Menu recommendation method and system, cooking equipment and storage medium

Abstract

The invention relates to the technical field of intelligent cooking, and discloses a menu recommendation method and system, cooking equipment and a storage medium, the cooking equipment end obtains cooking behavior data and food material information, and sends the cooking behavior data and the food material information to a cloud end; the cloud end receives food material information and cooking behavior data sent by a plurality of cooking equipment ends bound with a user, and stores the food material information and the cooking behavior data in a data storage device; the cloud end obtains user health state information submitted by a user through a mobile end, and integrates the user health state information, food material information extracted from a data storage device in a preset period and cooking behavior data into a multi-dimensional feature vector; according to the method and the system, the user data are input into a machine learning model for iterative training, and a menu recommendation result is output, so that recent cooking habits of the user, cooked food materials and personal data of the user are compared in a machine learning mode, and a private menu customization effect is obtained.

Description

Technical Field

[0001] The present invention relates to the field of intelligent cooking technology, and in particular to a recipe recommendation method, system, cooking device and storage medium. Background Art

[0002] Although relevant smart cooking devices have recipe recommendation functions, most of them only make recommendations based on preset programs or simple cuisine, taste and other factors, and fail to dynamically link cooking behavior with user health data, resulting in the recommended recipes being unable to meet personalized nutritional needs. Summary of the Invention

[0003] In view of this, the present invention provides a recipe recommendation method, system, cooking device and storage medium to solve the problem that cooking behavior is not dynamically associated with user health data, resulting in the recommended recipes being unable to meet personalized nutritional needs.

[0004] In a first aspect, the present invention provides a recipe recommendation method, which is applied to the cloud, and the method includes: receiving ingredient information and cooking behavior data sent by multiple cooking device terminals bound to the user, and saving the ingredient information and cooking behavior data in a data storage device; obtaining user health status information submitted by the user through a mobile terminal; integrating the user health status information, ingredient information and cooking behavior data within a preset period extracted from the data storage device into a multidimensional feature vector; inputting the multidimensional feature vector into a machine learning model for iterative training, and outputting a recipe recommendation result.

[0005] The recipe recommendation method provided by the present invention monitors the cooking process through the cooking device end, obtains cooking behavior data and ingredient information, and sends the cooking behavior data and ingredient information to the cloud; the cloud receives the ingredient information and cooking behavior data sent by multiple cooking device ends bound to the user, and saves the ingredient information and cooking behavior data in a data storage device; the cloud obtains the user health status information submitted by the user through the mobile end, and integrates the user health status information, the ingredient information and cooking behavior data within a preset period extracted from the data storage device into a multidimensional feature vector; the cloud inputs the multidimensional feature vector into a machine learning model for iterative training, and outputs a recipe recommendation result, thereby realizing the comparison of the user's recent cooking habits, the cooked ingredients and the user's personal data through machine learning, and obtaining the effect of personalized recipe customization.

[0006] In an optional embodiment, the recipe recommendation result includes at least a recommended recipe set and recommendations for alternative ingredients corresponding to each recipe, and the method further includes: forwarding the recipe recommendation result to a mobile terminal so that the mobile terminal displays the recommended recipe set and the replacement function options corresponding to each recipe to the user; and, in response to the user triggering the replacement function option corresponding to the target recipe, displaying the recommendations for alternative ingredients corresponding to the target recipe to the user.

[0007] The present invention displays recommended recipes to users and provides an ingredient replacement function, so that users can intelligently replace ingredients based on their own preferences and ingredient availability, solve problems such as ingredient shortages, allergies or preferences, improve user experience, and intelligently replace corresponding ingredients according to user health indicators, thereby promoting diversity and innovation in health management.

[0008] In an optional embodiment, the recipe recommendation result also includes a recommended recipe set and recommended cooking equipment corresponding to each recipe, and the method further includes: analyzing the cooking functions required for each recipe in the recommended recipe set; determining the recommended cooking equipment corresponding to each recipe based on the cooking functions required for each recipe, the corresponding achievable cooking functions of all cooking equipment bound to the user, and the operating status of each cooking equipment; forwarding the recommended recipe set and the recommended cooking equipment corresponding to each recipe to a mobile terminal, so that the mobile terminal displays the recommended recipe set and the recommended cooking equipment corresponding to each recipe to the user.

[0009] When recommending recipes, the present invention also recommends cooking equipment that the user already owns, avoiding the user being unable to try recipes due to not knowing the functions of the cooking equipment. It can also give priority to recommending idle equipment based on the operating status of the equipment, ensuring that the user does not need to wait for the equipment to be idle.

[0010] In an optional embodiment, the ingredient information includes at least the type of ingredients and the weight of the ingredients, and the method further includes: determining the user's nutritional intake data based on the type of ingredients and the weight of the ingredients cooked within the preset period; comparing the user's nutritional intake data with the nutritional intake standard range corresponding to the user's health status to obtain a nutritional intake comparison result; based on the nutritional intake comparison result, determining nutritional intake balance recommendations and corresponding ingredient recommendations; forwarding the nutritional intake balance recommendations and corresponding ingredient recommendations to the mobile terminal, so that the mobile terminal displays the nutritional intake balance recommendations and corresponding ingredient recommendations to the user.

[0011] The present invention can calculate the user's nutritional intake data through food type and weight data, and compare it with the nutritional standards corresponding to the user's health status, to achieve accurate early warning of nutritional imbalance risks, recommend specific ingredients based on nutritional imbalance problems, actively intervene in the user's health status, and cultivate scientific eating habits.

