Intelligent cooking method, device, equipment and medium

Abstract

The embodiment of the invention discloses an intelligent cooking method and device, equipment and a medium. The method comprises the steps that health data and habit data of a target user are acquired; determining intake data for the target user based on the health data; dish preparation information of the target user and nutritional ingredient data of various food materials in the dish preparation information are acquired, and a to-be-recommended food material menu is generated based on the intake data and the nutritional ingredient data; and formulating a to-be-recommended dish menu according to the to-be-recommended food material menu and the dietary habit data, and completing intelligent cooking according to the to-be-recommended dish menu. According to the method and the device, the targeted dish menu is generated by combining the health information, the eating habits and the daily work and rest habits of the user, so that the automatic cooking provides healthier dishes which better conform to user preferences for the user, and the user experience is improved.

Description

Technical Field

[0001] The present invention relates to the field of smart home technology, and in particular to a smart cooking method, device, equipment and medium. Background Art

[0002] Cooking is an indispensable task for human survival and development. People have been cooking once or more every day since ancient times. Different dishes in a meal use a variety of cooking utensils, ingredients, seasonings, and processes. If a person only follows the steps to complete a dish each time, it often takes a long time to cook a meal. With the continuous progress of society, although there have been great improvements in various cooking utensils, saving a certain amount of processing time, the preparation of dishes still needs to be completed manually according to the steps, which undoubtedly can no longer meet the fast pace of life of people today.

[0003] With the rapid development of intelligent technologies such as automation and the Internet of Things, some intelligent systems have emerged that can replace some manual cooking operations. However, they still need to prepare dishes according to menus provided by humans and cannot be separated from human participation. For some users who have difficulty in making choices, the process of providing dishes with menus is not easy, resulting in the degree of automation of existing intelligent cooking technology being far from meeting the needs of life. In addition, there is a risk that the menus provided by humans do not meet health needs, which can easily bring risks to the health of users. Preparing dishes only according to menus provided by humans is not conducive to the health needs of users. Summary of the invention

[0004] In view of this, the present invention provides an intelligent cooking method, device, equipment and medium, which are used to solve the problems in the prior art that the degree of automation is low and the actual needs of users are not taken into consideration.

[0005] To achieve one, part, or all of the above purposes or other purposes, the present invention proposes an intelligent communication method based on a privacy algorithm, comprising:

[0006] An intelligent cooking method, comprising:

[0007] Acquire health data and habit data of the target user, wherein the habit data includes dietary habit information and work and rest habit information;

[0008] determining intake data for the target user based on the health data;

[0009] Acquire the target user's meal preparation information and the nutritional component data of various ingredients in the meal preparation information, and generate a menu of ingredients to be recommended based on the intake data and the nutritional component data;

[0010] A menu of dishes to be recommended is formulated according to the menu of ingredients to be recommended and the habit data, and intelligent cooking is completed according to the menu of dishes to be recommended.

[0011] Optionally, the step of acquiring the health data and habit data of the target user, wherein the habit data includes dietary habit information and work and rest habit information, comprises:

[0012] Acquire activity information of the target user, the activity information including image data and operation data of each device in the area where the target user is located;

[0013] Acquiring health data of the target user through image recognition according to the image data;

[0014] Determine the work and rest habit information of the target user based on the operation data;

[0015] The target user's historical dietary data is obtained, and dietary habit information of the target user is determined according to the historical dietary data.

[0016] Optionally, the step of obtaining the target user's meal preparation information and the nutritional component data of various ingredients in the meal preparation information, and generating a menu of ingredients to be recommended based on the intake data and the nutritional component data includes:

[0017] Acquire the order information of the target user, wherein the order information includes image information of the purchase label of the food;

[0018] Input the image information into a first recognition model, and output the food corresponding to the image information through the first recognition model as the purchased food, wherein the first recognition model is obtained by machine learning training using multiple sets of data, each set of data in the multiple sets of data includes: image information and food corresponding to the image information, and the first recognition model includes a multi-layer long short-term memory network and a multi-layer convolutional neural network;

[0019] Acquire food image data in a food storage device in an area where the target user is located, wherein the food image data is hyperspectral data captured by a hyperspectral imaging device;

[0020] Input the food image data into a second recognition model, and output the food corresponding to the food image data through the second recognition model as the stored food, wherein the second recognition model is obtained by machine learning training using multiple sets of data, each set of data in the multiple sets of data includes: food image, spectral data and food corresponding to the food image, and the recognition model includes a multi-layer long short-term memory network and a multi-layer convolutional neural network;

[0021] The target user's meal preparation information is generated based on the purchased ingredients and the stored ingredients, and nutritional component data of each type of ingredient in the meal preparation information is obtained. The various types of ingredients in the meal preparation information are sorted based on the intake data and the nutritional component data to obtain a menu of ingredients to be recommended.

