Dial plate optimization method and device, electronic equipment and storage medium

Abstract

The embodiment of the invention provides a dial plate optimization method. The method comprises the following steps: acquiring current dressing characteristics of a user; performing retrieval processing in a preset image database based on the current dressing feature to obtain a target picture; decomposing the target picture to obtain at least one piece of dial background recommendation data; and performing editing processing based on the dial background recommendation data and a preset target template to obtain a target dial. According to the method, the target picture related to the current dressing of the user can be accurately determined by performing retrieval processing on the obtained current dressing characteristics in the preset image database, so that the dial background recommendation data related to the current dressing can be obtained after the target picture is decomposed, and the user experience is improved. And furthermore, the target dial plate which is more personalized at the current moment can be edited and obtained based on the dial plate background recommendation data and the preset target template, so that the user experience is improved.

Description

Technical Field

[0001] The present invention relates to the field of smart terminals, and in particular to a dial optimization method, device, electronic equipment and storage medium. Background Art

[0002] In today's society, with the advancement of technology, smart watches have gradually become a necessity in people's daily lives and are almost inseparable. However, the dials of traditional smart watches are often preset by the manufacturer or uploaded by users through pictures. The background picture is only a simple visual element and cannot be integrated into and enhance the user's personalized dressing style, which leads to a decrease in user experience. Therefore, how to provide a dial optimization method that can cleverly integrate the background of the smart watch dial into and enhance the user's personalized dressing style to enhance the user experience has become an urgent problem to be solved. Summary of the invention

[0003] The embodiment of the present invention provides a dial optimization method, which aims to solve the problem that the background picture of the existing dial optimization method is only a simple visual element and cannot be integrated into and enhance the personalized dressing style of the user. By searching and processing the acquired current clothing features in a preset image database, the target image related to the user's current clothing can be accurately determined, so that after decomposing the target image, the dial background recommendation data related to the current clothing can be obtained, and then based on the dial background recommendation data and the preset target template, a more personalized target dial at the current moment can be edited to enhance the user experience.

[0004] In a first aspect, an embodiment of the present invention provides a dial optimization method, the method comprising the following steps:

[0005] Get the user's current clothing characteristics;

[0006] Performing a search process in a preset image database based on the current clothing feature to obtain a target image;

[0007] Decomposing the target image to obtain at least one dial background recommendation data;

[0008] Editing is performed based on the recommended watch face background data and a preset target template to obtain a target watch face.

[0009] Optionally, the preset image database includes a first image database and a second image database, and before acquiring the current clothing features of the user, the method further includes:

[0010] Obtaining the user's photo album images and shopping records;

[0011] Performing face recognition processing based on the album image to obtain a target album image of the user;

[0012] Extracting the target image area of ​​the user from the target album image;

[0013] Based on the target image area, constructing the first image database;

[0014] Among the shopping records, determining shopping records of clothing;

[0015] The second image database is constructed based on the shopping records of the clothing category.

[0016] Optionally, the method is applied to a smart watch, a color sensor is deployed in the smart watch, the current clothing feature includes clothing color, and obtaining the current clothing feature of the user includes:

[0017] The clothing color is acquired through the color sensor.

[0018] Optionally, the decomposing the target image to obtain at least one dial background recommendation data includes:

[0019] Sliding the target image based on a preset sliding window to obtain a plurality of sliding images, wherein the sliding images contain image features;

[0020] Based on the image features, determining a target sliding image from the plurality of sliding images;

[0021] In the target sliding image, at least one recommended data of the dial background is determined.

[0022] Optionally, determining at least one recommended watch face background data in the target sliding image includes:

[0023] Calculate the image similarity between each target sliding image and other target sliding images;

[0024] Performing classification processing on the plurality of target sliding images based on the image similarity to obtain at least one category to be recommended;

[0025] Based on the category to be recommended, at least one dial background recommendation data is determined in the target sliding image.

[0026] Optionally, the editing process based on the recommended watch face background data and a preset target template to obtain a target watch face includes:

[0027] Based on all the recommended watch face background data and the preset target template, obtaining the user's selection instruction, and determining the target watch face background recommended data and the target template;

[0028] Using the target dial background recommendation data as the bottom layer of the dial, and adding the target template on the bottom layer;

[0029] The user's editing instruction on the target template is obtained, and the target watch face is obtained based on the editing instruction.

[0030] Optionally, obtaining the editing instruction of the user in the target template includes:

[0031] Obtaining the surrounding color of the user's current environment through a color sensor;

[0032] Based on the surrounding colors, construct a first color disk;

[0033] Based on the first color palette and a preset second color palette, an editing instruction of the user in the target template is obtained.