[0012] In a second aspect, the present invention provides a recipe recommendation method, which is applied to a cooking device end. The method includes: monitoring the cooking process, obtaining cooking behavior data and ingredient information, and sending the cooking behavior data and ingredient information to the cloud, so that the cloud receives the ingredient information and cooking behavior data sent by all cooking device ends bound to the user, and saves them in a data storage device, and integrates the user health status information, the ingredient information and cooking behavior data within a preset period extracted from the data storage device into a multidimensional feature vector, inputs the multidimensional feature vector into a machine learning model for iterative training, and outputs a recipe recommendation result, wherein the user health status information is submitted by the user through the mobile end.

[0013] In an optional embodiment, sending the cooking behavior data and ingredient information to the cloud includes: monitoring the current device system time; when the current device system time is consistent with the preset data upload time, sending the acquired cooking behavior data and ingredient information to the cloud, and the preset data upload time is determined by the period with the lowest power consumption within a preset cycle.

[0014] The present invention chooses to upload data during the low electricity consumption period when users are inactive, which will not interfere with the normal use of users and avoid overlapping with peak electricity consumption, thereby reducing power load pressure, overall energy consumption and data packet loss rate.

[0015] In an optional embodiment, sending the cooking behavior data and ingredient information to the cloud includes: encrypting the cooking behavior data and ingredient information using a preset encryption algorithm; and sending the encrypted cooking behavior data and ingredient information to the cloud using a preset communication protocol.

[0016] In a third aspect, the present invention provides a recipe recommendation system, which includes a cooking device end bound to a user, a cloud end, and a mobile end, wherein the cooking device end monitors the cooking process, obtains cooking behavior data and ingredient information, and sends the cooking behavior data and ingredient information to the cloud end; the cloud end receives ingredient information and cooking behavior data sent by multiple cooking device ends bound to the user, and saves the ingredient information and cooking behavior data in a data storage device; the cloud end obtains user health status information submitted by the user through the mobile end, and integrates the user health status information, ingredient information and cooking behavior data within a preset period extracted from the data storage device into a multidimensional feature vector; the cloud end inputs the multidimensional feature vector into a machine learning model for iterative training, and outputs a recipe recommendation result.

[0017] The recipe recommendation system provided by the present invention monitors the cooking process on the cooking device side, obtains cooking behavior data and ingredient information, and sends the cooking behavior data and ingredient information to the cloud; the cloud side receives the ingredient information and cooking behavior data sent by multiple cooking device sides bound to the user, and stores the ingredient information and cooking behavior data in a data storage device; the cloud side obtains the user health status information submitted by the user through the mobile side, and integrates the user health status information, the ingredient information and cooking behavior data within a preset period extracted from the data storage device into a multidimensional feature vector; the cloud side inputs the multidimensional feature vector into a machine learning model for iterative training, and outputs a recipe recommendation result, thereby realizing the comparison of the user's recent cooking habits, the cooked ingredients and the user's personal data through machine learning, and obtaining the effect of personalized recipe customization.

[0018] In a fourth aspect, the present invention provides a cooking device, comprising a cooking device end, wherein the cooking device end comprises: a memory and a processor, the memory and the processor being communicatively connected to each other, computer instructions being stored in the memory, and the processor executing the computer instructions to execute the recipe recommendation method of the above-mentioned second aspect or any corresponding embodiment thereof.

[0019] In an optional embodiment, the cooking device further includes: a cooking data acquisition device, which includes at least a power acquisition device, a weight acquisition device, a temperature acquisition device and an image acquisition device, wherein the power acquisition device is used to obtain the operating status and operating time of the cooking device, the weight acquisition device is used to measure the weight of the ingredients, the temperature acquisition device is used to monitor temperature changes during the cooking process, and the image acquisition device is used to monitor the types of ingredients being cooked.

[0020] In a fifth aspect, the present invention provides a computer-readable storage medium having computer instructions stored thereon, the computer instructions being used to enable a computer to execute the recipe recommendation method of the above-mentioned first aspect or any corresponding embodiment thereof, or to execute the recipe recommendation method of the above-mentioned second aspect or any corresponding embodiment thereof. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the specific embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0022] Figure 1 is a structural block diagram of a recipe recommendation system according to an embodiment of the present invention;

[0023] Figure 2 is a flowchart illustrating an example of a method for executing a recipe recommendation on the cloud according to an embodiment of the present invention;

[0024] Figure 3 is a schematic diagram of the interaction process of a recipe recommendation system according to an embodiment of the present invention;

[0025] Figure 4 is a flowchart illustrating a recipe recommendation method according to an embodiment of the present invention;

[0026] Figure 5 is a structural block diagram of a cooking device according to an embodiment of the present invention;

[0027] Figure 6 is a structural block diagram of a recipe recommendation device according to an embodiment of the present invention;

[0028] Figure 7 is a structural block diagram of another recipe recommendation device according to an embodiment of the present invention;

[0029] Figure 8 Schematic diagram of the hardware structure of the cooking device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0030] To make the purpose, technical solutions, and advantages of the embodiments of the present invention more clear, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without making creative efforts shall fall within the scope of protection of the present invention.

[0031] While current smart cooking devices on the market offer recipe recommendations, most rely solely on preset programs or simple categories like cuisine and flavor. Some devices generate preference reports by recording user data, but fail to dynamically link cooking behavior with user health data, resulting in recommended recipes that fail to meet personalized nutritional needs. Furthermore, while health management apps allow for the input of physical data, they lack integration with cooking device data and offer only general dietary recommendations, lacking specific guidance for actual cooking behavior.

