Push Method, Device, Electronic Device and Medium

Abstract

The present application discloses a pushing method, device, electronic device and medium, belonging to the field of information processing. The method includes: receiving a first input for a first image; in response to the first input, determining a target image element corresponding to a target object in the first image; and pushing target information to the user according to the target image element.

Description

Technical Field

[0001] This application belongs to the field of information processing, and particularly relates to a pushing method, device, electronic device, and medium. Background Art

[0002] With the rapid development of Internet technology, people's daily lives are increasingly closely connected to the Internet. At the same time, a vast amount of user and item data is continuously generated on the Internet every day, which makes it difficult, or even impossible, for Internet users to quickly find the information they need or are interested in.

[0003] Currently, when recommending information to users, personalized recommendations cannot be made according to users' needs. Summary of the Invention

[0004] The purpose of the embodiments of this application is to provide a pushing method, device, electronic device, and medium, which can solve the problem in the prior art that information cannot be pushed to users in a personalized manner.

[0005] In a first aspect, the embodiments of this application provide a pushing method, which includes:

[0006] Receiving a first input to a first image;

[0007] In response to the first input, determining a target image element corresponding to a target object in the first image;

[0008] According to the target image element,

[0009] Pushing target information to the user.

[0010] In a second aspect, the embodiments of this application provide a pushing device, which includes:

[0011] A first receiving module, configured to receive a first input to a first image;

[0012] A first determining module, configured to, in response to the first input, determine a target image element corresponding to a target object in the first image;

[0013] A pushing module, configured to push target information to the user according to the target image element.

[0014] In a third aspect, the embodiments of this application provide an electronic device, which includes a processor and a memory. The memory stores a program or instruction that can run on the processor, and when the program or instruction is executed by the processor, the steps of the method described in the first aspect are implemented.

[0015] Fourthly, an embodiment of the present application provides a readable storage medium, on which a program or instruction is stored, and when the program or instruction is executed by a processor, the steps of the method described in the first aspect are implemented.

[0016] Fifthly, an embodiment of the present application provides a chip, which includes a processor and a communication interface. The communication interface is coupled to the processor, and the processor is configured to run a program or instruction to implement the method described in the first aspect.

[0017] Sixthly, an embodiment of the present application provides a computer program product, which is stored in a storage medium and is executed by at least one processor to implement the method described in the first aspect.

[0018] In the embodiment of the present application, by responding to a first input to a first image, a target image element corresponding to a target object in the first image can be extracted from the first image, and then according to the target image element, target information corresponding to the target image element can be pushed to the user. In this way, the finally recommended target information is personalized according to the first image input by the user. Thus, there is no need for the user to select the required information one by one, thereby saving the energy and time consumed by the user in information selection and improving the user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 is one of the flowcharts of the pushing method shown according to an exemplary embodiment;

[0020] Figure 2 is a schematic diagram of a first image shown according to an exemplary embodiment;

[0021] Figure 3 is a schematic diagram of dividing a first image shown according to an exemplary embodiment;

[0022] Figure 4 is a schematic diagram of constructing a heat zone of an image partition shown according to an exemplary embodiment;

[0023] Figure 5 is the second flowchart of the pushing method shown according to an exemplary embodiment;

[0024] Figure 6 is a schematic structural diagram of a pushing device shown according to an exemplary embodiment;

[0025] Figure 7 is a schematic structural diagram of an electronic device shown according to an exemplary embodiment;

[0026] Figure 8 is a schematic hardware structure diagram of an electronic device shown in the embodiment of the present application. Specific Embodiments

[0027] The following will clearly describe the technical solutions in the embodiments of the present application with reference to the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, rather than all of them. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art belong to the scope of protection of the present application.

[0028] The terms "first", "second", etc. in the specification and claims of the present application are used to distinguish similar objects, rather than to describe a specific order or sequence. It should be understood that such data can be interchanged under appropriate circumstances so that the embodiments of the present application can be implemented in an order other than those illustrated or described herein, and the objects distinguished by "first", "second", etc. are generally of the same category, and the number of objects is not limited. For example, the first object can be one or more. In addition, "and / or" in the specification and claims means at least one of the connected objects, and the character " / " generally means that the related objects before and after are in an "or" relationship.

[0029] The embodiments of the present application provide a push method, device, electronic device and medium. By responding to a first input to a first image, a target image element corresponding to a target object in the first image can be extracted from the first image, and then, based on the target image element, target information corresponding to the target image element can be pushed to the user. In this way, the target information finally recommended to the user is personalized according to the first image input by the user. Thus, there is no need for the user to select the required target information one by one, thereby saving the energy and time consumed by the user in selecting the target information and improving the user experience.

[0030] The following will, with reference to the accompanying drawings, detail the push method provided by the embodiments of the present application through specific embodiments and their application scenarios.

[0031] Figure 1 is a schematic flowchart of a push method provided by an embodiment of the present application. The execution subject of the push method can be an electronic device. It should be noted that the above execution subject does not limit the embodiments of the present application.

[0032] In the embodiments of the present application, the electronic device can be a smart terminal or a smart wearable electronic device. For the smart terminal, it can be, but is not limited to, a personal computer (PC), a smart phone, a tablet computer or a personal digital assistant (PDA), etc.

[0033] Such as Figure 1As shown, the push method provided by the embodiments of the present application may include steps 110 - 150.

