredient. This information can be stored in structured data (such as JSON, XML format) or in the form of text description for subsequent system call and parsing. The user's once-made recipes refer to the specific names or identifiers of the dishes that the user has cooked using the intelligent induction cooker system in the past. These recipes can be pre-set by the system or generated by the user through the AI interaction module 5. The system can assign a unique identifier to each recipe and associate it with the user's cooking history. The personalized making process information refers to the specific cooking steps and parameters associated with a particular recipe that have been adjusted by the user. It differs from the standard making process information for that recipe and reflects the user's unique cooking habits. For example, for a dish of braised pork, the standard process may specify the amount of sugar, while the personalized process may record that the user is used to adding an extra spoonful of sugar or using rock sugar instead of white sugar. This information can be stored as a series of step instructions with timestamps and modification records, or in the form of a differential patch, only recording the differences from the standard process. Ingredient and / or seasoning addition and / or substitution is a specific way to reflect the user's preferences in personalized making process information. Ingredient addition can refer to the user's adjustment of the amount of ingredients during cooking; seasoning addition can refer to the user's adjustment of the amount of seasonings during cooking. Ingredient substitution can refer to the user's adjustment of the type of ingredients; seasoning substitution can refer to the user's adjustment of the type of seasonings. These adjustments can be explicitly informed to the system by the user through voice instructions before cooking, or modified in real time through voice feedback during cooking.

[0050] The AI interaction module 5 will perform a series of operations when guiding the user to cook step by step through the voice interaction module 4 according to the user-confirmed recipe combined with the reported information. First, determine whether the personalized cooking information in the memory module 3 contains the user-confirmed recipe. This step aims to actively query the memory module 3 before the system starts guiding cooking to determine whether there is a personalized cooking history record matching the current user-confirmed recipe. This can be achieved by comparing the recipe name, recipe ID or other unique identifiers. For example, the system can maintain a recipe index table containing the recipe ID and the storage location of the corresponding personalized cooking process information. If not, use the standard cooking process information of the user-confirmed recipe as the effective cooking process information. When the system fails to find personalized cooking information matching the user-confirmed recipe in the memory module 3, in order to ensure the smooth progress of cooking guidance, the system will fall back to using the default or preset standard cooking process information of the recipe. These standard process information is usually provided by the cloud AI large model when generating the recipe. Otherwise, extract the corresponding personalized cooking process information from the recognition memory module 3 as the effective cooking process information. When the system successfully finds personalized cooking information matching the user-confirmed recipe in the memory module 3, the system will preferentially select and extract these personalized cooking process information. These information will be the basis for this cooking guidance to ensure that the guidance content meets the user's historical preferences. Finally, according to the effective cooking process information, combined with the reported information, guide the user to cook step by step through the voice interaction module 4. This step is the core of realizing personalized cooking guidance. The system will provide real-time, step-by-step cooking instructions to the user through the voice broadcast device 401 according to the determined effective cooking process information (whether it is standard process or personalized process), combined with the real-time reported information of the pot temperature, whether to put the pot into the pot, and whether to put the food into the pot during the cooking process. For example, when the effective cooking process information indicates that the pot needs to be heated to 150°C, the system will continuously monitor the reported pot temperature and prompt the user to perform the next operation through voice when the temperature reaches the temperature.

[0051] The scheme further optimizes the cooking guidance logic of the AI interaction module 5 on the basis of the intelligent induction cooker system (including the induction cooker main circuit 1, the monitoring module 2, the memory module 3, the voice interaction module 4, and the AI interaction module 5). When the user confirms that a recipe is ready to start cooking, the AI interaction module 5 will first actively query the memory module 3 to determine whether personalized cooking information related to the recipe has been stored therein. The personalized cooking information here not only includes recipes that the user has made before, but more importantly, it includes the user's personalized cooking process information for these recipes. These process information may have additions, subtractions, and / or substitutions of ingredients and / or seasonings compared to the standard recipe. If the memory module 3 does not contain personalized information for the recipe, the AI interaction module 5 will use the standard cooking process information for the recipe as the effective cooking process information for this cooking, ensuring that even a recipe that is cooked for the first time can be guided. Conversely, if the memory module 3 contains corresponding personalized cooking process information, the AI interaction module 5 will preferentially extract these personalized information as the effective cooking process information. This mechanism enables the system to dynamically utilize the user's historical cooking preferences, thereby providing guidance that is more in line with the user's habits. Subsequently, the AI interaction module 5 will provide step-by-step cooking guidance to the user through the voice interaction module 4 (including the voice broadcast device 401 and the voice receiving device 402) based on the determined effective cooking process information and the reported information such as the pot temperature, whether the pot is placed, whether the ingredients are placed, etc. reported by the main control chip 102 in real time. For example, when the effective cooking process information indicates that the pot needs to be heated to a specific temperature, the AI interaction module 5 will continuously receive the pot temperature reported by the main control chip 102, and when the target temperature is reached, it will prompt the user to proceed to the next step through the voice broadcast device 401, such as "Temperature has reached 150°C, please add cooking oil". The combination of real-time feedback and personalized guidance makes the entire cooking process more intelligent, flexible, and able to adapt to temporary adjustments that may occur during cooking. This significantly improves the flexibility and personalization of cooking guidance, allowing users to obtain guidance that is more in line with their own tastes and habits during cooking, thereby greatly improving the user experience. At the same time, this mechanism also provides a basis for subsequent learning and optimization of the system, enabling the intelligent induction cooker to become more "understanding" of the user over time.