[0022] Optionally, the step of inputting the food image data into a second recognition model, and outputting the food corresponding to the food image data through the second recognition model as the stored food, wherein the second recognition model is obtained by machine learning training using multiple sets of data, each set of data in the multiple sets of data includes: a food image in a hyperspectral form and food corresponding to the food image, and the second recognition model includes a multi-layer long short-term memory network and a multi-layer convolutional neural network, including:

[0023] Processing the food image data to extract target food image and target spectrum data;

[0024] Inputting the target food image into the second recognition model to obtain first category information and a first recognition rate;

[0025] Determining whether the first recognition rate is higher than a preset first threshold;

[0026] If yes, the second recognition model outputs the first category information, and obtains the food corresponding to the food image data as the stored food;

[0027] If not, inputting the target spectrum data into the second recognition model to obtain second category information and a second recognition rate;

[0028] Determining whether the second recognition rate is higher than a preset second threshold;

[0029] If so, the second recognition model outputs the second category information and obtains the food corresponding to the food image data as the stored food.

[0030] Optionally, the step of formulating a menu of dishes to be recommended according to the menu of ingredients to be recommended and the habit data, and completing intelligent cooking according to the menu of dishes to be recommended includes:

[0031] Formulate a first recommended dish menu according to the to-be-recommended food menu and the dietary habit information in the habit data;

[0032] Formulate a second recommended dish menu according to the to-be-recommended food menu and the work and rest habit information in the habit data;

[0033] Generate and push push information based on the first recommended dish menu and the second recommended dish menu;

[0034] Acquire instruction information of the target user for the push information, wherein the instruction information includes selection information and control instructions;

[0035] Based on the selection information, the first recommended dish menu or the second recommended dish menu is determined as the dish menu to be recommended, and intelligent cooking is completed according to the dish menu to be recommended according to the control instruction.

[0036] Optionally, the step of obtaining instruction information of the target user for the pushed information, wherein the instruction information includes selection information and control instructions, comprises:

[0037] Dividing the area where the target user is located into at least two subspaces according to the area structure;

[0038] Selecting target devices for obtaining instruction information for the push information in each subspace to obtain at least two target devices, wherein the target devices are electronic devices in the same home network as the control device for intelligent cooking;

[0039] A human-computer interaction rule is formulated based on the target device, and instruction information of the target user for the pushed information is obtained according to the human-computer interaction rule.

[0040] Optionally, before the step of obtaining instruction information of the target user for the pushed information, wherein the instruction information includes selection information and control instructions, the step further includes:

[0041] Obtaining the browsing history of the target user, and filtering out the target browsing history corresponding to the ingredients in the menu of ingredients to be recommended from the browsing history;

[0042] Formulate a third recommended dish menu based on the target browsing record;

[0043] Push information is generated and pushed based on the first recommended dish menu, the second recommended dish menu and the third recommended dish menu.

[0044] On the other hand, an embodiment of the present application provides a smart cooking device, comprising:

[0045] A data collection module is used to obtain health data and habit data of the target user, wherein the habit data includes information on eating habits and rest habits;

[0046] an analysis module, configured to determine intake data for the target user based on the health data;

[0047] An ingredient determination module, used to obtain the target user's meal preparation information and the nutritional component data of various ingredients in the meal preparation information, and generate a menu of ingredients to be recommended based on the intake data and the nutritional component data;

[0048] The intelligent cooking module is used to formulate a menu of dishes to be recommended according to the menu of ingredients to be recommended and the habit data, and complete intelligent cooking according to the menu of dishes to be recommended.

[0049] On the other hand, an embodiment of the present application provides an electronic device, comprising: a processor, a memory and a bus, wherein the memory stores machine-readable instructions executable by the processor, and when the electronic device is running, the processor and the memory communicate through the bus, and when the machine-readable instructions are executed by the processor, the steps of smart cooking as described above are performed.

[0050] On the other hand, an embodiment of the present application provides a computer-readable storage medium, characterized in that a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, the steps of the above-mentioned intelligent cooking method are executed.

