Control Method and System for IoT-Based Image Recognition Smart Rice Cooker

Abstract

This application relates to the field of rice cooker control, and discloses a control method and system for an IoT-based image recognition smart rice cooker. The method includes: acquiring rice type information during cooking; determining multiple cooking stages and corresponding image recognition monitoring frequencies for each cooking stage based on the rice type information using a cooking monitoring database; performing image recognition monitoring on the inner pot of the rice cooker according to the image recognition monitoring frequency for each cooking stage during cooking, and obtaining image recognition monitoring results; determining cooking process adjustment instructions based on the rice type information and the image recognition monitoring results; and adjusting parameters for each cooking stage according to the cooking process adjustment instructions. The IoT-based image recognition smart rice cooker control method in this application can perform image monitoring at corresponding frequencies for different rice types, improving adaptability when cooking different rice types.

Description

Technical Field

[0001] This application relates to the field of rice cooker control technology, and more specifically, to a control method and system for an image recognition smart rice cooker based on the Internet of Things. Background Technology

[0002] Existing rice cookers typically execute cooking tasks according to pre-set specific cooking programs. These fixed programs often only cover basic heating and heat-keeping steps, failing to fully consider the differences in water absorption rates and starch gelatinization temperatures among different types of rice. Therefore, using the same heating curve and time control for different types of rice results in suboptimal rice texture and nutrient release, failing to effectively optimize cooking for the unique characteristics of different rice varieties.

[0003] With the development of smart technology, some image recognition smart rice cookers have the function of monitoring the conditions inside the pot during cooking. However, these rice cookers have significant shortcomings in rice type monitoring. They fail to perform personalized monitoring processes based on the characteristics of different rice types. For example, the monitoring process does not take into account the differences between different rice types in terms of grain expansion and moisture evaporation rate, resulting in a lack of specificity in the monitoring parameters. This makes it impossible to accurately capture the key changes in the cooking process of different rice types, ultimately leading to poor cooking monitoring results and difficulty in achieving ideal cooking quality control. Summary of the Invention

[0004] The purpose of this application is to provide a control method and system for an image recognition smart rice cooker based on the Internet of Things, which solves the technical problem that existing image recognition smart rice cookers cannot perform targeted cooking monitoring for different types of rice, and achieves the technical effect of targeted monitoring of the cooking process for different types of rice.

[0005] This application provides a control method for an IoT-based image recognition smart rice cooker. The method includes: acquiring rice type information during cooking; determining multiple cooking stages and corresponding image recognition monitoring frequencies for each cooking stage based on the rice type information using a cooking monitoring database; performing image recognition monitoring on the inner pot of the rice cooker according to the image recognition monitoring frequency for each cooking stage during cooking, and obtaining image recognition monitoring results; determining cooking process adjustment instructions based on the rice type information and the image recognition monitoring results; and adjusting parameters for each cooking stage according to the cooking process adjustment instructions.

[0006] In one possible implementation, during the cooking process, image recognition monitoring is performed on the inside of the rice cooker according to the image recognition monitoring frequency corresponding to each cooking stage to obtain image recognition monitoring results. This includes: in each cooking stage, driving a rotating camera on the lid of the rice cooker to rotate to a shooting position to capture images of the rice and water inside the rice cooker according to the image recognition monitoring frequency; after capturing images, the rotating camera rotates to a storage position; wherein, the rotating camera is cleaned by a silicone sheet during rotation; and the image recognition monitoring results are determined based on the rice type information and the rice and water images.

[0007] In another possible implementation, the image recognition monitoring result is determined based on the rice type information and the rice-water image, including: when the rice type information corresponds to mixed grain rice, during the soaking stage, acquiring the initial rice-water image at the start of the soaking stage, and taking images of the rice-water soaking in the rice cooker at a first frequency; determining the initial floating particle density of the mixed grain rice based on the initial rice-water image; determining the floating particle density of the mixed grain rice during soaking based on the rice-water image; and determining the cooking process adjustment instruction based on the rice type information and the image recognition monitoring result, including: acquiring the preset floating particle density change rate corresponding to the rice type information; determining the floating particle density change rate of the mixed grain rice during soaking based on the initial floating particle density and the floating particle density during soaking; when the floating particle density change rate during soaking is less than the preset floating particle density change rate, issuing a stirring prompt message to prompt stirring of the mixed grain rice in the rice cooker, and determining the cooking process adjustment instruction to control the rice-water temperature in the rice cooker to increase the preset adjustment temperature.

[0008] In another possible implementation, the image recognition monitoring result is determined based on the rice type information and the rice-water image. This further includes: when the rice type information corresponds to mixed grain rice, obtaining the preset initial floating particle density corresponding to the rice type information; determining the ratio of the initial floating particle density to the preset initial floating particle density as the floating particle density factor; and determining the cooking process adjustment command as controlling the rice-water temperature in the rice cooker to increase the preset adjustment temperature. This further includes: obtaining the soaking base temperature and soaking adjustment temperature corresponding to the rice type information; determining the product of the floating particle density factor and the soaking adjustment temperature as the rice type soaking adjustment temperature; determining the sum of the soaking base temperature and the soaking adjustment temperature as the preset adjustment temperature; and determining the cooking process adjustment command as controlling the rice-water temperature in the rice cooker to increase the preset adjustment temperature.

[0009] In another possible implementation, the image recognition monitoring result is determined based on the rice type information and the rice-water image. This further includes: when the rice type information corresponds to mixed grain rice, obtaining the preset initial floating particle density and particle size corresponding to the rice type information; determining the ratio of the initial floating particle density to the preset initial floating particle density as the floating particle density factor; determining the ratio of the particle size to the preset particle size as the particle size factor; and determining the cooking process adjustment instruction to control the rice-water temperature in the rice cooker to increase the preset adjustment temperature. This further includes: determining the product of the floating particle density factor, particle size factor, and soaking adjustment temperature as the rice soaking adjustment temperature; determining the sum of the soaking base temperature and the soaking adjustment temperature as the preset adjustment temperature; and determining the cooking process adjustment instruction to control the rice-water temperature in the rice cooker to increase the preset adjustment temperature.

