Method and apparatus for determining cooking parameters, storage medium and cooking device

Abstract

The application provides a cooking parameter determination method and device, a storage medium and a cooking equipment. In the case that a to-be-processed food material is placed in a cooking cavity, an image acquisition device is controlled to acquire an image of the to-be-processed food material to obtain a first image. The first image is recognized to determine first category information and first state information. The first category information is food material category information of the to-be-processed food material, and the first state information is food material state information of the to-be-processed food material. Target cooking parameters are generated from a first database based on the first category information, the first state information and first region information. The food material state information is information describing the cooking maturity of the to-be-processed food material, the first region information is current region information of the cooking equipment, and the first database is a database constructed based on historical cooking data. Without manual setting of cooking parameters by the user according to cooking experience, the participation of the user is reduced, and the cooking needs of different scenes are met.

Description

Technical Field

[0001] This invention relates to the field of cooking control technology, and more specifically, to a method, apparatus, storage medium, and cooking equipment for determining cooking parameters. Background Technology

[0002] Cooking appliances, such as ovens, are pre-programmed with multiple automatic menus before leaving the factory. These automatic menus contain cooking parameters, allowing users to perform one-button cooking.

[0003] However, automatic menus are expensive to create and therefore limited in number. For those who want to cook ingredients that do not use automatic menus, even if they have the cooking parameters for other devices, they may not know how to configure the cooking parameters due to limited cooking experience.

[0004] In addition, automatic menus are created for uncooked ingredients and are no longer applicable to cooked ingredients. Summary of the Invention

[0005] The present invention aims to at least solve the technical problems existing in the prior art or related technologies, such as the high cost of automatic menu production, resulting in limited quantity, and the lack of knowledge on how to configure cooking parameters for ingredients that do not have automatic menus, even if cooking parameters of other devices are available.

[0006] Therefore, a first aspect of the present invention is to provide a method for determining cooking parameters.

[0007] A second aspect of the present invention is that it provides an apparatus for determining cooking parameters.

[0008] A third aspect of the invention is that it provides yet another device for determining cooking parameters.

[0009] A fourth aspect of the present invention is that a readable storage medium is provided.

[0010] A fifth aspect of the present invention is that a cooking apparatus is provided.

[0011] In view of the above, according to a first aspect of the present invention, the present invention provides a method for determining cooking parameters for a cooking device, the cooking device including a cooking chamber and an image acquisition device, comprising: when a food to be processed is placed in the cooking chamber, controlling the image acquisition device to acquire an image of the food to be processed to obtain a first image; identifying the first image to determine first category information and first state information, wherein the first category information is the food category information of the food to be processed, and the first state information is the food state information of the food to be processed; generating target cooking parameters from a first database based on the first category information, the first state information, and the first region information; wherein the food state information is information describing the cooking maturity of the food to be processed, the first region information is the current region information where the cooking device is located, and the first database is a database constructed based on historical cooking data.

[0012] This invention proposes a method for determining cooking parameters. By running the above method for determining cooking parameters, an image acquisition device can be used to acquire an image of the food to be processed, namely, a first image. After acquiring the first image, image recognition is performed on the first image to know the food type information and food state information of the food to be processed, that is, to obtain the first type information and the first state information.

[0013] Having obtained the first state information and the first type information, the target cooking parameters are generated from the first database by combining the current region information of the cooking equipment, i.e., the first region information. In this process, the first state information is determined based on the first image of the ingredient to be processed; therefore, it can characterize the real-time cooking maturity of the ingredient. During the generation of the target cooking parameters, the real-time cooking maturity of the ingredient can be referenced to ensure that the generated target cooking parameters match the real-time cooking maturity of the ingredient. At this point, the cooking menu determined based on the target cooking parameters can be used for secondary cooking of already cooked ingredients, avoiding the predicament in related technical solutions where "automatic menus are created for uncooked ingredients and are no longer applicable to already cooked ingredients."

[0014] In the above technical solution, the current state of the ingredients to be processed can be used to generate suitable target cooking parameters. The cooking equipment can automatically generate cooking parameters, eliminating the need for users to manually set cooking parameters based on their cooking experience. This reduces the user's involvement in the cooking control process, simplifies user operation, and meets the cooking needs of different scenarios.

[0015] In addition, the method for determining cooking parameters proposed in this application has the following additional technical features.

[0016] In some technical solutions, optionally, the first database includes multiple sub-databases. Each data sample in each sub-database includes a second state information, a second region information, and a set of cooking parameters. Different sub-databases correspond to different ingredient types. The target cooking parameters are generated from the first database based on the first type information, the first state information, and the first region information. Specifically, this includes: finding the first sub-database in the first database, where the first sub-database is the sub-database corresponding to the first type information; determining multiple sets of similarities based on the second state information, the second region information, the first state information, and the first region information of each data sample in the first sub-database; and generating the target cooking parameters from the first sub-database based on the multiple sets of similarities.

[0017] In this technical solution, the first database is divided into multiple sub-databases based on the different types of ingredients. Each sub-database corresponds to a type of ingredient, and the data samples contained in each sub-database correspond to the same type of ingredient. Obviously, in the process of generating target cooking parameters by combining the first type information, the first region information, and the first state information, the first sub-database can be quickly located in the first database, reducing the amount of data that needs to be processed for matching data, thereby shortening the time for generating target cooking parameters.

[0018] In the above technical solution, multiple sets of similarity are calculated so that target cooking parameters can be generated from the first sub-database using multiple sets of similarity as references. In this process, cooking parameters that are most suitable for the ingredients to be processed can be generated as target cooking parameters, thereby ensuring the cooking effect of the ingredients to be processed.

[0019] In the above technical solution, similarity is used to describe the degree of similarity between the second state information and the second region information of each data sample and the first state information and the first region information corresponding to the first image. If the similarity is higher, it is considered that the food to be processed is closer to the data sample, and the cooking parameters corresponding to the data sample are more suitable for the food to be processed. When the cooking parameters that are most suitable for the food to be processed are obtained as the target cooking parameters, it can be determined that the food to be processed can achieve the best cooking effect and minimize cooking failure.

[0020] In some technical solutions, optionally, multiple sets of similarities are determined based on the second state information, second region information, first state information, and first region information of each data sample in the first sub-database. Specifically, this includes: processing the second state information, second region information, first state information, and first region information of each data sample using any one of multidimensional vector similarity, frequency statistics, or clustering algorithms to obtain a set of similarities corresponding to each data sample; and statistically analyzing each set of similarities to obtain multiple sets of similarities.

[0021] In this technical solution, any one of multidimensional vector similarity, frequency statistics, or clustering algorithms can be used to determine the similarity, so that the technical solution proposed in this invention can be adapted to the needs of different scenarios.

[0022] Multidimensional vector similarity can be understood as representing the second state information and the second region information of each data sample in vector form. For example, the second state information corresponds to the first vector, and the second region information is the second vector. At the same time, the first state information and the first region information are also represented in vector form, that is, the first state information corresponds to the third vector, and the first region information corresponds to the fourth vector. Then, the first vector and the third vector correspond to one similarity, and the second vector and the fourth vector correspond to one similarity. The set of similarities formed by the above two similarities is the similarity corresponding to the data sample.

[0023] In some technical solutions, multidimensional vector similarity can be cosine similarity.

[0024] In the above technical solutions, the frequency statistics and clustering algorithms can be selected according to actual needs, and will not be elaborated here.