[0052] Preferably, with reference to Figure 4 , the step of guiding the user to cook step by step through the voice interaction module 4 based on the effective cooking process information and the reported information can include: broadcasting the ingredient preparation information through the voice interaction module 4; the ingredient preparation information includes the type and amount of ingredients, the type and amount of seasonings, and the pretreatment method of each type of ingredient; After obtaining the material preparation completion instruction input by the user through the voice interaction module 4, instruct the main control chip 102 to monitor whether the pot is placed; If the monitoring result indicates that the pot has been placed, extract the material addition information, operation information, cooking temperature information, and stage end information of each cooking step from the effective cooking process information; In each cooking step, the corresponding material addition information and operation information are announced, and after the pot is placed as indicated in the reporting information, the main control chip 102 adjusts the power of the LC resonant circuit 106 according to the cooking temperature information of the current cooking step and the pot temperature in the reporting information; When the user determines that the current cooking step is completed based on the stage end information and inputs the completion confirmation information through the voice interaction module 4, the next cooking step is entered or the cooking is ended.

[0053] Specifically, the voice interaction module 4 announces the material preparation information, which includes the type and quantity of food materials, the type and quantity of seasonings, and the pretreatment method of each type of food material. The voice interaction module 4 is used to inform the user of the required material preparation information in the form of voice. The material preparation information not only includes a simple list of food materials, but also details the specific types of food materials, the required quantities, the types of seasonings, the quantities of seasonings, and the methods of pretreating each type of food material before cooking. For example, the pretreatment methods can include washing, cutting (such as dicing, slicing, and shredding), marinating, and blanching. This detailed announcement aims to ensure that the user can accurately prepare all the necessary materials and perform appropriate preliminary processing before starting cooking.

[0054] After obtaining the material preparation completion instruction input by the user through the voice interaction module 4, instruct the main control chip 102 to monitor whether the pot is placed. After the user completes all the material preparation work, the voice interaction module 4 issues a "material preparation completed" instruction to the system. After the system receives this instruction, it immediately instructs the main control chip 102 to start the pot monitoring function. The main control chip 102 obtains the energy information of the LC resonant circuit 106 and the pot temperature through the energy detection unit 202 and the temperature detection unit 201, and combines the preset judgment logic to determine whether the pot has been correctly placed on the induction cooker. This step aims to ensure that the cooking process is carried out with a pot, avoiding safety hazards and energy waste caused by heating an empty pot. The user can say specific wake-up words and instructions such as "material preparation completed", which are recognized by the voice receiving device 402 and passed to the AI interaction module 5, which then instructs the main control chip 102; or the system automatically enters a state of waiting for the user's voice confirmation after announcing the material preparation information, and the user only needs to say "complete" or "start cooking" instructions.

[0055] If the monitoring result indicates that the pot has been placed, the material addition information, operation information (such as stirring, stirring, covering the pot cover, etc.), cooking temperature information, and stage end information (such as food material change information, time length information of the current cooking step, etc.) of each cooking step are extracted from the effective cooking process information. Once the master chip 102 confirms that the pot has been correctly placed, the AI interaction module 5 will extract detailed guidance content required for each cooking step from the effective cooking process information on which the current cooking is based. These contents include: the type and amount of materials needed to be added (material addition information), the operation needed to be performed (such as stirring, stirring, covering the pot cover, etc. operation information), the ideal cooking temperature that should be reached in this step (cooking temperature information), and the basis for judging whether the current step is completed (stage end information). The stage end information can be a description of the change of the food material state (such as "fry until color change", "thick soup"), or the estimated time length of the current step. This detailed information extraction provides accurate basis for subsequent step-by-step guidance. The AI interaction module 5 can directly parse the structured data stored in the memory module 3 and extract the corresponding fields; or by calling the cloud AI large model, dynamically generate and extract these step information according to the effective cooking process information.

[0056] In each cooking step, the corresponding material addition information and operation information are broadcasted, and after the reported information indicates that the food material is placed, the master chip 102 is instructed to adjust the power of the LC resonant circuit 106 according to the cooking temperature information of the current cooking step combined with the pot temperature in the reported information. At the beginning of each specific cooking step, the voice interaction module 4 will broadcast to the user the materials needed to be added and the operations needed to be performed. For example, prompt the user to "please add ginger slices, garlic slices, and stir-fry evenly". When the master chip 102 confirms that the user has placed the food material according to the instructions through the reporting information of the monitoring module 2 (energy detection unit 202 and temperature detection unit 201), the AI interaction module 5 will calculate the required power adjustment amount according to the preset cooking temperature information of the current step combined with the real-time monitored pot temperature, and then instruct the master chip 102 to adjust the power of the LC resonant circuit 106. This real-time feedback and dynamic power adjustment mechanism ensures accurate temperature control during cooking, avoiding overheating or deficiency, thereby optimizing the cooking effect. The master chip 102 can adjust the output power of the LC resonant circuit 106 by adjusting the switching frequency or duty cycle of the power module 103 according to the instructions of the AI interaction module 5; the power adjustment can also use PID control algorithm to adjust in real time according to the deviation between the target temperature and the actual temperature.

[0057] When the user determines that the current cooking step is completed based on the stage end information and inputs the completion confirmation information through the voice interaction module 4, the next cooking step is entered or the cooking is ended. When the user determines that the current cooking step is completed according to the stage end information (for example, the color of the food material changes, the thickness of the soup reaches the requirement, or the preset time length is reached) broadcasted by the voice, the user can issue a “complete” or “next step” confirmation instruction to the system through the voice interaction module 4. After the system receives the confirmation information, the AI interaction module 5 will automatically enter the guidance of the next cooking step according to the preset process logic, or end the entire cooking process after all the steps are completed. This user-initiated confirmation mechanism makes the cooking process more flexible, adapts to the operation habits and judgment of the food material state of different users, avoids mechanical timing or fixed process, and improves the user experience. The voice receiving device 402 can recognize the user's verbal confirmation instruction, and the AI interaction module 5 processes and promotes the process; in addition to voice confirmation, the system can also provide physical buttons or touch screen interfaces as auxiliary confirmation methods.