[0010] In another possible implementation, the method further includes: obtaining the change rate of floating particle density during soaking corresponding to rice type information at different times; and determining the heating power curve of the rice cooker during the boiling stage based on the rice type information and the change rate of floating particle density during soaking corresponding to the rice type information at different times using a boiling stage control model; wherein the heating power curve includes the target change rate of floating particle density at the beginning of the boiling stage.

[0011] In another possible implementation, the method further includes: acquiring multiple historical cooking records corresponding to the rice type information, and acquiring the target floating particle density change rate and user cooking feedback information for each historical cooking record; wherein, the user cooking feedback information includes the rice cooking degree evaluation value and the rice hardness evaluation value; and through a cooking process adjustment model, determining the adjustment floating particle density change rate at the start of the boiling stage corresponding to the rice type information based on multiple historical cooking records, the target floating particle density change rate for each historical cooking record, and the user cooking feedback information, so as to adjust the target floating particle density change rate at the start of the boiling stage corresponding to the rice type information.

[0012] In another possible implementation, the method further includes: determining the ratio of the change rate of the density of the adjusted floating particles to the change rate of the density of the target floating particles as an adjustment factor for the soaking stage; and obtaining the boiling power heating duration of the heating power curve corresponding to the boiling stage; wherein the boiling power heating duration corresponds to the maximum heating power heating duration of the boiling stage; and determining the product of the boiling power heating duration and the soaking stage adjustment factor to adjust the boiling power heating duration.

[0013] In another possible implementation, the method further includes: using a boiling stage control model, determining the micro-boiling power heating duration of the heating power curve corresponding to the boiling stage of the rice cooker based on rice type information, particle size factor, and the rate of change of floating particle density during soaking at different times corresponding to rice type information; determining the product of the micro-boiling power heating duration and the floating particle density factor to adjust the micro-boiling power heating duration of the heating power curve corresponding to the boiling stage.

[0014] This application also provides a control system for an image recognition smart rice cooker based on the Internet of Things, including a unit for performing the method described in any of the preceding claims.

[0015] The beneficial effects of the embodiments in this application compared with the prior art are:

[0016] This application provides a control method for an IoT-based image recognition smart rice cooker. The method includes: acquiring rice type information during cooking; determining multiple cooking stages and corresponding image recognition monitoring frequencies for each stage based on the rice type information using a cooking monitoring database; performing image recognition monitoring on the inner pot of the rice cooker according to the image recognition monitoring frequencies for each cooking stage during cooking, and obtaining image recognition monitoring results; determining cooking process adjustment instructions based on the rice type information and the image recognition monitoring results; and adjusting parameters for each cooking stage according to the cooking process adjustment instructions. The method in this application can perform image monitoring at corresponding frequencies for different rice types, improving adaptability when cooking different types of rice. Attached Figure Description

[0017] To more clearly illustrate the technical solutions in the embodiments of this application, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0018] Figure 1 A flowchart illustrating the first IoT-based image recognition smart rice cooker control method provided in this application embodiment;

[0019] Figure 2 A flowchart illustrating a second IoT-based image recognition smart rice cooker control method provided in this application embodiment;

[0020] Figure 3 A flowchart illustrating the third method for controlling an image recognition smart rice cooker based on the Internet of Things, provided in an embodiment of this application;

[0021] Figure 4This is a schematic diagram of the logic structure of a control system for an image recognition smart rice cooker based on the Internet of Things, provided in an embodiment of this application. Detailed Implementation

[0022] It should be understood that, when used in this application specification and the appended claims, the term "comprising" indicates the presence of the described features, integrals, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components and / or a collection thereof.

[0023] It should also be understood that the term “and / or” as used in this application specification and the appended claims means any combination of one or more of the associated listed items and all possible combinations, and includes such combinations.

[0024] As used in this application specification and the appended claims, the term "if" may be interpreted, depending on the context, as "when," "once," "in response to determination," or "in response to detection." Similarly, the phrase "if determined" or "if detected [the described condition or event]" may be interpreted, depending on the context, as meaning "once determined," "in response to determination," "once detected [the described condition or event]," or "in response to detection [the described condition or event]."

[0025] Furthermore, in the description of this application and the appended claims, the terms "first," "second," "third," etc., are used only to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0026] References to "one embodiment" or "some embodiments" as described in this specification mean that one or more embodiments of this application include a specific feature, structure, or characteristic described in connection with that embodiment. Therefore, the phrases "in one embodiment," "in some embodiments," "in other embodiments," "in still other embodiments," etc., appearing in different parts of this specification do not necessarily refer to the same embodiment, but rather mean "one or more, but not all, embodiments," unless otherwise specifically emphasized. The terms "comprising," "including," "having," and variations thereof mean "including but not limited to," unless otherwise specifically emphasized.

[0027] Image recognition smart rice cookers cannot perform personalized monitoring processes based on the characteristics of different types of rice, ultimately resulting in poor cooking monitoring effects and difficulty in achieving ideal cooking quality control.

[0028] Based on the above reasons, this application provides a control method for an IoT-based image recognition smart rice cooker. The method includes: acquiring rice type information during cooking; determining multiple cooking stages and corresponding image recognition monitoring frequencies for each stage based on the rice type information using a cooking monitoring database; performing image recognition monitoring on the inner pot of the rice cooker according to the image recognition monitoring frequency for each cooking stage during cooking, and obtaining image recognition monitoring results; determining cooking process adjustment instructions based on the rice type information and the image recognition monitoring results; and adjusting parameters for each cooking stage according to the cooking process adjustment instructions. The method in this application can perform image monitoring at corresponding frequencies for different rice types, improving adaptability when cooking different rice types.

