Intelligent steaming and boiling control method, intelligent steaming and boiling control device, computer equipment and storage medium

A control method and technology of a computer program are applied in the fields of computer equipment and storage media, devices, and intelligent cooking control methods, which can solve the problems of time difference and staying in the taste of rice, and achieve the effect of uniform taste.

Active Publication Date: 2019-11-15
GREE ELECTRIC APPLIANCES INC OF ZHUHAI +1
11 Cites 2 Cited by

AI-Extracted Technical Summary

Problems solved by technology

However, the rice cooking method in the current family still stays at the manual stage, that is, the user puts the rice in the kettle and adds an appropriat...
View more

Abstract

The invention relates to an intelligent steaming and boiling control method, an intelligent steaming and boiling control device, computer equipment and a storage medium. The method comprises the following steps of collecting a rice grain image corresponding to rice grains to be steamed and boiled; obtaining nutrition parameters of the rice grains to be steamed and boiled according to the rice grain image, wherein the nutrition parameters include at least one parameter of the dimension, the chromaticity and the skin residue rate of the rice gains to be steamed and boiled; and selecting a corresponding steaming and boiling control strategy according to the nutrition parameters, wherein the steaming and boiling control strategy is used for controlling the steaming and boiling process of the rice grains to be steamed and boiled. During the steaming and boiling control strategy selection, the characteristics of the kind of rice grains to be steamed and boiled per se, including the dimension, the chromaticity, the skin residue rate and the like are considered, so that the obtained steaming and boiling control strategy is suitable for the kind of rice grains; the cooked rice is enabled toalways have the same mouthfeel; the condition that the mouthfeel is sometimes good and sometimes bad cannot occur; and the combination of artificial intelligence and a home appliance product is realized.

Application Domain

Character and pattern recognitionSteam cooking vessels +1

Technology Topic

Computer equipmentBoiling process +6

Image

  • Intelligent steaming and boiling control method, intelligent steaming and boiling control device, computer equipment and storage medium
  • Intelligent steaming and boiling control method, intelligent steaming and boiling control device, computer equipment and storage medium
  • Intelligent steaming and boiling control method, intelligent steaming and boiling control device, computer equipment and storage medium

Examples

  • Experimental program(1)