[0058] In fact, when the user inputs the completion confirmation information, the user can also inform the system of the actual food material change information or the actual time length information of the current cooking step, and the AI interaction module 5 can use the actual food material change information or the actual time length information of the current cooking step as the adjusted stage end information to participate in the subsequent personalized cooking information update.

[0059] The scheme of the present application realizes intelligent cooking guidance and control through the synergistic effect of the above steps. The whole process starts with the AI interaction module 5 using the voice interaction module 4 to broadcast detailed preparation information, solving the problem of unclear preparation of food and spices before cooking. After the user completes the preparation, the voice interaction module 4 issues a preparation completion instruction, and after the system receives it, the main control chip 102 immediately confirms whether the pot has been placed using its monitoring capability (based on energy information and pot temperature). This step ensures the safety and effectiveness of cooking and avoids heating an empty pot. Once the pot is confirmed to be placed, the AI interaction module 5 extracts the detailed guidance content required for each cooking step from the pre-determined effective cooking process information, including material addition information, operation information, cooking temperature information, and stage end information. The extraction of these information is dynamic and personalized, as the effective cooking process information may come from standard recipes generated by cloud AI large models or from user personalized cooking processes stored in the memory module 3. This mechanism enables the guidance content to accurately match the current cooking needs and user habits. In each cooking step, the voice interaction module 4 will broadcast material addition information and operation information in real time to guide the user to perform specific operations. The AI interaction module 5 will continuously receive energy information and pot temperature reported by the main control chip 102. When the reported information clearly indicates that the food has been placed in the pot, the AI interaction module 5 will accurately calculate and instruct the main control chip 102 to adjust the power of the LC resonant circuit 106 according to the cooking temperature information set for the current step and the real-time pot temperature. This closed-loop feedback control mechanism enables the induction cooker to dynamically adjust the heating power according to the cooking progress and food state, achieving precise temperature control and solving the problem of inaccurate power control of traditional induction cookers, significantly improving the success rate of cooking and the quality of dishes. Finally, the user judges whether the current step is completed according to the stage end information broadcast by the voice, and inputs the completion confirmation information through the voice interaction module 4. After the system receives this confirmation, it will smoothly enter the next cooking step, or end the cooking after all steps are completed. This user confirmation-based process advancement method enhances the flexibility of human-computer interaction and the user's dominance, avoiding the discomfort brought by mechanical processes, making the entire cooking process more smooth and humanized.

[0060] Preferably, in each cooking step, in addition to broadcasting the corresponding material addition information and operation information, the cooking temperature information of the current cooking step (i.e. the temperature required for the current cooking step) can also be further broadcasted, and during the cooking process, the system displays the pot temperature in real time to facilitate the user to monitor whether the pot temperature meets the cooking requirements, realizing manual monitoring of the system working state.

[0061] In some preferred embodiments, if no food material is detected within a preset time after the corresponding material adding information and operation information are announced in each cooking step, a warning is issued and the induction cooker is shut down.

[0062] Specifically, the "preset time" can be a fixed duration, such as 30 seconds or 1 minute, to provide sufficient response time for the user; alternatively, to adapt to the characteristics of different cooking steps, the preset time can also be dynamically adjusted according to the complexity of the current cooking step or the pre-processing requirements of the food material, for example, for steps that require quick stir-frying, the time can be shorter, while for steps that require slow addition of seasonings, the time can be appropriately extended; the preset time can be included in the recipe information or generated in real time by the AI interaction module 5. The judgment of "no detection of food material" can be achieved in various ways. For example, the main control chip 102 can continuously monitor the energy information of the LC resonance circuit 106, such as current data, voltage data, or resonance frequency data. When the food material is placed in the pot, the coupling characteristics of the pot and the food material will change, causing the energy information of the LC resonance circuit 106 to exhibit detectable fluctuations or trend changes. In addition, the temperature detection unit 201 can also be used to detect the rapid drop in pot temperature, as food materials are usually at room temperature or low temperature, and when placed in a hot pot, they will absorb heat, causing the pot temperature to drop momentarily. The "warning" can be issued in various ways. For example, the voice announcement device 401 of the voice interaction module 4 can issue a clear voice prompt, such as "Please add food material as soon as possible, otherwise the cooking will be interrupted"; at the same time, the indicator light on the control panel of the induction cooker can flash, or the display screen can display corresponding text information to visually remind the user. The "shutdown" operation aims to interrupt the unsafe or ineffective cooking process in a timely manner. This can be directly controlled by the main control chip 102 to cut off the power supply circuit 101 of the induction cooker main circuit 1, cutting off the power supply to the entire induction cooker system; alternatively, the main control chip 102 can instruct the power module 103 to stop energy output to the LC resonance circuit 106, causing the induction cooker to enter a safe standby state, thereby avoiding empty pot heating or energy waste.