[0034] In a second aspect, an embodiment of the present invention further provides a dial optimization device, the dial optimization device comprising:

[0035] The acquisition module is used to obtain the user's current clothing characteristics;

[0036] A retrieval module, used to perform retrieval processing in a preset image database based on the current clothing features to obtain a target image;

[0037] A decomposition module, used for decomposing the target image to obtain at least one dial background recommendation data;

[0038] The editing module is used to perform editing processing based on the recommended watch face background data and a preset target template to obtain a target watch face.

[0039] In a third aspect, an embodiment of the present invention provides an electronic device, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps in the dial optimization method provided in the embodiment of the present invention when executing the computer program.

[0040] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps in the dial optimization method provided in the embodiment of the invention are implemented.

[0041] In an embodiment of the present invention, the current dress features of the user are obtained; based on the current dress features, a search process is performed in a preset image database to obtain a target image; the target image is decomposed to obtain at least one dial background recommendation data; based on the dial background recommendation data and the preset target template, an editing process is performed to obtain a target dial. By performing a search process on the obtained current dress features in a preset image database, the target image related to the user's current dress can be accurately determined, so that after the target image is decomposed, the dial background recommendation data related to the current dress can be obtained, and then based on the dial background recommendation data and the preset target template, a more personalized target dial at the current moment can be edited to improve the user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0043] Figure 1 is a flow chart of a dial optimization method provided by an embodiment of the present invention;

[0044] Figure 2 It is a structural schematic diagram of a fixed template provided by an embodiment of the present invention;

[0045] Figure 3 It is a structural schematic diagram of a custom template provided by an embodiment of the present invention;

[0046] Figure 4 is a schematic diagram of the structure of an editable area provided by an embodiment of the present invention;

[0047] Figure 5 is a structural schematic diagram of a dial provided by an embodiment of the present invention;

[0048] Figure 6 is a structural schematic diagram of a dial optimization device provided in an embodiment of the present invention;

[0049] Figure 7 It is a structural schematic diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0050] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0051] like Figure 1 As shown, Figure 1 is a flow chart of a dial optimization method provided by an embodiment of the present invention, comprising:

[0052] 101. Obtain the user's current clothing features.

[0053] In an embodiment of the present invention, the dial optimization method can be applied to a smart watch. The smart watch can be a portable device equipped with multiple functions, which can be connected to a smart phone or the Internet, and supports functions such as communication, health monitoring, navigation and entertainment. At the same time, it allows users to expand its functions by installing applications to achieve a highly personalized user experience. Alternatively, in order to reduce the computing resource usage of the smart watch, the dial optimization method can also be applied to a smart watch management platform. The smart watch management platform can obtain the current dress features from the smart watch through the data transmission function, and implement the subsequent steps of the dial optimization method according to the current dress features to achieve dial optimization. The smart watch management platform can be constructed by a server or a server cluster. The server or server cluster can be any electronic device with functions such as data analysis, data processing, data transmission, and data storage.

[0054] The above-mentioned current dress features may include dress color and dress material. A color sensor and a material sensor or sensors with other functions may be deployed on the above-mentioned smart watch. The above-mentioned dress color can be collected through the above-mentioned color sensor, and the above-mentioned dress material can be collected through the above-mentioned material sensor. The above-mentioned color sensor can be any sensor that can collect color, for example, an RGB color sensor, a spectrum sensor, and a colorimeter. The above-mentioned material sensor can be any sensor that can detect the material of the target, for example, a microwave sensor, an infrared sensor, a capacitive sensor, etc., wherein, since different materials have different microwave absorption and reflection characteristics according to their density and composition, the microwave sensor can identify different types of materials by emitting microwaves and analyzing their reflected waves. Since different materials have different absorption and reflectivity in the infrared band, the infrared radiation emitted by the object can be detected by an infrared sensor to infer the type of material. Alternatively, since different fabrics and materials have different dielectric constants, the impact of different materials on the power plant can be detected by a capacitive sensor, and the material of the contact surface can be identified by detecting the change in capacitance. The above-mentioned user can be simply understood as the user of the above-mentioned smart watch.

[0055] 102. Based on the current clothing features, a search process is performed in a preset image database to obtain a target image.

[0056] In an embodiment of the present invention, the preset image database may include a first image database and a second image database. The first image database may be constructed from the user's album images, and the second image database may be constructed from the user's shopping records.