[0034] Step 110, receive a first input for a first image.

[0035] Among them, the first image can be any image, specifically, it can be an image containing the user's own outfit, as Figure 2 shown.

[0036] In some embodiments of the present application, the first image can be an image uploaded by the user or an image stored in the electronic device.

[0037] The first input can be the user's input for the first image. Specifically, the first input can be an operation of selecting the first image by the user's click input, double - click input, swipe input, fill - in input, voice input, and gesture input on the electronic device, or a combined operation of at least two of the above inputs.

[0038] Step 120, in response to the first input, determine the target image element corresponding to the target object in the first image.

[0039] Among them, the target object can be an object in the first image, for example, it can be a human object or a background object, etc.

[0040] In one example, continuing to refer to Figure 2 , the target object can be Figure 2 the human object 21 in. It can also be the building that the human object in Figure 2 leans against (not shown in Figure 2 ).

[0041] The target image element can be an image element extracted from the target object of the first image. It can also be an image element obtained after presetting and arranging the image elements extracted from the target object of the first image.

[0042] In some embodiments of the present application, determining the target image element corresponding to the target object in the first image can be detecting the target image element corresponding to the target object based on an image detection algorithm, or detecting the target image element corresponding to the target object based on a pre - set detection model. There is no limitation here, and any method that can determine the target image element corresponding to the target object in the first image is within the protection scope of the embodiments of the present application.

[0043] In some embodiments of the present application, in order to improve the determination efficiency of the target image element corresponding to the target object in the first image, the determining the target image element corresponding to the target object in the first image may specifically include:

[0044] Divide the first image according to at least one key feature of the target object to obtain at least two image partitions;

[0045] Identify the image elements in the target image partition to obtain a plurality of image elements;

[0046] Fuse a plurality of image elements to obtain a target image element.

[0047] Among them, the key feature may be the main feature of the target object.

[0048] In one example, continue to refer to Figure 2 , when the target object is Figure 2 the human object 21 in, the key feature here may be the key parts of the human object 21, such as the shoulders, waist and ankles, etc.

[0049] In another example, continue to refer to Figure 2 , when the target object is Figure 2 the background object against which the human object in leans, the key feature here may be the key parts of the background object.

[0050] In some embodiments of the present application, it may be to extract at least one key feature of the target object in the first image based on a feature extraction algorithm (such as a convolutional neural network), and then divide the first image according to at least one key feature of the target object to obtain at least two image partitions.

[0051] In one example, continue to refer to Figure 2 , taking the target object as Figure 2 the human object 21 in, and the key features being the shoulders, waist and ankles of the human object 21 as an example, then according to the shoulders, the area from the head to the shoulders of the human object in the first image can be determined as the first image partition 31; based on the shoulders and waist, the area from the shoulders to the waist of the human object in the first image can be determined as the second image partition 32; based on the waist and ankles, the area from the waist to the ankles of the human object in the first image can be determined as the third image partition 33; based on the ankles, the area from the ankles to the toes of the human object in the first image can be determined as the fourth image partition 33, to obtain Figure 3 .

[0052] It should be noted that in the above example, the human object is divided into four image partitions according to 3 key features of the human object. In actual applications, the number of key features is not limited, that is, how many image partitions the human object is divided into can be set by the user according to needs, and there is no limit here. Correspondingly, when the target object is a background object, the number of key features is not limited either, that is, how many image partitions the background object is divided into can also be set by the user according to needs, and there is no limit here.

[0053] In some embodiments of the present application, the image elements in the target image partition can be recognized to obtain a plurality of image elements. Then, the respective image elements are fused to obtain the target image element. Specifically, how to recognize the image elements in the target image partition to obtain a plurality of image elements, and then fuse the respective image elements to obtain the target image element will be introduced in detail later.

[0054] The target image partition here can be at least one of at least two image partitions.

[0055] In some embodiments of the present application, specifically, a preset recognition algorithm can be used to recognize the image elements in the target image partition to obtain a plurality of image elements.

[0056] In the embodiments of the present application, by dividing the first image according to at least one key feature of the target object, at least two image partitions can be obtained. Then, the image elements in each image partition are recognized to obtain a plurality of image elements, rather than recognizing the entire first image. In this way, the computing power of the server is saved, the image elements of the first image can be quickly extracted, the acquisition efficiency of the image elements is improved, and further the determination efficiency of the target image element is improved.

[0057] In some embodiments of the present application, when the target object is a human object, in order to accurately obtain the image elements in the target image partition, the recognizing the image elements in the target image partition to obtain a plurality of image elements may specifically include:

[0058] Recognizing the clothing elements and / or decorative elements worn by the human object in the target image partition to obtain the color and style of the clothing elements, and / or the color and style of the decorative elements;

[0059] Determining a plurality of image elements according to the color and style of the clothing elements, and / or the color and style of the decorative elements.

[0060] Among them, the clothing element can be the clothing worn by the human object. For example, as Figure 3 shown, it can be the upper garment, trousers and shoes worn by the human object 21.

[0061] The decorative element can be the ornament worn by the human object. For example, as Figure 3 shown, it can be the watch 22 worn by the human object 21.

[0062] For the clothing element (or decorative element), the style can be the style possessed by the clothing element. For example, it can be that there is an image of a vase statue on the upper garment of the human object 21 in Figure 2 ( Figure 2If not shown in the figure (not shown), the style of the clothing element is a vase statue.