Example Embodiment

[0021] In order to make the purpose, technical solutions and advantages of the embodiments of this application clearer, the technical solutions in the embodiments of this application will be described clearly and completely in conjunction with the drawings in the embodiments of this application. Obviously, the described embodiments These are a part of the embodiments of this application, but not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by those of ordinary skill in the art without creative work shall fall within the protection scope of this application.
[0022] In the first aspect, an intelligent cooking control method provided by an embodiment of the present application, such as figure 1 As shown, the method includes the following steps:
[0023] S110. Collect rice grain images corresponding to the rice grains to be cooked;
[0024] In practical applications, a camera, mobile phone or other terminal may be used to capture the rice grain image, and then the rice grain image can be obtained from the photographing terminal.
[0025] S120. Obtain nutritional parameters of the rice grains to be cooked according to the image of the rice grains; wherein the nutritional parameters include at least one of the size, color, and skin retention rate of the rice grains to be cooked;
[0026] In practical applications, different nutritional parameters have different obtaining methods. The three nutritional parameters of size, color, and skin retention rate are described below:
[0027] (1) The size of rice grains to be cooked
[0028] It is understandable that the size of the rice grains to be cooked can be length, width, length and width.
[0029] The process of obtaining the size of the rice grains to be cooked may specifically include:
[0030] S121a. Detect the calibration circle in the rice grain image by Hough operation, and calculate the number of pixels occupied by the diameter of the calibration circle; wherein, the calibration circle corresponds to the circular bottom of the preset cup, and the preset The cup contains the rice grains to be cooked;
[0031] Among them, the Hough operation can scan the rice grain image to determine the pixel range of the calibration circle in the rice grain image.
[0032] It is understandable that the number of pixels occupied by the diameter of the calibration circle can reflect the size of the calibration circle in the rice grain image.
[0033] Understandably, refer to figure 2 , Place a number of rice grains to be steamed in the preset cup, and then shoot to obtain a rice grain image. In the rice grain image, there is a calibration circle corresponding to the bottom of the circular cup, and there are several rice grains to be cooked in the calibration circle. Since the rice grain image is a calibration circle, the rice grain image must be taken perpendicular to the round bottom of the preset cup.
[0034] S122a. Determine the minimum circumscribed rectangle of each rice grain in the rice grain image, and determine the number of pixels occupied by the length of the rice grain and/or the width of the rice grain according to the minimum circumscribed rectangle of each rice grain in the rice grain image The number of pixels;
[0035] It is understandable that the minimum circumscribed matrix of each rice grain is determined here, the number of pixels occupied by the long side of the minimum circumscribed matrix is ​​taken as the number of pixels occupied by the length of the rice grain, and the short side of the minimum circumscribed matrix The number of pixels occupied is the number of pixels occupied by the width of the rice grain.
[0036] S123a. Determine the preset according to the diameter of the circular bottom of the preset cup, the number of pixels occupied by the diameter of the calibration circle, and the number of pixels occupied by the length and/or width of each rice grain The length and/or width of the corresponding rice grains in the cup;
[0037] For example, calculate the length and/or width of a rice grain in real space according to the following formula:
[0038] The length and/or width of a rice grain in the preset cup = the number of pixels corresponding to the length and/or width of the rice grain in the rice grain image* (the diameter of the circular bottom of the preset cup/the number of pixels State the number of pixels occupied by the diameter of the calibration circle)
[0039] That is to say, the size of the rice grain in the real space is determined according to the ratio of the round bottom of the preset cup to the size of the calibration circle, that is, the ratio of the size of the rice grain in the real space to the size of the rice grain in the rice grain image.
[0040] S124a: Determine the average length and/or average width of the rice grains in the preset cup according to the length and/or width of each rice grain in the preset cups.
[0041] Since there are many rice grains in the cup, the size of each rice grain is averaged to obtain the average size of one rice grain, and the average size is taken as the size of the rice grains to be cooked.
[0042] (2) The color of the rice to be cooked
[0043] The process of obtaining the color of the rice grains to be cooked may specifically include:
[0044] S121b. Convert the rice grain image into a rice grain image in the HSV color gamut, and record the image as an HSV color gamut image;
[0045] Among them, the HSV color gamut has 9 chromaticity ranges: white gray, orange, black, red 1, red 2, yellow, green, blue, and cyan. Each color gamut has an upper bound and a lower bound. Each chroma has three parameters: hue, saturation, and lightness. The HSV color gamut is adopted because the chromaticities are independent and there is no overlap.
[0046] S122b: Perform background filtering on the HSV color gamut image, and detect the contour of each rice grain in the HSV color gamut image after the background filtering;