[0025] In some technical solutions, optionally, each set of similarities includes a first similarity. Multiple sets of similarities are determined based on the second state information, second region information, first state information, and first region information of each data sample in the first sub-database. Specifically, this includes: calculating the second similarity between the second state information and the first state information of each data sample; calculating the third similarity between the second region information and the first region information of each data sample; and calculating the sum of the second similarity and the corresponding third similarity of each data sample to obtain the first similarity.

[0026] In this technical solution, the second similarity and the third similarity can be integrated to obtain the first similarity. In this process, a similarity can be used to characterize the similarity between the first state information, the first region information and the data sample, so as to simplify the steps of generating the target cooking parameters from the first sub-database based on multiple sets of similarities, thereby improving the efficiency of determining the target cooking parameters.

[0027] In some technical solutions, optionally, target cooking parameters are generated from a first sub-database based on multiple sets of similarities. Specifically, this includes: sorting the multiple sets of similarities, determining the data sample corresponding to the first similarity, where the first similarity is the maximum similarity among the multiple sets of similarities; and using the cooking parameters in the data sample corresponding to the first similarity as the target cooking parameters.

[0028] In this technical solution, a data sample that is most similar to the first state information and the first region information can be selected from the first sub-database, and the cooking parameters in the data sample can be used as the target cooking parameters. In this process, the cooking parameters that are most suitable for the ingredients to be processed can be selected as the target cooking parameters, thereby ensuring the cooking effect of the ingredients to be processed.

[0029] In some technical solutions, a convolutional neural network or an image classification model may be used to identify the first image to obtain first category information and first state information.

[0030] In this technical solution, a convolutional neural network or image classification model is used to identify the first image. This maximizes the ability of the convolutional neural network or image classification model to identify images, thereby shortening the time required to determine the first state information and the first category information, and improving the efficiency of generating target cooking parameters.

[0031] In some technical solutions, convolutional neural networks and image classification models can be selected according to actual needs, which will not be elaborated here.

[0032] In some technical solutions, the target cooking parameters may optionally include: cooking mode, cooking time, and cooking temperature.

[0033] In some technical solutions, the method for determining cooking parameters may optionally include: acquiring multiple historical cooking data, each historical cooking data including ingredient type information, ingredient status information, regional information, cooking parameters, and cooking completion degree; grouping the ingredient type information into multiple sub-databases, and constructing a first database by dividing the ingredient status information, regional information, cooking parameters, and cooking completion degree from the multiple historical cooking data into multiple sub-databases.

[0034] In this technical solution, historical cooking data is collected and used as reference data for generating target cooking parameters. Compared with cooking parameters from other devices or platforms, this data is more reliable and ensures that the determined target cooking parameters are more compatible with the state information of the ingredients to be processed, thus guaranteeing the cooking effect of the ingredients.

[0035] In the above technical solution, the data is divided into multiple sub-databases based on the different types of ingredients. Each sub-database corresponds to one type of ingredient. Obviously, the data samples contained in each sub-database correspond to the same type of ingredient. Clearly, in the process of generating target cooking parameters by combining the first type information, the first region information, and the first state information, the first sub-database can be quickly located in the first database, reducing the amount of data that needs to be processed for matching data, thereby shortening the time for generating target cooking parameters.

[0036] In the above technical solution, the cooking completion rate is statistically analyzed to update the first database. This allows the first database to learn and update cyclically, thereby adapting the most suitable cooking parameters for the ingredients to be processed as target cooking parameters and ensuring the cooking effect of the ingredients.

[0037] In some technical solutions, the method for determining cooking parameters may optionally include: receiving a first cooking completion rate after the cooking operation is completed according to the target cooking parameters; and updating a first database based on the first type information, the first status information, the first region information, the target cooking parameters, and the first cooking completion rate.

[0038] In this technical solution, the first cooking completion level is input by the user, which can be used to evaluate the cooking situation, and then the first cooking completion level, together with the first category information, the first status information, the first region information, and the target cooking parameters, are automatically updated in the first database.

[0039] Specifically, a first threshold can be preset. If the first cooking completion rate is greater than or equal to the first threshold, the data involved in this cooking will be used as a data sample and stored in the corresponding sub-database of the first database.

[0040] If the first cooking completion rate is less than the first threshold, discard the data involved in this cooking as a data sample.

[0041] In this process, by discarding historical cooking data with a first cooking completion rate of less than a first threshold, the first database can be updated in a positive direction, thereby adapting the most suitable cooking parameters for the ingredients to be processed as target cooking parameters, ensuring the cooking effect of the ingredients to be processed.

[0042] According to a second aspect of the present invention, the present invention provides a cooking parameter determination apparatus for a cooking device, the cooking device including a cooking chamber and an image acquisition device, comprising: a capturing unit, configured to control the image acquisition device to acquire an image of the food to be processed when the food to be processed is placed in the cooking chamber, thereby obtaining a first image; a determining unit, configured to identify the first image and determine first category information and first state information, wherein the first category information is the food category information of the food to be processed, and the first state information is the food state information of the food to be processed; and a generating unit, configured to generate target cooking parameters from a first database based on the first category information, the first state information, and the first region information; wherein the food state information is information describing the cooking maturity of the food to be processed, the first region information is the current region information of the cooking device, and the first database is a database constructed based on historical cooking data.

[0043] This invention proposes a device for determining cooking parameters. It can use an image acquisition device to acquire an image of the food to be processed, i.e., a first image. After acquiring the first image, image recognition is performed on the first image to know the food type information and food state information of the food to be processed, i.e., to obtain the first type information and the first state information.

[0044] Having obtained the first state information and the first type information, the target cooking parameters are generated from the first database by combining the current region information of the cooking equipment, i.e., the first region information. In this process, the first state information is determined based on the first image of the ingredient to be processed; therefore, it can characterize the real-time cooking maturity of the ingredient. During the generation of the target cooking parameters, the real-time cooking maturity of the ingredient can be referenced to ensure that the generated target cooking parameters match the real-time cooking maturity of the ingredient. At this point, the cooking menu determined based on the target cooking parameters can be used for secondary cooking of already cooked ingredients, avoiding the predicament in related technical solutions where "automatic menus are created for uncooked ingredients and are no longer applicable to already cooked ingredients."

[0045] In the above technical solution, the current state of the ingredients to be processed can be used to generate suitable target cooking parameters. The cooking equipment can automatically generate cooking parameters, eliminating the need for users to manually set cooking parameters based on their cooking experience. This reduces the user's involvement in the cooking control process, simplifies user operation, and meets the cooking needs of different scenarios.

[0046] In addition, the cooking parameter determination device proposed in this application has the following additional technical features.

[0047] In some technical solutions, optionally, the first database includes multiple sub-databases. Each data sample in each sub-database includes a second state information, a second region information, and a set of cooking parameters. The ingredient type information corresponding to different sub-databases is different. The generation unit is specifically used for: finding the first sub-database in the first database, where the first sub-database is the sub-database corresponding to the first type information; determining multiple sets of similarities based on the second state information, second region information, first state information, and first region information of each data sample in the first sub-database; and generating the target cooking parameters from the first sub-database based on the multiple sets of similarities.