[0029] In some scenarios, the image recognition-based smart rice cooker control method of this application embodiment can be applied to the control of rice cookers based on image recognition. It can perform image monitoring of different types of rice at corresponding frequencies, thereby improving the monitoring effect of cooking different types of rice and thus improving the cooking effect of different types of rice.

[0030] The following describes in detail, with specific examples, a control method for an image recognition smart rice cooker based on the Internet of Things provided in the embodiments of this application.

[0031] Figure 1 A flowchart illustrating the first IoT-based image recognition smart rice cooker control method provided in this application embodiment is shown below. Figure 1 As shown, the control method of this IoT-based image recognition smart rice cooker includes S110 to S120, and S110 to S120 will be described in detail below.

[0032] S110. Obtain rice type information during rice cooker cooking. Based on the rice type information and the cooking monitoring database, determine multiple cooking stages of the rice cooker and the corresponding image recognition monitoring frequency for each cooking stage.

[0033] During the cooking process of a smart rice cooker, the rice type information can be obtained. This information can include the rice type identifier, such as long-grain rice, short-grain rice, or glutinous rice. This information can be obtained through user interface input or automatic identification by sensors. Obtaining this rice type information helps to make subsequent customized controls based on the characteristics of different rice types.

[0034] For example, when cooking rice in a rice cooker, if the user selects short-grain rice, the rice type information will be recorded to facilitate subsequent stage division and monitoring frequency settings.

[0035] After obtaining the rice type information, the cooking monitoring database can be used to determine the multiple cooking stages of the rice cooker and the corresponding image recognition monitoring frequency for each cooking stage. The cooking monitoring database stores stage division data for different rice types, such as soaking, heating, boiling and simmering stages, as well as the recommended image recognition monitoring frequency for each stage.

[0036] For example, for rice varieties that are prone to overflow, a higher monitoring frequency can be set during the boiling stage.

[0037] S120. During the cooking process, image recognition monitoring is performed on the inner pot of the rice cooker according to the image recognition monitoring frequency corresponding to each cooking stage, and the image recognition monitoring results are obtained. Based on the rice type information and the image recognition monitoring results, cooking process adjustment instructions are determined. Parameters are adjusted for each cooking stage according to the cooking process adjustment instructions.

[0038] During the cooking process, rice and water images can be detected according to the image recognition monitoring frequency corresponding to each cooking stage to obtain image recognition monitoring results. The detection of rice and water images can be done through the built-in camera of the rice cooker, and the rice and water images are sent to the image recognition model deployed in the cloud via the Internet of Things to obtain image recognition monitoring results. The image recognition monitoring results can include real-time data such as water level, foam volume, or boiling status.

[0039] In this implementation, detecting rice-water images at corresponding frequencies according to different rice types ensures sufficient data collection during critical stages such as the boiling period, while reducing resource consumption during non-critical stages.

[0040] For example, during the boiling stage, if the monitoring frequency is set to high, the camera will frequently capture images and identify changes in the amount of foam in the rice water.

[0041] After obtaining the image recognition monitoring results, cooking process adjustment instructions can be determined based on the rice type information and the monitoring results. The determination process combines rice type characteristics and real-time image status. For example, when image recognition shows excessive foam or abnormal water level, adjustment instructions such as reducing heating power or extending cooking time are generated. Rice type information provides a benchmark reference for the cooking process adjustment instructions, ensuring that the instructions are targeted.

[0042] For example, when the rice type is glutinous rice and the image recognition shows that the water level is low, the cooking process adjustment command can be to reduce the heating power.

[0043] After receiving the cooking process adjustment instructions, you can adjust the parameters for each cooking stage according to the instructions. The cooking process adjustment instructions include adjusting the heating power, time or temperature, etc., to ensure that each stage, such as the boiling period or the simmering period, is executed optimally and to avoid overflow or undercooking problems.

[0044] For example, when the rice cooker receives a cooking process adjustment command to reduce power during the boiling stage, it can immediately reduce the heating output to prevent the rice water from overflowing.

[0045] The beneficial effects of the above implementation method are that, through the cooking monitoring database, based on rice type information, it is possible to determine multiple cooking stages of the rice cooker and the corresponding image recognition monitoring frequency for each cooking stage, thereby performing image monitoring at corresponding frequencies for different rice types, improving the adaptability when cooking different rice types; and detecting rice and water images at corresponding frequencies according to different rice types can ensure sufficient data collection in critical stages such as the boiling period, while reducing resource consumption in non-critical stages.

[0046] The beneficial effect of the above implementation method is that by determining the cooking process adjustment instructions according to the image monitoring corresponding to different rice varieties, the timeliness of cooking adjustment when cooking different rice varieties is improved, and the cooking effect is improved.

[0047] In some implementations, in the above-mentioned S120, during the cooking process, image recognition monitoring is performed on the inside of the rice cooker according to the image recognition monitoring frequency corresponding to each cooking stage to obtain image recognition monitoring results, including S121 to S122. S121 to S122 will be explained in detail below.

[0048] S121. During each cooking stage, the rotating camera on the lid of the rice cooker is driven to rotate to the shooting position to capture images of the rice and water inside the rice cooker according to the image recognition monitoring frequency. After shooting, the rotating camera rotates to the storage position. The rotating camera is cleaned using a silicone sheet during rotation.

[0049] During the cooking process of the rice cooker, the rice and water images can be detected according to the image recognition monitoring frequency corresponding to each cooking stage, thereby obtaining the image recognition monitoring results. This allows for dynamic tracking of changes in the rice and water state inside the pot, ensuring precise control over the cooking process.