[0063] In some embodiments of the present application, the clothing elements and / or decorative elements worn by the human object in the target image partition can be identified according to a preset recognition algorithm to obtain the color and style of the clothing elements, and / or the color and style of the decorative elements. Then, the color and style of the clothing elements, and / or the color and style of the decorative elements are used as multiple image elements.

[0064] In the embodiments of the present application, by using the color and style of the clothing elements and / or the color and style of the decorative elements worn by the human object in the identified target image partition as multiple image elements, multiple image elements in the target image partition can be accurately and quickly obtained, improving the acquisition efficiency of the image elements.

[0065] In some embodiments of the present application, when the target image partition is Figure 3 the first image partition and the fourth image partition in, multiple image elements of the target image partition can be identified by referring to the above method. When the target image partition is Figure 3 the second image partition and the third image partition in, before identifying multiple image elements of the image partition based on the above method, the wallpaper pushing method involved above may further include:

[0066] Taking the elbow joint in the second image partition as the origin, constructing an oblique line along the arm to form a thermal area corresponding to the second image partition;

[0067] Taking the knee joint in the third image partition as the origin, constructing an oblique line along the leg to form a thermal area corresponding to the third image partition.

[0068] Correspondingly, the identifying the clothing elements and / or decorative elements worn by the human object in the target image partition to obtain the color and style of the clothing elements, and / or the color and style of the decorative elements may specifically be: identifying the clothing elements and / or decorative elements worn by the human object in the thermal area corresponding to the target image partition to obtain the color and style of the clothing elements, and / or the color and style of the decorative elements.

[0069] In an example, as Figure 4 shown, the target object is the human object 21, the elbow joint is in the second image partition 32, the knee joint is in the third image partition 33. Then, taking the elbow joint 421 as the origin and constructing an oblique line 422 along the arm, a thermal area corresponding to the second image partition can be formed, and this thermal area is the area enclosed by the constructed oblique line 422. Taking the knee joint 431 as the origin and constructing an oblique line 432 along the leg, a thermal area corresponding to the second image partition can be formed, and this thermal area is the area enclosed by the constructed oblique line 432.

[0070] In an embodiment of the present application, a thermal zone is drawn by dividing the second image partition and the third image partition, so that the color and style of clothing elements worn by the human object in the thermal zone, and / or the color and style of decorative elements can be identified. In this way, there is no need to calculate the color and style of clothing elements worn by the human object in the entire image partition, and / or the color and style of decorative elements, thereby saving calculation time and improving the efficiency of determining image elements in the target image partition.

[0071] In some embodiments of the present application, in order to accurately obtain the target image element, the fusion of multiple image elements to obtain the target image element may specifically include:

[0072] For the colors of the target elements in the target image partition, determine the main colors and matching colors among the colors according to their proportions;

[0073] For the styles of the target elements in the target image partition, sort the styles from large to small according to the number of occurrences, and select the top N styles as the target styles corresponding to the target image partition; N is a positive integer;

[0074] The main color, color matching and target style corresponding to each image partition are summarized respectively to obtain the target image element;

[0075] Among them, the target elements can be clothing elements and decorative elements.

[0076] The preset position may be a pre-set position.

[0077] The main color may be a color that is ranked first (for example, the color ranked first) selected after sorting the colors in the target image partition according to their proportions from large to small.

[0078] The color matching may be other colors except the main color among the colors in the target image partition.

[0079] In some embodiments of the present application, the target style may be the top N styles selected after sorting the styles in the target image partition according to the number of occurrences from large to small.

[0080] In an example, if it is identified that the styles of clothing colors and decorative elements in the first image partition of the first image include vase statues and art statues, where the vase statue appears twice and the art statue appears three times, the vase statue and the art statue can be sorted from large to small according to the number of appearances (that is, the sorting result is: art statue-vase statue), and then the first style with the highest sorting is selected, that is, the art statue is used as the target style corresponding to the first image partition.

[0081] In some embodiments of the present application, the dominant colors, complementary colors, and target styles corresponding to each image partition can be summarized respectively. Specifically, only one of the repeated colors (or styles) can be retained to obtain the target image elements.

[0082] In one example, referring to Figure 3 , taking the dominant color and complementary color as an example, if the colors corresponding to the first image partition are yellow, green, and red, the colors corresponding to the second image partition are brown and white, the colors corresponding to the third image partition are yellowish-brown, and the colors corresponding to the fourth image partition are yellow and blue. Since yellow exists in both the first image partition and the fourth image partition, when summarizing the colors of each image partition, only one yellow is retained, and the obtained target image elements are: yellow, green, red, brown, white, yellowish-brown, and blue.

[0083] In the embodiments of the present application, the dominant color and complementary color of each color of the target element in the target image partition are determined according to the proportion; the styles of the target element in the target image partition are sorted from large to small according to the number of occurrences, and the top N styles with the highest ranking are selected as the target styles corresponding to the target image partition; then the dominant colors, complementary colors, and target styles corresponding to each image partition can be summarized respectively to obtain the target image elements. In this way, the target image elements corresponding to the first image can be accurately obtained, and then the target information matching the first image can be selected based on the target image elements.

[0084] Step 130, push the target information to the user according to the target image elements.

[0085] Among them, the target information can be the information corresponding to the target image elements pushed to the user.