[0047] Wherein, the process of background removal may be: calculating the number of pixels occupied by each chromaticity in the HSV color gamut image; taking the upper bound of the chromaticity with the largest number of pixels as the threshold, and filtering out the HSV Pixels in the color gamut image whose chroma is lower than the threshold. Here, the upper bound of the chromaticity that occupies the largest number of pixels is used as the threshold, and the upper bound of the chromaticity that occupies the largest area in the entire rice grain image is used as the threshold. Since the background area is the largest in the rice grain image, the upper bound of the chromaticity that occupies the most area in the entire rice grain image is taken as the threshold, and pixels with chromaticity less than the threshold are considered to be background. After the background is removed, the outline of the rice grain can be detected more easily. Specifically, the outline of the rice grain can be detected by the canny algorithm, which is beneficial to the subsequent mask processing.
[0048] S123b. Generate a mask according to the contour of each rice grain;
[0049] It is understandable that the mask is equivalent to covering the pixels outside the outline of the rice grain, so that the pixels outside the outline of the rice grain do not participate in subsequent processing steps.
[0050] S124b. Extract the rice grain pixels in the mask; determine the average chromaticity of the rice grains to be cooked according to the rice grain pixels.
[0051] It is understandable that the extracted pixels are multiple rice grain contours, and there are multiple pixels in each rice grain contour. Therefore, the chromaticity of several pixels extracted from multiple rice grain contours is averaged. An average color is obtained, and the average color is used as the average color of the rice grains to be cooked.
[0052] (3) Skin retention rate of rice grains to be cooked
[0053] The process of obtaining the skin retention rate of the rice grains to be cooked may specifically include:
[0054] S121c. Divide the rice grain image into multiple sub-images; wherein each sub-image includes only one rice grain; for example, figure 2 Divide into multiple sub-images, and each sub-image contains only one rice grain.
[0055] S122c. Input each sub-image into the pre-trained convolutional neural network to obtain the probability that the rice grains in the sub-image belong to each category, and the categories include skin-free rice grains and skin-free rice grains; The probability that the rice grains in the sub-image belong to each category, and determine the category of the rice grains in the sub-image;
[0056] It is understandable that the input of the convolutional neural network is a sub-image, and the output is the probability that the rice grains in the sub-image belong to each category. Since there are categories of rice grains with skins and rice grains without skins, the convolutional neural network will output two probability values, one probability value is the probability of the rice grains with skins, and the other probability is the probability of the rice grains without skins. For example, if the probability of a rice grain with skin is 60%, and the probability of a rice grain without skin is 40%, the rice grain is considered to be a rice grain with skin.
[0057] Among them, the convolutional neural network has many structural forms, one of which is introduced below:
[0058] The convolutional neural network includes an input layer, a plurality of feature extraction modules, a fully connected layer, and a classifier, which are sequentially connected; wherein: each feature extraction module includes a convolutional layer and a pooling layer connected to the convolutional layer , The convolutional layer is used to perform convolution processing on the image input to the convolutional layer to obtain a convolutional feature map; the pooling layer is used to perform pooling processing on the convolutional feature map to obtain a pooled feature Figure; The fully connected layer is used to convert the pooled feature map output by the last feature extraction module into a corresponding vector, and the classifier is used to generate a probability corresponding to each category according to the vector.
[0059] Among them, the convolution layer is mainly composed of a convolution kernel, which is a square matrix, for example, a matrix with a size of 3*3, and the convolution kernel is equivalent to a fully connected layer with a slightly smaller size. Use the convolution kernel to scan from the upper left corner of the input image, from left to right, from top to bottom, every time a unit area (the same area as the convolution kernel) is scanned, the pixels of the unit area on the input image and convolution The kernel matrix is ​​calculated to obtain a feature map (ie feature map), and all the obtained feature maps form a large feature map, that is, a convolution feature map is obtained. The role of the convolutional layer is to extract features from the input image.
[0060] Among them, the processing of the pooling layer is similar to that of the convolution kernel. A fixed-size area is scanned on the convolution feature map. The difference is that the pooling layer performs block processing on the area, for example, maximum pooling processing , That is to take the largest pixel in the area, for another example, the average pooling process, that is, calculate the average of the pixels in the area. After the pooling process, the pooling feature layer is obtained. The purpose of pooling processing is to perform further feature extraction on the convolutional feature map to reduce feature redundancy.
[0061] Among them, there can be multiple fully connected layers, for example, three. The pooled feature layer in matrix form can be converted into a vector through the fully connected layer, so as to facilitate subsequent processing.