[0032] Based on the above problems, the embodiment of the present invention provides a recipe recommendation system, such as Figure 1As shown, the system includes a cooking device terminal 1 bound to the user, a cloud terminal 2 and a mobile terminal 3. Specifically, the cooking device terminal 1 monitors the cooking process, obtains cooking behavior data and ingredient information, and sends the cooking behavior data and ingredient information to the cloud terminal 2; the cloud terminal 2 receives the ingredient information and cooking behavior data sent by multiple cooking device terminals 1 bound to the user, and saves the ingredient information and cooking behavior data in a data storage device; the cloud terminal 2 obtains the user health status information submitted by the user through the mobile terminal 3, and integrates the user health status information, the ingredient information and cooking behavior data within a preset period extracted from the data storage device into a multidimensional feature vector; the cloud terminal 2 inputs the multidimensional feature vector into a machine learning model for iterative training, and outputs a recipe recommendation result.

[0033] The embodiment of the present invention does not limit the type of mobile terminal 3, as long as it has an interactive interface and can realize data transmission with the cloud 2. For example, the mobile terminal 3 is a mobile phone, etc., which has a health management APP installed. The user uploads his or her health status data through the health management APP, and then the mobile terminal 3 uploads the user's health status data to the cloud 2. The mobile terminal 3 can also be a smart bracelet for health monitoring, a physical health data monitoring device and other equipment, which can monitor the user's health status data and upload the monitored user's health status data to the cloud 2 via WIFI or Bluetooth. The user's health status data may include the user's basic information, age, gender, weight, and physical precautions, etc., just as an example.

[0034] The cooking device end 1 of the embodiment of the present invention can be a single cooking device or all devices that have participated in cooking and are bound to the user. However, considering that a single cooking device can only send cooking data that is adapted to itself (for example, an air fryer can only send information on ingredients such as fried chicken wings and French fries, resulting in the misjudgment of the user's single diet type), and when recommending subsequent cooking devices, only recipes that are adapted to the function of a single device can be recommended (for example, it is impossible to know the types of other available devices and only recommend food that can be made in an air fryer); the data fusion solution of multiple cooking devices (such as steam ovens, stir-fry machines, juicers, etc.) can cover the full nutrient combination of each meal or day, can judge the overall nutritional balance, and avoid the omission of key nutrients in the data of a single device. When recommending recipes subsequently, the unique functions of different cooking devices can be combined to recommend multiple devices to collaborate to complete the cooking of a meal, breaking through the functional limitations of a single device and ensuring the balanced nutritional intake of the user. Therefore, this solution uses multiple devices bound to the user to perform recipe recommendation operations.

[0035] Each cooking device end 1 in the embodiment of the present invention can monitor the current cooking process when it detects that it is in the cooking operation state, and can obtain cooking behavior data and food information through the cooking data acquisition device. There is no limitation on the type of the cooking data acquisition device, and the data acquisition device installed in the actual cooking device is mainly used. Specifically, the cooking data acquisition device at least includes a power acquisition device, a weight acquisition device, a temperature acquisition device and an image acquisition device, wherein the power acquisition device can be a current sensor for monitoring the power changes of the cooking device in real time, and judging the working mode of the cooking device by analyzing the current fluctuation characteristics. For example, the power curve characteristics can be used to identify the cooking device in different working states and working modes such as preheating, heating, and insulation, that is, the preheating stage: at the beginning of the device starting to work, since the internal temperature of the device needs to be raised to the level required for work, the power consumption of the device is relatively high at this time, but as time goes by. As time goes by, the power will gradually decrease. On the power curve, this stage is usually manifested as a process of rapid decline from high power to a lower level; heating stage: when the device enters the heating stage, the power curve may show a relatively stable or slightly fluctuating state, which depends on the design and working mode of the device. For some devices, during the heating process, in order to maintain a certain heating rate, the power may be maintained at a relatively high level, or intermittent heating may be used, causing the power curve to show periodic fluctuations; insulation stage: when the device reaches the set temperature, it enters the insulation stage. At this time, the main task of the device is to maintain a constant temperature. In this stage, the power curve usually shows a lower and more stable level, because only a small amount of energy is required to compensate for heat loss. Sometimes, the device will also use pulsed heating to maintain the temperature, resulting in slight fluctuations in the power curve. This is just an example.

[0036] The weight acquisition device designed in the embodiments of the present invention can be a weight sensor installed inside the cooking device to monitor the amount of food loaded. The weight sensor uses high-precision weighing technology to accurately measure the weight of the food and output the food weight data in the form of a digital signal. The temperature acquisition device can be a temperature probe, which can be placed in a key position inside the cooking device to monitor temperature changes during the cooking process in real time and obtain a temperature curve. The temperature data acquisition accuracy must reach ±0.1°C to ensure the accuracy of temperature monitoring. The image acquisition device can be a camera that uses image recognition technology to detect the food cooked by the user and record the type of food. The cooking data acquisition device periodically records cooking behavior data and food information, including device operating status (operating mode, power value, operating time (the time from the start to the end of cooking); cooking parameters (temperature curve, food type, food weight, heating time (the total heating time of the complete cooking process, if any pause is stopped, only the heating time is counted)); user operation records (such as device start and stop times, temperature settings, and timer settings), etc., are just examples.