[0057] Specifically, the current dress feature can be used as a retrieval condition to perform a retrieval process in the above-mentioned first image database and the second image database, thereby obtaining the target image. Since the first image database is constructed from the user's album images, and the second image database is obtained from the user's shopping records, whether the target image is successfully retrieved from the first image database or the second image database, the retrieved target images are all the clothes worn by the user at a historical moment or the clothes purchased at a historical moment. Therefore, the current dress feature is used as a retrieval condition, and a retrieval process is performed in the preset image database. The target images obtained are usually the clothes worn by the user at the current moment. Its accuracy depends on whether the images in the preset image database are accurate. If there are more missing images, the accuracy will be relatively reduced. If there are fewer or no missing images, the accuracy will be relatively improved.

[0058] More specifically, the above retrieval process may be a serial search in the first image database and the second image database. When the target image is not found in the first image database, the second image database is searched again, or when the target image is not found in the second image database, the first image database is searched again. Alternatively, a preset number (e.g., 3) is searched in the first image database, and then a preset number (e.g., 3) is searched in the second image database. Alternatively, the first image database and the second image database may be searched in parallel, using the current clothing features as search conditions, and performing search processing in the first image database and the second image database at the same time. When the target image is retrieved in any one image database, the other image database may also stop searching.

[0059] 103. Decompose the target image to obtain at least one dial background recommendation data.

[0060] In an embodiment of the present invention, a sliding window of a preset size can be used to slide in the target image to obtain multiple sliding images, and a target sliding image can be determined from the multiple sliding images based on the image features in each sliding image, and the multiple target sliding images can be classified to obtain multiple categories to be recommended, and one target sliding image can be selected from the multiple target sliding images corresponding to each category to be recommended as dial background recommendation data. The above selection can be random selection, or the average similarity between each target sliding image and other target sliding images can be calculated based on the similarity between each target sliding image and other target sliding images, and the sliding image with the highest average similarity can be used as the representative image of the category to be recommended, and the above representative image can be used as dial background recommendation data.

[0061] In a possible embodiment, a feature extractor can be used to extract image features of each coordinate in the target image, and the same or similar features can be used as a category. In each category, a feature can be selected as a representative feature, and a representative area of ​​the category can be divided in the target image according to the coordinates of the representative feature. The image of the representative area can be used as the dial background recommendation data corresponding to the category, thereby obtaining the dial background recommendation data corresponding to each category.

[0062] 104. Edit and process the recommended watch face background data and the preset target template to obtain a target watch face.

[0063] In an embodiment of the present invention, when there is only one recommended background data for the watch face, the recommended background data for the watch face can be used as the bottom layer of the watch face, and the above-mentioned target template can be added to the upper layer of the bottom layer so that the user can edit the above-mentioned target template and obtain the above-mentioned target watch face after editing is completed.

[0064] When there are multiple recommended watch face background data, multiple recommended watch face background data can be provided to the user for selection. If the user selects the target recommended watch face background data within the preset time, the target recommended watch face background data will be used as the bottom layer of the watch face, and the above target template will be added to the upper layer of the bottom layer, so that the user can edit the above target template, and the above target watch face will be obtained after the editing is completed. Correspondingly, if the user does not select the above target recommended watch face background data within the preset time, the target recommended watch face background data can be randomly selected from multiple recommended watch face background data.

[0065] It should be noted that the above-mentioned preset target template can be selected from a fixed template, or can also be created by the user through the drawing board. If it is a fixed template, the target template can be selected from the above-mentioned fixed template and added to the upper layer of the bottom layer. If it is a custom template, the preset target template can be directly used as the target template and the target template can be added to the upper layer of the bottom layer.

[0066] In an embodiment of the present invention, the current dress features of the user are obtained; based on the current dress features, a search process is performed in a preset image database to obtain a target image; the target image is decomposed to obtain at least one dial background recommendation data; based on the dial background recommendation data and the preset target template, an editing process is performed to obtain a target dial. By performing a search process on the obtained current dress features in a preset image database, the target image related to the user's current dress can be accurately determined, so that after the target image is decomposed, the dial background recommendation data related to the current dress can be obtained, and then based on the dial background recommendation data and the preset target template, a more personalized target dial at the current moment can be edited to improve the user experience.

[0067] It is understandable that in the specific implementation of the present application, related data such as album images, shopping records, clothing features and peripheral colors are involved. When the embodiments in the present application are applied to specific products or technologies, user permission or consent is required, and the collection, use and processing of relevant data and the use of user interaction interfaces need to comply with relevant laws, regulations and standards of relevant countries and regions.

[0068] It should be noted that the dial optimization method provided in the embodiment of the present invention can be applied to computers, servers and other devices that can perform dial optimization.

[0069] Optionally, before the step of obtaining the user's current clothing features, the user's album images and shopping records can also be obtained; face recognition processing is performed based on the album images to obtain the user's target album images; in the target album images, the user's target image area is extracted; based on the target image area, a first image database is constructed; in the shopping records, shopping records of clothing categories are determined; based on the shopping records of clothing categories, a second image database is constructed.