[0050] During each cooking stage, the rotating camera on the lid of the rice cooker can be driven to rotate to the shooting position to capture images of the rice and water inside the rice cooker according to the image recognition monitoring frequency. After shooting, the rotating camera rotates to the storage position. During the rotation, the rotating camera is cleaned by a silicone cleaning pad. This method ensures that the camera is only exposed to the cooking environment when necessary, avoiding the accumulation of steam or dirt that may affect the shooting quality. The silicone cleaning pad automatically wipes the lens surface while rotating, thus maintaining optical clarity.

[0051] S122. Determine the image recognition monitoring results based on rice type information and rice-water images.

[0052] After obtaining the rice-water images, the image recognition monitoring results can be determined based on the rice type information and the rice-water images. The rice type information provides a reference for the cooking characteristics of specific rice types. Combined with the real-time captured rice-water images, the water level, boiling degree, or rice grain state can be analyzed more accurately, and the monitoring results can be output for subsequent control decisions.

[0053] For example, during the porridge-cooking stage of a rice cooker, image recognition monitoring is performed frequently. A rotating camera is driven to the shooting position to capture images of the rice and water inside the pot. After shooting, it rotates back to the storage position, while a silicone cleaning sheet removes any residual moisture from the lens. Based on the rice type information input by the user, the image recognition monitoring results are analyzed to determine whether there is a risk of overflow or insufficient moisture.

[0054] The beneficial effect of the above implementation method is that it can rotate the rotating camera to the shooting position to capture images of rice and water inside the rice cooker, and clean the rotating camera in time with a silicone cleaning sheet, thereby improving the cooking monitoring effect.

[0055] In some implementations, in S122 above, determining the image recognition monitoring result based on the rice type information and the rice-water image includes: when the rice type information corresponds to mixed grain rice, during the soaking stage, acquiring the initial rice-water image at the start of the soaking stage, and taking images of the soaking rice-water inside the rice cooker at a first frequency. Based on the initial rice-water image, determining the initial floating particle density of the mixed grain rice. Based on the soaking rice-water image, determining the floating particle density of the mixed grain rice during soaking.

[0056] When the rice type information corresponds to mixed grain rice, during the soaking stage, the initial rice-water image at the start of the soaking stage can be obtained, and the rice-water image during soaking in the rice cooker can be captured at the first frequency. The initial floating particle density of the mixed grain rice can be determined based on the initial rice-water image, and the floating particle density of the mixed grain rice during soaking can be determined based on the rice-water image during soaking. The floating particle density during soaking can reflect the distribution change of floating particles in the mixed grain rice on the top surface of the rice-water.

[0057] For example, during the process of cooking mixed grain rice in a rice cooker, the initial rice-water image can capture the initial floating state of the grains, while the rice-water image during soaking is taken at regular intervals at the first frequency to show the dynamics of the grains rising over time, helping to identify the density change trend of the floating grains.

[0058] Figure 2 A flowchart illustrating the second IoT-based image recognition smart rice cooker control method provided in this application embodiment is shown below. Figure 2 As shown, in the above-mentioned S120, the cooking process adjustment instructions are determined based on the rice type information and image recognition monitoring results, including S210 to S220. S210 to S220 will be explained in detail below.

[0059] S210. Obtain the preset floating particle density change rate corresponding to the rice type information.

[0060] When determining the cooking process adjustment instructions, the preset floating particle density change rate corresponding to the rice type information can be obtained.

[0061] S220. Based on the initial floating particle density and the floating particle density during soaking, determine the rate of change of floating particle density during soaking of the mixed grain rice. When the rate of change of floating particle density during soaking is less than the preset rate of change of floating particle density, issue a stirring prompt message to prompt the mixed grain rice in the rice cooker to be stirred, and determine that the cooking process adjustment command is to control the rice and water temperature in the rice cooker to increase the preset adjustment temperature.

[0062] Based on the initial floating particle density and the floating particle density during soaking, the change rate of floating particle density during soaking of mixed grain rice can be calculated. The change rate of floating particle density during soaking can reflect the water absorption and cooking ease of mixed grain rice, and thus the cooking process can be adjusted according to the change rate of floating particle density during soaking.

[0063] After obtaining the density change rate of floating particles during soaking, if the density change rate of floating particles during soaking is less than the preset density change rate of floating particles, a stirring prompt message can be issued to prompt the rice in the rice cooker to be stirred, and the cooking process adjustment command can be determined to control the rice and water temperature in the rice cooker to increase the preset adjustment temperature in order to improve the soaking effect of the rice.

[0064] For example, when cooking mixed grain rice in a rice cooker, if the density change rate of the floating grains during soaking is too low, the system can generate a stirring prompt to remind the user to stir manually. At the same time, it will automatically raise the temperature of the rice and water to accelerate the grains' water absorption and optimize the subsequent boiling cooking effect.

[0065] The beneficial effect of the above implementation method is that by determining the rate of change in the density of floating particles during the soaking of mixed grains, the soaking effect of mixed grains can be monitored, and the top surface of the rice water can be accurately monitored, thus improving the accuracy of monitoring the soaking effect of mixed grains.

[0066] The beneficial effect of the above implementation method is that when the density change rate of floating particles during soaking is less than the preset density change rate of floating particles, the soaking temperature is increased to improve the soaking effect, thereby improving the subsequent cooking effect.

[0067] In some implementations, S122 above, determining the image recognition monitoring result based on rice type information and rice-water image, further includes: when the rice type information corresponds to mixed grain rice, obtaining the preset initial floating particle density corresponding to the rice type information. The ratio of the initial floating particle density to the preset initial floating particle density is determined as the floating particle density factor.

[0068] When the rice type information indicates mixed grain rice, the preset initial floating particle density corresponding to that rice type information can be obtained. At the same time, the ratio of the initial floating particle density to the preset initial floating particle density can be determined as the floating particle density factor. The floating particle density factor can quantify the degree of deviation of the current floating particle density from the standard value.

[0069] It should be noted that both the initial floating particle density and the preset initial floating particle density correspond to the same amount of mixed grain rice to be cooked, thus ensuring that the benchmark for comparing the initial floating particle density and the preset initial floating particle density is consistent.

