Image-based composition modulation method, composition modulation apparatus, and storage medium

Abstract

The invention relates to the field of image recognition, and provides an image-based composition modulation method, which is applied to composition modulation equipment and comprises the following steps: acquiring a target image; identifying at least one feature in the target image; determining a proportion corresponding to each feature in the at least one feature and a target preparation corresponding to each feature according to a corresponding relationship between the features and proportions, and obtaining a proportion corresponding to each target preparation; and fusing all the target preparations corresponding to the at least one feature and the corresponding proportions by using the composition preparation equipment to obtain a target composition. By utilizing the method, the visual information can be converted into the taste information and the smell information, so that the composition in which the taste information and the smell information are embodied in a concrete manner is obtained.

Description

Technical Field

[0001] The present application belongs to the field of image recognition technology, and in particular relates to an image-based composition modulation method, a composition modulation device and a storage medium. Background Art

[0002] Human vision, taste and smell are important components of the sensory system. They have different functions and characteristics, and there is a certain connection and interaction between these senses. However, in current technology, vision and hearing have achieved information replication, transmission and storage, but the informationization of smell and taste is still under exploration. Existing technology cannot achieve the informationization of smell and taste through the mutual conversion of sensory information. Summary of the invention

[0003] In view of the above, it is necessary to provide an image-based preparation method, composition preparation device and storage medium, which can solve the problem that visual information cannot be converted into taste information and olfactory information through the mutual conversion of sensory information.

[0004] An embodiment of the present application provides an image-based composition modulation method, which is applied to a composition modulation device, and the method includes: acquiring a target image; identifying at least one feature in the target image; determining the ratio corresponding to each feature in the at least one feature and the target preparation corresponding to each feature according to the correspondence between the feature and the ratio, and obtaining the ratio corresponding to each target preparation; using the composition modulation device to fuse all target preparations corresponding to the at least one feature and the corresponding ratios, and obtain a target composition.

[0005] In one embodiment, acquiring the target image includes: when it is detected that the distance between the user and the composition modulation device is less than a preset distance threshold, displaying a login interface on the display of the composition modulation device; in response to the user's login operation on the login interface, photographing at least one user image of the user using a photographing device; in response to the user's selection operation of any image among the at least one user image, using the user image selected by the user as the target image.

[0006] In one embodiment, the identifying at least one feature in the target image includes: identifying an expression feature of the user in the target image, and identifying a preset number of color features in the target image.

[0007] In one embodiment, the target preparation corresponding to the expression feature in the target image includes a base beverage as a base of the modulated composition, and the target preparation corresponding to each color feature in the target image includes a flavored beverage as a condiment of the modulated composition.

[0008] In one embodiment, acquiring the target image further includes receiving the target image input by a user, and before identifying at least one feature in the target image, the method further includes: determining the type of the target image, wherein the type includes a famous painting image, a scene image, and an object image.

[0009] In one embodiment, identifying at least one feature in the target image includes: when the target image is an image of a famous painting, identifying a preset number of color features in the target image; or when the target image is a scene image, determining the scene category in the scene image and identifying the preset number of color features in the target image; or when the target image is an object image, determining the object category in the object image and identifying the preset number of color features in the target image.

[0010] In one embodiment, a target preparation corresponding to each color feature in the target image includes an essential oil liquid as a seasoning for the modulated composition; a target preparation corresponding to a scene category in the target image includes an essential oil liquid as a base for the modulated composition; and a target preparation corresponding to an object category in the target image includes an essential oil liquid as a base for the modulated composition.

[0011] In one embodiment, the method further includes: using the composition modulation device to generate and save the composition information of the target composition, the composition information of the target composition including: the characteristics of the target image corresponding to the target composition, and the corresponding proportion of each target preparation contained in the target composition.

[0012] An embodiment of the present application provides a composition preparation device, which includes a processor, a memory, a camera, a sensor, and a display. The processor is used to implement the image-based composition preparation method when executing a computer program stored in the memory.

[0013] An embodiment of the present application provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the image-based composition modulation method is implemented.