[0086] In some embodiments of the present application, when the first image is an image including the user's outfit, the target information here can be the target wallpaper corresponding to the target image elements, or the target outfit information corresponding to the target image elements. That is, according to the image including the user's outfit, the target wallpaper matching the user's outfit can be recommended to the user, or the outfit information similar to the user's outfit style can be recommended to the user, so that the user can match clothes according to the target outfit information.

[0087] In one example, when the first image is an image including the user's outfit, taking the target information can be the target wallpaper corresponding to the target image elements as an example, according to the user's outfit image, the target wallpaper matching the user's outfit can be pushed to the user. The target wallpaper can be, for example, the wallpaper used on the electronic device worn by the user, such as the wallpaper of a smart bracelet.

[0088] In one example, when the first image is an image containing the user's outfit, taking the target information as the target outfit information corresponding to the target image element, based on the user's outfit image, the target outfit information matching the user's outfit style can be pushed to the user. For example, if the user inputs an outfit image with the color and style of Chanel, then based on this outfit image, the target outfit information similar to the user's glamorous outfit style can be pushed to the user. For example, the outfit information conforming to the Chanel style can be pushed to the user. It should be noted that when pushing outfit information of different colors to the user, the recommendation can be made according to the matching effects of different colors. For example, before the recommendation, the main color among the determined colors is red, and the complementary colors are green, blue, and white. Then, when recommending, the matching effect of red and green is not very good, so the main color red can be recommended, and then one of the complementary colors can be selected for recommendation, such as white.

[0089] In an embodiment of the present application, according to the target image element, the target wallpaper corresponding to the target image element is pushed to the user, so that the user can obtain the wallpaper matching the outfit in the first image. It can also be to push the target outfit information corresponding to the target image element to the user. In this way, the outfit information matching the user's outfit style can be recommended to the user, improving the user experience.

[0090] In some embodiments of the present application, in order to accurately determine the target information pushed to the user, step 130 may specifically include: determining the target element index of the wallpaper according to the target image element;

[0091] According to the target element index, the target information corresponding to the target element index is searched from the target information element index library;

[0092] Push the target information to the user.

[0093] Among them, the target element index may be an index used to search for the target information corresponding to the target image element.

[0094] In some embodiments of the present application, the target element index may be an index type containing the target image element and the target information. For example, taking the target information as the target wallpaper, if the target element image is red and its corresponding wallpaper is Wallpaper 1, then the target element index of the wallpaper corresponding to the target element image (red) may be in the form of: red → Wallpaper 1.

[0095] In some embodiments of the present application, in order to further improve the user experience, when determining the target element index of the target information, the following two situations may be included:

[0096] (1) The situation where the target element index of the target information is determined for the first time

[0097] When the target element index of the target information is determined for the first time, that is, when the target information is pushed to the user for the first time, receive a second input from the user for the first target image element;

[0098] In response to the second input, determine the first target image element;

[0099] Based on the pre-set correspondence between the first target image element and the target element index, determine the target element index.

[0100] Among them, the first target image element can be at least one of the target image elements.

[0101] The second input can be used to determine the first target image element. The second input can be a click input, a double-click input, a swipe input, a fill input, etc. for at least one of the target image elements, or a combined operation of at least two of the above inputs.

[0102] In one example, if the target image elements are yellow, green, red, brown, white, yellow-brown, and blue, and the user selects yellow (the first target image element), then yellow is used as the first target image element. If the target information is a wallpaper, and the pre-set correspondence between yellow and the target element index is: yellow → wallpaper 2, then according to this correspondence, the target element index can be determined as yellow → wallpaper 2.

[0103] In the embodiments of the present application, when the target element index is determined for the first time, by responding to the second input for the first target image element, the first target image element can be determined. In this way, the target element index can be directly determined based on the pre-set correspondence between the first target image element and the target element index. In this way, when the target element index is determined for the first time, the user can select the first target image element required by the user according to the user's needs, and then obtain the target information that meets the user's needs and matches the first image, improving the user experience.

[0104] (2) The case where the target element index of the target information is determined non-first

[0105] When the target element index of the target information is determined non-first, that is, when the target information is not pushed to the user for the first time, obtain the second target image element of the second image;

[0106] Determine the differential image element between the second target image element and the target image element corresponding to the first image;

[0107] Based on the pre-set correspondence between the differential image element and the target element index, determine the target element index.

[0108] Among them, the second image can be an image of the user before the first image. Specifically, it can be an image for which target information has been pushed before the target information corresponding to the first image is pushed.

[0109] The second target image element can be the target image element corresponding to the extracted second image.

[0110] The difference image element can be the image element of the difference between the target image element corresponding to the first image and the second image element.

[0111] In one example, if the target image elements corresponding to the first image are yellow, green, red, brown, white, yellow-brown, and blue, and the second target image elements corresponding to the second image are yellow, green, red, brown, white, yellow-brown, and purple, then the difference image element is purple. If the target information is a wallpaper, and the pre-set corresponding relationship between purple and the target element index is: purple → wallpaper 3, then according to this corresponding relationship, the target element index can be determined as purple → wallpaper 3.