[0070] For example, during the cooking process in a rice cooker, image recognition can be used to monitor the rice and water image and extract the initial floating particle density. If the rice is mixed grain rice, the preset initial floating particle density can be obtained based on historical data. A floating particle density factor greater than 1 indicates that the particles are relatively dense, while a factor less than 1 indicates that they are relatively sparse. The floating particle density factor helps to reflect the specific information corresponding to the rice type.

[0071] In some implementations, the cooking process adjustment instruction in S120 above is to control the rice and water temperature in the rice cooker to increase the preset adjustment temperature, and also includes S230 to S240. S230 to S240 will be explained in detail below.

[0072] S230. Obtain the soaking base temperature and soaking adjustment temperature corresponding to the rice type information.

[0073] In this implementation, the soaking base temperature and soaking adjustment temperature corresponding to the rice type information can be obtained. The soaking base temperature is the lowest soaking temperature corresponding to the rice type information, and the soaking adjustment temperature is the lowest adjustment temperature when adjusting the soaking temperature corresponding to the rice type information.

[0074] S240. Determine the product of the floating particle density factor and the soaking adjustment temperature as the rice soaking adjustment temperature. Determine the sum of the soaking base temperature and the soaking adjustment temperature as the preset adjustment temperature. Determine the cooking process adjustment command to control the rice and water temperature in the rice cooker to increase the preset adjustment temperature.

[0075] After obtaining the floating particle density factor and the soaking adjustment temperature, the product of the floating particle density factor and the soaking adjustment temperature can be calculated to obtain the rice type soaking adjustment temperature. Next, the sum of the soaking base temperature and the soaking adjustment temperature can be determined as the preset adjustment temperature, and cooking process adjustment instructions can be generated to control the rice and water temperature in the rice cooker to increase the preset adjustment temperature, thereby adjusting the soaking temperature corresponding to the rice type information.

[0076] For example, when processing mixed grain rice in a rice cooker, the base soaking temperature might be 40°C, and the soaking adjustment temperature might be 5°C. With a floating particle density factor of 1.8, the rice soaking adjustment temperature is determined to be 9°C. The preset adjustment temperature is 40°C plus 9°C, which equals 49°C. Therefore, the cooking process adjustment instruction is to control the rice-water temperature inside the rice cooker to increase the preset adjustment temperature to 49°C, thus optimizing the soaking process of the mixed grain rice.

[0077] The beneficial effect of the above implementation method is that the ratio of the initial floating particle density to the preset initial floating particle density corresponding to the rice variety information is determined as the floating particle density factor. The floating particle density factor can characterize the special characteristics of the floating particle density in the rice variety, the rice variety information can characterize the specific cooking requirements of the rice variety, and the temperature of the soaking rice water is adjusted according to the floating particle density factor to ensure the overall cooking degree of the mixed grain rice.

[0078] The beneficial effect of the above implementation method is that by obtaining the soaking base temperature and soaking adjustment temperature corresponding to the rice type information, and adjusting the soaking water temperature to a preset adjustment temperature based on the soaking base temperature and soaking adjustment temperature corresponding to the rice type information, the cooking degree of mixed grain rice can be guaranteed according to the rice type information.

[0079] In some implementations, S122 above, determining the image recognition monitoring result based on rice variety information and rice-water image, further includes: when the rice variety information corresponds to mixed grain rice, obtaining the preset initial floating particle density and particle size corresponding to the rice variety information; determining the ratio of the initial floating particle density to the preset initial floating particle density as the floating particle density factor; and determining the ratio of the particle size to the preset particle size as the particle size factor.

[0080] During the cooking process of a smart rice cooker, when the rice type is identified as mixed grain rice, the preset initial floating particle density and particle size corresponding to that rice type can be obtained. The preset initial floating particle density can represent the reference value of the floating particle density of standard mixed grain rice in the initial cooking stage, and the particle size can characterize the size characteristic parameter of the rice grain. These preset values ​​can be set based on historical cooking data or rice type database, thereby providing a benchmark for the subsequent soaking and adjustment process.

[0081] After obtaining the preset initial floating particle density and particle size, the ratio of the initial floating particle density to the preset initial floating particle density can be determined as the floating particle density factor; at the same time, the ratio of the particle size to the preset particle size can be determined as the particle size factor. The floating particle density factor can quantify the deviation of the actual floating particle density from the standard value, and the particle size factor can reflect the difference ratio between the rice grain size and the ideal particle size. The floating particle density factor and the particle size factor can be used as dynamic adjustment parameters to adapt to the soaking requirements of different miscellaneous grains.

[0082] In some implementations, S240 above, determining that the cooking process adjustment instruction is to control the rice-water temperature in the rice cooker to increase the preset adjustment temperature, further includes: determining the product of the floating particle density factor, particle size factor, and soaking adjustment temperature as the rice soaking adjustment temperature. The sum of the soaking base temperature and the soaking adjustment temperature is determined as the preset adjustment temperature, and the cooking process adjustment instruction is determined to control the rice-water temperature in the rice cooker to increase the preset adjustment temperature.

[0083] When the cooking process adjustment command is determined to control the rice and water temperature in the rice cooker to increase the preset adjustment temperature, the product of the floating particle density factor, particle size factor and soaking adjustment temperature can be calculated as the rice soaking adjustment temperature; then the sum of the soaking base temperature and the rice soaking adjustment temperature is determined as the preset adjustment temperature. Subsequent cooking process adjustment commands can control the rice cooker heating system to increase the rice and water temperature to the preset adjustment temperature, thus optimizing the soaking process.

[0084] For example, when cooking mixed grain rice in a rice cooker, if the grain size is large, resulting in a high particle size factor, the soaking temperature of the rice may be increased accordingly. This will raise the preset temperature and ensure that the rice grains fully absorb water, thus avoiding uneven cooking caused by uneven grain size.