[0048] In this technical solution, the first database is divided into multiple sub-databases based on the different types of ingredients. Each sub-database corresponds to a type of ingredient, and the data samples contained in each sub-database correspond to the same type of ingredient. Obviously, in the process of generating target cooking parameters by combining the first type information, the first region information, and the first state information, the first sub-database can be quickly located in the first database, reducing the amount of data that needs to be processed for matching data, thereby shortening the time for generating target cooking parameters.

[0049] In the above technical solution, multiple sets of similarity are calculated so that target cooking parameters can be generated from the first sub-database using multiple sets of similarity as references. In this process, cooking parameters that are most suitable for the ingredients to be processed can be generated as target cooking parameters, thereby ensuring the cooking effect of the ingredients to be processed.

[0050] In the above technical solution, similarity is used to describe the degree of similarity between the second state information and the second region information of each data sample and the first state information and the first region information corresponding to the first image. If the similarity is higher, it is considered that the food to be processed is closer to the data sample, and the cooking parameters corresponding to the data sample are more suitable for the food to be processed. When the cooking parameters that are most suitable for the food to be processed are obtained as the target cooking parameters, it can be determined that the food to be processed can achieve the best cooking effect and minimize cooking failure.

[0051] In some technical solutions, optionally, the generation unit is specifically used to: process the second state information, second region information, first state information and first region information of each data sample using any one of multidimensional vector similarity, frequency statistics and clustering algorithms to obtain a set of similarities corresponding to each data sample; and to perform statistics on each set of similarities to obtain multiple sets of similarities.

[0052] In this technical solution, any one of multidimensional vector similarity, frequency statistics, or clustering algorithms can be used to determine the similarity, so that the technical solution proposed in this invention can be adapted to the needs of different scenarios.

[0053] Multidimensional vector similarity can be understood as representing the second state information and the second region information of each data sample in vector form. For example, the second state information corresponds to the first vector, and the second region information is the second vector. At the same time, the first state information and the first region information are also represented in vector form, that is, the first state information corresponds to the third vector, and the first region information corresponds to the fourth vector. Then, the first vector and the third vector correspond to one similarity, and the second vector and the fourth vector correspond to one similarity. The set of similarities formed by the above two similarities is the similarity corresponding to the data sample.

[0054] In some technical solutions, multidimensional vector similarity can be cosine similarity.

[0055] In the above technical solutions, the frequency statistics and clustering algorithms can be selected according to actual needs, and will not be elaborated here.

[0056] In some technical solutions, optionally, each set of similarities includes a first similarity. The generation unit is specifically used to: calculate the second similarity between the second state information and the first state information of each data sample; calculate the third similarity between the second regional information and the first regional information of each data sample; and calculate the sum of the second similarity and the corresponding third similarity of each data sample to obtain the first similarity.

[0057] In this technical solution, the second similarity and the third similarity can be integrated to obtain the first similarity. In this process, a similarity can be used to characterize the similarity between the first state information, the first region information and the data sample, so as to simplify the steps of generating the target cooking parameters from the first sub-database based on multiple sets of similarities, thereby improving the efficiency of determining the target cooking parameters.

[0058] In some technical solutions, optionally, the generating unit is specifically used to: sort multiple sets of similarities, determine the data sample corresponding to the first similarity, wherein the first similarity is the maximum similarity among multiple sets of similarities; and use the cooking parameters in the data sample corresponding to the first similarity as the target cooking parameters.

[0059] In this technical solution, a data sample that is most similar to the first state information and the first region information can be selected from the first sub-database, and the cooking parameters in the data sample can be used as the target cooking parameters. In this process, the cooking parameters that are most suitable for the ingredients to be processed can be selected as the target cooking parameters, thereby ensuring the cooking effect of the ingredients to be processed.

[0060] In some technical solutions, a convolutional neural network or an image classification model may be used to identify the first image to obtain first category information and first state information.

[0061] In this technical solution, a convolutional neural network or image classification model is used to identify the first image. This maximizes the ability of the convolutional neural network or image classification model to identify images, thereby shortening the time required to determine the first state information and the first category information, and improving the efficiency of generating target cooking parameters.

[0062] In some technical solutions, convolutional neural networks and image classification models can be selected according to actual needs, which will not be elaborated here.

[0063] In some technical solutions, the target cooking parameters may optionally include: cooking mode, cooking time, and cooking temperature.

[0064] In some technical solutions, optionally, the generating unit is also used to: acquire multiple historical cooking data, each historical cooking data including ingredient type information, ingredient status information, regional information, cooking parameters and cooking completion degree; group the ingredient status information, regional information, cooking parameters and cooking completion degree in the multiple historical cooking data into multiple sub-databases by ingredient type information, so as to construct a first database.

[0065] In this technical solution, historical cooking data is collected and used as reference data for generating target cooking parameters. Compared with cooking parameters from other devices or platforms, this data is more reliable and ensures that the determined target cooking parameters are more compatible with the state information of the ingredients to be processed, thus guaranteeing the cooking effect of the ingredients.

[0066] In the above technical solution, the data is divided into multiple sub-databases based on the different types of ingredients. Each sub-database corresponds to one type of ingredient. Obviously, the data samples contained in each sub-database correspond to the same type of ingredient. Clearly, in the process of generating target cooking parameters by combining the first type information, the first region information, and the first state information, the first sub-database can be quickly located in the first database, reducing the amount of data that needs to be processed for matching data, thereby shortening the time for generating target cooking parameters.

[0067] In the above technical solution, the cooking completion rate is statistically analyzed to update the first database. This allows the first database to learn and update cyclically, thereby adapting the most suitable cooking parameters for the ingredients to be processed as target cooking parameters and ensuring the cooking effect of the ingredients.

[0068] In some technical solutions, optionally, the generating unit is also used to: receive a first cooking completion degree after the operation according to the target cooking parameters is completed; and update the first database based on the first type information, the first status information, the first region information, the target cooking parameters and the first cooking completion degree.

[0069] In this technical solution, the first cooking completion level is input by the user, which can be used to evaluate the cooking situation, and then the first cooking completion level, together with the first category information, the first status information, the first region information, and the target cooking parameters, are automatically updated in the first database.

[0070] Specifically, a first threshold can be preset. If the first cooking completion rate is greater than or equal to the first threshold, the data involved in this cooking will be used as a data sample and stored in the corresponding sub-database of the first database.

[0071] If the first cooking completion rate is less than the first threshold, discard the data involved in this cooking as a data sample.

[0072] In this process, by discarding historical cooking data with a first cooking completion rate of less than a first threshold, the first database can be updated in a positive direction, thereby adapting the most suitable cooking parameters for the ingredients to be processed as target cooking parameters, ensuring the cooking effect of the ingredients to be processed.

[0073] According to a third aspect of the present invention, the present invention provides an apparatus for determining cooking parameters, comprising a processor and a memory, the memory storing a program or instructions executable on the processor, wherein the program or instructions, when executed by the processor, implement the steps of the method for determining cooking parameters as described above.

[0074] According to a fourth aspect of the present invention, the present invention provides a readable storage medium on which a program or instructions are stored, which, when executed by a processor, implement the steps of a method for determining cooking parameters as described above.

[0075] According to a fifth aspect of the present invention, a cooking apparatus is provided, comprising: a means for determining any of the cooking parameters described above; and / or a readable storage medium as described above.