[0112] In the embodiments of the present application, when it is determined that the target element index is not determined for the first time, the second target image elements of the second image for which the target information has been recommended before the first image can be obtained, the difference image elements between the second target image elements and the target image elements corresponding to the first image can be determined, and then according to the pre-set corresponding relationship between the difference image elements and the target element index, the target element index can be determined. In this way, when it is determined that the target element index is not determined for the first time, the target element index matching the image element difference between the first image input by the user this time and the second image input by the user last time can be obtained based on the image element difference between the two images input by the user, and then the target information required by the user can be obtained, improving the user experience.

[0113] In some embodiments of the present application, the target information corresponding to the target element index can be queried from the target information element index library.

[0114] In one example, if the target information is a target wallpaper and the determined target element index is: purple → wallpaper 3, then querying this index in the wallpaper element index library can obtain the target wallpaper corresponding to this target element index as wallpaper 3.

[0115] In some embodiments of the present application, in order to accurately determine the target information, it is necessary to pre-construct a target information element index library. The specific construction process can be as follows:

[0116] Obtain at least one candidate information and at least one image element for constructing the target information element index library;

[0117] Establish a correspondence between each candidate information and each image element to generate at least one element index;

[0118] Generate a target information element index library based on each element index.

[0119] Among them, the candidate information can be the information for constructing the target information element index library.

[0120] In one example, if the target information is a target wallpaper, there are candidate wallpapers: Wallpaper 1 (which can be a picture of the sea), Wallpaper 2 (which can be a picture of flames), Wallpaper 3 (which can be a picture of a green grassland in spring), and Wallpaper 4 (which can be a bouquet of flowers inserted into a vase). The image elements are red, blue, vase statue, and green. Then, Wallpaper 1 can be corresponded with blue to generate an element index: blue → Wallpaper 1; Wallpaper 2 can be corresponded with red to generate an element index: red → Wallpaper 2; Wallpaper 3 can be corresponded with green to generate an element index: green → Wallpaper 3; Wallpaper 4 can be corresponded with the vase statue to generate an element index: vase statue → Wallpaper 4. Then, store the generated element indexes in a database to generate a wallpaper element index library.

[0121] In some embodiments of the present application, in order to more clearly understand the technical solution of the present application, the technical solution of the present application will be described below by taking the target object as a human object, the first image as an image including the user's outfit, and the target information as the target wallpaper as an example.

[0122] As Figure 5 is a schematic flowchart of another push method provided by an embodiment of the present application. As Figure 5 shown, the push method provided by the embodiment of the present application may include step 510 - step 590.

[0123] Step 510, construct a wallpaper element index library.

[0124] Step 520, receive a first input from the user for the first image.

[0125] Step 530, in response to the first input, identify whether there is a human object in the first image. If there is, execute step 540; if not, return to execute step 520.

[0126] In some embodiments of the present application, an extraction algorithm can be used to identify whether there are parts such as the head, shoulders, waist, arms, legs, and feet of a human object in the first image. If there are, step 540 can be executed.

[0127] Step 540, divide the first image according to at least one key feature of the human object to obtain at least two image partitions.

[0128] Step 550: Identify the image elements in the target image partition to obtain multiple image elements.

[0129] Among them, the target image partition can be at least one of the at least two image partitions.

[0130] Step 560: Fuse the multiple image elements to obtain a target image element.

[0131] Step 570: Determine the target element index of the wallpaper according to the target image element.

[0132] Step 580: According to the target element index, search for the target wallpaper corresponding to the target element index in the wallpaper element index library.

[0133] Step 590: Push the target wallpaper to the user.

[0134] In some embodiments of the present application, steps 510 - 590 have been introduced in the above embodiments and will not be elaborated here.

[0135] In the push method provided by the embodiments of the present application, the execution subject can be a push device. In the embodiments of the present application, taking the push device executing the push method as an example, the push device provided by the embodiments of the present application is described.

[0136] Figure 6 It is a schematic structural diagram of a push device shown according to an exemplary embodiment.

[0137] As Figure 6 shown, the push device 600 may include:

[0138] A first receiving module 610, configured to receive a first input of a user for a first image;

[0139] A first determining module 620, configured to determine a target image element corresponding to a target object in the first image in response to the first input;

[0140] A push module 630, configured to push target information to the user according to the target image element.

[0141] In the embodiments of the present application, in response to the first input received by the first receiving module from the user for the first image, the first determining module can extract the target image element corresponding to the target object in the first image from the first image. Then, based on the second determining module, according to the target image element, the target information corresponding to the target image element can be pushed to the user. In this way, the finally recommended target information for the user is personalized according to the first image input by the user. In this way, the user does not need to select the required target information one by one by himself, thus saving the energy and time consumed by the user in selecting the target information and improving the user experience.

[0142] In some embodiments of the present application, in order to improve the determination efficiency of the target image element corresponding to the target object in the first image, the first determination module 620 may include:

[0143] A partitioning unit, configured to partition the first image according to at least one key feature of the target object, to obtain at least two image partitions;

[0144] An identification unit, configured to identify image elements in the target image partition, to obtain a plurality of image elements; the target image partition is at least one of the at least two image partitions;

[0145] A fusion unit, configured to fuse the plurality of image elements to obtain a target image element.