[0062] Among them, the classifier can be implemented using the softmax function, and the probability value corresponding to each category can be obtained through the softmax function.
[0063] It is understandable that, based on multiple probability values, the threshold for determining the category of rice grains can be set according to actual conditions, and is not limited to 50%.
[0064] S123c: Determine the skin retention rate of the rice grains to be cooked according to the number of sub-images of which the category of the rice grains are skinned rice grains and the total number of the multiple sub-images.
[0065] It is understandable that the category of rice grains is that the number of sub-images with skin rice grains in the rice grain image is the number of skin rice grains, and the total number of the multiple sub-images is the number of rice grains in the rice grain image. The total number of. Skin retention rate=The category of rice grains is the number of sub-images with skin rice grains/the total number of the multiple sub-images.
[0066] S130. Select a corresponding cooking control strategy according to the nutritional parameters; wherein, the cooking control strategy is used to control the cooking process of the rice grains to be cooked.
[0067] Among them, the specific process of selecting a cooking control strategy can include:
[0068] S131: Determine the deviation value of the nutritional parameter according to each nutritional parameter and the preset standard value of the nutritional parameter;
[0069] For example, the comparison table of each nutritional parameter, the preset standard value of each nutritional parameter, the deviation value and the deviation weight obtained in step S120 is shown in Table 1:
[0070] Table 1
[0071]
[0072] S132. According to the deviation value of each nutrient parameter and the deviation weight of each nutrient parameter, determine the control parameters required for each stage of the cooking process of the rice grains to be cooked, and the control parameters required for each stage include those required for the stage. The time and heating temperature of the rice to be cooked, the control parameters required at each stage of the cooking process, form the cooking control strategy corresponding to the rice to be cooked.
[0073] Among them, the calculation formula of time t is as follows:
[0074]
[0075] Among them, the calculation formula of heating temperature T is as follows:
[0076]
[0077] Where w t Is the time weight, b t Is the time offset, w T Is the temperature weight, b T Is the temperature bias. At different stages, these weights and bias parameters are different and can be set in advance.
[0078] It is understandable that the process of cooking rice is generally divided into a rice soaking stage, a heating stage, a pressure increasing stage, a boiling stage, a braising stage and a heat preservation stage. These six stages are as image 3 The six line segments of the broken line in, as long as you determine the time required for each stage and the temperature that each stage needs to reach, you can draw image 3 The line chart shown. In other words, as long as six points (t, T) are determined, one point corresponds to one stage. For the points corresponding to each stage, the time and heating temperature can be obtained according to the corresponding weight and bias parameter of the stage, the deviation value and deviation weight of the nutrition parameter (that is, through the above two formulas). It is understandable that these 6 points constitute a cooking control strategy. After the control parameters of each stage are determined, the power of the cooking device can be controlled according to the control parameters, and then the rice can be cooked.
[0079] The intelligent steaming control method provided in this application can be executed by a steaming device. For example, the rice grain image is captured by a mobile phone or a camera. The steaming device collects the rice grain image from the mobile phone or camera, and then executes the subsequent steps to obtain the steaming control strategy. The control strategy controls the cooking of the rice to be cooked. However, the smart cooking control method provided in this application can also be executed by a smart terminal (mobile phone, PC, etc.). The smart terminal obtains an image of rice grains by shooting, and then executes the subsequent steps to obtain the cooking control strategy, and then transmits the cooking control strategy to the cooking Equipment, and then the cooking equipment performs cooking control on the rice to be cooked according to the cooking control strategy. That is to say, the hardware implementation equipment of the method provided in the present application may be independent of the cooking equipment, or may be a cooking equipment.
[0080] The intelligent cooking control method provided by the embodiments of the present application collects rice grain images, then obtains the nutritional parameters of the rice grains to be cooked based on the rice grain images, and selects the corresponding cooking control strategy based on the nutritional parameters, and then controls the cooking process of the rice grains to be cooked. Different types of rice grains require different cooking control strategies. When choosing a cooking control strategy, consider the characteristics of the rice grains to be cooked-size, color, and skin retention rate, etc., to obtain a cooking control strategy It is suitable for this kind of rice grains, thus ensuring that the cooked rice always tastes the same without time difference and time difference, realizing the combination of artificial intelligence and home appliances.
[0081] In the second aspect, this application provides a smart cooking control device, such as Figure 4 As shown, the device 400 includes:
[0082] The image collection module 410 is used to collect rice grain images corresponding to the rice grains to be cooked;