[0063] The scheme of the present application effectively solves the safety problem caused by user operation delay or negligence by introducing a time monitoring and response mechanism, ensuring the reliability and safety of the cooking process. Specifically, during the process of guiding the user to cook step by step by the AI interaction module 5 through the voice interaction module 4, after the voice interaction module 4 broadcasts the material addition information and operation information required for the current cooking step, the system will start a preset time timer. Within this preset time, the main control chip 102 will continuously monitor the energy information and the temperature of the pot inside by using the energy detection unit 202 and the temperature detection unit 201 in the monitoring module 2 to determine whether the user has added the food material according to the instruction. If the main control chip 102 still does not detect the addition of the food material at the end of the preset time, the AI interaction module 5 will immediately issue a warning through the voice interaction module 4 to remind the user to operate in time. If the user still does not operate after the warning is issued, or the addition of the food material is still not detected within a certain period of time after the warning is issued, the system will further perform a shutdown operation. The synergistic effect of this series of actions can effectively avoid the empty pot heating, energy waste and potential safety hazards caused by the user's failure to respond in time in the above-mentioned step-by-step cooking guidance scheme. In this way, the present application not only provides intelligent cooking guidance, but also strengthens safety protection at the user interaction level, making the entire cooking process more intelligent, safe and reliable.

[0064] Preferably, the memory module 3 can include a temporary storage unit 301 and a removable local storage unit 302; The cooking process information includes material adjustment information; the material adjustment information includes increase / decrease information and / or replacement information of food materials and / or seasonings (if the user inputs the completion confirmation information in each cooking step, and informs the system of the actual food material change information or the actual time length information of the current cooking step, the cooking process information can also include the adjusted stage end information, i.e. the actual food material change information or the actual time length information); After obtaining the material preparation completion instruction input by the user through voice, the AI interaction module 5 also performs the following operation before instructing the main control chip 102 to monitor whether the food material is put into the pot: obtaining the material adjustment information through the voice interaction module 4 (in fact, the material adjustment information can also be obtained through the voice interaction module 4 in each cooking step); When updating the personalized cooking information in the memory module 3 according to the cooking process information, the AI interaction module 5 performs: According to the material adjustment information and the effective production process information (if the cooking process information also includes the adjusted stage end information, the adjusted stage end information also needs to be combined), the latest personalized production process information of the recipe for this cooking is generated; The recipe of the cooking and the latest personalized cooking process information are taken as the personalized cooking information to be stored and stored in the temporary storage unit 301; Confirm with the user through the voice interaction module 4 whether the personalized cooking information in the memory module 3 needs to be updated; If the user confirms that the personalized cooking information in the memory module 3 needs to be updated, the personalized cooking information to be stored is transferred to the local storage unit 302 for personalized cooking information update.

[0065] The memory module 3 is a component for storing personalized cooking information of the user. The temporary storage unit 301 contained therein can be a volatile memory such as a RAM (Random Access Memory) for temporarily saving data during cooking to realize fast reading and writing and temporary data buffering. Another implementation is to use a cache or a partial flash memory area as temporary storage. The removable local storage unit 302 can be a non-volatile memory such as an SD card, a USB flash disk or a pluggable solid state disk for long-term storage of personalized cooking information and supporting user data migration between different devices or backup. For example, the local storage unit 302 can preferably be an SPI Flash with a capacity of more than 8M and support for expansion SD card.

[0066] The cooking process information refers to the data related to the cooking process recorded by the system when the user is cooking. Among them, the material adjustment information is any modification made by the user to the ingredients or seasonings specified in the recipe during the actual cooking process, such as increasing the amount of a certain ingredient, reducing a certain seasoning, or replacing the original ingredient with another. These information can be obtained through the voice interaction module 4 and serve as an important basis for updating personalized cooking information. The AI interaction module 5 is responsible for handling the interaction logic between the user and the induction cooker system. After the user completes the preparation and issues the instruction, but before the main control chip 102 starts monitoring the state of the pot, the AI interaction module 5 will actively inquire through the voice interaction module 4 (such as the voice receiving device 402) whether the user has made any adjustments to the ingredients or seasonings, and receive the user's voice input to obtain the specific material adjustment information. This is done to ensure that the system can timely capture and record the user's personalized modifications to the recipe before the cooking officially begins, providing accurate basis for subsequent cooking guidance and personalized information update. When the AI interaction module 5 needs to update the personalized cooking information in the memory module 3, it will consider the material adjustment information provided by the user during this cooking process, as well as the effective production process information currently being used (which may be a standard recipe process or a personalized process stored by the user before). Based on these two types of information, the AI interaction module 5 will intelligently generate a brand new personalized production process information that reflects the actual cooking situation this time. This generation process may involve modification, supplementation or deletion of the original process to accurately record the user's cooking habits. After generating the latest personalized production process information for this cooking, the AI interaction module 5 will package the recipe and its corresponding latest process information to form a "to-be-stored personalized cooking information" data package. This data package will first be stored in the temporary storage unit 301 in the memory module 3. The temporary storage unit 301 serves as a buffer area to temporarily save these data, so as to avoid the risks that may be caused by direct writing to the permanent storage before the user confirms. In order to ensure that the user has full control over the update of the personalized cooking information, the AI interaction module 5 will issue a query to the user through the voice interaction module 4 (such as the voice broadcast device 401) to confirm whether the user wants to save the latest personalized production process information formed during this cooking process to the memory module 3 to overwrite the original personalized cooking information or add new personalized cooking information. This interactive confirmation mechanism can effectively avoid the misoperation or situation that does not meet the user's wishes caused by automatic update of the system. Once the user explicitly indicates agreement to update the personalized cooking information through the voice interaction module 4, the AI interaction module 5 will formally transfer the "to-be-stored personalized cooking information" stored in the temporary storage unit 301 to the local storage unit 302 in the memory module 3.This updating process can choose to overwrite the original personalized cooking process information of the recipe or store it as new personalized recipe information, thereby realizing long-term recording and learning of the user's cooking habits.