[0076] Additional aspects and advantages of the invention will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. Attached Figure Description

[0077] The above and / or additional aspects and advantages of the present invention will become apparent and readily understood from the description of the embodiments taken in conjunction with the following drawings, in which:

[0078] Figure 1 A flowchart illustrating a method for determining cooking parameters according to an embodiment of the present invention is shown;

[0079] Figure 2 A schematic diagram of the structure of a cooking device according to an embodiment of the present invention is shown:

[0080] Figure 3 An interactive schematic diagram of the cooking equipment in an embodiment of the present invention is shown;

[0081] Figure 4 A schematic block diagram of a cooking parameter determination device according to an embodiment of the present invention is shown;

[0082] Figure 5 The second schematic block diagram shows a device for determining cooking parameters according to an embodiment of the present invention.

[0083] in, Figure 2The correspondence between the reference numerals and component names in the attached drawings is as follows:

[0084] 200 Cooking equipment, 202 Cooking cavity, 204 Image acquisition device. Detailed Implementation

[0085] To better understand the above aspects, features, and advantages of the present invention, the present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments. It should be noted that, unless otherwise specified, the embodiments and features described in these embodiments can be combined with each other.

[0086] Many specific details are set forth in the following description in order to provide a full understanding of the invention. However, the invention may also be practiced in other ways different from those described herein, and therefore the scope of protection of the invention is not limited to the specific embodiments disclosed below.

[0087] In one embodiment of this application, such as Figure 1 and Figure 2 As shown, a method for determining cooking parameters is provided for a cooking device 200. The cooking device 200 includes a cooking cavity 202 and an image acquisition device 204, comprising:

[0088] Step 102: With the food to be processed placed into the cooking cavity, control the image acquisition device to acquire an image of the food to be processed to obtain a first image;

[0089] Step 104: Recognize the first image to determine the first type information and the first state information. The first type information is the type information of the food to be processed, and the first state information is the state information of the food to be processed.

[0090] Step 106: Target cooking parameters are generated from the first database based on the first type information, the first state information, and the first region information.

[0091] Among them, the ingredient status information describes the cooking maturity of the ingredients to be processed, the first region information is the current region where the cooking equipment is located, and the first database is a database built based on historical cooking data.

[0092] This invention proposes a method for determining cooking parameters. By running the above method for determining cooking parameters, an image acquisition device can be used to acquire an image of the food to be processed, namely, a first image. After acquiring the first image, image recognition is performed on the first image to know the food type information and food state information of the food to be processed, that is, to obtain the first type information and the first state information.

[0093] Having obtained the first state information and the first type information, the target cooking parameters are generated from the first database by combining the current region information of the cooking device, i.e., the first region information. In this process, the first state information is determined based on the first image of the ingredient to be processed; therefore, it can characterize the real-time cooking maturity of the ingredient. During the generation of the target cooking parameters, the real-time cooking maturity of the ingredient can be referenced to ensure that the generated target cooking parameters match the real-time cooking maturity of the ingredient. At this point, the cooking menu determined based on the target cooking parameters can be used for secondary cooking of already cooked ingredients, avoiding the predicament in related embodiments where "automatic menus are created for uncooked ingredients and are no longer applicable to already cooked ingredients."

[0094] In the above embodiments, the target cooking parameters can be generated by referring to the current state of the ingredients to be processed. The cooking equipment can automatically generate cooking parameters, eliminating the need for users to manually set cooking parameters based on their cooking experience. This reduces the user's involvement in the cooking control process, simplifies user operation, and meets the cooking needs of different scenarios.

[0095] Furthermore, if the ingredients to be processed are cooked a second time using the cooking parameters used when the ingredients are completely "raw", the cooked ingredients may be overcooked.

[0096] In embodiments of the present invention, the target cooking parameters are generated with reference to the current state of the ingredients to be processed, rather than being determined based on the ingredients being completely "raw". Therefore, the target cooking parameters can be adapted to the current state of the ingredients to be processed, thereby ensuring the cooking effect of the ingredients to be processed.

[0097] For example, if a user reheats a cooked steamed bun using the automatic menu of an automatic steamer, the bun will become dry and hard, which will seriously affect its taste.

[0098] By referencing the state information of the cooked steamed buns and determining the target cooking parameters, a second cooking of the cooked steamed buns can effectively improve the problem of the steamed buns being dry and hard, thereby ensuring the reheating effect.

[0099] In the above embodiments, since the first database is a database built based on historical cooking data, the historical cooking data of the cooking equipment can be used to generate target cooking parameters. It can be understood that using the user's historical cooking data as reference data for generating target cooking parameters is more referential than cooking parameters of other devices or platforms, making the determined target cooking parameters more compatible with the food status information of the ingredients to be processed, and ensuring the cooking effect of the ingredients to be processed.

[0100] Furthermore, the use of first-region information can eliminate the influence of regional dietary differences on target cooking parameters, thereby making the target cooking parameters more accurate and ensuring the cooking effect of the ingredients to be processed.

[0101] In the above embodiments, the first region information can be determined by locating the cooking equipment.

[0102] In some embodiments, optionally, when the cooking device is first used and connected to the network, the cooking device is registered to obtain information about the current location of the cooking device, thereby obtaining first location information.

[0103] In some embodiments, optionally, when a user uses an electronic device to perform close-range linkage control with a cooking device, the positioning information of the electronic device is used to determine the first region information.

[0104] For example, if the electronic device and the cooking device are linked and controlled via Bluetooth, then if the electronic device is located in the first city of the first province, then the first city of the first province will be used as the first region information of the cooking device.

[0105] For example, if an electronic device and a cooking device are simultaneously connected to the same Wi-Fi hotspot, and the Wi-Fi hotspot's Internet Protocol address is located in the first city of the first province, then the first city of the first province will be used as the first region information of the cooking device.

[0106] In the above embodiments, the information on the type of ingredients can be understood as the type of ingredients, such as fish, steamed buns, rice, noodles or other types, which will not be elaborated here.

[0107] In the above embodiments, the ingredient status information serves as information describing the cooking doneness of the ingredients to be processed. It can be "completely raw", "half-cooked", "fully cooked", or other descriptive methods used to describe the cooking doneness of the ingredients.

[0108] For example, the cooking process of the ingredients is divided into percentages, and the state of the ingredients under different percentage conditions is recorded. When a first image is obtained, the state of the ingredients in the first image is compared with the state of the ingredients under different percentage conditions, and then the target percentage corresponding to the ingredients to be processed in the first image is determined. This target percentage is then used as the first state information.

[0109] In some embodiments, optionally, the first database includes multiple sub-databases. Each data sample in each sub-database includes a second state information, a second region information, and a set of cooking parameters. Different sub-databases correspond to different ingredient types. The target cooking parameters are generated from the first database based on the first type information, the first state information, and the first region information. Specifically, this includes: finding the first sub-database in the first database, where the first sub-database is the sub-database corresponding to the first type information; determining multiple sets of similarities based on the second state information, the second region information, the first state information, and the first region information of each data sample in the first sub-database; and generating the target cooking parameters from the first sub-database based on the multiple sets of similarities.

[0110] In this embodiment, the first database is divided into multiple sub-databases based on the different types of ingredients. Each sub-database corresponds to a type of ingredient, and the data samples contained in each sub-database correspond to the same type of ingredient. Obviously, in the process of generating target cooking parameters by combining the first type information, the first region information, and the first state information, the first sub-database can be quickly located in the first database, reducing the amount of data that needs to be processed for matching data, thereby shortening the time for generating target cooking parameters.