[0051] Implementing the embodiments of the present invention will have the following beneficial effects:

[0052] By obtaining the health data and habit data of the target user, the habit data includes dietary habit information and work and rest habit information; determining the intake data for the target user based on the health data; obtaining the target user's meal preparation information and the nutritional data of various ingredients in the meal preparation information, and generating a menu of ingredients to be recommended based on the intake data and the nutritional data; formulating a menu of dishes to be recommended based on the menu of ingredients to be recommended and the habit data, and completing intelligent cooking based on the menu of dishes to be recommended. In combination with the user's health information, dietary habits, and work and rest habits, a menu of dishes for the target user is intelligently generated, so that automated cooking does not rely on the menu of dishes provided by the user, avoiding the entangled emotions generated when the user manually formulates the menu, and at the same time considering the user's health information to formulate the menu so that automated cooking can provide users with healthier and more reasonable dishes, improving the user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0054] in:

[0055] Figure 1 is a flow chart of an intelligent cooking method provided by an embodiment of the present application;

[0056] Figure 2 is a flow chart of another intelligent cooking method provided by an embodiment of the present application;

[0057] Figure 3 is a flow chart of another intelligent cooking method provided in an embodiment of the present application;

[0058] Figure 4 is a flow chart of another intelligent cooking method provided by an embodiment of the present application;

[0059] Figure 5 is a structural schematic diagram of an intelligent cooking device provided in an embodiment of the present application;

[0060] Figure 6 It is a structural schematic diagram of an electronic device provided in an embodiment of the present application;

[0061] Figure 7 It is a structural schematic diagram of a computer-readable storage medium provided in an embodiment of the present application. DETAILED DESCRIPTION

[0062] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only 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 ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0063] like Figure 1 As shown, the embodiment of the present application provides an intelligent cooking method, including:

[0064] S101, obtaining health data and habit data of a target user, wherein the habit data includes information on eating habits and rest habits;

[0065] Exemplarily, the health data and the habit data can be directly provided by the user or obtained through data analysis. When obtaining the health data and habit data of the target user through data analysis, it is necessary to collect the life information of the target user, such as case information, image information, order information, etc.

[0066] Exemplarily, the health data includes disease information (for example, diseases such as colds and diabetes), status information (health status such as sub-health status and pregnancy status), the eating habit information is the user's preference data, for example, preference for fried food, preference for spicy food, etc., and the work and rest habit information is the user's life and work routine data, for example, regularity of eating time, regularity of rest time, etc.

[0067] Exemplarily, when there are multiple target users, the health data and habit data of each target user are acquired, wherein the habit data includes dietary habit information and work and rest habit information, and a health data set and a habit data set are generated.

[0068] S102, determining intake data for the target user based on the health data;

[0069] Exemplarily, since the intake of different nutrients required by the human body in different health states is different, for example, when a user suffers from diabetes, the user's sugar intake should be much less than that of a normal user. Therefore, the intake data for the target user is determined based on the health data of the target user to ensure that the subsequently generated food menu is targeted, that is, targeted at the target user.

[0070] Exemplarily, when there are multiple target users, the intake data for the target users is determined based on the health data set. For example, when there are two target users, user A suffers from diabetes, and the health data of user B is in a disease-free state (healthy state). The sugar intake for the target users determined based on the health data is the sum of the sugar amount required by user A and the sugar amount required by user B.

[0071] S103, obtaining the target user's meal preparation information and the nutritional component data of various ingredients in the meal preparation information, and generating a menu of ingredients to be recommended based on the intake data and the nutritional component data;

[0072] Exemplarily, the user's meal preparation information includes one or more ingredients, and the meal preparation information can be obtained through the user's grocery shopping order or by identifying the ingredients stored in the user's refrigerator. The user's shopping information can express the user's intention to a certain extent. For example, when the user purchases a certain ingredient, it can express that the user wants to eat this ingredient. Therefore, the user's eating intention is determined based on the meal preparation information of the target user, and the ingredients to be recommended are selected from the various ingredients in the meal preparation information in combination with the user's intake, to obtain a menu of ingredients to be recommended.

[0073] S104: formulating a menu of dishes to be recommended according to the menu of ingredients to be recommended and the habit data, and completing intelligent cooking according to the menu of dishes to be recommended.

[0074] Exemplarily, after the ingredients are determined, it is necessary to determine the preparation method of the ingredients, that is, determine the preparation method of the ingredients according to the user's habit data. For example, if the user's eating habit data shows that the user likes fried food, then the preparation method of the ingredients is determined to be frying. For example, if the user's work and rest habit data shows that the user likes to go to bed late (stay up late), then the preparation method of the ingredients is determined to be steaming, blanching, etc.

[0075] For example, when there are two target users, user A suffers from diabetes, and user B's health data is in a disease-free state (healthy state), after the ingredients are determined, the sugar content of the determined ingredients is compared, and the preparation and processing method of the ingredients with high sugar content is determined through the habit data of user B, and the preparation and processing method of the ingredients with low sugar content is determined through the habit data of user A.