[0037] In the embodiment of the present invention, each cooking device terminal 1 can send the acquired cooking behavior data and ingredient information to the cloud 2 via built-in WIFI or Bluetooth. The cloud 2 is integrated with a machine learning model, which can generate recipe recommendation results based on the cooking behavior data and ingredient information sent by each cooking device terminal 1 and the user health status information submitted by the user through the mobile terminal 3. Specifically, there is no limitation on the type of machine learning model. Taking the prediction model based on gradient boosting ensemble learning (XGBoost) as an example, this model integrates multiple weak learners and can iteratively optimize model parameters based on the newly added multi-dimensional feature vector to adjust the recipe recommendation in real time. Considering that the more data input into the model, the higher the model accuracy, therefore, after the cloud 2 receives the cooking behavior data and ingredient information sent by each cooking device end 1, it can first save the data in the data storage device. When the model is iteratively trained based on the preset period, the cooking behavior data and ingredient information of the preset period are obtained from the data storage device, and the data and the user's health status data are used as multidimensional feature vectors to be input into the machine learning model for iterative training, and recipe recommendations are output. Among them, there is no limit on the preset period, such as model iterative training once a week. If the user usage frequency is low, the training iteration period can also be adjusted. This is just an example.

[0038] Specifically, the preset cycle is one week, for example. Figure 2As shown, the cloud 2 can obtain the ingredient information of the cooking behavior data sent by each cooking device end 1 in the previous week from the data storage device every Monday, and integrate it with the physical health status information submitted by the user into a multidimensional feature vector, and input the multidimensional feature vector into the machine learning model for iterative training, optimize the model parameters to improve the recommendation accuracy, and finally, output the recipe recommendation, wherein the machine learning model can output the recommended recipe queue within a preset period, for example, generate a recommended recipe queue for the next 7 days, including daily main dish, side dish and soup recommendations, to achieve weekly cycle recipe recommendations.

[0039] The recipe recommendation system provided by the present invention monitors the cooking process on the cooking device side, obtains cooking behavior data and ingredient information, and sends the cooking behavior data and ingredient information to the cloud; the cloud side receives the ingredient information and cooking behavior data sent by multiple cooking device sides bound to the user, and stores the ingredient information and cooking behavior data in a data storage device; the cloud side obtains the user health status information submitted by the user through the mobile side, and integrates the user health status information, the ingredient information and cooking behavior data within a preset period extracted from the data storage device into a multidimensional feature vector; the cloud side inputs the multidimensional feature vector into a machine learning model for iterative training, and outputs a recipe recommendation result, thereby realizing the comparison of the user's recent cooking habits, the cooked ingredients and the user's personal data through machine learning, and obtaining the effect of personalized recipe customization.

[0040] In an optional embodiment, the cooking device end 1 monitors the current device system time; when the current device system time is consistent with the preset data upload time, the acquired cooking behavior data and ingredient information are sent to the cloud 2. The preset data upload time is determined by the period with the lowest power consumption within the preset cycle.

[0041] After acquiring cooking behavior data and ingredient information, the cooking device 1 of the embodiment of the present invention may first cache the acquired data in a local storage device and then monitor the current device system time in real time. When the current device system time coincides with a preset data upload time, the cooking behavior data and ingredient information cached in the local storage device may be sent to the cloud 2. After determining that the data has been successfully sent, the data cached in the local storage device may be deleted. The preset data upload time may be determined by the period with the lowest power consumption within a preset period. The preset period may be set based on factors such as data transmission consumption and the frequency of use of the cooking device. For example, taking a day as an example, the period with the lowest power consumption may be selected as the data upload time. For example, the power consumption data of all periods of each day in a week may be counted to filter out the period with the lowest power consumption. Then, the period with the most number of periods with the lowest power consumption or the middle period within the range of the periods with the lowest power consumption may be selected as the data upload time. For example, early morning is the low power consumption period. In this case, the cooking device 1 may upload the cooking behavior data and ingredient information cached in the local storage device to the cloud 2 at dawn to avoid affecting the normal use of the user.

[0042] The present invention chooses to upload data during the low electricity consumption period when users are inactive, which will not interfere with the normal use of users and avoid overlapping with peak electricity consumption, thereby reducing power load pressure, overall energy consumption and data packet loss rate.

[0043] Specifically, the cooking device 1 uses a preset encryption algorithm to encrypt the cooking behavior data and ingredient information; and uses a preset communication protocol to send the encrypted cooking behavior data and ingredient information to the cloud 2.

[0044] The cooking device end 1 of the embodiment of the present invention can use a preset encryption algorithm to encrypt the cooking behavior data and ingredient information to ensure the security of data transmission. There is no limitation on the encryption algorithm. Taking AES-256 as an example, the passenger uses a preset communication protocol to send the encrypted cooking behavior data and ingredient information to the cloud 2. The communication protocol can be Message Queuing Telemetry Transport (MQTT) as an example. It has the characteristics of low bandwidth and high reliability, which is suitable for the data transmission needs of IoT devices.

[0045] In an optional embodiment, the cloud 2 forwards the recipe recommendation results to the mobile terminal 3, so that the mobile terminal 3 displays the recommended recipe set and the replacement function options corresponding to each recipe to the user; and, in response to the user triggering the replacement function option corresponding to the target recipe, the alternative ingredients corresponding to the target recipe are recommended to the user.

[0046] The recipe recommendation results include at least a set of recommended recipes and recommendations for alternative ingredients corresponding to each recipe.

[0047] The machine learning model of the embodiment of the present invention can construct an ingredient knowledge graph based on the nutrition database or the user's historical replacement behavior, including ingredient attributes and the substitutable relationship between each ingredient, such as direct substitution of similar ingredients (beef and lamb), substitution of ingredients with the same function (butter and coconut oil), and substitution of ingredients with similar nutrition (spinach and kale). After generating recipe recommendations based on cooking behavior data, ingredient information and user health status information, other ingredients that can replace the ingredients used in the current recipe in the recommended recipe set can be found from the ingredient knowledge graph. It is necessary to ensure that the nutritional composition of the alternative is close to that of the original recipe to ensure the user's nutritional balance; subsequently The cloud 2 can forward the recipe recommendation results to the mobile terminal 3. The mobile terminal 3 can customize the recipe list and display recommended healthy recipes. The user can click to view the specific recipe. At the same time, the mobile terminal 3 can set a corresponding replacement function option on each recommended recipe. In response to the user triggering the replacement function option corresponding to the target recipe, the alternative ingredients corresponding to the target recipe can be recommended to the user. There is no limitation on the form of the replacement function option. For example, it can be a replacement suggestion button. After the user clicks the replacement suggestion button, the alternative ingredients are displayed to the user. It can also be displayed to the user in response to the voice information output by the user to view the replacement ingredients. This is just an example.