[0085] The beneficial effect of the above implementation method is that it further determines the ratio of the particle size of the mixed grain rice to the preset particle size as the particle size factor, and determines the product of the floating particle density factor, particle size factor and soaking adjustment temperature as the rice type soaking adjustment temperature, thereby improving the soaking and cooking effects of mixed grain rice with different particle sizes.

[0086] Figure 3 A flowchart illustrating the third IoT-based image recognition smart rice cooker control method provided in this application embodiment is shown below. Figure 3 As shown, the above method also includes S310 to S320, which will be described in detail below.

[0087] S310. Obtain the change rate of floating particle density during soaking at different times for rice type information.

[0088] During the cooking process in a rice cooker, the density change rate of floating particles during soaking can be obtained for different rice types at different times. This rate reflects the rate at which the density of floating particles in the soaking water changes over time. This helps to understand the water absorption state of the rice grains and the evolution process of the floating particles, providing basic data for subsequent control.

[0089] For example, when cooking mixed grains, the density change rate of floating particles can be monitored in real time to capture the dynamic trend of rice grain expansion, thereby dynamically adjusting the cooking process.

[0090] S320. Using a boiling stage control model, based on rice type information and the rate of change of floating particle density during soaking at different times, determine the heating power curve of the rice cooker during the boiling stage. The heating power curve includes the target rate of change of floating particle density at the start of the boiling stage.

[0091] After obtaining the density change rate of floating particles during soaking, the heating power curve of the rice cooker during the boiling stage can be determined by using the boiling stage control model, based on the rice type information and the density change rate of floating particles during soaking at different times.

[0092] It should be noted that the heating power curve includes the target floating particle density change rate at the start of the boiling stage, which means that the heating of the boiling stage is started when the target floating particle density change rate is reached.

[0093] For example, the boiling stage control model can be a deep learning model based on neural networks, capable of analyzing the overall trend of density change rate and predicting the optimal boiling initiation point. The boiling stage control model can be trained using sample rice type information, the density change rate of floating particles during sample soaking, and the sample heating power curve. The calculation process of the boiling stage control model considers the temporal evolution of the density change rate and optimizes the power adjustment during the boiling stage.

[0094] For example, when cooking mixed grains, the boiling stage control model can output a heating power curve based on the real-time monitored change rate of floating particle density, ensuring a smooth transition to the boiling stage when the target change rate of floating particle density is reached.

[0095] The beneficial effect of the above implementation method is that by determining the heating power curve of the rice cooker during the boiling stage by the density change rate of floating particles during soaking, the boiling stage can be adjusted in combination with the density change rate of floating particles during soaking, thereby improving the overall cooking effect on the floating particles of mixed grains.

[0096] The beneficial effect of the above implementation method is that by determining the rate of change of the target floating particle density at the beginning of the boiling stage, the rice and water can be heated to boil after the target floating particle density is reached, thus ensuring the cooking effect.

[0097] In some implementations, the above method also includes S330 to S340, which will be described in detail below.

[0098] S330: Obtain multiple historical cooking records corresponding to the rice variety information, and obtain the target floating particle density change rate and user cooking feedback information for each historical cooking record. The user cooking feedback information includes rice cookedness evaluation values ​​and rice hardness evaluation values.

[0099] During the cooking process of a smart rice cooker, multiple historical cooking records corresponding to the rice type information can be obtained. The target floating particle density change rate and user cooking feedback information for each historical cooking record can be obtained. The user cooking feedback information can include the rice cooking degree evaluation value and the rice hardness evaluation value. This helps to collect complete data of past cooking instances. The target floating particle density change rate reflects the trend of the suspension state change of rice grains at the beginning of the boiling stage. The user feedback information provides an objective evaluation of the cooking results, providing a basis for subsequent adjustments.

[0100] For example, when cooking different types of rice, such as long-grain rice or short-grain rice, in a rice cooker, the rate of change in the density of target floating grains during historical cooking can be recorded, while user ratings of the cookedness and firmness of the rice can be collected.

[0101] S340. By adjusting the cooking process model, based on multiple historical cooking records, the target floating particle density change rate of each historical cooking record, and user cooking feedback information, determine the adjustment floating particle density change rate at the start of the boiling stage corresponding to the rice type information, so as to adjust the target floating particle density change rate at the start of the boiling stage corresponding to the rice type information.

[0102] After obtaining the target floating particle density change rate and user cooking feedback information for each historical cooking record, the model can be adjusted through the cooking process. Based on multiple historical cooking records, the target floating particle density change rate for each historical cooking record, and user cooking feedback information, the adjustment floating particle density change rate at the start of the boiling stage corresponding to the rice type information can be determined, so as to adjust the target floating particle density change rate at the start of the boiling stage corresponding to the rice type information.

[0103] For example, the cooking process adjustment model can be a deep learning model based on neural networks. The cooking process adjustment model can be trained by multiple historical cooking records, the sample target floating particle density change rate of each historical cooking record, sample user cooking feedback information, and the sample adjustment floating particle density change rate at the beginning of the boiling stage corresponding to the rice type information. The cooking process adjustment model can dynamically optimize the floating particle density change rate at the beginning of the boiling stage to ensure that the rice grain state matches the user's preferences.

[0104] For example, the cooking process adjustment model analyzes the historical data of long-grain rice, including the target floating particle density change rate and user evaluation of the cookedness, to calculate the adjustment floating particle density change rate. In subsequent cooking, this adjustment value is used to control the boiling point to avoid over-soaking or under-soaking of the rice grains, thereby improving the overall cooking quality of mixed grain rice.

[0105] The beneficial effect of the above implementation method is that by adjusting the cooking process model, based on multiple historical cooking records, the target floating particle density change rate of each historical cooking record, and user cooking feedback information, the adjustment floating particle density change rate at the start of the boiling stage corresponding to the rice type information is determined, and the cooking process is adjusted to improve the cooking effect.