[0076] By obtaining the health data and habit data of the target user, the habit data includes dietary habit information and work and rest habit information; determining the intake data for the target user based on the health data; obtaining the target user's meal preparation information and the nutritional data of various ingredients in the meal preparation information, and generating a menu of ingredients to be recommended based on the intake data and the nutritional data; formulating a menu of dishes to be recommended based on the menu of ingredients to be recommended and the habit data, and completing intelligent cooking based on the menu of dishes to be recommended. In combination with the user's health information, dietary habits, and work and rest habits, a menu of dishes for the target user is intelligently generated, so that automated cooking does not rely on the menu of dishes provided by the user, avoiding the entangled emotions generated when the user manually formulates the menu, and at the same time considering the user's health information to formulate the menu so that automated cooking can provide users with healthier and more reasonable dishes, improving the user experience.

[0077] In a possible implementation, the step of acquiring the health data and habit data of the target user, wherein the habit data includes dietary habit information and work and rest habit information, includes:

[0078] Acquire activity information of the target user, the activity information including image data and operation data of each device in the area where the target user is located;

[0079] Acquiring health data of the target user through image recognition according to the image data;

[0080] Determine the work and rest habit information of the target user based on the operation data;

[0081] The target user's historical dietary data is obtained, and dietary habit information of the target user is determined according to the historical dietary data.

[0082] Exemplarily, the image data of the target user is obtained through an intelligent monitoring system or other device that can obtain images, and then the health data of the target user is obtained through image recognition based on the image data. For example, the facial features of the user are obtained based on the facial image of the user, and the current health data of the user is determined based on the facial features. The operating data of each device in the area where the target user is located is obtained, for example, the time when the TV is turned on / off, the time when the computer is turned on / off, and the time when portable electronic devices such as mobile phones are turned on / off, and then the work and rest habits information of the target user is determined based on the operating data.

[0083] Exemplarily, the work and rest habits information of the target user can also be determined by obtaining the physiological information (heart rate, breathing rate, etc.) of the target user through intelligent monitoring equipment, such as a smart bracelet or other equipment.

[0084] For example, Figure 2 As shown, an embodiment of obtaining the health data of the target user through image recognition according to the image data includes: using a smartphone camera to record a face video in real time, and the output content after recording the face video includes: a front face picture, an upper tongue picture, a lower tongue picture, and a 1-minute front face video; identifying facial symptoms based on the front face picture, and identifying tongue symptoms based on the tongue picture; identifying pulse symptoms based on the 1-minute face video; based on the facial symptoms, tongue symptoms, and pulse symptom information recognized from the face video image, the facial symptoms, tongue symptoms, and pulse symptoms identified by analyzing the known symptom set are strongly associated in the medical knowledge graph. degree, infer other symptoms that the user may have, and obtain the final symptom set S; based on the confirmed and collected symptom set S, calculate its correlation strength with all syndromes, normalize the confidence of the syndrome associated with the five internal organs, and then integrate and calculate to obtain the probability distribution of energy imbalance of the five internal organs; based on the probability distribution of the five internal organs, infer the closest syndrome type, and give the confidence of the inferred syndrome type; based on the correspondence between syndrome and constitution and disease, infer the closest constitution tendency type and suspected disease name; the medical knowledge graph is a medical knowledge causal network constructed based on the terminology dictionary of symptoms, syndromes, constitution and diseases described in existing literature.

[0085] By acquiring the health data of the target user through image recognition, changes in the user's health status can be acquired in a timely manner, so that subsequent intake data can change with changes in the user's health status, and then subsequent menus can change with changes in the user's health status, which is more intelligent and can help provide reasonable services to users.

[0086] Exemplarily, when obtaining the target user's eating habit information, the target user's historical table images can be obtained, the target user's historical eating data can be identified based on the historical table images, and the target user's eating habit information can be judged based on the historical eating data; the target user's historical takeout orders (historical meal orders) can also be obtained, and the target user's eating habit information can be judged based on the historical takeout orders.

[0087] Exemplarily, when obtaining the target user's dietary habit information, it can also be obtained by querying the target user's historical browsing records. For example, the target user's historical browsing records are filtered to filter out browsing records related to food and dishes, and the target user's browsing time is obtained based on the browsing records. Then, the target user's dietary habit information is judged based on the browsing time (the longer the browsing time, the more the user is considered to like the browsed videos, images, etc.).