[0070] In an embodiment of the present invention, the preset image database includes a first image database and a second image database. The target album image can be understood as an image containing the user, while the image not containing the user can be a non-target album image. Usually, the user's album image may include images related to scenery taken by the user, or images related to animals or other people. The user may not exist in the above images, so it is necessary to perform face recognition processing based on the album images to obtain the target album image. The face recognition processing can be constructed by any algorithm capable of face recognition to obtain a face recognition model, and each target album image is input into the face recognition model for face recognition processing, so that the album image containing the user is used as the target album image. The face recognition model can be deployed on the smart watch, or it can also be deployed on the cloud platform, and the smart watch sends a corresponding request to the cloud platform to implement the face recognition processing. The above-mentioned face recognition algorithms can be lightweight face recognition algorithms such as MobileFaceNets, FaceNet, BlazeFace, LibraFace, NanoFace, etc., whose model sizes are correspondingly small, and the computational complexity is also reduced, and they can be well adapted to mobile devices such as smart watches.

[0071] After determining the target album image, the user's human figure outline in the target image can be analyzed to obtain a human figure image, and the human figure image is stored in a preset empty database. After all human figures are stored in the preset empty database, the first image database is obtained.

[0072] Generally, shopping records often contain thumbnails, details, enlarged images, material descriptions, men's / women's clothing, suitable age groups, and names of items. Based on the above names, shopping records of clothing can be screened out from the shopping records, so that the thumbnails of items in the shopping records of clothing are added to the preset empty database. After the thumbnails of items in all shopping records of clothing are added to the preset empty database, the second image database is obtained.

[0073] Specifically, the shopping records may include not only the goods purchased by the user for himself, but also the goods purchased by the user for others due to work or family factors. Therefore, according to the age and gender of the user, clothing categories related to the age and gender of the user can be screened out from all clothing shopping records as target shopping records, and the thumbnails of the items in the target shopping records are added to the preset empty database to obtain the second image database.

[0074] It should be noted that the above-mentioned screening can be specifically based on the clothing material, material description, details, enlarged pictures, men's / women's clothing and suitable age data recorded in the shopping records of the above-mentioned clothing categories, and the above-mentioned target shopping records can be screened out from all the shopping records of the above-mentioned clothing categories.

[0075] Optionally, in the step of acquiring the current clothing features of the user, the clothing color may also be acquired through a color sensor.

[0076] In an embodiment of the present invention, the dial optimization method is applied to a smart watch, in which a color sensor is deployed, and the current clothing feature includes the clothing color. During the use of the smart watch, if the dial is to be optimized, the color sensor can be used to obtain the clothing color. After obtaining the clothing color, the subsequent steps of the dial optimization method can be implemented according to the current clothing feature to achieve dial optimization.

[0077] In a possible embodiment, a material sensor may be deployed inside the smart watch, and the current dressing feature may further include the dressing material. During the use of the smart watch, if one wants to optimize the dial, the dressing sensor may be used to obtain the dressing material. After obtaining the dressing material, the dressing material may be matched with the material information recorded in the target shopping record in the second image database to obtain the target shopping record matching the dressing material, and in the target shopping record matching the dressing material, a corresponding thumbnail or enlarged picture may be determined as the target picture.

[0078] In another possible embodiment, when the color sensor and the material sensor are simultaneously deployed inside the smart watch, the color of the clothing can be used as a retrieval target in the first image database and the second image database to perform a first retrieval process to obtain at least one first retrieval picture, and the material of the clothing can be used as a retrieval target in the second image database to perform a second retrieval process to obtain at least one second retrieval picture, and the image similarity between each first retrieval picture and each second retrieval picture is calculated. Any one of the pictures with the highest similarity (i.e., the first retrieval picture and the second retrieval picture corresponding to the highest similarity) is used as the target picture.

[0079] Optionally, in the step of decomposing the target image to obtain at least one dial background recommendation data, it is also possible to slide in the target image based on a preset sliding window to obtain multiple sliding images, and the sliding images contain image features; based on the image features, determine the target sliding image from the multiple sliding images; and determine at least one dial background recommendation data from the target sliding image.

[0080] In an embodiment of the present invention, the size of the preset sliding window can be set according to the size of the target image, that is, the size of the preset sliding window can be determined according to the size of the target image at a corresponding ratio (e.g., 10% or 5%). The step length of the sliding can be the response size of the sliding window. Assuming that the length of the sliding window is 1mm, the step length of the horizontal sliding is also 1mm. Assuming that the width of the sliding window is 2mm, the step length of the vertical sliding is also 2mm. The sliding window can be one or more. If there are more than one sliding window, the multiple sliding windows can slide side by side, such as two windows vertically, to increase the sliding efficiency.