[0014] In summary, the image-based composition modulation method described in the present application can recognize the features of the objects in the image, modulate the composition corresponding to the image according to the preparation corresponding to the image features, and can convert the user's visual perception of the image into a concrete composition of smell or taste, thereby realizing the replication, transmission and storage of olfactory and taste information through sensory information conversion. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 It is a structural diagram of a composition preparation device provided in one embodiment of the present application.

[0016] Figure 2 It is a flow chart of an image-based composition modulation method provided in one embodiment of the present application.

[0017] Figure 3 This is a flowchart for acquiring a target image provided by an embodiment of the present application.

[0018] Figure 4 This is a flowchart for acquiring a target image provided by another embodiment of the present application. DETAILED DESCRIPTION

[0019] In order to more clearly understand the above-mentioned purposes, features and advantages of the present application, the present application is described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be noted that the embodiments of the present application and the features in the embodiments can be combined with each other without conflict.

[0020] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which this application belongs. The terms used herein in the specification of this application are only for the purpose of describing the embodiments in one embodiment and are not intended to limit this application.

[0021] It should be noted that in this application, "at least one" means one or more, and "more than one" means two or more than two. "And / or" describes the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone, where A and B can be singular or plural. The terms "first", "second", "third", "fourth", etc. (if any) in the specification, claims and drawings of this application are used to distinguish similar objects, rather than to describe a specific order or sequence.

[0022] In the embodiments of the present application, words such as "exemplary" or "for example" are used to indicate examples, illustrations or descriptions. Any embodiment or design described as "exemplary" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "exemplary" or "for example" is intended to present related concepts in a concrete way. The following embodiments and features in the embodiments may be combined with each other without conflict.

[0023] In one embodiment, with the continuous development of information technology, audio-visual information has long been informatized, but olfactory and taste information has been ignored. However, different senses have different functions and characteristics, and there are certain connections and interactions between these senses. For example, people will secrete saliva unconditionally when they see lemons, and strawberry-flavored ice cream is always pink. However, in the related art, it is impossible to convert the user's visual perception of the image into a concrete combination of olfactory or taste.

[0024] To solve the above problems, the embodiments of the present application provide an image-based composition preparation method, which can convert odor information or flavor information based on the image information by performing feature recognition on colors or objects in the image and modulating the composition corresponding to the image according to the preparation corresponding to the image features, thereby converting the user's visual perception information of the image into a concrete composition medium of olfactory information or taste information, thereby solving the problem in the related art that olfactory information or taste information cannot be copied, transmitted and stored.

[0025] Figure 1 This is a schematic diagram of the structure of a composition preparation device provided in an embodiment of the present application. Figure 1 As shown, the composition preparation device 10 may include a communication module 101, a memory 102, a processor 103, an input / output (I / O) interface 104 and a bus 105, a camera 106, a sensor 107, a display 108, and a printing device 109. The processor 103 is coupled to the communication interface 101, the memory 102, the I / O interface 104, the camera 106, the sensor 107, the display 108, and the printing device 109 through the bus 105.

[0026] The communication module 101 may include a wired communication module and / or a wireless communication module. The wired communication module may provide one or more wired communication solutions such as universal serial bus (USB), controller area network bus (CAN, Controller Area Network). The wireless communication module may provide one or more wireless communication solutions such as wireless fidelity (wireless fidelity, Wi-Fi), bluetooth (bluetooth, BT), mobile communication network, frequency modulation (frequency modulation, FM), near field communication technology (near field communication, NFC), infrared technology (infrared, IR), etc.

[0027] The memory 102 may include one or more random access memories (RAM) and one or more non-volatile memories (NVM). The random access memory can be directly read and written by the processor 103, and can be used to store executable programs (such as machine instructions) of the operating system or other running programs, and can also be used to store user and application data. The random access memory may include static random-access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), etc.

[0028] The non-volatile memory may also store executable programs and user and application data, etc., and may be pre-loaded into the random access memory for direct reading and writing by the processor 110. The non-volatile memory may include a disk storage device and a flash memory.