[0088] In a possible implementation, the step of obtaining the target user's meal preparation information and the nutritional component data of various ingredients in the meal preparation information, and generating a menu of ingredients to be recommended based on the intake data and the nutritional component data includes:

[0089] Acquire the order information of the target user, wherein the order information includes image information of the purchase label of the food;

[0090] Input the image information into a first recognition model, and output the food corresponding to the image information through the first recognition model as the purchased food, wherein the first recognition model is obtained by machine learning training using multiple sets of data, each set of data in the multiple sets of data includes: image information and food corresponding to the image information, and the first recognition model includes a multi-layer long short-term memory network and a multi-layer convolutional neural network;

[0091] Acquire food image data in a food storage device in an area where the target user is located, wherein the food image data is hyperspectral data captured by a hyperspectral imaging device;

[0092] Input the food image data into a second recognition model, and output the food corresponding to the food image data through the second recognition model as the stored food, wherein the second recognition model is obtained by machine learning training using multiple sets of data, each set of data in the multiple sets of data includes: food image, spectral data and food corresponding to the food image, and the recognition model includes a multi-layer long short-term memory network and a multi-layer convolutional neural network;

[0093] The target user's meal preparation information is generated based on the purchased ingredients and the stored ingredients, and nutritional component data of each type of ingredient in the meal preparation information is obtained. The various types of ingredients in the meal preparation information are sorted based on the intake data and the nutritional component data to obtain a menu of ingredients to be recommended.

[0094] For example, Figure 3 As shown, the method of obtaining the image information of the purchase label of the above-mentioned food material can be through an image acquisition device arranged inside the refrigerator. The above-mentioned image acquisition device can be a camera, a still camera, etc. The number of the above-mentioned image acquisition devices can be one or more. In the case where the above-mentioned image acquisition device is multiple, the multiple image acquisition devices are respectively arranged on the inner wall inside the refrigerator. In addition, the method of obtaining the image information of the purchase label of the above-mentioned food material can also be to record it before putting it into the refrigerator, and record the food material and the purchase label corresponding to the food material pasted on the food material into the image through the recording image acquisition device to generate image information. The above-mentioned first recognition model is obtained by machine learning training using multiple sets of data, for example, a convolutional neural network recognition model, etc., which can perform machine learning recognition models, for example, by training multiple sets of data until the model converges and has the recognition ability between input data and output data. Each set of data in the multiple sets of data includes: image information and food material corresponding to the image information. The above-mentioned first recognition model includes a multi-layer long short-term memory network and a multi-layer convolutional neural network. The long short-term memory network is a time recursive neural network, which is suitable for processing and predicting events with very long intervals and extensions in time series. The above convolutional neural network is a feedforward neural network, where artificial neurons can influence surrounding units and can process large images. Combining the above multi-layer long short-term memory network with the multi-layer convolutional neural network can make the recognition effect of the above recognition model better.

[0095] Exemplarily, food image data in a food storage device within the area where the target user is located is obtained, the food image data is hyperspectral data taken by a hyperspectral imaging device, the hyperspectral data may include a set number of ternary data groups, each ternary data group includes two image pixel elements and a spectral wavelength element for a pixel point, each pixel point has multiple ternary data groups, and the resolution of the spectral wavelength of each pixel point in the hyperspectral data is less than or equal to 2nm.

[0096] In a possible implementation, the food image data is input into a second recognition model, and the food corresponding to the food image data is output through the second recognition model as the stored food, wherein the second recognition model is obtained by machine learning training using multiple sets of data, each set of data in the multiple sets of data includes: a food image in a hyperspectral form and food corresponding to the food image, and the second recognition model includes a multi-layer long short-term memory network and a multi-layer convolutional neural network, including:

[0097] Processing the food image data to extract target food image and target spectrum data;

[0098] Inputting the target food image into the second recognition model to obtain first category information and a first recognition rate;

[0099] Determining whether the first recognition rate is higher than a preset first threshold;

[0100] If yes, the second recognition model outputs the first category information, and obtains the food corresponding to the food image data as the stored food;

[0101] If not, inputting the target spectrum data into the second recognition model to obtain second category information and a second recognition rate;

[0102] Determining whether the second recognition rate is higher than a preset second threshold;

[0103] If so, the second recognition model outputs the second category information and obtains the ingredients corresponding to the ingredient image data as stored ingredients.

[0104] For example, Figure 4 As shown, after receiving the instruction to identify the type of food, the hyperspectral imaging device is started to obtain the hyperspectral data obtained by shooting; the hyperspectral data is preprocessed, and image data and spectral data are extracted respectively; the type of food is identified according to the extracted image data and / or spectral data, wherein the target food image is extracted by analyzing the data in the image pixel elements, and the target spectral data is extracted by analyzing the data in the spectral wavelength elements. The first recognition rate reflects the accuracy of the first type of information obtained by analysis. For example, the first threshold is set to 80%. If the calculated first recognition rate is higher than 80%, it is determined that the food identification is passed, and the first type of information is output. Similarly, the second recognition rate reflects the accuracy of the second type of information obtained by analysis. The second threshold is set to 70%. If the calculated second recognition rate is higher than 70%, it is determined that the food identification is passed, and the second type of information is output.