[0081] Specifically, a sliding window of size X may be used to slide in the target image to obtain multiple sliding images, and a sliding image with a large change in image features (comparing the image features of two adjacent sliding images, if the change is large, it means that new image features have entered) or a sliding image with more image features is determined from the multiple sliding images, and the images are saved and captured as the target sliding images.

[0082] After obtaining the above-mentioned target sliding images, if the number of the above-mentioned target sliding images is small (for example, less than a preset number threshold), each target sliding image can be used as the above-mentioned dial background recommendation data. If the number of the above-mentioned target sliding images is large (for example, more than or equal to the preset number threshold), the above-mentioned target sliding images can be deduplicated to avoid the appearance of repeated dial background recommendation data, so as to improve the optimization accuracy of the dial optimization. The above-mentioned deduplication processing can be implemented based on the similarity between each target sliding image and other target sliding images.

[0083] Optionally, in the step of determining at least one dial background recommendation data in the target sliding image, the image similarity between each target sliding image and other target sliding images can also be calculated; based on the image similarity, multiple target sliding images are classified to obtain at least one category to be recommended; based on the category to be recommended, at least one dial background recommendation data is determined in the target sliding image.

[0084] In the embodiment of the present invention, the above image similarity can be calculated by any method capable of calculating image similarity, such as mean square error (MSE), structural similarity index (SSIM), feature matching, etc. After calculating the image similarity between each target sliding image and other target sliding images, if the image similarity between the target sliding image A1 and the target sliding image A2 is greater than a preset similarity threshold, it is considered that A1 and A2 are similar or identical, so A1 and A2 can be determined as a category B1 to be recommended. Correspondingly, if the image similarity between A1 or A2 and other target sliding images is greater than the preset similarity threshold, the other target sliding images can also be added to the B1 category.

[0085] After the categories to be recommended are determined, any target sliding image can be extracted from each category to be recommended as a representative image of the category to be recommended, thereby determining the representative image of each category to be recommended as a dial background recommendation data.

[0086] Optionally, in the step of obtaining the target dial by editing based on the recommended dial background data and the preset target template, the user's selection instructions can also be obtained based on all the recommended dial background data and the preset target template to determine the target dial background recommended data and the target template; the target dial background recommended data is used as the bottom layer of the dial, and the target template is added to the bottom layer; the user's editing instructions in the target template are obtained, and the target dial is obtained based on the editing instructions.

[0087] In an embodiment of the present invention, all dial background recommendation data and preset target templates can be provided to the user, and can be provided to the user in a list or in a rotating display, so that the user can select the target dial background recommendation data from all dial background recommendation data and preset target templates (during the selection process, the above-mentioned smart watch can receive the above-mentioned selection instruction, and the above-mentioned selection instruction can correspond to a dial background recommendation data and a preset target template. After receiving, the corresponding above-mentioned dial background recommendation data can be used as the above-mentioned target dial background recommendation data, and the corresponding preset target template can be used as the above-mentioned target template). The target dial background recommendation data is used as the bottom layer of the dial, and the above-mentioned target template is added to the bottom layer. The user can perform editing processing on the above-mentioned target template (including but not limited to editing operations of parameters such as color, transparency, brightness, saturation and color temperature, and all editing operations are integrated together, which is the above-mentioned editing instruction). After editing is completed, the above-mentioned target dial can be obtained.

[0088] Specifically, the preset target template can be a fixed template or a custom template. The user selects a template from the fixed templates as the target template, or the user can customize the target template through tools such as drawing boards. The fixed template means that multiple style dials with templates are provided, and blanks are reserved for user creation. Specifically, the fixed template can be selected by Figure 2 The structural diagram of a fixed template is shown as an example. Figure 2 There are 8 fixed templates included. Users can select any one of the 8 fixed templates as the above target template and create in the reserved blank space.

[0089] The custom template is an interface that can provide users with a way to create their own works, provide brushes for free creation, and then perform subsequent color filling. Specifically, the custom template can be created by Figure 3 The structural diagram of a custom template shown further illustrates that Figure 3 There are 3 kinds of custom templates included. Users can create any number of custom templates until they create a satisfactory custom template and use it as the target template mentioned above.

[0090] The color, transparency (whether the underlying background image can be seen), brightness, saturation, color temperature and other parameters of any submodule in the target template can be adjusted. A small window for adjusting settings can be provided on the smart watch. You can slide left and right to select and adjust. Figure 5 The structural schematic diagram of a dial is shown, and the effect that can be presented after obtaining the recommended dial background data + target template and adjusting the sub-module color and transparency.

[0091] More specifically, the above editing can be done in a local editing or in a hierarchical editing manner.