[0111] In the above embodiments, by calculating multiple sets of similarity, target cooking parameters are generated from the first sub-database using multiple sets of similarity as references. In this process, cooking parameters that are most suitable for the ingredients to be processed can be generated as target cooking parameters, thereby ensuring the cooking effect of the ingredients to be processed.

[0112] In the above embodiments, similarity is used to describe the degree of similarity between the second state information and the second region information of each data sample and the first state information and the first region information corresponding to the first image. If the similarity is higher, it is considered that the food to be processed is closer to the data sample, and the cooking parameters corresponding to the data sample are more suitable for the food to be processed. When the cooking parameters that are most suitable for the food to be processed are obtained as the target cooking parameters, it can be determined that the food to be processed can achieve the best cooking effect and minimize cooking failure.

[0113] In some embodiments, optionally, multiple sets of similarities are determined based on the second state information, second region information, first state information, and first region information of each data sample in the first sub-database. Specifically, this includes: processing the second state information, second region information, first state information, and first region information of each data sample using any one of multidimensional vector similarity, frequency statistics, or clustering algorithms to obtain a set of similarities corresponding to each data sample; and performing statistics on each set of similarities to obtain multiple sets of similarities.

[0114] In this embodiment, any one of multidimensional vector similarity, frequency statistics, or clustering algorithms can be used to determine the similarity, so that the embodiment proposed in this invention can be adapted to the needs of different scenarios.

[0115] Multidimensional vector similarity can be understood as representing the second state information and the second region information of each data sample in vector form. For example, the second state information corresponds to the first vector, and the second region information is the second vector. At the same time, the first state information and the first region information are also represented in vector form, that is, the first state information corresponds to the third vector, and the first region information corresponds to the fourth vector. Then, the first vector and the third vector correspond to one similarity, and the second vector and the fourth vector correspond to one similarity. The set of similarities formed by the above two similarities is the similarity corresponding to the data sample.

[0116] In some embodiments, multidimensional vector similarity can be cosine similarity.

[0117] In the above embodiments, the frequency statistics and clustering algorithms can be selected according to actual needs, and will not be elaborated further here.

[0118] In some embodiments, optionally, each set of similarities includes a first similarity. Multiple sets of similarities are determined based on the second state information, second region information, first state information, and first region information of each data sample in the first sub-database. Specifically, this includes: calculating the second similarity between the second state information and the first state information of each data sample; calculating the third similarity between the second region information and the first region information of each data sample; and calculating the sum of the second similarity and the corresponding third similarity of each data sample to obtain the first similarity.

[0119] In this embodiment, the second similarity and the third similarity can be integrated to obtain the first similarity. In this process, a similarity can be used to characterize the similarity between the first state information, the first region information and the data sample, so as to simplify the steps of generating the target cooking parameters from the first sub-database based on multiple sets of similarities, thereby improving the efficiency of determining the target cooking parameters.

[0120] In some embodiments, optionally, the target cooking parameters are generated from the first sub-database based on multiple sets of similarities, specifically including: sorting the multiple sets of similarities, determining the data sample corresponding to the first similarity, wherein the first similarity is the maximum similarity among the multiple sets of similarities; and using the cooking parameters in the data sample corresponding to the first similarity as the target cooking parameters.

[0121] In this embodiment, a data sample that is most similar to the first state information and the first region information can be selected from the first sub-database, and the cooking parameters in the data sample can be used as the target cooking parameters. In this process, the cooking parameters that are most suitable for the ingredients to be processed can be selected as the target cooking parameters, thereby ensuring the cooking effect of the ingredients to be processed.

[0122] In some embodiments, a convolutional neural network or an image classification model may be used to identify the first image to obtain first category information and first state information.

[0123] In this embodiment, using a convolutional neural network or image classification model to identify the first image can maximize the image recognition capabilities of the convolutional neural network or image classification model, thereby shortening the time required to determine the first state information and the first category information, and improving the efficiency of generating target cooking parameters.

[0124] In some embodiments, convolutional neural networks and image classification models can be selected according to actual needs, which will not be elaborated here.

[0125] In some embodiments, the target cooking parameters may optionally include: cooking mode, cooking time, and cooking temperature.

[0126] In the above embodiments, the cooking mode can be one or more of "hot air", "steam", "bake", "microwave" and "electric heating tube".

[0127] In some embodiments, the method for determining cooking parameters may further include: acquiring multiple historical cooking data, each historical cooking data including ingredient type information, ingredient status information, regional information, cooking parameters, and cooking completion degree; grouping the ingredient status information, regional information, cooking parameters, and cooking completion degree in the multiple historical cooking data into multiple sub-databases to construct a first database.

[0128] In this embodiment, each historical cooking data is statistically analyzed, and the user's historical cooking data is used as reference data to generate target cooking parameters. Compared with cooking parameters from other devices or platforms, this data is more reliable and makes the determined target cooking parameters more compatible with the food status information of the ingredients to be processed, thus ensuring the cooking effect of the ingredients to be processed.

[0129] In the above embodiments, the data is divided into multiple sub-databases based on the different types of ingredients. Each sub-database corresponds to one type of ingredient. Obviously, the data samples contained in each sub-database correspond to the same type of ingredient. Clearly, in the process of generating target cooking parameters by combining the first type information, the first region information, and the first state information, the first sub-database can be quickly located in the first database, reducing the amount of data that needs to be processed for matching data, thereby shortening the time for generating target cooking parameters.

[0130] In the above embodiments, the cooking completion rate is statistically analyzed to update the first database, enabling the first database to learn and update cyclically. This allows the most suitable cooking parameters to be matched as target cooking parameters for the ingredients to be processed, ensuring the cooking effect of the ingredients.

[0131] In some embodiments, the method for determining cooking parameters may optionally include: receiving a first cooking completion rate after the operation is completed according to the target cooking parameters; and updating a first database based on first category information, first status information, first region information, target cooking parameters, and the first cooking completion rate.

[0132] In this embodiment, the first cooking completion level is input by the user and can be used to evaluate the cooking situation. Then, the first cooking completion level, along with the first category information, the first status information, the first region information, and the target cooking parameters, are automatically updated in the first database.

[0133] Specifically, a first threshold can be preset. If the first cooking completion rate is greater than or equal to the first threshold, the data involved in this cooking will be used as a data sample and stored in the corresponding sub-database of the first database.

[0134] If the first cooking completion rate is less than the first threshold, discard the data involved in this cooking as a data sample.

[0135] In this process, by discarding historical cooking data with a first cooking completion rate of less than a first threshold, the first database can be updated in a positive direction, thereby adapting the most suitable cooking parameters for the ingredients to be processed as target cooking parameters, ensuring the cooking effect of the ingredients to be processed.

[0136] In one embodiment, the method for determining cooking parameters includes the following steps:

[0137] Step 1: After each user completes a cooking session, image recognition technology records multiple dimensions of the cooking process in the server database, including the type of ingredients, their initial state, the user's region, cooking temperature, cooking time, cooking mode, and cooking completion rate.

[0138] Among them, the type of ingredients is the same as the information on the type of ingredients in this application, the initial state of the ingredients is the same as the state information of the ingredients, and the cooking completion degree is the same as the cooking maturity degree.

[0139] Step 2: When the user's historical cooking data reaches a certain level, the database will group and filter according to the type of ingredients. In the database of each type of ingredients, the initial state of the ingredients, the user's region, and cooking parameters will be statistically analyzed and clustered to form an effective cooking parameter (mode, temperature, time) database.