[0105] Through two identifications, the accuracy of food identification is guaranteed. By using hyperspectral data, unclear images caused by weak pipelines in food storage equipment are avoided, which in turn affects the accuracy of image recognition (food identification).

[0106] In a possible implementation, the step of formulating a menu of dishes to be recommended according to the menu of ingredients to be recommended and the habit data, and completing intelligent cooking according to the menu of dishes to be recommended includes:

[0107] Formulate a first recommended dish menu according to the to-be-recommended food menu and the dietary habit information in the habit data;

[0108] Formulate a second recommended dish menu according to the to-be-recommended food menu and the work and rest habit information in the habit data;

[0109] Generate and push push information based on the first recommended dish menu and the second recommended dish menu;

[0110] Acquire instruction information of the target user for the push information, wherein the instruction information includes selection information and control instructions;

[0111] Based on the selection information, the first recommended dish menu or the second recommended dish menu is determined as the dish menu to be recommended, and intelligent cooking is completed according to the dish menu to be recommended according to the control instruction.

[0112] Exemplarily, the preparation method of ingredients is determined based on the user's habit data. For example, if the user's eating habit data shows that he or she likes fried food, then the preparation method of ingredients is determined to be frying. For example, if the user's work and rest habit data shows that he or she has a habit of going to bed late (staying up late), then the preparation method of ingredients is determined to be steaming, blanching, etc. That is, two recommended dish menus are generated for the user to choose from, providing the user with choices and achieving a better balance between user preferences and health, avoiding making dishes that the user does not like for the sake of health, and avoiding ignoring the user's health for the sake of user preferences.

[0113] Exemplarily, you can also randomly select any dish A from the first recommended dish menu, and randomly select any dish B from the second recommended dish menu, build a target recommended dish menu based on the dish A and the dish B, and send the target recommended dish menu directly to the smart cooking device to complete smart cooking.

[0114] In a possible implementation, the step of obtaining instruction information of the target user for the pushed information, wherein the instruction information includes selection information and control instructions, includes:

[0115] Dividing the area where the target user is located into at least two subspaces according to the area structure;

[0116] Selecting target devices for obtaining instruction information for the push information in each subspace to obtain at least two target devices, wherein the target devices are electronic devices in the same home network as the control device for intelligent cooking;

[0117] A human-computer interaction rule is formulated based on the target device, and instruction information of the target user for the pushed information is obtained according to the human-computer interaction rule.

[0118] Exemplarily, the area where the target user is located is divided into at least two subspaces according to the area structure. For example, the user's house is divided into subspaces such as the living room, bedroom, and study. A target device is set in each subspace to be associated with smart cooking, so that the user can send instructions to the smart cooking device in any subspace. For example, in the living room, the monitoring device in the living room is used as the target device. Since the function of the monitoring device is to acquire images, the human-computer interaction rules are formulated to achieve the selection of the recommended dish menu based on the user's first specific gesture (posture), and to achieve the control of the smart cooking device based on the user's second specific gesture (posture).

[0119] In a possible implementation, before the step of obtaining instruction information of the target user in response to the push information, wherein the instruction information includes selection information and control instructions for completing intelligent cooking according to the menu of dishes to be recommended, the step further includes:

[0120] Obtaining the browsing history of the target user, and filtering out the target browsing history corresponding to the ingredients in the menu of ingredients to be recommended from the browsing history;

[0121] Formulate a third recommended dish menu based on the target browsing record;

[0122] Push information is generated and pushed based on the first recommended dish menu, the second recommended dish menu and the third recommended dish menu.

[0123] Exemplarily, the browsing history of the target user is obtained, where the browsing history includes browsing history of a computer, browsing history of a portable device such as a mobile phone, browsing history of a television, etc., and target browsing records corresponding to ingredients in the menu of ingredients to be recommended are filtered out from the browsing records. For example, the ingredient in the menu of ingredients to be recommended is broccoli, and target browsing records corresponding to broccoli are filtered out from the browsing records, and a third recommended dish menu is formulated, and push information is generated and pushed based on the first recommended dish menu, the second recommended dish menu, and the third recommended dish menu.

[0124] In a possible implementation, Figure 5 As shown, an embodiment of the present application provides a smart cooking device, the device comprising:

[0125] The data collection module 201 is used to obtain the health data and habit data of the target user, wherein the habit data includes the dietary habit information and the work and rest habit information;

[0126] An analysis module 202, configured to determine intake data for the target user based on the health data;

[0127] The ingredient determination module 203 is used to obtain the target user's meal preparation information and the nutritional component data of each type of ingredient in the meal preparation information, and generate a menu of ingredients to be recommended based on the intake data and the nutritional component data;

[0128] The intelligent cooking module 204 is used to formulate a menu of dishes to be recommended according to the menu of ingredients to be recommended and the habit data, and complete intelligent cooking according to the menu of dishes to be recommended.