[0092] The above local editing can be done by Figure 4 The schematic diagram of the structure of an editable area shown further illustrates that: Figure 4 In the example, the target template can be divided into multiple editable areas, such as Optional 1 / 2 / 3 / 4 / 5. When the user selects "Optional 1" in a way, such as long pressing, or explodes the editable area after long pressing, and then selects one of them, the content of "Optional 1" becomes larger and is displayed at the forefront of the dial. Among them, the four numbers can be selected separately (each number to be selected will jump during the process to prompt the user to select a color for the number. After it is selected and confirmed, it will stop jumping and the next number will jump immediately), or all of them can be selected as one color (the four numbers will jump uniformly); further, after the yellow flower in Optional 2 is obtained as the background recommendation, the yellow flower can also be used as the user-editable part. For example, after the user obtains the shape of the flower and wants to change the color of the flower, it can be edited again according to the user's needs).

[0093] The above-mentioned hierarchical editing can also be done by Figure 4 The schematic diagram of the structure of an editable area shown further illustrates that: Figure 4 In the , the dial design can be divided into levels, from the lowest end to the front end, it can be Optional 5—>Optional 2—>Optional 3—>Optional 4—>Optional 1 (where Optional 1, Optional 3 and Optional 4 can be in the same level). The level can be determined according to the number of times the screen is clicked. For example, I click once to select Optional 1 at the front end; click three times to select Optional 3; after the level is selected, the colorable content in the level jumps and can be enlarged (to facilitate users to fill in colors) until the color is selected and stops jumping.

[0094] In addition, it can also include the operation process of gradient color. Figure 4 Optional 2 in the figure is used as a schematic illustration. When the color data of the color sensor is obtained and it is determined that Optional 2 is yellow, the Optional 2 part can be expanded and divided into multiple editable areas. For example, each petal can be used as an editable unit, or the petals around a circle can be used as an editable unit. The unit can be used for color adjustment of the same color system, and a color adjustment operation dial for darkening (+) or lightening (-) the yellow color is provided. Finally, the color of the editable unit is determined by the user.

[0095] In addition to the above methods, jump color recommendations can also be made based on the above gradient color operation process. Figure 2 The structural diagram of a fixed template is shown in FIG. Figure 2The fixed template in the first row of the second row is used as an example template for illustrative explanation. Assume that after the above-mentioned gradient color operation process, the three ellipses in the example template present a gradient yellow. At this time, a jump color part and a jump color can be recommended for the user to choose. Of course, if the user is not satisfied with the recommended jump color part and jump color, the user can also choose the jump color part and jump color by himself.

[0096] Optionally, in the step of obtaining the user's editing instructions in the target template, the surrounding colors of the user's current environment can also be obtained through a color sensor; based on the surrounding colors, a first color palette is constructed; based on the first color palette and a preset second color palette, the user's editing instructions in the target template are obtained.

[0097] In an embodiment of the present invention, under normal circumstances, users will not stay in an environment they dislike for a long time, or if they need to stay in a certain environment for a long time, they will usually arrange the environment to be a more comfortable environment for themselves. For example, in dormitories, workstations, desks, homes, etc., where it is inevitable to stay for a long time, the above environment is often arranged to be a more comfortable environment for themselves. Therefore. When the user's environment is a common environment, the above smart watch can automatically obtain the surrounding colors of the user's current environment. And construct a first color palette based on the surrounding colors, and in the process of user creation and color selection, give priority to the colors in the above first color palette. If the user does not select the desired color in the first color palette, the second color palette can be provided to the user so that the user can edit on the target template.

[0098] Alternatively, when the user's environment is not a common environment, it does not fall under the above-mentioned normal situation, and it is impossible to determine whether the color of the flowers in a new environment, such as a new park environment, is what the user likes. Therefore, it is impossible to automatically obtain the above-mentioned surrounding colors through the above-mentioned smart watch. At this time, the user can directly obtain the above-mentioned surrounding colors through the color sensor of the above-mentioned smart watch.

[0099] Alternatively, when the environment is not taken into consideration, the user can use the color sensor deployed on the smart watch to obtain the surrounding color according to actual needs.

[0100] like Figure 6 As shown, an embodiment of the present invention further provides a dial optimization device, comprising:

[0101] The acquisition module 601 is used to acquire the current clothing characteristics of the user;

[0102] A retrieval module 602 is used to perform a retrieval process in a preset image database based on the current clothing feature to obtain a target image;

[0103] A decomposition module 603 is used to decompose the target image to obtain at least one dial background recommendation data;

[0104] The editing module 604 is used to perform editing processing based on the recommended watch face background data and a preset target template to obtain a target watch face.