[0029] The memory 102 is used to store one or more computer programs. The one or more computer programs are configured to be executed by the processor 103. The one or more computer programs include a plurality of instructions, and when the plurality of instructions are executed by the processor 103, the image-based composition preparation method executed on the composition preparation device 10 can be implemented.

[0030] In other embodiments, the composition preparation device 10 further includes an external memory interface for connecting to an external memory to expand the storage capacity of the composition preparation device 10 .

[0031] The processor 103 may include one or more processing units, for example, the processor 103 may include an application processor (AP), a modem processor, a graphics processor (GPU), an image signal processor (ISP), a controller, a video codec, a digital signal processor (DSP), a baseband processor, and / or a neural-network processing unit (NPU), etc. Different processing units may be independent devices or integrated into one or more processors.

[0032] The processor 103 provides computing and control capabilities. For example, the processor 103 is used to execute a computer program stored in the memory 102 to implement the above-mentioned image-based composition preparation method.

[0033] The I / O interface 104 is used to provide a channel for user input or output. For example, the I / O interface 104 can be used to connect various input and output devices, such as a mouse, keyboard, touch device, display screen, etc., so that the user can enter information or visualize information.

[0034] The bus 105 is at least used to provide a channel for mutual communication among the communication module 101 , the memory 102 , the processor 103 , the I / O interface 104 , the camera 106 , the sensor 107 , the display 108 , and the printing device 109 in the composition preparation device 10 .

[0035] The camera 106 is used to capture images, such as capturing user images including the user's face, etc. The camera 106 may include but is not limited to a hemispherical camera, an integrated camera, an infrared day and night camera, etc.

[0036] The sensor 107 is used to detect the distance between the user and the composition preparation device. The sensor 107 may include but is not limited to an ultrasonic distance measurement sensor, a laser distance measurement sensor, an infrared distance measurement sensor, a radar sensor, and the like.

[0037] The display 108 is used to display a visual interface (such as a login interface) to the user, implement interactive operations with the user, etc. The display 108 may include a touch screen display screen.

[0038] The printing device 109 is used to print the label of the prepared composition, and the printing device 109 includes but is not limited to a laser printer, an inkjet printer and a dot matrix printer.

[0039] It is understood that the structure illustrated in the embodiment of the present application does not constitute a specific limitation on the composition preparation device 10. In other embodiments of the present application, the composition preparation device 10 may include more or fewer components than shown in the figure, or combine some components, or separate some components, or arrange the components differently. The components shown in the figure may be implemented in hardware, software, or a combination of software and hardware.

[0040] Figure 2 : is a flow chart of an image-based composition preparation method provided in an embodiment of the present application. The image-based composition preparation method is applied to a composition preparation device, such as Figure 1 The composition preparation device 10 specifically includes the following steps. According to different requirements, the order of the steps in the flowchart can be changed, and some steps can be omitted.

[0041] S21, acquiring a target image.

[0042] In one embodiment, the target image may include a composition that is intended to be prepared according to its visual features so that the user can perceive the smell or taste corresponding to the target image according to the prepared target composition.

[0043] The target image may be an image containing multiple colors, for example, the target image may be an RGB image containing three color channels: red, green, and blue. The target composition may include, but is not limited to, a beverage composition (such as a mixed drink, a mixed wine, etc.), a perfume composition (such as perfume, aromatherapy, etc.).

[0044] In one embodiment, when acquiring a target image, a shooting device (e.g. Figure 1 The shooting device 106 in the image captures the user's image as the target image, and the composite modulation device can also be used to receive the target image (such as a famous painting image, a scene image, an object image, etc.) input by the user, and the image pre-stored in the memory of the composite modulation device can also be used as the target image.

[0045] In one embodiment, Figure 3 As shown, the process of acquiring the target image may include the following steps:

[0046] S31, when it is detected that the distance between the user and the composition preparation device is less than a preset distance threshold, a login interface is displayed on the display of the composition preparation device.