[0067] In the process of user cooking guidance, the AI interaction module 5 will first guide the user to cook step by step through the voice interaction module 4 according to the user-confirmed recipe combined with the pot temperature and energy information reported by the main control chip 102. In this process, in order to more accurately capture the user's personalized cooking habits, the AI interaction module 5 will actively obtain the material adjustment information that the user may make in the preparation stage, such as the increase, decrease or replacement of ingredients or seasonings, through the voice interaction module 4 after obtaining the user's preparation completion instruction input through voice, and before instructing the main control chip 102 to monitor whether the pot is put in. These material adjustment information is combined with the effective cooking process information (whether it is a standard recipe process or the user's existing personalized process) to generate the latest personalized cooking process information of the recipe for this cooking by the AI interaction module 5. In order to ensure the accuracy of data updating and the active participation of the user, the generated latest personalized cooking process information will not immediately overwrite the original data, but will first be stored as to-be-stored personalized cooking information in the temporary storage unit 301 in the memory module 3. The temporary storage unit 301 serves as a data buffer and pre-audit area at this time, allowing the system to verify or wait for user confirmation before formal writing to permanent storage. Subsequently, the AI interaction module 5 will explicitly ask the user through the voice interaction module 4 whether the personalized information formed in this cooking process needs to be updated in the memory module 3. Only when the user explicitly confirms the need for updating, the AI interaction module 5 will transfer the to-be-stored personalized cooking information in the temporary storage unit 301 to the local storage unit 302. The local storage unit 302 as a permanent storage area can choose to overwrite the original personalized cooking process information of the recipe or store it as new personalized recipe information according to the user's wishes. Through this hierarchical storage and interactive confirmation mechanism, the scheme of the present application can effectively solve the limitations of traditional induction cookers in personalized information updating. The temporary storage unit 301 and the removable local storage unit 302 in the memory module 3 work together to realize the separation of data temporary storage and permanent storage, not only improving the flexibility of data processing, but also enhancing data security. The AI interaction module 5 obtains material adjustment information at key nodes, ensuring accurate recording of the user's real-time adjustments. At the same time, the user confirmation mechanism gives the user control over the update of personalized data, avoiding unnecessary errors. This design enables the system to continuously learn and accumulate the user's real cooking habits, thereby continuously optimizing personalized cooking guidance and improving user experience.

[0068] Preferably, the energy detection unit 202 is a current sampling unit, a voltage sampling unit, or a frequency detection unit; the current sampling unit is used to collect current data of the LC resonance circuit 106; the voltage sampling unit is used to collect voltage data of the LC resonance circuit 106; the frequency detection unit is used to collect resonance frequency data of the LC resonance circuit 106. Correspondingly, the energy information includes current data, voltage data, or resonance frequency data of the LC resonance circuit 106.

[0069] Specifically, the energy detection unit 202 can be configured in multiple forms to adapt to different detection needs. When the energy detection unit 202 is a current sampling unit, its main function is to monitor the current size and waveform in the LC resonance circuit 106 in real time. The implementation of this current sampling unit can include using a Hall effect sensor for non-contact current measurement, or indirectly obtaining current information by connecting a low-resistance sampling resistor in series in the circuit and then measuring the voltage drop across the resistor. Current data is one of the important parameters reflecting the energy state of the LC resonance circuit 106, and by collecting current data, the load condition and energy transmission efficiency of the circuit can be intuitively understood. When the energy detection unit 202 is a voltage sampling unit, its main function is to monitor the voltage size and waveform across the LC resonance circuit 106 in real time. The implementation of this voltage sampling unit can include using a voltage dividing resistor network to reduce the high voltage to a range acceptable to the microcontroller, or using an isolation amplifier for voltage isolation and sampling. Voltage data, together with current data, constitutes the energy information of the LC resonance circuit 106, and by collecting voltage data, the working state and power output of the circuit can be evaluated. When the energy detection unit 202 is a frequency detection unit, its main function is to monitor the resonance frequency of the LC resonance circuit 106 in real time. The implementation of this frequency detection unit can include using a phase-locked loop (PLL) circuit to track changes in resonance frequency, or extracting frequency components by performing Fourier transform (FFT) analysis on the voltage or current signal of the LC resonance circuit 106. Resonance frequency is a key characteristic parameter of the LC resonance circuit 106, which directly affects the efficiency and stability of energy transmission. By detecting resonance frequency data, it can be determined whether the LC resonance circuit 106 is in the best working state, and frequency adjustment can be made as needed. Finally, the energy information can include one or more of the current data, voltage data, or resonance frequency data of the LC resonance circuit 106, and these information is the basis for intelligent control by the master control chip 102, providing the induction cooker with multi-dimensional and more comprehensive circuit state perception capabilities.

[0070] The scheme of the present application provides various implementations of the energy detection unit 202, so that the intelligent induction cooker system can flexibly select and configure the energy information collection mode according to actual needs. Specifically, the energy detection unit 202 can be configured as a current sampling unit, a voltage sampling unit, or a frequency detection unit, each of which is responsible for collecting current data, voltage data, or resonance frequency data of the LC resonance circuit 106. These collected data collectively constitute the energy information and are reported to the master chip 102. The master chip 102 uses these multi-dimensional and more accurate energy information, combined with the pot temperature detected by the temperature detection unit 201, to more accurately monitor whether the pot is placed and whether the food is placed during cooking. For example, when the pot is placed, the load of the LC resonance circuit 106 will change significantly, causing the current, voltage, or resonance frequency data to produce identifiable characteristic changes; when the food is placed in the pot, the temperature of the pot and the energy transmission characteristics of the LC resonance circuit 106 will also change, which can be captured by the energy detection unit 202 and the temperature detection unit 201. In this way, the master chip 102 can make judgments based on more comprehensive and accurate energy information, thereby improving the accuracy and reliability of the system's perception of the cooking state. This diverse energy information collection capability enables the system to maintain efficient and accurate monitoring capabilities when faced with different types of pots and different cooking scenarios, effectively solving the problem of incomplete or inaccurate energy information collection that may be caused by traditional single detection methods.