[0048] The present invention displays recommended recipes to users and provides an ingredient replacement function, so that users can intelligently replace ingredients based on their own preferences and ingredient availability, solve problems such as ingredient shortages, allergies or preferences, improve user experience, and intelligently replace corresponding ingredients according to user health indicators, thereby promoting diversity and innovation in health management.

[0049] In an optional embodiment, the cloud 2 can also forward the cooking behavior data sent by the cooking device 1 to the mobile terminal 3. The mobile terminal 3 can display the user's cooking data in the form of charts, including but not limited to cooking frequency, power consumption, cooking time, etc., among which, it can also support a variety of chart forms (such as line charts, bar charts) for users to choose from, so that users can intuitively perceive cooking behavior, identify high-energy-consuming operations, and adjust habits to save energy.

[0050] In an optional embodiment, the cloud 2 analyzes the cooking functions required for each recipe in the recommended recipe set; determines the recommended cooking equipment corresponding to each recipe based on the cooking functions required for each recipe, the corresponding achievable cooking functions of all cooking equipment bound to the user, and the operating status of each cooking equipment; and forwards the recommended recipe set and the recommended cooking equipment corresponding to each recipe to the mobile terminal 3, so that the mobile terminal 3 displays the recommended recipe set and the recommended cooking equipment corresponding to each recipe to the user.

[0051] In the embodiment of the present invention, the cloud 2 generates a recommended recipe set through a machine learning model, analyzes the cooking functions required for each recipe in the recommended recipe set, obtains a list of devices bound to the user, detects the operating status of each device in the device list (such as online, idle, and faulty), filters out devices in an idle state, and compares the achievable cooking functions corresponding to the devices in the idle state with the cooking functions required for each recipe. The cooking energy consumption of each cooking device and the user's preference for cooking equipment can also be comprehensively considered, and a weighted scoring algorithm can be used to determine the recommended cooking equipment corresponding to each recipe, as an example only; the recommended recipe set and the recommended cooking equipment corresponding to each recipe can then be forwarded to the mobile terminal 3, so that the mobile terminal 3 displays the recommended recipe set and the recommended cooking equipment corresponding to each recipe to the user. The cloud 2 can also recommend recipes based on the user's existing cooking equipment to avoid purchasing new equipment for a single recipe, thereby reducing the user's economic cost and resource waste.

[0052] When recommending recipes, the present invention also recommends cooking equipment that the user already owns, avoiding the user being unable to try recipes due to not knowing the functions of the cooking equipment. It can also give priority to recommending idle equipment based on the operating status of the equipment, ensuring that the user does not need to wait for the equipment to be idle.

[0053] In an optional embodiment, the cloud 2 determines the user's nutritional intake data based on the types and weights of ingredients cooked within a preset period; compares the user's nutritional intake data with the nutritional intake standard range corresponding to the user's health status to obtain a nutritional intake comparison result; based on the nutritional intake comparison result, determines nutritional intake balance recommendations and corresponding ingredient recommendations; and forwards the nutritional intake balance recommendations and corresponding ingredient recommendations to the mobile terminal 3, so that the mobile terminal 3 displays the nutritional intake balance recommendations and corresponding ingredient recommendations to the user.

[0054] The cloud 2 of the embodiment of the present invention can determine the user's nutritional intake data based on the types and weights of ingredients cooked within a preset period. For example, the user's recent calorie intake, protein intake, and dietary fiber intake can be obtained based on the known nutrient content of every 100g of food. At the same time, the standard range of nutritional intake within the user's period can be determined based on the user's health status. The user's nutritional intake data can then be compared with the standard range of nutritional intake to obtain a nutritional intake comparison result, such as a nutritional gap or excessive intake of a certain element. A recommended ingredient list can then be generated based on the nutritional intake comparison result and the user's dietary restrictions. The recommended ingredient list can be generated by screening out ingredient combinations rich in nutritional gap components, giving priority to recommending ingredients with high historical user preferences, and automatically filtering allergen ingredients. As an example only, the cloud 2 can forward nutritional intake balance suggestions and corresponding ingredient recommendations to the mobile terminal 3. The mobile terminal 3 can provide health warning information based on the nutritional intake balance suggestions, such as "sodium intake exceeds the standard within a week", and can give improvement suggestions.

[0055] The present invention can calculate the user's nutritional intake data through food type and weight data, and compare it with the nutritional standards corresponding to the user's health status, to achieve accurate early warning of nutritional imbalance risks, recommend specific ingredients based on nutritional imbalance problems, actively intervene in the user's health status, and cultivate scientific eating habits.

[0056] The present invention also provides a recipe recommendation method, which is applied to Figure 1 The cooking device 1, cloud 2 and mobile terminal 3 shown in FIG. Figure 3 As shown, the cooking device end is used to execute steps S101 to S102, the cloud end 2 is used to execute steps S201 to S203, and the mobile end 3 is used to execute step S301.

[0057] Step S101: monitor the cooking process and obtain cooking behavior data and ingredient information.