[0140] Step 3: When the user puts in the ingredients, the camera immediately determines the type of the ingredients based on the image. Then, based on the type of ingredients, their condition, the user's region, and other multi-dimensional information, it matches the cooking parameter database for that ingredient. By comparing the similarity of the multi-dimensional information, the corresponding cooking parameters can be generated.

[0141] Step 4: Finally, the user starts the device according to the generated cooking parameters. After cooking is completed, the user can score the cooking completion. The score is then stored in the user's cooking history database and a self-learning loop is implemented.

[0142] In step 1, the image recognition technology can identify the types of cooking ingredients and their initial state through convolutional neural networks and visual classification algorithms. When a new category appears in the database, the data can be automatically added to update the category, and the system can be trained and optimized.

[0143] In step 2, the type of ingredients, the initial state of the ingredients, and the user's region are all important dimensions to consider in statistics and clustering. For example, the cooking methods for the same ingredient will vary greatly in different regions.

[0144] Step 3 can use multidimensional vector similarity, frequency statistics, clustering algorithms, etc. to generate cooking parameters.

[0145] In this embodiment, the problem of existing cooking parameter generation schemes being limited by the number of automatic menus and the ingredient status of the automatic menus is solved. Users can use cooking parameters that have been successfully cooked to generate target cooking parameters, and a self-learning loop can be implemented. This technology can also be applied to devices on the same platform.

[0146] The first database can be applied to environments with servers, integration services, or data storage systems.

[0147] Specifically, such as Figure 3 As shown, a historical cooking database is constructed and deployed on a cloud service. Access is performed on the local computer. The database contains a large number of high-resolution cooking ingredient images obtained through photography and users' historical cooking data. Cooking parameters can be added and updated in the database. During the database construction, data cleaning and labeling services are deployed on the cloud service platform to achieve preprocessing of users' historical cooking images and data.

[0148] Based on the user's historical cooking database, the system groups, statistically analyzes, and clusters the multidimensional data in the database to generate corresponding cooking parameters for different ingredients, their initial states, and different regions. During user cooking, image recognition is deployed in the cloud, while cooking parameter generation can be implemented either on cloud services or locally.

[0149] The user's historical cooking database is updated after each user finishes cooking. Users can rate the cooking results to indicate their level of completion; otherwise, the backend can add supplementary annotations based on before-and-after images.

[0150] In one embodiment, such as Figure 4 As shown, the present invention provides a cooking parameter determination device 400 for a cooking device, the cooking device including a cooking chamber and an image acquisition device, including: a shooting unit 402, used to control the image acquisition device to acquire an image of the food to be processed when the food to be processed is placed in the cooking chamber, to obtain a first image; a determination unit 404, used to identify the first image and determine first type information and first state information, the first type information being the type information of the food to be processed, and the first state information being the state information of the food to be processed; and a generation unit 406, used to generate target cooking parameters from a first database based on the first type information, the first state information, and the first region information; wherein, the food state information is information describing the cooking maturity of the food to be processed, the first region information is the current region information of the cooking device, and the first database is a database constructed based on historical cooking data.

[0151] The present invention proposes a cooking parameter determination device 400, which can use an image acquisition device to acquire an image of the food to be processed, namely a first image. After acquiring the first image, image recognition is performed on the first image to know the food type information and food state information of the food to be processed, that is, to obtain the first type information and the first state information.

[0152] Having obtained the first state information and the first type information, the target cooking parameters are generated from the first database by combining the current region information of the cooking device, i.e., the first region information. In this process, the first state information is determined based on the first image of the ingredient to be processed; therefore, it can characterize the real-time cooking maturity of the ingredient. During the generation of the target cooking parameters, the real-time cooking maturity of the ingredient can be referenced to ensure that the generated target cooking parameters match the real-time cooking maturity of the ingredient. At this point, the cooking menu determined based on the target cooking parameters can be used for secondary cooking of already cooked ingredients, avoiding the predicament in related embodiments where "automatic menus are created for uncooked ingredients and are no longer applicable to already cooked ingredients."

[0153] In the above embodiments, the target cooking parameters can be generated by referring to the current state of the ingredients to be processed. The cooking equipment can automatically generate cooking parameters, eliminating the need for users to manually set cooking parameters based on their cooking experience. This reduces the user's involvement in the cooking control process, simplifies user operation, and meets the cooking needs of different scenarios.

[0154] Furthermore, if the ingredients to be processed are cooked a second time using the cooking parameters used when the ingredients are completely "raw", the cooked ingredients may be overcooked.

[0155] In embodiments of the present invention, the target cooking parameters are generated with reference to the current state of the ingredients to be processed, rather than being determined based on the ingredients being completely "raw". Therefore, the target cooking parameters can be adapted to the current state of the ingredients to be processed, thereby ensuring the cooking effect of the ingredients to be processed.

[0156] For example, if a user reheats a cooked steamed bun using the automatic menu of an automatic steamer, the bun will become dry and hard, which will seriously affect its taste.

[0157] By referencing the state information of the cooked steamed buns and determining the target cooking parameters, a second cooking of the cooked steamed buns can effectively improve the problem of the steamed buns being dry and hard, thereby ensuring the reheating effect.

[0158] In the above embodiments, since the first database is a database built based on historical cooking data, the historical cooking data of the cooking equipment can be used to generate target cooking parameters. It can be understood that using the user's historical cooking data as reference data for generating target cooking parameters is more referential than cooking parameters of other devices or platforms, making the determined target cooking parameters more compatible with the food status information of the ingredients to be processed, and ensuring the cooking effect of the ingredients to be processed.

[0159] Furthermore, the use of first-region information can eliminate the influence of regional dietary differences on target cooking parameters, thereby making the target cooking parameters more accurate and ensuring the cooking effect of the ingredients to be processed.

[0160] In the above embodiments, the first region information can be determined by locating the cooking equipment.

[0161] In some embodiments, optionally, when the cooking device is first used and connected to the network, the cooking device is registered to obtain information about the current location of the cooking device, thereby obtaining first location information.

[0162] In some embodiments, optionally, when a user uses an electronic device to perform close-range linkage control with a cooking device, the positioning information of the electronic device is used to determine the first region information.

[0163] For example, if the electronic device and the cooking device are linked and controlled via Bluetooth, then if the electronic device is located in the first city of the first province, then the first city of the first province will be used as the first region information of the cooking device.

[0164] For example, if an electronic device and a cooking device are simultaneously connected to the same Wi-Fi hotspot, and the Wi-Fi hotspot's Internet Protocol address is located in the first city of the first province, then the first city of the first province will be used as the first region information of the cooking device.

[0165] In the above embodiments, the information on the type of ingredients can be understood as the type of ingredients, such as fish, steamed buns, rice, noodles or other types, which will not be elaborated here.

[0166] In the above embodiments, the ingredient status information serves as information describing the cooking doneness of the ingredients to be processed. It can be "completely raw", "half-cooked", "fully cooked", or other descriptive methods used to describe the cooking doneness of the ingredients.

[0167] For example, the cooking process of the ingredients is divided into percentages, and the state of the ingredients under different percentage conditions is recorded. When a first image is obtained, the state of the ingredients in the first image is compared with the state of the ingredients under different percentage conditions, and then the target percentage corresponding to the ingredients to be processed in the first image is determined. This target percentage is then used as the first state information.