[0071] In some embodiments, see Figure 5 , the master chip 102, when monitoring whether the pot is placed, performs: Under the preset operating parameter condition, the energy information collected by the energy detection unit 202 is obtained as the observed energy information; Compare the observed energy information with the reference energy information to determine whether the pot is placed; the reference energy information is the standard energy information when no pot is placed under the preset operating parameter condition.

[0072] Among them, the preset operating parameter condition refers to a standardized and controllable working state of the system when monitoring the placement of the pot. This can include setting the output power, working frequency, excitation mode of the coil disc 104, etc. of the induction cooker to a fixed value. For example, the induction cooker can be set to 100W power and 150kHz frequency for short-time excitation to obtain stable energy information. By setting the preset operating parameter condition, the interference caused by changes in operating parameters on energy information collection can be eliminated, ensuring the comparability of each monitoring result.

[0073] When the pot is placed on the induction cooker, the electromagnetic coupling characteristics of the LC resonant circuit 106 will change, resulting in a significant change in energy information. For example, when the pot is placed, the load of the LC resonant circuit 106 increases, the amplitude of the current or voltage changes, and the resonant frequency may also shift. These collected real-time energy information is used as observation energy information, providing an objective data basis for subsequent judgment.

[0074] The reference energy information refers to the standard energy information measured without placing a pot under the same preset operating parameter conditions as the observation energy information. This reference value can be calibrated when the induction cooker is shipped and stored in the memory module 3, or self-calibrated each time it is started. For example, under the preset operating parameter conditions, when there is no pot placed on the induction cooker coil disc 104, the current, voltage or resonant frequency data collected by the energy detection unit 202 can be recorded as the standard reference value under the no-pot condition.

[0075] Comparing the observation energy information with the reference energy information to determine whether a pot is placed refers to the master control chip 102 comparing the two energy information through an algorithm. The comparison method can include calculating the difference, ratio or correlation between the two. For example, an energy information difference threshold can be set, and if the difference between the observation energy information and the reference energy information exceeds the threshold, it is determined that a pot has been placed; otherwise, it is determined that a pot has not been placed. This comparison method based on a standard reference value effectively avoids the misjudgment that a single threshold value may cause, improving the accuracy and robustness of the monitoring.

[0076] Through the above technical solutions, the application solves the problem of insufficient precision in pot state monitoring of traditional induction cookers, avoids the heating safety hazards or energy waste caused by misjudgment, provides an accurate prerequisite for subsequent intelligent cooking guidance, and improves the intelligent level of the system and the user experience.

[0077] Preferably, the reference Figure 6 When monitoring whether food materials are placed, the master control chip 102 can perform: obtain a reference temperature change curve and a reference energy information change curve of the current cooking step; the reference temperature change curve reflects the change of the pot temperature before and after the food materials are placed, and the reference energy information change curve reflects the change of the energy information before and after the food materials are placed; extract a temperature sequence of the pot temperature using a sliding window method, and calculate the matching degree of the temperature sequence and the reference temperature change curve to determine whether food materials are placed, obtaining a first judgment result; The energy information sequence is extracted from the energy information in a sliding window manner, and a matching degree of the energy information sequence and the reference energy information change curve is calculated to determine whether the food material is put in, to obtain a second determination result; The first determination result and the second determination result are comprehensively determined to finally determine whether the food material is put in.

[0078] Specifically, obtaining the reference temperature change curve and the reference energy information change curve of the current cooking step means that the master control chip 102 obtains preset data reflecting the expected change mode of the pot temperature and the energy information of the LC resonant circuit 106 after the food material is put in the specific cooking step. These reference curves can be pre-stored in the memory module 3 as part of the recipe standard making process information, and are extracted from the memory module 3 by the AI interaction module 5 according to the current cooking step and provided to the master control chip 102; or these reference curves can also be generated or obtained in real time by a cloud AI large model, when the AI interaction module 5 calls the cloud AI large model to generate a recipe, the large model simultaneously provides or generates these reference curves.

[0079] Extracting the temperature sequence of the pot temperature in a sliding window manner means that the master control chip 102 periodically obtains the pot temperature data from the temperature detection unit 201, and slides a fixed size “window” on the continuous temperature data stream, and extracts the data in the window to form a temperature sequence each time. For example, the master control chip 102 can sample the pot temperature once per second, and use the last 10 seconds of data as a sliding window to form a sequence containing 10 temperature values. The step length of the sliding window can be adjusted according to the dynamic nature of the cooking stage, and a smaller step length and more frequent sampling can be used in the sensitive stage of the expected food material to improve the response speed.

[0080] Calculating the matching degree of the temperature sequence and the reference temperature change curve to determine whether the food material is put in, to obtain the first determination result, means that the master control chip 102 compares the similarity of the real-time extracted temperature sequence and the preset reference temperature change curve by algorithm. For example, the Euclidean distance, correlation coefficient or dynamic time warping (DTW) algorithm can be used to calculate the matching degree, and the higher the matching degree, the more the real-time temperature change conforms to the expectation. When the calculated matching degree reaches or exceeds the preset threshold, the master control chip 102 determines that the pot temperature change conforms to the characteristics of putting in the food material, thereby obtaining the first determination result.

[0081] The energy information sequence extracted by the sliding window method is that the master control chip 102 periodically acquires the energy information (for example, current data, voltage data or resonance frequency data) of the LC resonance circuit 106 from the energy detection unit 202, and also uses the sliding window method to form an energy information sequence with the energy information data in the recent period. For example, the energy detection unit 202 can collect energy information at a higher frequency (such as once every 0.1 seconds), and the master control chip 102 forms a sequence containing 20 energy information values with the data in the last 2 seconds as a sliding window. The size and step of the sliding window can be configured independently of the sliding window of the temperature sequence to adapt to the different change characteristics and response speeds that the energy information may have.