[0105] Optionally, the preset image database includes a first image database and a second image database, and the dial optimization device further includes:

[0106] A second acquisition module, used to acquire the album images and shopping records of the user;

[0107] A first recognition module, configured to perform face recognition processing based on the album image to obtain a target album image of the user;

[0108] A first extraction module, used to extract the target image area of ​​the user from the target album image;

[0109] A first construction module, used to construct the first image database based on the target image area;

[0110] A first determining module, configured to determine a shopping record of clothing in the shopping record;

[0111] The second construction module is used to construct the second image database based on the shopping records of the clothing category.

[0112] Optionally, the dial optimization method is applied to a smart watch, a color sensor is deployed in the smart watch, the current clothing feature includes clothing color, and the acquisition module 601 includes:

[0113] The first acquisition submodule is used to acquire the clothing color through the color sensor.

[0114] Optionally, the decomposition module 603 includes:

[0115] A first sliding submodule, configured to slide in the target image based on a preset sliding window to obtain a plurality of sliding images, wherein the sliding images contain image features;

[0116] A first determination submodule, based on the image features, determines a target sliding image from the plurality of sliding images;

[0117] The second determination submodule is used to determine at least one recommended dial background data in the target sliding image.

[0118] Optionally, the first determining submodule includes:

[0119] A first calculation unit, used for calculating the image similarity between each target sliding image and other target sliding images;

[0120] A first classification unit, configured to perform classification processing on the plurality of target sliding images based on the image similarity to obtain at least one category to be recommended;

[0121] The first determining unit is used to determine at least one dial background recommendation data in the target sliding image based on the category to be recommended.

[0122] Optionally, the editing module 604 includes:

[0123] A first selection submodule is used to obtain the user's selection instruction based on all the dial background recommendation data and the preset target template, and determine the target dial background recommendation data and the target template;

[0124] A first adding submodule is used to use the target dial background recommendation data as the bottom layer of the dial, and add the target template on the bottom layer;

[0125] The second acquisition submodule is used to acquire the user's editing instructions on the target template, and obtain the target watch face based on the editing instructions.

[0126] Optionally, the second acquisition submodule includes:

[0127] A first acquisition unit, configured to acquire the surrounding color of the user's current environment through a color sensor;

[0128] A first construction unit, configured to construct a first color disk based on the peripheral colors;

[0129] The first editing unit is used to obtain the editing instruction of the user in the target template based on the first color palette and a preset second color palette.

[0130] like Figure 7 As shown, an embodiment of the present invention further provides an electronic device, characterized in that it includes a processor, and the processor can execute any one of the above-mentioned dial optimization methods.

[0131] Specifically, it includes a processor 701 and a memory 702, and a computer program for executing the dial optimization method stored in the memory 702 and capable of running on the processor 701, wherein:

[0132] The processor 701 runs the computer program of the dial optimization method stored in the memory 702 to perform the following steps:

[0133] Get the user's current clothing characteristics;

[0134] Performing a search process in a preset image database based on the current clothing feature to obtain a target image;

[0135] Decomposing the target image to obtain at least one dial background recommendation data;

[0136] Editing is performed based on the recommended watch face background data and a preset target template to obtain a target watch face.

[0137] Optionally, the preset image database executed by the processor 701 includes a first image database and a second image database, and before acquiring the current clothing feature of the user, the method further includes:

[0138] Obtaining the user's photo album images and shopping records;

[0139] Performing face recognition processing based on the album image to obtain a target album image of the user;

[0140] Extracting the target image area of ​​the user from the target album image;

[0141] Based on the target image area, constructing the first image database;

[0142] Among the shopping records, determining shopping records of clothing;

[0143] The second image database is constructed based on the shopping records of the clothing category.

[0144] Optionally, the method is applied to a smart watch, a color sensor is deployed in the smart watch, the current clothing feature includes clothing color, and the processor 701 performs the step of obtaining the current clothing feature of the user, including:

[0145] The clothing color is acquired through the color sensor.

[0146] Optionally, the processor 701 performs decomposition processing on the target image to obtain at least one dial background recommendation data, including:

[0147] Sliding the target image based on a preset sliding window to obtain a plurality of sliding images, wherein the sliding images contain image features;

[0148] Based on the image features, determining a target sliding image from the plurality of sliding images;

[0149] In the target sliding image, at least one recommended data of the dial background is determined.

[0150] Optionally, the determining, in the target sliding image, of at least one recommended watch face background data performed by the processor 701 includes:

[0151] Calculate the image similarity between each target sliding image and other target sliding images;

[0152] Performing classification processing on the plurality of target sliding images based on the image similarity to obtain at least one category to be recommended;

[0153] Based on the category to be recommended, at least one dial background recommendation data is determined in the target sliding image.