[0058] Step S102: Send cooking behavior data and ingredient information to the cloud.

[0059] Step S201: receiving food information and cooking behavior data sent by multiple cooking equipment terminals bound to the user, and storing the food information and cooking behavior data in a data storage device.

[0060] Step S202 : Integrate the user's health status information, the food information within a preset period extracted from the data storage device, and the cooking behavior data into a multi-dimensional feature vector.

[0061] Step S203: Input the multidimensional feature vector into a machine learning model for iterative training to output recipe recommendation results.

[0062] Step S301: forward the user health status information submitted by the user to the cloud.

[0063] The recipe recommendation method provided by the present invention monitors the cooking process through the cooking device end, obtains cooking behavior data and ingredient information, and sends the cooking behavior data and ingredient information to the cloud; the cloud receives the ingredient information and cooking behavior data sent by multiple cooking device ends bound to the user, and saves the ingredient information and cooking behavior data in a data storage device; the cloud obtains the user health status information submitted by the user through the mobile end, and integrates the user health status information, the ingredient information and cooking behavior data within a preset period extracted from the data storage device into a multidimensional feature vector; the cloud inputs the multidimensional feature vector into a machine learning model for iterative training, and outputs a recipe recommendation result, thereby realizing the comparison of the user's recent cooking habits, the cooked ingredients and the user's personal data through machine learning, and obtaining the effect of personalized recipe customization.

[0064] In a specific embodiment, Figure 4 As shown, the cooking device end of the embodiment of the present invention can obtain cooking behavior data and ingredient information in real time during the cooking process, and can cache the obtained cooking behavior data and ingredient information in a data storage device in advance, and can periodically send the cooking behavior data and ingredient information cached in the data storage device to the cloud. Taking the daily low electricity consumption period in the early morning as an example, the cloud obtains the user health status data submitted by the user through the mobile terminal, and then integrates the user health status information, the ingredient information within a preset period extracted from the data storage device, and the cooking behavior data into a multidimensional feature vector, and inputs the multidimensional feature vector into the machine learning model for iterative training, and outputs the recipe recommendation result. The cloud can forward the generated recipe recommendation result to the mobile terminal, such as the APP terminal, and the APP terminal can display intelligent recipe recommendations and customized ingredient diet suggestions through the interactive interface. For detailed description, please refer to the above embodiment and will not be repeated here.

[0065] The embodiment of the present invention also provides a cooking device, such as Figure 5 As shown, the cooking device includes a cooking device end 1, which includes: a memory and a processor. The memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the recipe recommendation method described in the above embodiment by executing the computer instructions.

[0066] In an optional embodiment, the cooking device further includes: a cooking data acquisition device, which includes at least a power acquisition device, a weight acquisition device, a temperature acquisition device and an image acquisition device, wherein the power acquisition device is used to obtain the operating status and operating time of the cooking device, the weight acquisition device is used to measure the weight of the ingredients, the temperature acquisition device is used to monitor temperature changes during the cooking process, and the image acquisition device is used to monitor the types of ingredients being cooked.

[0067] The embodiment of the present invention also provides a recipe recommendation device, which is applied to Figure 1 As shown in the cloud 2, Figure 6 As shown, the device includes: a cooking data receiving module 601, which is used to receive ingredient information and cooking behavior data sent by multiple cooking device terminals bound to the user, and save the ingredient information and cooking behavior data in a data storage device; a user information receiving module 602, which is used to obtain user health status information submitted by the user through a mobile terminal; a vector integration module 603, which is used to integrate user health status information, ingredient information and cooking behavior data within a preset period extracted from the data storage device into a multidimensional feature vector; a recipe recommendation module 604, which is used to input the multidimensional feature vector into a machine learning model for iterative training, and output a recipe recommendation result.

[0068] In an optional embodiment, the recipe recommendation result includes at least a recommended recipe set and recommendations for alternative ingredients corresponding to each recipe. The recipe recommendation device also includes: a data forwarding module, which is used to forward the recipe recommendation result to the mobile terminal so that the mobile terminal displays the recommended recipe set and the replacement function options corresponding to each recipe to the user; and an ingredient display module, which is used to display the recommendations for alternative ingredients corresponding to the target recipe to the user in response to the user triggering the replacement function option corresponding to the target recipe.

[0069] In an optional embodiment, the recipe recommendation result also includes a recommended recipe set and recommended cooking equipment corresponding to each recipe, and the recipe recommendation device also includes: a cooking function analysis module, which is used to analyze the cooking functions required for each recipe in the recommended recipe set; a cooking equipment recommendation module, which is used to determine the recommended cooking equipment corresponding to each recipe based on the cooking functions required for each recipe, the corresponding achievable cooking functions of all cooking equipment bound to the user, and the operating status of each cooking equipment; an equipment recommendation forwarding module, which is used to forward the recommended recipe set and the recommended cooking equipment corresponding to each recipe to the mobile terminal, so that the mobile terminal displays the recommended recipe set and the recommended cooking equipment corresponding to each recipe to the user.

[0070] In an optional embodiment, the ingredient information includes at least the type of ingredients and the weight of the ingredients, and the recipe recommendation device also includes: a nutritional intake determination module, which is used to determine the user's nutritional intake data based on the type of ingredients and the weight of the ingredients cooked within a preset period; a nutritional comparison module, which is used to compare the user's nutritional intake data with the nutritional intake standard range corresponding to the user's health status to obtain a nutritional intake comparison result; a nutritional suggestion module, which is used to determine nutritional intake balance suggestions and corresponding ingredient recommendations based on the nutritional intake comparison result; and a nutritional suggestion display module, which is used to forward the nutritional intake balance suggestions and corresponding ingredient recommendations to the mobile terminal, so that the mobile terminal displays the nutritional intake balance suggestions and corresponding ingredient recommendations to the user.