[0129] In a possible implementation, Figure 6 As shown, an embodiment of the present application provides an electronic device 300, including: a memory 310, a processor 320, and a computer program 311 stored in the memory 310 and executable on the processor 320. When the processor 320 executes the computer program 311, it implements: obtaining health data and habit data of a target user, wherein the habit data includes dietary habit information and work and rest habit information; determining intake data for the target user based on the health data; obtaining meal preparation information of the target user and nutritional component data of various ingredients in the meal preparation information, and generating a menu of ingredients to be recommended based on the intake data and the nutritional component data; formulating a menu of dishes to be recommended according to the menu of ingredients to be recommended and the habit data, and completing intelligent cooking according to the menu of dishes to be recommended.

[0130] In a possible implementation, Figure 7 As shown, an embodiment of the present application provides a computer-readable storage medium 400 on which a computer program 411 is stored. When the computer program 411 is executed by a processor, it implements: obtaining health data and habit data of a target user, wherein the habit data includes dietary habit information and work and rest habit information; determining intake data for the target user based on the health data; obtaining meal preparation information of the target user and nutritional component data of various ingredients in the meal preparation information, and generating a menu of ingredients to be recommended based on the intake data and the nutritional component data; formulating a menu of dishes to be recommended based on the menu of ingredients to be recommended and the habit data, and completing intelligent cooking based on the menu of dishes to be recommended.

[0131] The computer storage medium of the embodiment of the present invention can adopt any combination of one or more computer-readable media. The computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. The computer-readable storage medium can be, for example, but not limited to: an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples (non-exhaustive list) of computer-readable storage media include: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this document, a computer-readable storage medium can be any tangible medium containing or storing a program, which can be used by an instruction execution system, device or device or used in combination with it.

[0132] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, which carry computer-readable program code. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0133] The program code contained on the computer-readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, optical cable, etc., or any suitable combination of the foregoing.

[0134] Computer program code for performing the operations of the present invention may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0135] It should be understood by those skilled in the art that the modules or steps of the present invention described above can be implemented by a general-purpose computing device, they can be concentrated on a single computing device, or distributed on a network composed of multiple computing devices, optionally, they can be implemented by a program code executable by a computer device, so that they can be stored in a storage device and executed by the computing device, or they can be made into individual integrated circuit modules, or multiple modules or steps therein can be made into a single integrated circuit module for implementation. Thus, the present invention is not limited to any specific combination of hardware and software.

[0136] Note that the above are only preferred embodiments of the present invention and the technical principles used. Those skilled in the art will understand that the present invention is not limited to the specific embodiments described above, and that various obvious changes, readjustments and substitutions can be made by those skilled in the art without departing from the scope of protection of the present invention. Therefore, although the present invention has been described in more detail through the above embodiments, the present invention is not limited to the above embodiments, and may include more other equivalent embodiments without departing from the concept of the present invention, and the scope of the present invention is determined by the scope of the appended claims.

[0137] The above disclosure is only the preferred embodiment of the present invention, which certainly cannot be used to limit the scope of the present invention. Therefore, equivalent changes made according to the claims of the present invention are still within the scope of the present invention.

Claims

1. An intelligent cooking method, characterized in that: include: Acquire health data and habit data of the target user, wherein the habit data includes dietary habit information and work and rest habit information; determining intake data for the target user based on the health data; Acquire the target user's meal preparation information and the nutritional component data of various ingredients in the meal preparation information, and generate a menu of ingredients to be recommended based on the intake data and the nutritional component data; A menu of dishes to be recommended is formulated according to the menu of ingredients to be recommended and the habit data, and intelligent cooking is completed according to the menu of dishes to be recommended.

2. The intelligent cooking method according to claim 1, characterized in that: The step of obtaining the health data and habit data of the target user, wherein the habit data includes dietary habit information and work and rest habit information, comprises: Acquire activity information of the target user, the activity information including image data and operation data of each device in the area where the target user is located; Acquiring health data of the target user through image recognition according to the image data; Determine the work and rest habit information of the target user based on the operation data; The target user's historical dietary data is obtained, and dietary habit information of the target user is determined according to the historical dietary data.