[0154] Optionally, the processor 701 performs editing based on the watch face background recommendation data and a preset target template to obtain a target watch face, including:

[0155] Based on all the recommended watch face background data and the preset target template, obtaining the user's selection instruction, and determining the target watch face background recommended data and the target template;

[0156] Using the target dial background recommendation data as the bottom layer of the dial, and adding the target template on the bottom layer;

[0157] The user's editing instruction on the target template is obtained, and the target watch face is obtained based on the editing instruction.

[0158] Optionally, the obtaining of the editing instruction of the user in the target template executed by the processor 701 includes:

[0159] Obtaining the surrounding color of the user's current environment through a color sensor;

[0160] Based on the surrounding colors, construct a first color disk;

[0161] Based on the first color palette and a preset second color palette, an editing instruction of the user in the target template is obtained.

[0162] An embodiment of the present invention also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the various processes of the dial optimization method or the application-end dial optimization method provided in the embodiment of the present invention are implemented, and the same technical effect can be achieved. To avoid repetition, it will not be repeated here.

[0163] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program, and the above-mentioned computer program can be stored in a computer-readable storage medium, and when the program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, the above-mentioned computer-readable storage medium can be a disk, an optical disk, a read-only memory (ROM) or a random access memory (RAM), etc.

[0164] The above disclosure is only the preferred embodiment of the present invention, which certainly cannot be used to limit the scope of the present invention. Therefore, equivalent changes made according to the claims of the present invention are still within the scope of the present invention.

Claims

1. A dial optimization method, characterized in that: The method comprises the following steps: Get the user's current clothing features; Performing a search process in a preset image database based on the current clothing feature to obtain a target image; Decomposing the target image to obtain at least one dial background recommendation data; Editing is performed based on the recommended watch face background data and a preset target template to obtain a target watch face.

2. The dial optimization method according to claim 1, characterized in that: The preset image database includes a first image database and a second image database. Before acquiring the current clothing features of the user, the method further includes: Obtaining the user's photo album images and shopping records; Performing face recognition processing based on the album image to obtain a target album image of the user; Extracting the target image area of ​​the user from the target album image; Based on the target image area, constructing the first image database; Among the shopping records, determining shopping records of clothing; The second image database is constructed based on the shopping records of the clothing category.

3. The dial optimization method according to claim 1 or 2, characterized in that: The method is applied to a smart watch, wherein a color sensor is deployed in the smart watch, the current clothing feature includes clothing color, and obtaining the current clothing feature of the user includes: The clothing color is acquired through the color sensor.

4. The dial optimization method according to claim 1, characterized in that: The step of decomposing the target image to obtain at least one dial background recommendation data includes: Sliding the target image based on a preset sliding window to obtain a plurality of sliding images, wherein the sliding images contain image features; Based on the image features, determining a target sliding image from the plurality of sliding images; In the target sliding image, at least one recommended data of the dial background is determined.

5. The dial optimization method according to claim 4, characterized in that: Determining at least one recommended watch face background data in the target sliding image includes: Calculate the image similarity between each target sliding image and other target sliding images; Performing classification processing on the plurality of target sliding images based on the image similarity to obtain at least one category to be recommended; Based on the category to be recommended, at least one dial background recommendation data is determined in the target sliding image.

6. The dial optimization method according to claim 1, characterized in that: The editing process based on the recommended watch face background data and a preset target template to obtain a target watch face includes: Based on all the recommended watch face background data and the preset target template, obtaining the user's selection instruction, and determining the target watch face background recommended data and the target template; Using the target dial background recommendation data as the bottom layer of the dial, and adding the target template on the bottom layer; The user's editing instruction on the target template is obtained, and the target watch face is obtained based on the editing instruction.

7. The dial optimization method according to claim 6, characterized in that: The obtaining the editing instruction of the user in the target template includes: Obtaining the surrounding color of the user's current environment through a color sensor; Based on the surrounding colors, construct a first color disk; Based on the first color palette and a preset second color palette, an editing instruction of the user in the target template is obtained.

8. A dial optimization device, characterized in that: The dial optimization device comprises: The acquisition module is used to obtain the user's current clothing characteristics; A retrieval module, used to perform retrieval processing in a preset image database based on the current clothing features to obtain a target image; A decomposition module, used for decomposing the target image to obtain at least one dial background recommendation data; The editing module is used to perform editing processing based on the recommended watch face background data and a preset target template to obtain a target watch face.

9. An electronic device, characterized in that: include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps in the dial optimization method as described in any one of claims 1 to 7 when executing the computer program.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps in the dial optimization method as described in any one of claims 1 to 7.

Images