[0168] In addition, the cooking parameter determination device proposed in this application has the following additional technical features.

[0169] In some embodiments, optionally, the first database includes multiple sub-databases, and each data sample in each sub-database includes a second state information, a second region information, and a set of cooking parameters. The ingredient type information corresponding to different sub-databases is different. The generation unit 406 is specifically used for: finding the first sub-database in the first database, the first sub-database being the sub-database corresponding to the first type information; determining multiple sets of similarities based on the second state information, second region information, first state information, and first region information of each data sample in the first sub-database; and generating target cooking parameters from the first sub-database based on the multiple sets of similarities.

[0170] In this embodiment, the first database is divided into multiple sub-databases based on the different types of ingredients. Each sub-database corresponds to a type of ingredient, and the data samples contained in each sub-database correspond to the same type of ingredient. Obviously, in the process of generating target cooking parameters by combining the first type information, the first region information, and the first state information, the first sub-database can be quickly located in the first database, reducing the amount of data that needs to be processed for matching data, thereby shortening the time for generating target cooking parameters.

[0171] In the above embodiments, by calculating multiple sets of similarity, target cooking parameters are generated from the first sub-database using multiple sets of similarity as references. In this process, cooking parameters that are most suitable for the ingredients to be processed can be generated as target cooking parameters, thereby ensuring the cooking effect of the ingredients to be processed.

[0172] In the above embodiments, similarity is used to describe the degree of similarity between the second state information and the second region information of each data sample and the first state information and the first region information corresponding to the first image. If the similarity is higher, it is considered that the food to be processed is closer to the data sample, and the cooking parameters corresponding to the data sample are more suitable for the food to be processed. When the cooking parameters that are most suitable for the food to be processed are obtained as the target cooking parameters, it can be determined that the food to be processed can achieve the best cooking effect and minimize cooking failure.

[0173] In some embodiments, optionally, the generation unit 406 is specifically used to: process the second state information, second region information, first state information and first region information of each data sample using any one of multidimensional vector similarity, frequency statistics and clustering algorithms to obtain a set of similarities corresponding to each data sample; and perform statistics on each set of similarities to obtain multiple sets of similarities.

[0174] In this embodiment, any one of multidimensional vector similarity, frequency statistics, or clustering algorithms can be used to determine the similarity, so that the embodiment proposed in this invention can be adapted to the needs of different scenarios.

[0175] Multidimensional vector similarity can be understood as representing the second state information and the second region information of each data sample in vector form. For example, the second state information corresponds to the first vector, and the second region information is the second vector. At the same time, the first state information and the first region information are also represented in vector form, that is, the first state information corresponds to the third vector, and the first region information corresponds to the fourth vector. Then, the first vector and the third vector correspond to one similarity, and the second vector and the fourth vector correspond to one similarity. The set of similarities formed by the above two similarities is the similarity corresponding to the data sample.

[0176] In some embodiments, multidimensional vector similarity can be cosine similarity.

[0177] In the above embodiments, the frequency statistics and clustering algorithms can be selected according to actual needs, and will not be elaborated further here.

[0178] In some embodiments, optionally, each set of similarities includes a first similarity, and the generation unit 406 is specifically configured to: calculate the second similarity between the second state information and the first state information of each data sample; calculate the third similarity between the second region information and the first region information of each data sample; and calculate the sum of the second similarity and the corresponding third similarity of each data sample to obtain the first similarity.

[0179] In this embodiment, the second similarity and the third similarity can be integrated to obtain the first similarity. In this process, a similarity can be used to characterize the similarity between the first state information, the first region information and the data sample, so as to simplify the steps of generating the target cooking parameters from the first sub-database based on multiple sets of similarities, thereby improving the efficiency of determining the target cooking parameters.

[0180] In some embodiments, optionally, the generating unit 406 is specifically used to: sort multiple sets of similarities, determine the data sample corresponding to the first similarity, wherein the first similarity is the maximum similarity among multiple sets of similarities; and use the cooking parameters in the data sample corresponding to the first similarity as the target cooking parameters.

[0181] In this embodiment, a data sample that is most similar to the first state information and the first region information can be selected from the first sub-database, and the cooking parameters in the data sample can be used as the target cooking parameters. In this process, the cooking parameters that are most suitable for the ingredients to be processed can be selected as the target cooking parameters, thereby ensuring the cooking effect of the ingredients to be processed.

[0182] In some embodiments, a convolutional neural network or an image classification model may be used to identify the first image to obtain first category information and first state information.

[0183] In this embodiment, using a convolutional neural network or image classification model to identify the first image can maximize the image recognition capabilities of the convolutional neural network or image classification model, thereby shortening the time required to determine the first state information and the first category information, and improving the efficiency of generating target cooking parameters.

[0184] In some embodiments, convolutional neural networks and image classification models can be selected according to actual needs, which will not be elaborated here.

[0185] In some embodiments, the target cooking parameters may optionally include: cooking mode, cooking time, and cooking temperature.

[0186] In the above embodiments, the cooking mode can be one or more of "hot air", "steam", "bake", "microwave" and "electric heating tube".

[0187] In some embodiments, optionally, the generating unit 406 is further configured to: acquire multiple historical cooking data, each historical cooking data including ingredient type information, ingredient status information, region information, cooking parameters and cooking completion degree; group the ingredient status information, region information, cooking parameters and cooking completion degree in the multiple historical cooking data into multiple sub-databases by ingredient type information, so as to construct a first database.

[0188] In this embodiment, each historical cooking data is statistically analyzed, and the user's historical cooking data is used as reference data to generate target cooking parameters. Compared with cooking parameters from other devices or platforms, this data is more reliable and makes the determined target cooking parameters more compatible with the food status information of the ingredients to be processed, thus ensuring the cooking effect of the ingredients to be processed.

[0189] In the above embodiments, the data is divided into multiple sub-databases based on the different types of ingredients. Each sub-database corresponds to one type of ingredient. Obviously, the data samples contained in each sub-database correspond to the same type of ingredient. Clearly, in the process of generating target cooking parameters by combining the first type information, the first region information, and the first state information, the first sub-database can be quickly located in the first database, reducing the amount of data that needs to be processed for matching data, thereby shortening the time for generating target cooking parameters.

[0190] In the above embodiments, the cooking completion rate is statistically analyzed to update the first database, enabling the first database to learn and update cyclically. This allows the most suitable cooking parameters to be matched as target cooking parameters for the ingredients to be processed, ensuring the cooking effect of the ingredients.

[0191] In some embodiments, the generating unit 406 is optionally further configured to: receive a first cooking completion degree after the operation according to the target cooking parameters is completed; and update the first database based on the first category information, the first status information, the first region information, the target cooking parameters, and the first cooking completion degree.

[0192] In this embodiment, the first cooking completion level is input by the user and can be used to evaluate the cooking situation. Then, the first cooking completion level, along with the first category information, the first status information, the first region information, and the target cooking parameters, are automatically updated in the first database.

[0193] Specifically, a first threshold can be preset. If the first cooking completion rate is greater than or equal to the first threshold, the data involved in this cooking will be used as a data sample and stored in the corresponding sub-database of the first database.

[0194] If the first cooking completion rate is less than the first threshold, discard the data involved in this cooking as a data sample.