[0082] The matching degree of the energy information sequence and the reference energy information change curve is calculated to determine whether the food is put in, and the second judgment result is obtained, which means that the master control chip 102 compares the similarity of the real-time extracted energy information sequence and the preset reference energy information change curve by algorithm. For example, when the food is put into the pot, the impedance of the pot will change, causing the current or voltage of the LC resonance circuit 106 to fluctuate in a specific pattern, and the matching degree of the real-time energy information sequence and this fluctuation pattern is calculated to determine. When the calculated matching degree reaches or exceeds the preset threshold, the master control chip 102 determines that the energy change is consistent with the characteristics of putting in food, thereby obtaining the second judgment result.

[0083] The first judgment result and the second judgment result are combined to finally determine whether the food is put in, which means that the master control chip 102 combines the two independent judgment results based on temperature and energy to improve the accuracy and robustness of the judgment. For example, the logic "and" judgment can be used, that is, only when the first judgment result and the second judgment result both indicate that the food has been put in, it is finally determined that the food has been put in. In addition, the importance weight of temperature and energy information in different cooking stages can also be combined for comprehensive judgment, for example, in one cooking step, the importance weight of temperature is greater, then the first judgment result is used as the standard, otherwise the second judgment result is used as the standard.

[0084] The scheme of the present application effectively solves the accuracy problem caused by environmental interference when the food material is put into the monitoring by introducing a reference curve matching and comprehensive judgment mechanism, and improves the robustness and reliability of the system. Specifically, the reference temperature change curve and the reference energy information change curve of the current cooking step are obtained, which provides a standardized expected change mode, reduces the interference of non-food material factors on the monitoring, and ensures that the judgment is based on historical or standard data; the temperature sequence of the pot temperature is extracted in a sliding window manner, and the matching degree of the temperature sequence with the reference temperature change curve is calculated, which can analyze the temperature dynamic change trend in real time, quantify the deviation between the actual and the expected, accurately identify the timing of putting in the food material, and obtain a first judgment result; the energy information sequence of the energy information is extracted in a sliding window manner, and the matching degree of the energy information sequence with the reference energy information change curve is calculated, which can capture the trend of energy change, reduce the influence of noise, enhance the stability of the judgment, and obtain a second judgment result; the first judgment result and the second judgment result are comprehensively combined, the information in the two dimensions of temperature and energy is fused, the limitations of single index are avoided, and finally the high-precision determination of whether to put in the food material is realized.

[0085] In some preferred embodiments, when the AI interaction module 5 sends the demand instruction generated according to the food material information and the taste information to the cloud platform to call the cloud AI large model, and obtains at least one recipe and its standard making process information matched with the food material information and the taste information fed back by the cloud AI large model, the AI interaction module 5 can also match the recipe and its personalized making process information of the corresponding taste in the personalized cooking information in the memory module 3 according to the taste information (for example, the personalized cooking information in the memory module 3 also contains the taste information corresponding to each recipe, and the matching is performed by comparing the real-time input taste information with the taste information in the personalized cooking information), and send all the matched recipes and their personalized making process information (hereinafter referred to as reference matching information) to the cloud platform, so that the cloud AI large model generates the recipe by referring to the reference matching information when calling the cloud AI large model; so that the recipe recommended by the cloud AI large model is more in line with the user's taste, and more personalized service is provided for the user.

[0086] The above only describes the embodiments of the present application and does not limit the protection scope of the present application. For those skilled in the art, the present application can have various modifications and changes. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. An intelligent induction cooker system, characterized in that, include: The main circuit (1) of the induction cooker includes a power supply circuit (101), a main control chip (102), a power module (103), and an LC resonant circuit (106) composed of a coil (104) and a resonant capacitor (105). The monitoring module (2) includes a temperature detection unit (201) and an energy detection unit (202) electrically connected to the main control chip (102). The temperature detection unit (201) is used to detect the temperature of the cookware, and the energy detection unit (202) is used to detect the energy information of the LC resonant circuit (106). Memory module (3) is used to store the user's personalized cooking information; The voice interaction module (4) includes a voice broadcasting device (401) and a voice receiving device (402). The AI ​​interaction module (5) supports network communication and is electrically connected to the main control chip (102), the memory module (3) and the voice interaction module (4); The main control chip (102) is used to monitor whether the pot is put in and whether the ingredients are put in during the cooking process based on the energy information and the pot temperature, and to report the monitoring results and the pot temperature as reporting information to the AI ​​interaction module (5). The AI ​​interaction module (5) is used to perform: Based on the ingredient and flavor information input by the user through the voice interaction module (4), the corresponding recipe is generated by calling the cloud-based AI big model; Recipe information feedback and confirmation are provided through the voice interaction module (4); Based on the recipe confirmed by the user and the reported information, the user is guided step by step to cook through the voice interaction module (4), and the personalized cooking information in the memory module (3) is updated according to the cooking process information.

2. The intelligent induction cooker system according to claim 1, characterized in that, The power module (103) includes a silicon carbide MOSFET (107) and its driving module (108); the driving module (108) can control the gate of the silicon carbide MOSFET (107) to generate a switching frequency higher than 20kHz, and can provide the silicon carbide MOSFET (107) with a DC driving voltage of 18V-22V, and can provide the silicon carbide MOSFET (107) with a DC gate turn-off voltage of -5V to -3V; the main control chip (102) can generate a control output frequency of 20kHz-250kHz, and the feedback response speed reaches more than 150kHz.