[0047] In one embodiment, a sensor (e.g. Figure 1 The sensor 107 in the embodiment detects the distance between the user and the composition preparation device, and the preset distance threshold can be based on the current display (e.g. Figure 1The preset distance threshold may be set to be proportional to the size of the display 108 in the display. For example, the preset distance threshold may be set to be proportional to the size of the display.

[0048] In one embodiment, when it is detected that the distance between the user and the composition preparation device is less than a preset distance threshold (e.g., 0.5 meters), a registration interface or a login interface is displayed on the display screen. A first-time user can enter user information through the registration interface to register an account, and the login interface can be used to indicate the user information that the user needs to enter and the corresponding input box, input method interface, etc. The user information may include but is not limited to user name (Name), user gender (Gender), user age (Age), etc.

[0049] In other embodiments, the composition preparation device may further include a corresponding terminal application (eg, mobile phone software), and the user may implement a remote login operation in the terminal application.

[0050] S32: In response to the user's login operation on the login interface, using a photographing device to photograph at least one user image of the user.

[0051] In one embodiment, the login interface may also be used to provide a login button for the user. When the user inputs user information and clicks the login button, the composition preparation device confirms that the user has performed the login operation.

[0052] After the user performs a login operation on the login interface, the composition preparation device takes at least one (for example, 3) user images for the user in response to the login operation, and the user image may include the user's face.

[0053] S33: In response to the user's selection operation on any one of the at least one user image, use the user image selected by the user as the target image.

[0054] In one embodiment, in order to improve the accuracy of feature recognition of the target image, after capturing at least one user image of the user, the method may further include: displaying at least one user image to the user, selecting a user image with the highest image quality from the at least one user image; and displaying indication information for the user image with the highest image quality.

[0055] In one embodiment, the image quality includes but is not limited to clarity, contrast, distortion, exposure, etc. The method of selecting the user image with the highest image quality from at least one user image includes but is not limited to: quantifying the quality of each user image using a preset image evaluation index (such as a structural similarity index, a peak signal-to-noise ratio, etc.), and taking the user image with the highest image evaluation index score as the user image with the highest image quality; or, training an image quality evaluation model based on a deep learning algorithm, using the image quality evaluation model to determine the evaluation score of each user image, and taking the user image with the highest evaluation score as the user image with the highest image quality.

[0056] In one embodiment, when displaying the at least one user image to the user and displaying indication information for the user image with the highest image quality, all user images may be arranged in descending order of image quality, indication information may be annotated under the user image with the highest image quality (for example, this image has the highest image quality and may be selected preferentially), and the user image with the highest image quality may be highlighted (for example, adding a bright border to the user image with the highest image quality, centering and enlarging the user image with the highest image quality, etc.).

[0057] In one embodiment, when the composition preparation device confirms that the user has performed a point selection operation on any image in the display, it is determined that the user has performed a selection operation on the image. In response to the user's selection operation on any image of the at least one user image, the user image selected by the user is used as the target image.

[0058] In other embodiments, the composition preparation device may also receive an image remotely transmitted by a user in a terminal application as a target image, for example Figure 4 As shown, the following steps may be included:

[0059] S41, when it is detected that the distance between the user and the composition preparation device is less than a preset distance threshold, a login interface is displayed on the display of the composition preparation device.

[0060] S42, in response to the user's login operation on the login interface, receiving an image input by the user as a target image.

[0061] S22, identifying at least one feature in the target image.

[0062] In one embodiment, in order to improve the accuracy of feature recognition of the target image, before identifying at least one feature in the target image, the method may further include preprocessing the target image. Specifically, the preprocessing may include but is not limited to: resizing, for example, resizing the target image to the size of the input required by the feature recognition model; image optimization, for example, improving the texture clarity of the target image based on an interpolation algorithm (such as a bilinear interpolation algorithm); grayscale processing, for example, converting the target image into a grayscale image using a weighted average method; filtering processing, for example, using a preset filter (such as a mean filter, a median filter, etc.) to smooth the target image to remove noise.

[0063] In one embodiment, a pre-trained feature recognition model may be used to recognize at least one feature in the target image. Specifically, the feature recognition model may be a model based on a convolutional neural network, for example, the feature recognition model may be VGGNet, GoogLeNet, ResNet, etc.