[0071] The embodiment of the present invention also provides a recipe recommendation device, which is applied to Figure 1 The cooking device end 1 shown, as Figure 7 As shown, the device includes: a cooking monitoring module 701, which is used to monitor the cooking process, obtain cooking behavior data and ingredient information, and send the cooking behavior data and ingredient information to the cloud, so that the cloud receives the ingredient information and cooking behavior data sent by all cooking equipment ends bound to the user, and saves them in a data storage device, and integrates the user health status information, the ingredient information and cooking behavior data within a preset period extracted from the data storage device into a multidimensional feature vector, inputs the multidimensional feature vector into a machine learning model for iterative training, and outputs a recipe recommendation result. The user health status information is submitted by the user through the mobile terminal.

[0072] In an optional embodiment, the cooking monitoring module 701 includes: a system time monitoring unit for monitoring the current device system time; a data uploading unit for sending the acquired cooking behavior data and ingredient information to the cloud when the current device system time is consistent with the preset data upload time, and the preset data upload time is determined by the period with the lowest power consumption within the preset cycle.

[0073] In an optional embodiment, the cooking monitoring module 701 includes: using a preset encryption algorithm to encrypt the cooking behavior data and ingredient information; a protocol upload unit, used to use a preset communication protocol to send the encrypted cooking behavior data and ingredient information to the cloud.

[0074] The recipe recommendation device in this embodiment is presented in the form of a functional unit, where the unit refers to an ASIC (Application Specific Integrated Circuit) circuit, a processor and memory that executes one or more software or fixed programs, and / or other devices that can provide the above functions.

[0075] See also Figure 8 , Figure 8 This is a structural diagram of a cooking device provided by an optional embodiment of the present invention, such as Figure 8 As shown, the cooking device end includes: one or more processors 10, a memory 20, and interfaces for connecting various components, including high-speed interfaces and low-speed interfaces. The various components are connected to each other using different buses for communication and can be installed on a common motherboard or installed in other ways as needed. The processor can process instructions executed within the cooking device end, including instructions stored in or on the memory to display graphical information of the GUI on an external input / output device (such as a display device coupled to the interface). In some optional embodiments, if necessary, multiple processors and / or multiple buses can be used together with multiple memories and multiple memories. Similarly, multiple cooking device ends can be connected, with each device providing part of the necessary operations (for example, as a server array, a group of blade servers, or a multi-processor system). Figure 8 A processor 10 is taken as an example.

[0076] The processor 10 may be a central processing unit, a network processor, or a combination thereof. The processor 10 may further include a hardware chip. The hardware chip may be an application-specific integrated circuit, a programmable logic device, or a combination thereof. The programmable logic device may be a complex programmable logic device, a field programmable gate array, a general purpose array logic, or any combination thereof.

[0077] The memory 20 stores instructions that can be executed by at least one processor 10, so as to enable at least one processor 10 to execute the method shown in the above embodiment.

[0078] The memory 20 may include a program storage area and a data storage area. The program storage area may store an operating system and at least one application required for a function; the data storage area may store data generated based on the use of the cooking device. Furthermore, the memory 20 may include high-speed random access memory and non-volatile memory, such as at least one disk storage device, flash memory device, or other non-volatile solid-state memory device. In some optional embodiments, the memory 20 may optionally include a remote memory device located relative to the processor 10. Such remote memory device may be connected to the cooking device via a network. Examples of such networks include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0079] The memory 20 may include a volatile memory, such as a random access memory; the memory may also include a non-volatile memory, such as a flash memory, a hard disk or a solid-state drive; the memory 20 may also include a combination of the above types of memory.

[0080] The cooking device also includes an input device 30 and an output device 40. The processor 10, the memory 20, the input device 30 and the output device 40 can be connected via a bus or other means. Figure 8 The bus connection is taken as an example.

[0081] The input device 30 can receive input digital or character information and generate key signal input related to user settings and function control of the cooking device, such as a touch screen, a keypad, a mouse, a trackpad, a touch pad, an indicator stick, one or more mouse buttons, a trackball, a joystick, etc. The output device 40 can include a display device, an auxiliary lighting device (e.g., an LED), and a tactile feedback device (e.g., a vibration motor). The above-mentioned display device includes but is not limited to a liquid crystal display, a light emitting diode, a display, and a plasma display. In some optional embodiments, the display device can be a touch screen.

[0082] The embodiments of the present invention also provide a computer-readable storage medium. The methods according to the embodiments of the present invention described above can be implemented in hardware, firmware, or as computer code that can be recorded on a storage medium, or downloaded over a network and originally stored in a remote storage medium or a non-transitory machine-readable storage medium and then stored in a local storage medium. Thus, the methods described herein can be stored in such software processing on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. The storage medium can be a magnetic disk, an optical disk, a read-only storage memory, a random access memory, a flash memory, a hard disk, or a solid-state drive, etc.; further, the storage medium can also include a combination of the above types of memory. It can be understood that the computer, processor, microprocessor cooking device end, or programmable hardware includes a storage component that can store or receive software or computer code. When the software or computer code is accessed and executed by the computer, processor, or hardware, the methods shown in the above embodiments are implemented.