[0106] The beneficial effect of the above implementation method is that by adjusting the model during the cooking process and adjusting the rate of change of the density of floating particles at the beginning of the boiling stage, it is possible to ensure the cooking degree of a specific rice variety and improve the cooking effect.

[0107] In some implementations, the above method also includes S350 to S360, which will be described in detail below.

[0108] S350. Determine the ratio of the adjusted floating particle density change rate to the target floating particle density change rate as the adjustment factor for the soaking stage. Also, obtain the rapid boiling power heating time of the heating power curve corresponding to the boiling stage. The rapid boiling power heating time corresponds to the maximum heating power heating time of the boiling stage.

[0109] In this method, the ratio of the change rate of the density of the adjusted floating particles to the change rate of the density of the target floating particles can be used as the adjustment factor for the soaking stage. The soaking stage adjustment factor characterizes the adjustment range of the soaking stage in S440.

[0110] Simultaneously, the heating duration of the rapid boiling power curve corresponding to the boiling stage can be obtained, which represents the duration of the maximum heating power during the boiling stage.

[0111] S360. Determine the product of the boiling power heating time and the soaking stage adjustment factor to adjust the boiling power heating time.

[0112] After obtaining the soaking stage adjustment factor and the boiling power heating time, the adjusted boiling power heating time can be obtained by multiplying the boiling power heating time and the soaking stage adjustment factor, thus achieving optimized control of the boiling power heating time.

[0113] The beneficial effect of the above implementation method is that it determines the ratio of the change rate of floating particle density to the target change rate of floating particle density as the adjustment factor for the soaking stage, and further adjusts the heating time of the boiling power according to the adjustment factor for the soaking stage, and adjusts the cooking effect of the rice according to the duration of the boiling stage, thereby further improving the accuracy of the adjustment of the cooking stage and improving the cooking effect.

[0114] In some implementations, the above method also includes S370 to S380, which will be described in detail below.

[0115] S370. By using the boiling stage control model, based on rice type information, particle size factor, and the rate of change of floating particle density during soaking at different times corresponding to rice type information, the micro-boiling power heating time of the rice cooker corresponding to the boiling stage heating power curve is determined.

[0116] During the cooking process of a smart rice cooker, a boiling stage control model can be used to determine the micro-boiling power heating time of the rice cooker's heating power curve at different times by using rice type information, particle size factor, and the rate of change of floating particle density during soaking. The micro-boiling power heating time represents the heating time when the boiling amplitude is relatively weak during the boiling stage.

[0117] In this implementation, the boiling stage control model can comprehensively consider the characteristics of rice varieties, particle size distribution, and the dynamic change trend of floating particle density during soaking to accurately calculate the micro-boiling power heating time, so as to adapt to the boiling control requirements of different rice varieties.

[0118] For example, the boiling stage control model can be a deep learning model based on neural networks. The boiling stage control model is trained by the sample rice type information, sample particle size factor, the rate of change of floating particle density during sample soaking, and the sample micro-boiling power heating time. The boiling stage control model can learn the complex relationship between input features, ensuring that the heating time can be optimized according to the actual rice type and particle characteristics during the boiling stage, thereby improving the model's generalization ability.

[0119] S380. Determine the product of the micro-boiling power heating time and the floating particle density factor to adjust the micro-boiling power heating time of the heating power curve corresponding to the boiling stage.

[0120] After determining the micro-boiling power heating time, the product of the micro-boiling power heating time and the floating particle density factor can be determined to adjust the micro-boiling power heating time of the heating power curve corresponding to the boiling stage. By multiplying by the floating particle density factor, the heating time can be further fine-tuned according to the density characteristics of the floating particles to ensure that the heating power curve adapts to changes in particle density.

[0121] For example, when cooking mixed grain rice in a rice cooker, the density factor of the floating particles can reflect the density differences of different particles. By adjusting the product, the heating time can be extended for particles with higher density to ensure that all particles are heated evenly and to avoid some particles being undercooked.

[0122] The beneficial effect of the above implementation method is that, by using the boiling stage control model and further combining the particle size factor, the micro-boiling power heating time of the heating power curve corresponding to the boiling stage of the rice cooker is determined. Based on the particle size factor, the cooking of raw materials with different particle sizes in mixed grain rice is guaranteed, thereby improving the cooking effect of mixed grain rice.

[0123] The beneficial effect of the above implementation method is that by adjusting the micro-boiling power heating time through the floating particle density factor, the cooking effect of floating particles with different densities in mixed grains is further guaranteed, thus improving the cooking effect.

[0124] This application also provides a control system for an image recognition smart rice cooker based on the Internet of Things, including a unit for performing the method described in any of the preceding claims.

[0125] Figure 4 A schematic diagram of the logic structure of a control system for an image recognition smart rice cooker based on the Internet of Things, provided in an embodiment of this application, is shown below. Figure 4 As shown, the system 1 of this embodiment includes a processing unit 11, a storage unit 12, and a transceiver unit 13. The processing unit 11 is used to process data, the storage unit 12 is used to store data, and the transceiver unit 13 is used to send and receive data. The processing unit 11, the storage unit 12, and the transceiver unit 13 cooperate with each other to implement the above-described method. The beneficial effects of the embodiments of this application have been described in the above-described method and will not be repeated here.

[0126] It should be noted that the information interaction and execution process between the above-mentioned devices / units are based on the same concept as the method embodiments of this application. For details on their specific functions and technical effects, please refer to the method embodiments section, and they will not be repeated here.

[0127] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional units and modules is merely an example. In practical applications, the above functions can be assigned to different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiments can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit. Furthermore, the specific names of the functional units and modules are only for easy differentiation and are not intended to limit the scope of protection of this application. The specific working process of the units and modules in the above system can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0128] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the methods of the above embodiments of this application can be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include at least: any entity or device capable of carrying computer program code to a photographing device / terminal device, a recording medium, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electrical carrier signal, a telecommunication signal, and a software distribution medium. Examples include USB flash drives, portable hard drives, magnetic disks, or optical disks. In some jurisdictions, according to legislation and patent practice, computer-readable media cannot be electrical carrier signals or telecommunication signals.