[0146] In some embodiments of the present application, when the target object is a human object, in order to accurately obtain the image elements in the target image partition, the identification unit may specifically be configured to:

[0147] Identify the clothing elements and / or decorative elements worn by the human object in the target image partition, to obtain the color and style of the clothing elements, and / or the color and style of the decorative elements;

[0148] Determine the plurality of image elements according to the color and style of the clothing elements, and / or the color and style of the decorative elements;

[0149] In some embodiments of the present application, in order to accurately obtain the target image element, the fusion unit may specifically be configured to:

[0150] For the color of the target element in the target image partition, determine the main color and the complementary color in each color according to the proportion;

[0151] For the style of the target element in the target image partition, sort each style in descending order according to the number of occurrences, and select the top N styles with the highest ranking as the target style corresponding to the target image partition; N is a positive integer;

[0152] Summarize the main color, complementary color, and the target style corresponding to each image partition respectively, to obtain the target image element;

[0153] Wherein, the target element is the clothing element and the decorative element.

[0154] In some embodiments of the present application, in order to further improve the user experience, the push module 630 may specifically be configured to:

[0155] Push a target wallpaper or target dressing information corresponding to the target image element to the user according to the target image element.

[0156] The wallpaper pushing device in the embodiments of the present application may be an electronic device or a component in an electronic device, such as an integrated circuit or a chip. The electronic device may be a terminal or other devices other than the terminal. Exemplarily, the electronic device may be a mobile phone, a tablet computer, a laptop computer, a handheld computer, a vehicle-mounted electronic device, a Mobile Internet Device (MID), an augmented reality (AR) / virtual reality (VR) device, a robot, a wearable device, an ultra-mobile personal computer (UMPC), a netbook, or a personal digital assistant (PDA), etc., and may also be a server, a Network Attached Storage (NAS), a personal computer (PC), a television (TV), a teller machine, or a self-service machine, etc. The embodiments of the present application do not make specific limitations.

[0157] The wallpaper pushing device in the embodiments of the present application may be a device with an operating system. The operating system may be an Android operating system, an iOS operating system, or other possible operating systems. The embodiments of the present application do not make specific limitations.

[0158] The wallpaper pushing device provided in the embodiments of the present application can implement Figure 1 and Figure 5 Each process implemented by the method embodiments, to avoid repetition, will not be elaborated here.

[0159] Optionally, as Figure 7 shown, the embodiments of the present application further provide an electronic device 700, including a processor 701 and a memory 702. A program or instruction that can run on the processor 701 is stored on the memory 702. When the program or instruction is executed by the processor 701, each step of the above-mentioned wallpaper pushing method embodiment is implemented, and the same technical effect can be achieved. To avoid repetition, it will not be elaborated here.

[0160] It should be noted that the electronic devices in the embodiments of the present application include the above-mentioned mobile electronic devices and non-mobile electronic devices.

[0161] Figure 8 Schematic diagram of the hardware structure of an electronic device for implementing the embodiments of the present application.

[0162] The electronic device 800 includes, but is not limited to, components such as a radio frequency unit 801, a network module 802, an audio output unit 803, an input unit 804, a sensor 805, a display unit 806, a user input unit 807, an interface unit 808, a memory 809, and a processor 810.

[0163] Those skilled in the art can understand that the electronic device 800 may further include a power source (such as a battery) for supplying power to each component. The power source can be logically connected to the processor 810 through a power management system, so as to implement functions such as management of charging, discharging, and power consumption management through the power management system. Figure 8 The structure of the electronic device shown does not limit the electronic device. The electronic device may include more or fewer components than shown, or combine certain components, or have different component arrangements, which will not be elaborated here.

[0164] Among them, the user input unit 807 is used to receive a first input of the user to the first image;

[0165] The processor 810 is configured to, in response to the first input, determine a target image element corresponding to a target object in the first image; and push target information to the user according to the target image element.

[0166] In this way, by responding to the first input of the user to the first image, a target image element corresponding to the target object in the first image can be extracted from the first image. Then, according to the target image element, the target information corresponding to the target image element can be pushed to the user. Thus, the finally recommended target information to the user is personalized according to the first image input by the user himself. In this way, it is not necessary for the user to select the required target information one by one, thereby saving the energy and time consumed by the user in selecting the target information and improving the user experience.

[0167] Optionally, the processor 810 may specifically be configured to: divide the first image according to at least one key feature of the target object to obtain at least two image partitions; identify image elements in the target image partition to obtain a plurality of image elements; and fuse the plurality of image elements to obtain a target image element.

[0168] In this way, by dividing the first image according to at least one key feature of the target object, at least two image partitions can be obtained. Then, the image elements in each image partition are identified to obtain a plurality of image elements, rather than identifying the entire first image. In this way, the computing power of the server is saved, the image elements of the first image can be quickly extracted, the acquisition efficiency of the image elements is improved, and further the determination efficiency of the target image element is improved.

[0169] Optionally, the target object is a human object, and the processor 810 may specifically be configured to: identify the clothing elements and / or decorative elements worn by the human object in the target image partition, obtain the color and style of the clothing elements, and / or the color and style of the decorative elements; and determine the multiple image elements according to the color and style of the clothing elements, and / or the color and style of the decorative elements.

[0170] In this way, by using the color and style of the clothing elements and / or the color and style of the decorative elements worn by the human object in the identified target image partition as the multiple image elements, the multiple image elements in the target image partition can be accurately and quickly obtained, improving the acquisition efficiency of the image elements.