3. The intelligent cooking method according to claim 1, characterized in that: The step of obtaining the target user's meal preparation information and the nutritional component data of various ingredients in the meal preparation information, and generating a menu of ingredients to be recommended based on the intake data and the nutritional component data, comprises: Acquire the order information of the target user, wherein the order information includes image information of the purchase label of the food; Input the image information into a first recognition model, and output the food corresponding to the image information through the first recognition model as the purchased food, wherein the first recognition model is obtained by machine learning training using multiple sets of data, each set of data in the multiple sets of data includes: image information and food corresponding to the image information, and the first recognition model includes a multi-layer long short-term memory network and a multi-layer convolutional neural network; Acquire food image data in a food storage device in an area where the target user is located, wherein the food image data is hyperspectral data captured by a hyperspectral imaging device; Input the food image data into a second recognition model, and output the food corresponding to the food image data through the second recognition model as the stored food, wherein the second recognition model is obtained by machine learning training using multiple sets of data, each set of data in the multiple sets of data includes: food image, spectral data and food corresponding to the food image, and the second recognition model includes a multi-layer long short-term memory network and a multi-layer convolutional neural network; The target user's meal preparation information is generated based on the purchased ingredients and the stored ingredients, and nutritional component data of each type of ingredient in the meal preparation information is obtained. The various types of ingredients in the meal preparation information are sorted based on the intake data and the nutritional component data to obtain a menu of ingredients to be recommended.

4. The intelligent cooking method according to claim 3, characterized in that: The step of inputting the food image data into a second recognition model, and outputting the food corresponding to the food image data through the second recognition model as the stored food, wherein the second recognition model is obtained by machine learning training using multiple sets of data, each set of data in the multiple sets of data includes: a food image in a hyperspectral form and food corresponding to the food image, and the second recognition model includes a multi-layer long short-term memory network and a multi-layer convolutional neural network, including: Processing the food image data to extract target food image and target spectrum data; Inputting the target food image into the second recognition model to obtain first category information and a first recognition rate; Determining whether the first recognition rate is higher than a preset first threshold; If yes, the second recognition model outputs the first category information, and obtains the food corresponding to the food image data as the stored food; If not, inputting the target spectrum data into the second recognition model to obtain second category information and a second recognition rate; Determining whether the second recognition rate is higher than a preset second threshold; If so, the second recognition model outputs the second category information and obtains the food corresponding to the food image data as the stored food.

5. The intelligent cooking method according to claim 1, characterized in that: The step of formulating a menu of dishes to be recommended according to the menu of ingredients to be recommended and the habit data, and completing intelligent cooking according to the menu of dishes to be recommended includes: Formulate a first recommended dish menu according to the to-be-recommended food menu and the dietary habit information in the habit data; Formulate a second recommended dish menu according to the to-be-recommended food menu and the work and rest habit information in the habit data; Generate and push push information based on the first recommended dish menu and the second recommended dish menu; Acquire instruction information of the target user for the push information, wherein the instruction information includes selection information and control instructions; Based on the selection information, the first recommended dish menu or the second recommended dish menu is determined as the dish menu to be recommended, and intelligent cooking is completed according to the dish menu to be recommended according to the control instruction.

6. The intelligent cooking method according to claim 5, characterized in that: The step of obtaining instruction information of the target user for the pushed information, wherein the instruction information includes selection information and control instructions, comprises: Dividing the area where the target user is located into at least two subspaces according to the area structure; Selecting target devices for obtaining instruction information for the push information in each subspace to obtain at least two target devices, wherein the target devices are electronic devices in the same home network as the control device for intelligent cooking; A human-computer interaction rule is formulated based on the target device, and instruction information of the target user for the pushed information is obtained according to the human-computer interaction rule.

7. The intelligent cooking method according to claim 5, characterized in that: Before the step of obtaining instruction information of the target user for the push information, wherein the instruction information includes selection information and control instructions, the step further includes: Obtaining the browsing history of the target user, and filtering out the target browsing history corresponding to the ingredients in the menu of ingredients to be recommended from the browsing history; Formulate a third recommended dish menu based on the target browsing record; Push information is generated and pushed based on the first recommended dish menu, the second recommended dish menu and the third recommended dish menu.

8. An intelligent cooking device, characterized in that: The device comprises: A data collection module is used to obtain health data and habit data of the target user, wherein the habit data includes information on eating habits and rest habits; an analysis module, configured to determine intake data for the target user based on the health data; An ingredient determination module, used to obtain the target user's meal preparation information and the nutritional component data of various ingredients in the meal preparation information, and generate a menu of ingredients to be recommended based on the intake data and the nutritional component data; The intelligent cooking module is used to formulate a menu of dishes to be recommended according to the menu of ingredients to be recommended and the habit data, and complete intelligent cooking according to the menu of dishes to be recommended.

9. An electronic device, characterized in that: include: A processor, a memory and a bus, wherein the memory stores machine-readable instructions executable by the processor, and when the electronic device is running, the processor and the memory communicate through the bus, and when the machine-readable instructions are executed by the processor, the steps of the intelligent cooking method as described in any one of claims 1 to 7 are performed.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the intelligent cooking method according to any one of claims 1 to 7 are executed.

Images