[0129] In the above embodiments, the descriptions of each embodiment have different focuses. For parts that are not described in detail or recorded in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0130] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0131] In the embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative. For instance, the division of modules or units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0132] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0133] The above-described embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application, and should all be included within the protection scope of this application.

Claims

1. A control method for an image recognition smart rice cooker based on the Internet of Things, characterized in that, The method includes: Obtain rice type information during rice cooking in the rice cooker; based on the rice type information and the cooking monitoring database, determine multiple cooking stages of the rice cooker and the corresponding image recognition monitoring frequency for each cooking stage; During the cooking process, the inner pot of the rice cooker is monitored by image recognition at the frequency corresponding to each cooking stage to obtain the image recognition monitoring results; based on the rice type information and the image recognition monitoring results, cooking process adjustment instructions are determined; and parameters are adjusted for each cooking stage according to the cooking process adjustment instructions. During the cooking process, image recognition monitoring is performed inside the rice cooker according to the image recognition monitoring frequency corresponding to each cooking stage, and the image recognition monitoring results are obtained, including: During each cooking stage, the rotating camera on the lid of the rice cooker is driven to rotate to the shooting position to capture images of the rice and water inside the rice cooker according to the image recognition monitoring frequency. After the shooting is completed, the rotating camera rotates to the storage position. During the rotation, the rotating camera is cleaned by a silicone sheet. When the rice type information corresponds to mixed grain rice, during the soaking stage, the initial rice-water image at the start of the soaking stage is acquired, and the rice-water image during soaking in the rice cooker is captured at a first frequency; based on the initial rice-water image, the initial floating particle density of the mixed grain rice is determined; based on the rice-water image during soaking, the floating particle density of the mixed grain rice during soaking is determined; when the rice type information corresponds to mixed grain rice, the preset initial floating particle density corresponding to the rice type information is acquired; the ratio of the initial floating particle density to the preset initial floating particle density is determined as the floating particle density factor; Based on rice type information and image recognition monitoring results, cooking process adjustment instructions are determined, including: Obtain the preset floating particle density change rate corresponding to rice type information; Based on the initial floating particle density and the floating particle density during soaking, the rate of change of floating particle density during soaking of the mixed grain rice is determined; when the rate of change of floating particle density during soaking is less than the preset rate of change of floating particle density, a stirring prompt message is issued to prompt the mixed grain rice in the rice cooker to be stirred; the base soaking temperature and soaking adjustment temperature corresponding to the rice type information are obtained; the product of the floating particle density factor and the soaking adjustment temperature is determined as the rice type soaking adjustment temperature; the sum of the base soaking temperature and the soaking adjustment temperature is determined as the preset adjustment temperature; and the cooking process adjustment command is determined to control the rice water temperature in the rice cooker to increase the preset adjustment temperature. The method further includes: Obtain the rate of change in the density of floating particles during soaking at different times for rice variety information; By using a boiling stage control model, the heating power curve of the rice cooker during the boiling stage is determined based on rice type information and the change rate of floating particle density during soaking at different times corresponding to the rice type information; wherein, the heating power curve includes the target change rate of floating particle density at the beginning of the boiling stage. The method further includes: The system acquires multiple historical cooking records corresponding to rice type information, and obtains the target floating particle density change rate and user cooking feedback information for each historical cooking record; among which, the user cooking feedback information includes rice cooking degree evaluation value and rice hardness evaluation value; By adjusting the cooking process model, based on multiple historical cooking records, the target floating particle density change rate for each historical cooking record, and user cooking feedback, the adjustment floating particle density change rate at the start of the boiling stage corresponding to the rice type information is determined, so as to adjust the target floating particle density change rate at the start of the boiling stage corresponding to the rice type information.

2. The method as described in claim 1, characterized in that, Based on rice type information and rice-water images, the determination of image recognition monitoring results also includes: When the rice type information corresponds to mixed grain rice, obtain the preset initial floating particle density and particle size corresponding to the rice type information; determine the ratio of the initial floating particle density to the preset initial floating particle density as the floating particle density factor; determine the ratio of the particle size to the preset particle size as the particle size factor. The cooking process adjustment instructions are defined as controlling the rice-water temperature inside the rice cooker to increase the preset adjustment temperature, and also include: The product of the floating particle density factor, particle size factor, and soaking adjustment temperature is determined as the rice soaking adjustment temperature; the sum of the soaking base temperature and the soaking adjustment temperature is determined as the preset adjustment temperature; and the cooking process adjustment command is determined to control the rice and water temperature in the rice cooker to increase the preset adjustment temperature.

3. The method as described in claim 1, characterized in that, The method further includes: The ratio of the adjusted floating particle density change rate to the target floating particle density change rate is determined as the adjustment factor for the soaking stage; and the boiling power heating time of the heating power curve corresponding to the boiling stage is obtained; wherein, the boiling power heating time corresponds to the maximum heating power heating time of the boiling stage. The product of the boiling power heating time and the soaking stage adjustment factor is determined to adjust the boiling power heating time.

4. The method as described in claim 3, characterized in that, The method further includes: By using the boiling stage control model, based on rice type information, particle size factor, and the rate of change of floating particle density during soaking at different times corresponding to rice type information, the micro-boiling power heating time of the rice cooker corresponding to the boiling stage heating power curve is determined. The product of the micro-boiling power heating time and the floating particle density factor is determined to adjust the micro-boiling power heating time of the heating power curve corresponding to the boiling stage.

5. A control system for an image recognition smart rice cooker based on the Internet of Things, characterized in that, Includes a unit for performing the method according to any one of claims 1 to 4.

Images