[0171] Optionally, the processor 810 may specifically be configured to: for the color of the target element in the target image partition, determine the main color and the complementary color of each color according to the proportion; for the style of the target element in the target image partition, sort the styles according to the number of occurrences from large to small, and select the top N styles with the highest ranking as the target style corresponding to the target image partition; and summarize the main color, the complementary color, and the target style corresponding to each image partition respectively to obtain the target image elements.

[0172] In this way, for the colors of the target elements in the target image partition, determine the main color and the complementary color of each color according to the proportion; for the styles of the target elements in the target image partition, sort the styles according to the number of occurrences from large to small, and select the top N styles with the highest ranking as the target style corresponding to the target image partition; then the main color, the complementary color, and the target style corresponding to each image partition can be summarized respectively to obtain the target image elements. In this way, the target image elements corresponding to the first image can be accurately obtained, and then the target information matching the first image can be selected based on the target image elements.

[0173] Optionally, the processor 810 may specifically be configured to: push a target wallpaper or target dressing information corresponding to the target image elements to the user.

[0174] In this way, according to the target image elements, push the target wallpaper corresponding to the target image elements to the user so that the user can obtain a wallpaper that matches the dressing in the first image, or push the target dressing information corresponding to the target image elements to the user. In this way, dressing information that matches the user's dressing style can be recommended to the user, improving the user experience.

[0175] It should be understood that in the embodiments of the present application, the input unit 804 may include a Graphics Processing Unit (GPU) 8041 and a microphone 8042. The GPU 8041 processes the image data of static pictures or videos obtained by an image capture device (such as a camera) in the video capture mode or the image capture mode. The display unit 806 may include a display panel 8061, and the display panel 8061 may be configured in the form of a liquid crystal display, an organic light emitting diode, etc. The user input unit 807 includes at least one of a touch panel 8071 and other input devices 8072. The touch panel 8071 is also called a touch screen. The touch panel 8071 may include two parts: a touch detection device and a touch controller. The other input devices 8072 may include, but are not limited to, a physical keyboard, function keys (such as volume control keys, switch keys, etc.), a trackball, a mouse, and a joystick, which will not be elaborated here.

[0176] The memory 809 can be used to store software programs and various data. The memory 809 mainly includes a first storage area for storing programs or instructions and a second storage area for storing data. Among them, the first storage area can store an operating system, applications or instructions required for at least one function (such as a sound playback function, an image playback function, etc.). In addition, the memory 809 may include a volatile memory or a non-volatile memory, or the memory 809 may include both a volatile memory and a non-volatile memory. Among them, the non-volatile memory may be a Read-Only Memory (ROM), a Programmable ROM (PROM), an Erasable PROM (EPROM), an Electrically EPROM (EEPROM), or a flash memory. The volatile memory may be a Random Access Memory (RAM), a Static RAM (SRAM), a Dynamic RAM (DRAM), a Synchronous DRAM (SDRAM), a Double Data Rate SDRAM (DDR SDRAM), an Enhanced SDRAM (ESDRAM), a Synch link DRAM (SLDRAM), and a Direct Rambus RAM (DRRAM). The memory 809 in the embodiments of the present application includes, but is not limited to, these and any other suitable types of memories.

[0177] The processor 810 may include one or more processing units; optionally, the processor 810 integrates an application processor and a modem processor. Among them, the application processor mainly processes operations related to the operating system, user interface, application programs, etc., and the modem processor mainly processes wireless communication signals, such as a baseband processor. It can be understood that the above-mentioned modem processor may not be integrated into the processor 810 either.

[0178] The embodiment of the present application also provides a readable storage medium, on which a program or instruction is stored. When the program or instruction is executed by a processor, it implements each process of the above-mentioned embodiment of the wallpaper pushing method and can achieve the same technical effect. To avoid repetition, it will not be elaborated here.

[0179] Among them, the processor is the processor in the electronic device described in the above embodiment. The readable storage medium includes a computer-readable storage medium, such as a computer read-only memory ROM, a random access memory RAM, a magnetic disk, or an optical disc, etc.

[0180] The embodiment of the present application further provides a chip, which includes a processor and a communication interface. The communication interface is coupled to the processor, and the processor is used to run a program or instruction to implement each process of the above-mentioned embodiment of the wallpaper pushing method and can achieve the same technical effect. To avoid repetition, it will not be elaborated here.

[0181] It should be understood that the chip mentioned in the embodiment of the present application may also be referred to as a system-on-chip, system chip, chip system, or system-on-chip, etc.

[0182] The embodiment of the present application provides a computer program product, which is stored in a storage medium and is executed by at least one processor to implement each process of the above-mentioned embodiment of the wallpaper pushing method and can achieve the same technical effect. To avoid repetition, it will not be elaborated here.

[0183] It should be noted that in this text, the term "including", "comprising", or any other variant thereof is intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus comprising a series of elements includes not only those elements but also other elements not expressly listed, or elements that are inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the statement "comprising an..." does not exclude the presence of additional identical elements in the process, method, article, or apparatus comprising that element. In addition, it should be pointed out that the scope of the methods and apparatuses in the embodiments of the present application is not limited to performing functions in the order shown or discussed, and may also include performing functions in a substantially simultaneous manner or in the reverse order according to the functions involved. For example, the described methods may be performed in an order different from that described, and various steps may be added, omitted, or combined. Additionally, features described with reference to certain examples may be combined in other examples.