[0083] The parameter obtaining module 420 is configured to obtain nutritional parameters of the rice grains to be cooked according to the image of the rice grains; wherein the nutritional parameters include at least one of the size, color, and skin retention rate of the rice grains to be cooked;
[0084] The strategy selection module 430 is configured to select a corresponding cooking control strategy according to the nutritional parameters; wherein, the cooking control strategy is used to control the cooking process of the rice grains to be cooked.
[0085] In some embodiments, the parameter acquisition module is specifically used to: detect the calibration circle in the rice grain image by Hough operation, and calculate the number of pixels occupied by the diameter of the calibration circle; wherein, the calibration circle corresponds to the preset A round bottom of the cup is provided, and the preset cup contains the rice grains to be steamed; the smallest circumscribed rectangle of each rice grain in the rice grain image is determined, and the smallest circumscribed rectangle of each rice grain in the rice grain image is determined Rectangle, determine the number of pixels occupied by the length of the rice grain and/or the number of pixels occupied by the width of the rice grain; according to the diameter of the circular bottom of the preset cup and the diameter of the calibration circle The number of pixels and the number of pixels occupied by the length and/or width of each rice grain determine the length and/or width of the corresponding rice grain in the preset cup; according to the length and the length of each rice grain in the preset cup /Or width, determining the average length and/or average width of the rice grains in the preset cup.
[0086] In some embodiments, the parameter acquisition module is specifically configured to: convert the rice grain image into an HSV color gamut rice grain image, and record the image as an HSV color gamut image; perform background filtering on the HSV color gamut image, After the background is filtered, the contour of each rice grain in the HSV color gamut image is detected; a mask is generated according to the contour of each rice grain; the rice grain pixels in the mask are extracted; the rice grains to be cooked are determined according to the rice grain pixels Average chromaticity.
[0087] In some embodiments, the process of the parameter acquisition module performing background filtering on the HSV color gamut image includes: calculating the number of pixels occupied by each chromaticity in the HSV color gamut image; and calculating the number of pixels occupied The upper bound of the most chromaticity is used as the threshold, and pixels with chromaticity lower than the threshold in the HSV color gamut image are filtered out.
[0088] In some embodiments, the parameter acquisition module is specifically used to: divide the rice grain image into multiple sub-images; wherein each sub-image includes only one rice grain; and input each sub-image to a pre-trained In the convolutional neural network, the probability that the rice grains in the sub-image belong to each category is obtained. The categories include rice grains with and without skin; according to the probability that the rice grains in each sub-image belong to each category, determine The category of the rice grains in the sub-image; the skin retention rate of the rice grains to be cooked is determined according to the number of sub-images in which the category of the rice grains are skinned rice grains and the total number of the multiple sub-images.
[0089] In some embodiments, the convolutional neural network includes an input layer, a plurality of feature extraction modules, a fully connected layer, and a classifier that are sequentially connected; wherein: each feature extraction module includes a convolutional layer and a convolutional layer. A layer-connected pooling layer, the convolutional layer is used to perform convolution processing on the image input to the convolutional layer to obtain a convolutional feature map; the pooling layer is used to pool the convolutional feature map Processing to obtain a pooled feature map; the fully connected layer is used to convert the pooled feature map output by the last feature extraction module into a corresponding vector, and the classifier is used to generate a probability corresponding to each category according to the vector.
[0090] In some embodiments, the strategy selection module is specifically configured to: determine the deviation value of the nutritional parameter according to each nutritional parameter and the preset standard value of the nutritional parameter; according to the deviation value of each nutritional parameter and the deviation weight of each nutritional parameter , Determine the control parameters required for each stage of the cooking process of the rice to be cooked, the control parameters required for each stage include the time and heating temperature required for the stage, and the temperature of the rice to be cooked during the cooking process The control parameters required at each stage form a cooking control strategy corresponding to the rice grains to be cooked.
[0091] It is understandable that, for the control device provided in the embodiment of the present application, for the explanation, examples, beneficial effects and other parts of the relevant content, reference may be made to the corresponding part in the first aspect, and details are not repeated here.
[0092] In a third aspect, an embodiment of the present application provides a computer device, which includes a memory, a processor, and a computer program stored in the memory and running on the processor, wherein the processor executes the computer program The program implements the steps of the method provided in the first aspect.