[0064] In one embodiment, since the target image may include multiple categories, the features to be identified in each target image may be different. Therefore, before identifying at least one feature in the target image, the method also includes: determining the category of the target image, the categories including user images, famous painting images (such as Van Gogh's famous paintings "Starry Night" and "Sunflowers", etc.), scene images (such as typical outdoor scenes within a certain area, such as buildings, streets, parks, waters, temples, mountains, etc.), and object images (such as images containing apples, bananas, etc.).

[0065] In one embodiment, the method for determining the type of the target image may include: using a feature recognition model to identify whether the icon image contains facial features, and when the target image contains facial features, determining that the target image is a user image; and / or performing image matching between the target image and a famous painting image in a preset database, and when the database contains a famous painting image that matches the target image, determining that the target image is a famous painting image; and / or using a feature recognition model to identify whether the icon image contains preset scene image features (for example, buildings, streets, parks, waters, temples, mountains, etc.), and when the target image contains preset scene image features, determining that the target image is a scene image; and / or using a feature recognition model to identify whether the icon image contains preset object features (for example, food such as apples and bananas), and when the target image contains preset object features, determining that the target image is an object image.

[0066] In one embodiment, the identifying at least one feature in the target image includes: when the target image is a user image, identifying the expression features of the user in the target image, and identifying a preset number of color features in the target image; or when the target image is an image of a famous painting, identifying a preset number of color features in the target image; or when the target image is a scene image, determining the scene category (for example, buildings, streets, parks, waters, temples, mountains, etc.) in the scene image and identifying the preset number of color features in the target image; or when the target image is an object image, determining the object category in the object image and identifying the preset number of color features in the target image.

[0067] In one embodiment, when identifying the facial features of the user in the target image, multiple (e.g., 108) facial landmarks in the user's face in the target image may be first identified, such as the brow peak, eyebrow tail, mouth corner, eye corner, etc.; multiple regions of interest are then generated based on the multiple facial landmarks, for example, the region of interest includes the region where muscles move when the face shows an expression, such as the region where eyebrows, eyes, mouth, and other facial landmarks are located; the facial features are determined by judging the category of the facial landmarks in the region of interest through a classification algorithm (e.g., a classifier model), for example, the category of the region of interest corresponding to the lips is smile, indicating that the user's facial features are smile. By identifying the facial features of the user, the current emotion of the user in the target image may be determined, so that a target preparation that meets the user's current emotion is obtained in the subsequent steps, so that the target composition obtained based on the target preparation is more in line with user needs, and the accuracy of the result of converting vision into taste and smell is improved.

[0068] In one embodiment, when identifying the preset number (e.g., 4) of color features in the target image, the method may include: (1) firstly counting the color information of each pixel in the target image. For example, a preset color table may be used to determine the color category corresponding to each pixel. The color table may include the RGB value of the pixel and the corresponding color. For example, when the RGB value of the pixel is (227, 207, 87), it indicates banana color; when the RGB value of the pixel is (135, 206, 235), it indicates sky blue; and when the RGB value of the pixel is (124, 252, 0), it indicates grass. Green, etc.; In addition, the value range of each color channel can also be used in the color table to represent the color category of the corresponding pixel point, for example, when the RGB value range is ([210,230), [190,210), [70,90)), it represents yellow; (2) Thereafter, the proportion of each color in the target image is obtained, and the proportion values ​​are sorted from high to low, and the color features corresponding to the preset number of proportion values ​​in the sequence are selected, for example, the preset number of color features can be sky blue with a proportion of 41%, light yellow with a proportion of 29%, white with a proportion of 11%, and black with a proportion of 9%. By selecting the preset number of color features with higher proportion values, the most prominent color feature in the target image can be obtained, so as to achieve the target preparation corresponding to the most prominent color feature in the subsequent steps, so that the target composition obtained based on the target preparation is more in line with the characteristics of the target image, and the accuracy of the result of converting vision into taste and smell is improved.