3. The intelligent induction cooker system according to claim 1, characterized in that, When the AI ​​interaction module (5) generates a corresponding recipe by calling the cloud-based AI big model based on the ingredient and flavor information input by the user through the voice interaction module (4), it performs the following: The voice interaction module (4) monitors the surrounding sound information and analyzes whether the sound information contains a wake-up command. When the sound information contains a wake-up command, the user's ingredient information and flavor information input by voice are obtained through the voice interaction module (4); Based on the ingredient information and the flavor information, a demand instruction is generated and sent to the cloud platform to invoke the cloud AI model, and at least one recipe and its standard production process information that match the ingredient information and the flavor information are obtained from the cloud AI model.

4. The intelligent induction cooker system according to claim 1, characterized in that, The personalized cooking information includes recipes that the user has previously made and their personalized preparation process information; the personalized preparation process information differs from the standard preparation process information of the corresponding recipe in that ingredients and / or seasonings are added, subtracted, and / or replaced. When the AI ​​interaction module (5) guides the user step-by-step in cooking based on the recipe confirmed by the user and the reported information, it executes the following: Determine whether the personalized cooking information in the memory module (3) contains a recipe confirmed by the user; If not included, the standard production process information of the recipe confirmed by the user shall be used as the valid production process information; otherwise, the corresponding personalized production process information shall be extracted from the recognition memory module (3) as the valid production process information. Based on the effective production process information and the reported information, the user is guided step by step to cook using the voice interaction module (4).

5. The intelligent induction cooker system according to claim 4, characterized in that, The steps of guiding the user to cook step by step through the voice interaction module (4) based on the effective production process information and the reported information include: The preparation information is broadcast through the voice interaction module (4); the preparation information includes the types of ingredients, the amount of ingredients, the types of seasonings, the amount of seasonings, and the pre-processing methods of various ingredients; After receiving the preparation completion instruction input by the user through the voice interaction module (4), the main control chip (102) is instructed to monitor whether the pot is put in. If the monitoring result indicates that the pot has been placed in the cookware, then extract the material addition information, operation information, cooking temperature information and stage end information for each cooking step from the effective production process information; In each cooking step, the corresponding material addition information and operation information are broadcast, and after the reported information indicates that the ingredients are put in, the main control chip (102) is instructed to adjust the power of the LC resonant circuit (106) according to the cooking temperature information of the current cooking step and the pot temperature in the reported information. When the user determines that the current cooking step has been completed based on the stage end information and inputs the completion confirmation information through the voice interaction module (4), the user can proceed to the next cooking step or end the cooking process.

6. The intelligent induction cooker system according to claim 5, characterized in that, If no ingredients are detected within a preset time after the corresponding material addition and operation information is broadcast during each cooking step, a warning will be issued and the machine will be shut down.

7. The intelligent induction cooker system according to claim 5, characterized in that, The memory module (3) includes a temporary storage unit (301) and a removable local storage unit (302). The cooking process information includes material adjustment information; the material adjustment information includes information on the addition, subtraction, and / or substitution of ingredients and / or seasonings; After the AI ​​interaction module (5) receives the user's instruction to complete the preparation of materials via voice input, and before instructing the main control chip (102) to monitor whether to put the pot in, it also performs the following: obtains material adjustment information through the voice interaction module (4); When the AI ​​interaction module (5) updates the personalized cooking information in the memory module (3) based on the cooking process information, it performs the following: Based on the material adjustment information and the effective production process information, the latest personalized production process information for this cooking recipe is generated; The recipe for this cooking and the latest personalized cooking process information are stored as personalized cooking information to be stored in the temporary storage unit (301). The voice interaction module (4) confirms with the user whether they need to update the personalized cooking information in the memory module (3); If the user confirms that the personalized cooking information in the memory module (3) needs to be updated, the personalized cooking information to be stored is transferred to the local storage unit (302) for personalized cooking information update.

8. The intelligent induction cooker system according to claim 1, characterized in that, The energy detection unit (202) is a current sampling unit, a voltage sampling unit, or a frequency detection unit; the current sampling unit is used to collect the current data of the LC resonant circuit (106); the voltage sampling unit is used to collect the voltage data of the LC resonant circuit (106); and the frequency detection unit is used to collect the resonant frequency data of the LC resonant circuit (106). Correspondingly, the energy information includes current data, voltage data, or resonant frequency data of the LC resonant circuit (106).

9. The intelligent induction cooker system according to claim 1, characterized in that, When the main control chip (102) monitors whether a pot has been placed in the pan, it executes the following: Under preset operating parameters, the energy information collected by the energy detection unit (202) is acquired as the energy information for observation; Compare the observed energy information with the reference energy information to determine whether to put the pot in; The reference energy information is the standard energy information under the preset operating parameters when no cookware is placed in the pot.

10. The intelligent induction cooker system according to claim 1, characterized in that, When the main control chip (102) monitors whether food has been added, it executes the following: Obtain the reference temperature change curve and reference energy information change curve for the current cooking step; the reference temperature change curve reflects the change in the pot temperature before and after the ingredients are added, and the reference energy information change curve reflects the change in energy information before and after the ingredients are added. The temperature sequence of the cookware is extracted using a sliding window method, and the matching degree between the temperature sequence and the reference temperature change curve is calculated to determine whether to put in food, thus obtaining a first judgment result. The energy information sequence is extracted using a sliding window method, and the matching degree between the energy information sequence and the reference energy information change curve is calculated to determine whether to add food and obtain a second judgment result. Based on the combined results of the first and second judgments, a final decision is made as to whether or not to add ingredients.

Images