[0184] Through the description of the above embodiments, those skilled in the art can clearly understand that the above-described example methods can be implemented by means of software plus a necessary general hardware platform. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation. Based on this understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art, can be embodied in the form of a computer software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes several instructions to enable a terminal (which can be a mobile phone, computer, server, or network device, etc.) to execute the methods described in the various embodiments of the present application.

[0185] The embodiments of the present application have been described above in conjunction with the accompanying drawings. However, the present application is not limited to the above specific embodiments. The above specific embodiments are merely illustrative and not restrictive. Those of ordinary skill in the art, under the inspiration of the present application and without departing from the spirit and scope protected by the claims of the present application, can still make many forms, all of which fall within the protection scope of the present application.

Claims

1. A pushing method, characterized in that, Applied to a wearable device, the method includes: Receiving a first input from a user for a first image; In response to the first input, determining a target image element corresponding to a target object in the first image; According to the target image element, pushing target information to the user, the target information including a target wallpaper; The pushing the target information to the user according to the target image element includes: In the case of determining that it is not the first time to push target information to the user, obtaining a second target image element of a second image, where the second image is an image for which target information has been pushed before pushing target information for the first image; Determining a difference image element between the second target image element and the target image element corresponding to the first image; Based on a pre-set correspondence between the difference image element and the target element index, determining the target element index; According to the target element index, looking up, in a target information element index library, target information corresponding to the target element index; Pushing target information to the user.

2. The method according to claim 1, wherein The determining the target image element corresponding to the target object in the first image specifically includes: Dividing the first image according to at least one key feature of the target object to obtain at least two image partitions; Identifying image elements in a target image partition to obtain a plurality of image elements; the target image partition is at least one of the at least two image partitions; Fusing the plurality of image elements to obtain a target image element.

3. The method according to claim 2, wherein The target object is a human object; The identifying the image elements in the target image partition to obtain a plurality of image elements includes: Identifying clothing elements and / or decoration elements worn by the human object in the target image partition to obtain the color and style of the clothing elements, and / or, the color and style of the decoration elements; Determining the plurality of image elements according to the color and style of the clothing elements, and / or, the color and style of the decoration elements.

4. The method according to claim 3, characterized in that The fusing the plurality of image elements to obtain a target image element specifically includes: For the color of a target element in the target image partition, determining the main color and the complementary color in each color according to the proportion; For the style of a target element in the target image partition, sorting each style according to the number of occurrences from large to small, and selecting the top N styles with the highest ranking as the target style corresponding to the target image partition; N is a positive integer; Summarizing the main color, the complementary color, and the target style corresponding to each image partition respectively to obtain a target image element; Wherein, the target element is the clothing element and the decoration element.

5. The method according to any one of claims 1-4, characterized in that The pushing the target information to the user according to the target image element includes: Pushing target dressing information corresponding to the target image element to the user according to the target image element.

6. A wallpaper pushing device, characterized in that, Applied to a wearable device, the apparatus includes: A first receiving module, configured to receive a first input for a first image; A first determining module, configured to, in response to the first input, determine a target image element corresponding to a target object in the first image; A push module, configured to push target information to a user according to the target image element, where the target information includes a target wallpaper; Specifically, the push module is configured to: when it is determined that it is not the first time to push target information to the user, obtain a second target image element of a second image, where the second image is an image that has been pushed with target information before the target information is pushed for the first image; determine a difference image element between the second target image element and the target image element corresponding to the first image; determine a target element index based on a pre-set correspondence between the difference image element and the target element index; according to the target element index, look up target information corresponding to the target element index in a target information element index library; and push the target information to the user.

7. The device according to claim 6, characterized in that The first determination module includes: A division unit, configured to divide the first image according to at least one key feature of the target object, to obtain at least two image partitions; An identification unit, configured to identify image elements in a target image partition to obtain a plurality of image elements; the target image partition is at least one of the at least two image partitions; A fusion unit, configured to fuse the plurality of image elements to obtain a target image element.

8. The device according to claim 7, characterized in that, The target object is a human object; specifically, the identification unit is configured to: Identify clothing elements and / or decoration elements worn by the human object in the target image partition, to obtain the color and style of the clothing elements, and / or the color and style of the decoration elements; Determine the plurality of image elements according to the color and style of the clothing elements, and / or the color and style of the decoration elements.

9. The device according to claim 8, characterized in that Specifically, the fusion unit is configured to: For the color of the target element in the target image partition, determine the main color and the complementary color in each color according to the proportion; For the style of the target element in the target image partition, sort each style according to the number of occurrences from large to small, and select the top N styles with the highest ranking as the target style corresponding to the target image partition; N is a positive integer; Summarize the main color, the complementary color, and the target style corresponding to each image partition respectively to obtain a target image element; Wherein, the target element is the clothing element and the decoration element.

10. The device according to any one of claims 6-9, characterized in that, Specifically, the push module is configured to: Push target dressing information corresponding to the target image element to the user according to the target image element.

11. An electronic device, characterized in that, It includes a processor and a memory, where the memory stores a program or instruction that can run on the processor, and when the program or instruction is executed by the processor, the steps of the push method according to any one of claims 1-5 are implemented.

12. A readable storage medium, characterized in that, A program or instruction is stored on the readable storage medium, and when the program or instruction is executed by a processor, the steps of the push method according to any one of claims 1-5 are implemented.

Images