[0069] Step S23, according to the correspondence between the feature and the ratio, determine the ratio corresponding to each feature of the at least one feature and the target preparation corresponding to each feature, and obtain the ratio corresponding to each target preparation.

[0070] In one embodiment, the corresponding relationship between features and proportions is pre-stored in the composition modulation device, which can be used to determine the proportion corresponding to each feature of the at least one feature. For example, when the target image is a user image, the proportion corresponding to the expression feature is 75%, and the proportion corresponding to the color feature is 25%; when the target image is a scene image, the proportion corresponding to the scene category is 60%, and the proportion corresponding to the color feature is 40%; when the target image is an object image, the proportion corresponding to the object category is 50%, and the proportion corresponding to the color feature is 50%; when the target image is a famous painting image, the proportion corresponding to the preset number of color features in the famous painting image can be normalized to obtain the proportion corresponding to each color feature.

[0071] In addition, a feature preparation correspondence table is pre-stored in the composition preparation device, and the feature preparation correspondence table contains the target preparation corresponding to each feature. Depending on the target composition to be prepared, the target preparation corresponding to each feature will also be different. For example, the target composition may include but is not limited to beverage compositions (such as prepared beverages, prepared wines, etc.), perfume compositions (such as perfumes, aromatherapy, daily chemical products, etc.). The display of the composition preparation device can be used to display buttons or logos corresponding to different target compositions in the user's login interface, and the target preparation corresponding to each feature in the target image can be determined by responding to the user's selection operation of the target composition.

[0072] In one example, in response to a user's selection operation of a beverage composition, determining the target preparation corresponding to each feature in the target image includes: when the target image is a user image, determining that the target preparation corresponding to the expression feature in the target image includes a base beverage as a base of the prepared composition, and determining that the target preparation corresponding to each color feature in the target image includes a flavored beverage as a condiment of the prepared composition. Each expression feature corresponds to a different base beverage, and each color feature corresponds to a different flavored beverage. For example, when the expression feature is a smile, the base beverage may be Snow Beer; the red color feature may correspond to a rose-flavored flavored beverage, and the pink color feature may correspond to a raspberry-flavored flavored beverage, etc.

[0073] In another example, in response to a user's operation on the fragrance composition, determining a target formulation corresponding to each feature in the target image includes:

[0074] When the target image is an image of a famous painting, it is determined that the target preparation corresponding to each color feature in the target image includes an essential oil liquid as a seasoning for the modulated composition, wherein different color features correspond to different essential oil liquids, for example, the essential oil liquid corresponding to blue may be sea salt-flavored essential oil or a mixed essential oil blended after testing and investigation, the essential oil liquid corresponding to red may be rose-flavored essential oil or a mixed essential oil blended after testing and investigation, and the essential oil liquid corresponding to yellow may be citrus-flavored essential oil or a mixed essential oil blended after testing and investigation; or

[0075] When the target image is a scene image, it is determined that the target preparation corresponding to the scene category in the target image includes an essential oil liquid as a base of the modulated composition, and it is determined that the target preparation corresponding to each color feature in the target image includes an essential oil liquid as a seasoning of the modulated composition, wherein different scene categories correspond to different essential oil liquids, for example, the essential oil liquid corresponding to the mountain range may be a certain specific mixed essential oil formulated after testing and investigation, and the park also corresponds to a certain specific mixed essential oil formulated after testing and investigation; or

[0076] When the target image is an object image, it is determined that a target preparation corresponding to the object category in the target image includes an essential oil liquid as a base of the modulated composition, and it is determined that a target preparation corresponding to each color feature in the target image includes an essential oil liquid as a seasoning for the modulated composition, wherein different object categories correspond to different essential oil liquids, for example, the essential oil liquid corresponding to banana may be banana-flavored essential oil, and the essential oil liquid corresponding to apple includes apple-flavored essential oil.