[0093] Figure 5 Shows an internal structure diagram of a computer device in an embodiment. Such as Figure 5 As shown, the computer equipment includes the computer equipment including a processor, a memory, a network interface, an input device, and a display screen connected through a system bus. Among them, the memory includes a non-volatile storage medium and an internal memory. The non-volatile storage medium of the computer device stores an operating system and can also store a computer program. When the computer program is executed by the processor, the processor can realize the intelligent cooking control method. A computer program may also be stored in the internal memory. When the computer program is executed by the processor, the processor can execute the intelligent cooking control method. The display screen of the computer equipment can be a liquid crystal display screen or an electronic ink display screen. It can be an external keyboard, touchpad, or mouse.
[0094] Those skilled in the art can understand, Figure 5 The structure shown in is only a block diagram of part of the structure related to the solution of the application, and does not constitute a limitation on the computer equipment to which the solution of the application is applied. The specific computer equipment may include more or Fewer parts, or combine some parts, or have a different arrangement of parts.
[0095] In one embodiment, the intelligent cooking control device provided by the present application can be implemented in the form of a computer program, and the computer program can be Figure 5 Run on the computer equipment shown. The memory of the computer equipment can store various program modules that make up the intelligent cooking control device, for example, Figure 4 The image acquisition module 410, the parameter acquisition module 420, and the strategy selection module 430 are shown. The computer program composed of each program module causes the processor to execute the steps in the intelligent cooking control method of each embodiment of the present application described in this specification.
[0096] E.g, Figure 5 The computer equipment shown can be passed as Figure 4 The image acquisition module in the control device shown is to collect rice grain images corresponding to the rice grains to be cooked; the parameter acquisition module executes to acquire the nutritional parameters of the rice grains to be cooked according to the rice grain image; wherein, the nutritional parameters include the rice grains to be cooked At least one of the size, color, and skin retention rate of the cooked rice grains; the strategy selection module executes the selection of a corresponding cooking control strategy according to the nutritional parameters; wherein, the cooking control strategy is used to control the cooking of the rice grains to be cooked. The cooking process is controlled.
[0097] It is understandable that, for the computer equipment provided in the embodiments of the present application, for the explanations, examples, beneficial effects and other parts of the relevant content, please refer to the corresponding parts in the first aspect, which will not be repeated here.
[0098] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium on which a computer program is stored, and when the computer program is executed by a processor, the steps of the method provided in the first aspect are implemented.
[0099] It is understandable that, for the computer-readable storage medium provided in the embodiments of the present application, for the explanations, examples, beneficial effects and other parts of the relevant content, please refer to the corresponding parts in the first aspect, which will not be repeated here.
[0100] It is understandable that any reference to memory, storage, database or other media used in the embodiments provided in this application may include non-volatile and/or volatile memory. Non-volatile memory may include read only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not a limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous chain Channel (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.
[0101] It should be noted that in this article, relational terms such as "first" and "second" are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply these There is any such actual relationship or sequence between entities or operations. Moreover, the terms "include", "include" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements not only includes those elements, but also includes those that are not explicitly listed Other elements of, or also include elements inherent to this process, method, article or equipment. If there are no more restrictions, the element defined by the sentence "including a..." does not exclude the existence of other same elements in the process, method, article, or equipment that includes the element.
[0102] The above are only specific embodiments of the present invention, so that those skilled in the art can understand or implement the present invention. Various modifications to these embodiments will be obvious to those skilled in the art, and the general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown in this document, but should conform to the widest scope consistent with the principles and novel features applied in this document.

PUM

no PUM

Description & Claims & Application Information

We can also present the details of the Description, Claims and Application information to help users get a comprehensive understanding of the technical details of the patent, such as background art, summary of invention, brief description of drawings, description of embodiments, and other original content. On the other hand, users can also determine the specific scope of protection of the technology through the list of claims; as well as understand the changes in the life cycle of the technology with the presentation of the patent timeline. Login to view more.
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products