[0083] A portion of the present invention may be applied as a computer program product, such as a computer program instruction, which, when executed by a computer, can call or provide the method and / or technical solution according to the present invention through the operation of the computer. Those skilled in the art should understand that the form in which the computer program instruction exists in a computer-readable medium includes, but is not limited to, a source file, an executable file, an installation package file, etc. Accordingly, the way in which the computer program instruction is executed by the computer includes, but is not limited to: the computer directly executes the instruction, or the computer compiles the instruction and then executes the corresponding compiled program, or the computer reads and executes the instruction, or the computer reads and installs the instruction and then executes the corresponding installed program. Here, the computer-readable medium may be any available computer-readable storage medium or communication medium that can be accessed by the computer.

[0084] Although the embodiments of the present invention have been described with reference to the accompanying drawings, those skilled in the art may make various modifications and variations without departing from the spirit and scope of the present invention. Such modifications and variations are all within the scope defined by the appended claims.

Claims

1. A recipe recommendation method, characterized in that: Applied to the cloud, the method includes: Receiving food information and cooking behavior data sent by multiple cooking devices bound to the user, and storing the food information and cooking behavior data in a data storage device; Obtain user health status information submitted by the user through the mobile terminal; Integrating the user's health status information, food information within a preset period extracted from a data storage device, and cooking behavior data into a multidimensional feature vector; The multidimensional feature vector is input into a machine learning model for iterative training, and a recipe recommendation result is output.

2. The method according to claim 1, characterized in that The recipe recommendation result includes at least a set of recommended recipes and recommendations of alternative ingredients corresponding to each recipe, and the method further includes: Forwarding the recipe recommendation result to the mobile terminal so that the mobile terminal displays the recommended recipe set and the corresponding replacement function options of each recipe to the user; and In response to the user triggering a replacement function option corresponding to the target recipe, recommendations for alternative ingredients corresponding to the target recipe are displayed to the user.

3. The method according to claim 1, characterized in that The recipe recommendation result also includes a recommended recipe set and recommended cooking equipment corresponding to each recipe, and the method further includes: Analyzing the cooking functions required for each recipe in the recommended recipe collection; Determine the recommended cooking equipment for each recipe based on the cooking functions required for each recipe, the cooking functions that can be achieved by all cooking equipment bound to the user, and the operating status of each cooking equipment; The recommended recipe set and the recommended cooking equipment corresponding to each recipe are forwarded to a mobile terminal, so that the mobile terminal displays the recommended recipe set and the recommended cooking equipment corresponding to each recipe to the user.

4. The method according to claim 1, wherein The food information includes at least the type and weight of the food, and the method further includes: Determining nutritional intake data of the user based on the types and weights of ingredients cooked during the preset period; Comparing the user's nutritional intake data with a nutritional intake standard range corresponding to the user's health status to obtain a nutritional intake comparison result; Based on the nutritional intake comparison results, determining nutritional intake balance suggestions and corresponding food recommendations; The balanced nutrition intake suggestion and the corresponding food ingredient recommendation are forwarded to the mobile terminal, so that the mobile terminal displays the balanced nutrition intake suggestion and the corresponding food ingredient recommendation to the user.

5. A recipe recommendation method, characterized in that: Applied to a cooking device, the method includes: The cooking process is monitored to obtain cooking behavior data and ingredient information, and the cooking behavior data and ingredient information are sent to the cloud, so that the cloud receives the ingredient information and cooking behavior data sent by all cooking equipment ends bound to the user, and saves them in a data storage device, and integrates the user health status information, the ingredient information and cooking behavior data within a preset period extracted from the data storage device into a multidimensional feature vector, inputs the multidimensional feature vector into a machine learning model for iterative training, and outputs a recipe recommendation result, where the user health status information is submitted by the user through the mobile terminal.

6. The method according to claim 5, characterized in that The sending of the cooking behavior data and the food information to the cloud comprises: Monitor the current device system time; When the current device system time is consistent with the preset data upload time, the acquired cooking behavior data and ingredient information will be sent to the cloud. The preset data upload time is determined by the period with the lowest power consumption within the preset cycle.

7. The method according to claim 5 or 6, characterized in that The sending of the cooking behavior data and the food information to the cloud comprises: Encrypting the cooking behavior data and ingredient information using a preset encryption algorithm; Using the preset communication protocol, the encrypted cooking behavior data and ingredient information are sent to the cloud.

8. A recipe recommendation system, characterized in that: The system includes a cooking device terminal, a cloud terminal and a mobile terminal bound to the user, wherein: The cooking device monitors the cooking process, obtains cooking behavior data and ingredient information, and sends the cooking behavior data and ingredient information to the cloud; The cloud receives the food information and cooking behavior data sent by multiple cooking devices bound to the user, and stores the food information and cooking behavior data in a data storage device; The cloud obtains the user health status information submitted by the user through the mobile terminal, and integrates the user health status information, the food information within a preset period extracted from the data storage device and the cooking behavior data into a multidimensional feature vector; the cloud inputs the multidimensional feature vector into the machine learning model for iterative training, and outputs the recipe recommendation results.

9. A cooking device, characterized in that: The cooking device includes a cooking device end, and the cooking device end includes: a memory and a processor, the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the recipe recommendation method described in any one of claims 5 to 7 by executing the computer instructions.

10. The cooking device according to claim 9, characterized in that The cooking device also includes: a cooking data acquisition device, which includes at least a power acquisition device, a weight acquisition device, a temperature acquisition device and an image acquisition device, wherein the power acquisition device is used to obtain the operating status and operating time of the cooking device, the weight acquisition device is used to measure the weight of the ingredients, the temperature acquisition device is used to monitor the temperature changes during the cooking process, and the image acquisition device is used to monitor the type of cooking ingredients.

11. A computer-readable storage medium, characterized in that The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a computer to execute the recipe recommendation method according to any one of claims 1 to 4, or to execute the recipe recommendation method according to any one of claims 5 to 7.

Images