[0077] In one embodiment, the method for obtaining the feature-preparation correspondence table includes but is not limited to: (a) receiving multiple questionnaires input by users, wherein the questionnaires include user information of multiple survey users and the survey users' selected answers for the correspondence between features and preparations; by counting the selected answers for the correspondence in the questionnaires, the feature-preparation correspondence table is constructed according to the answers whose repetition exceeds a preset threshold (e.g., 50%); (b) searching for open source database information, and setting different authoritative weight coefficients for the open source database to which the database information belongs, counting the correspondence between features and preparations in all database information, and constructing the feature-preparation correspondence table according to the authoritative weight coefficient of each database and the repetition of the correspondence in the database information corresponding to it; (c) in response to the user's login operation on the display, displaying multiple features and multiple preparations to the user, in response to the user's confirmation operation on the correspondence between features and preparations, constructing the feature-preparation correspondence table for this user, and storing the user information of the user in correspondence with the feature-preparation correspondence table, wherein the multiple features and multiple preparations displayed to the user can be selected from the feature-preparation correspondence table in the (a) or (b) method.

[0078] In one embodiment, the characteristic preparation correspondence table is constructed by the above method, which can combine the perceptual conversion relationship of multiple senses of the general public, the research on the perceptual conversion relationship of multiple senses from authoritative database sources, and the user's own perceptual preferences or personal style, thereby being able to convert visual presentation into taste and olfactory perception while improving the accuracy of the results of converting vision into taste and smell.

[0079] Step S24, using the composition preparation device to merge all target preparations corresponding to the at least one feature and the corresponding proportions to obtain a target composition.

[0080] In one embodiment, the composition modulation device also includes a preparation storage container (e.g., a beer pressure tank), each preparation storage container has a corresponding gate valve controller, and the processor of the composition modulation device can control the dose or volume of the target preparation released in the preparation storage container by controlling the time between the opening and closing of the gate valve controller. The composition modulation device also includes a collection container (e.g., a glass) for the target composition, and the dose or volume to be released from the preparation storage container can be determined based on the volume of the collection container and all the target preparations and the corresponding ratio. When all the target preparations corresponding to the at least one feature in the target image are collected into the collection container according to the corresponding ratio, the modulation of the target composition is achieved.

[0081] In one embodiment, the method further includes: using the composition modulation device to generate and save the composition information of the target composition, the composition information of the target composition including: the characteristics of the target image corresponding to the target composition, and the corresponding proportion of each target preparation contained in the target composition.

[0082] In one embodiment, the method further includes: generating label information according to the component information of the target composition; and controlling the printing device of the composition preparation device to print a label corresponding to the label information according to the label information. The label may also include user information of the user, printing time, etc. The method further includes: pasting the label to the surface of the collection container.

[0083] In another embodiment, the composition preparation device can also: respond to an image remotely input by a user in a terminal application as a target image; respond to a first instruction issued by the user in the terminal application to identify at least one feature in the target image; respond to a second instruction issued by the user in the terminal application to determine, based on the correspondence between the feature and the ratio, the ratio corresponding to each feature in the at least one feature and the target preparation corresponding to each feature to obtain the ratio corresponding to each target preparation; respond to a third instruction issued by the user in the terminal application to fuse all target preparations corresponding to the at least one feature and the corresponding ratios to obtain a target composition.

[0084] In another embodiment, the terminal application can be used to respond to the user's first instruction to identify at least one feature in the target image; the terminal application can be used to respond to the user's second instruction to determine the ratio corresponding to each feature of the at least one feature and the target preparation corresponding to each feature based on the correspondence between the feature and the ratio, and obtain the ratio corresponding to each target preparation; the terminal application can be used to respond to the user's third instruction to send the target preparation corresponding to each feature and the ratio corresponding to each target preparation to the composition preparation device; the composition preparation device can be used to receive the target preparation corresponding to each feature and the ratio corresponding to each target preparation, and all target preparations corresponding to the at least one feature and the corresponding ratios can be merged to obtain the target composition.

[0085] Through remote communication between the composition preparation device and the terminal application, it is possible to obtain the target composition required by the user in a variety of application environments, provide users with a better user experience, and improve the efficiency of composition preparation. For example, when the user is not at home, the composition preparation device can be controlled by the terminal application to obtain the desired fragrance, and when the user returns to the residence, the user can enjoy the environment full of fragrance, and the user does not need to return to the residence and waste time waiting for the composition preparation device to prepare the fragrance.