[0195] In this process, by discarding historical cooking data with a first cooking completion rate of less than a first threshold, the first database can be updated in a positive direction, thereby adapting the most suitable cooking parameters for the ingredients to be processed as target cooking parameters, ensuring the cooking effect of the ingredients to be processed.

[0196] In one embodiment, such as Figure 5 As shown, the present invention provides a cooking parameter determination device 500, including a processor 502 and a memory 504. The memory 504 stores a program or instruction that can be executed on the processor 502. When the program or instruction is executed by the processor 502, it implements the steps of the cooking parameter determination method as described above.

[0197] The memory 504 can be used to store software programs and various data. The memory 504 mainly includes a first storage area for storing programs or instructions and a second storage area for storing data. The first storage area can store the operating system, application programs or instructions required for at least one function (such as sound playback function, image playback function, etc.). Furthermore, the memory 504 can include volatile memory or non-volatile memory, or both. The non-volatile memory can be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. Volatile memory can be random access memory (RAM), static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDRSDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link dynamic random access memory (SLDRAM), and direct memory bus RAM (DRRAM). The memory in the embodiments of this application includes, but is not limited to, these and any other suitable types of memory.

[0198] In one embodiment, the present invention provides a readable storage medium storing a program or instructions that, when executed by a processor, implement the steps of a method for determining cooking parameters as described above.

[0199] In one embodiment, the present invention provides a cooking apparatus, comprising: a means for determining any of the cooking parameters described above; and / or a readable storage medium as described above.

[0200] In some embodiments, the cooking device may be one of a microwave oven, an electric oven, or a microwave-steam-grill combination appliance.

[0201] The terms "first" and "second" in the specification and claims of this application may explicitly or implicitly include one or more of the features. In the textual description of this invention, unless otherwise stated, "a plurality of" means two or more. Furthermore, in the specification and claims, "and / or" indicates at least one of the connected objects, and the character " / " generally indicates that the preceding and following objects are in an "or" relationship.

[0202] In the textual description of this invention, it is understood that, unless explicitly specified and limited, the terms "installation," "connection," and "linking" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal communication between two components. Those skilled in the art will understand the specific meaning of the above terms in this invention based on the specific circumstances.

[0203] In the claims, description, and accompanying drawings of this invention, the terms "one embodiment," "some embodiments," "specific embodiment," etc., refer to a specific feature, structure, material, or characteristic described in connection with that embodiment or example, which is included in at least one embodiment or example of the invention. In the claims, description, and accompanying drawings of this invention, illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0204] The above are merely preferred embodiments of the present invention and are not intended to limit the present invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A method for determining cooking parameters, used in a cooking device, the cooking device comprising a cooking cavity and an image acquisition device, characterized in that, include: When the food to be processed is placed into the cooking cavity, the image acquisition device is controlled to acquire an image of the food to be processed, and a first image is obtained. The first image is identified to determine first type information and first state information. The first type information is the food type information of the food to be processed, and the first state information is the food state information of the food to be processed. Target cooking parameters are generated from the first database based on the first type information, the first state information, and the first region information. The ingredient status information describes the cooking maturity of the ingredient to be processed, the first region information is the current region where the cooking equipment is located, and the first database is a database built based on historical cooking data.

2. The method for determining cooking parameters according to claim 1, characterized in that, The first database includes multiple sub-databases. Each data sample in each sub-database includes a second state information, a second region information, and a set of cooking parameters. Different sub-databases correspond to different ingredient types. The step of generating target cooking parameters from the first database based on the first type information, the first state information, and the first region information specifically includes: The first sub-database is found in the first database, and the first sub-database is the sub-database corresponding to the first type of information; Multiple sets of similarity are determined based on the second state information, the second region information, the first state information, and the first region information of each data sample in the first sub-database; Target cooking parameters are generated from the first sub-database based on multiple sets of similarities.

3. The method for determining cooking parameters according to claim 2, characterized in that, The determination of multiple sets of similarities based on the second state information, the second region information, the first state information, and the first region information of each data sample in the first sub-database specifically includes: The second state information, second region information, first state information, and first region information of each data sample are processed using any one of the following algorithms: multidimensional vector similarity, frequency statistics, and clustering, to obtain a set of similarities corresponding to each data sample. Statistical analysis was performed on each group of similarities to obtain multiple groups of similarities.

4. The method for determining cooking parameters according to claim 2, characterized in that, Each similarity set includes a first similarity. The determination of multiple similarity sets based on the second state information, second region information, first state information, and first region information of each data sample in the first sub-database specifically includes: Calculate the second similarity between the second state information and the first state information for each data sample; Calculate the third similarity between the second region information and the first region information for each data sample; The first similarity is obtained by summing the second similarity and the corresponding third similarity for each data sample.

5. The method for determining cooking parameters according to claim 2, characterized in that, The generation of target cooking parameters from the first sub-database based on multiple sets of similarities specifically includes: The data sample corresponding to the first similarity is determined by sorting the multiple sets of similarities, where the first similarity is the maximum similarity among the multiple sets of similarities; The cooking parameters in the data sample corresponding to the first similarity are used as the target cooking parameters.

6. The method for determining cooking parameters according to claim 1, characterized in that, The first image is identified using a convolutional neural network or an image classification model to obtain the first category information and the first state information.

7. The method for determining cooking parameters according to any one of claims 1 to 6, characterized in that, The target cooking parameters include: Cooking mode, cooking time, and cooking temperature.

8. The method for determining cooking parameters according to any one of claims 1 to 6, characterized in that, The method for determining the cooking parameters also includes: Acquire multiple historical cooking data, each of which includes information on ingredient type, ingredient status, region, cooking parameters, and cooking completion rate; The first database is constructed by grouping the ingredient type information into multiple sub-databases, which are then divided into multiple sub-databases based on the ingredient status information, the region information, the cooking parameters, and the cooking completion degree from multiple historical cooking data.

9. The method for determining cooking parameters according to any one of claims 1 to 6, characterized in that, The method for determining the cooking parameters also includes: After the cooking process is completed according to the target cooking parameters, the first cooking completion rate is received; The first database is updated based on the first type information, the first status information, the first region information, the target cooking parameters, and the first cooking completion rate.

10. A device for determining cooking parameters, used in a cooking apparatus, the cooking apparatus comprising a cooking cavity and an image acquisition device, characterized in that, include: The imaging unit is used to control the image acquisition device to acquire an image of the food to be processed when the food to be processed is placed into the cooking cavity, so as to obtain a first image; The determining unit is used to identify the first image and determine first category information and first state information, wherein the first category information is the food category information of the food to be processed and the first state information is the food state information of the food to be processed. The generation unit is used to generate target cooking parameters from the first database based on the first type information, the first state information, and the first region information. The ingredient status information describes the cooking maturity of the ingredient to be processed, the first region information is the current region where the cooking equipment is located, and the first database is a database built based on historical cooking data.

11. A device for determining cooking parameters, characterized in that, It includes a processor and a memory, the memory storing a program or instructions that can run on the processor, the program or instructions being executed by the processor to implement the steps of the method for determining cooking parameters as described in any one of claims 1 to 9.

12. A readable storage medium, characterized in that, The readable storage medium stores a program or instructions that, when executed by a processor, implement the steps of the method for determining cooking parameters as described in any one of claims 1 to 9.

13. A cooking appliance, characterized in that, include: The apparatus for determining cooking parameters as described in claim 10 or 11; and / or The readable storage medium as described in claim 12.

Images