[0086] An embodiment of the present application further provides a computer-readable storage medium, on which a computer program is stored. The computer program includes program instructions. The method implemented when the program instructions are executed can refer to the methods in the above-mentioned embodiments of the present application.

[0087] Wherein, the computer-readable storage medium may be an internal memory of the composition preparation device described in the above embodiment, such as a hard disk or memory of the composition preparation device. The computer-readable storage medium may also be an external storage device of the composition preparation device, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. equipped on the composition preparation device.

[0088] In some embodiments, the computer-readable storage medium may include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function, etc.; the data storage area may store data created according to the use of the composition modulation device, etc.

[0089] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0090] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example 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 performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0091] In the embodiments provided in the present application, it should be understood that the disclosed devices / terminal equipment and methods can be implemented in other ways. For example, the device / terminal equipment embodiments described above are only schematic. For example, the division of the modules or units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0092] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0093] The embodiments described above are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, a person skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

Claims

1. An image-based composition preparation method, applied to a composition preparation device, characterized in that: The method comprises: Get the target image; identifying at least one feature in the target image; According to the correspondence between the features and the ratios, determining the ratio corresponding to each feature of the at least one feature and the target preparation corresponding to each feature, and obtaining the ratio corresponding to each target preparation; The composition preparation device is used to merge all target preparations corresponding to the at least one characteristic and the corresponding proportions to obtain a target composition.

2. The image-based composition preparation method according to claim 1, characterized in that: The acquiring of the target image comprises: When it is detected that the distance between the user and the composition preparation device is less than a preset distance threshold, displaying a login interface on a display of the composition preparation device; In response to the user's login operation on the login interface, at least one user image of the user is photographed by a photographing device; in response to the user's selection operation on any one of the at least one user image, the user image selected by the user is used as the target image; or, In response to a login operation of the user on the login interface, an image input by the user is received as a target image.

3. The image-based composition preparation method according to claim 2, characterized in that: The identifying at least one feature in the target image comprises: The facial expression features of the user in the target image are identified, and a preset number of color features in the target image are identified.

4. The image-based composition preparation method according to claim 3, characterized in that: The target preparation corresponding to the expression feature in the target image includes a base drink serving as a base of the modulated composition, and the target preparation corresponding to each color feature in the target image includes a flavored drink serving as a condiment of the modulated composition.

5. The image-based composition preparation method according to claim 1, characterized in that: The acquiring of the target image further includes receiving the target image input by a user, and before the identifying of at least one feature in the target image, the method further includes: The types of the target image are determined, where the types include famous painting images, scene images, and object images.

6. The image-based composition preparation method according to claim 5, characterized in that: The identifying at least one feature in the target image comprises: When the target image is an image of a famous painting, identifying a preset number of color features in the target image; or When the target image is a scene image, determining a scene category in the scene image and identifying the preset number of color features in the target image; or When the target image is an object image, the object category in the object image is determined and the preset number of color features in the target image is identified.

7. The image-based composition preparation method according to claim 6, characterized in that: A target preparation corresponding to each color feature in the target image includes an essential oil liquid as a seasoning for the modulated composition; a target preparation corresponding to a scene category in the target image includes an essential oil liquid as a base for the modulated composition; and a target preparation corresponding to an object category in the target image includes an essential oil liquid as a base for the modulated composition.

8. The image-based composition preparation method according to claim 1, characterized in that: The method further comprises: The composition preparation device is used to generate and save the composition information of the target composition, and the composition information of the target composition includes: the characteristics of the target image corresponding to the target composition, and the corresponding proportion of each target preparation contained in the target composition.

9. A composition preparation device, characterized in that: The composition preparation device includes a processor, a memory, a camera, a sensor, and a display. The processor is used to implement the image-based composition preparation method as described in any one of claims 1 to 8 when executing the computer program stored in the memory.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the image-based composition preparation method according to any one of claims 1 to 8 is implemented.

Images