Clothing recommendation method, device, equipment and storage medium

Abstract

This invention provides a method, apparatus, device, and storage medium for recommending clothing outfits. The method involves: acquiring an image of clothing to be styled; matching the image of the clothing to be styled with pre-stored outfit images in an outfit image library to obtain at least one candidate outfit image, where each candidate outfit image contains a first garment with a similarity to the image of the clothing to be styled exceeding a first threshold; determining at least one target outfit image based on the at least one candidate outfit image and a user's clothing library, where the user's clothing library contains pre-stored images of user clothing; and outputting the at least one target outfit image. This invention matches the clothing to be styled with an outfit image library to obtain candidate outfit images containing the same or similar clothing as the clothing to be styled, and then combines this with the user's clothing library to determine the target outfit image. This allows users to style clothing based on the target outfit image, meeting user needs and improving user experience.

Description

TECHNICAL FIELD

[0001] The embodiment of the present application belongs to the technical field of smart home, and particularly relates to a clothes matching recommendation method, device, equipment and storage medium. BACKGROUND

[0002] With the increasing improvement of people's living standards, people's requirements for clothing are also increasing. In the face of various styles of clothing, people usually hope to get matching suggestions.

[0003] In the prior art, when a user needs to match a single clothing item, the user usually queries how to match the clothing item through the network, fashion magazines and other ways, which is time-consuming and laborious, and sometimes the user cannot determine the appropriate matching way, which cannot meet the user's demand. SUMMARY

[0004] The embodiment of the present application provides a clothes matching recommendation method, device, equipment and storage medium to recommend clothes matching to users, meet user demand and improve user experience.

[0005] The first aspect of the embodiment of the present application is to provide a clothes matching recommendation method, which comprises:

[0006] Obtaining an image of a clothing item to be matched;

[0007] Matching the image of the clothing item to be matched with a pre-stored matching image in a matching image library to obtain at least one alternative matching image, the alternative matching image containing a first clothing item with a similarity higher than a first threshold to the image of the clothing item to be matched;

[0008] Determining at least one target matching image according to the at least one alternative matching image and a user clothing library, the user clothing library pre-storing images of user clothing;

[0009] Outputting the at least one target matching image.

[0010] In a possible design, the determining at least one target matching image according to the at least one alternative matching image and the user clothing library comprises:

[0011] Obtaining an image of a second clothing item in each of the alternative matching images except the first clothing item;

[0012] According to the similarity between the image of the second clothing item and the image of the user clothing in the user clothing library, screening at least one target matching image from the at least one alternative matching image.

[0013] In a possible design, the target matching image comprises a first type of target matching image and a second type of target matching image.

[0014] The filtering of the at least one target dressing image from the at least one candidate dressing image according to the similarity between the image of the second clothing and the image of the user clothing in the user clothing library comprises:

[0015] If the image of the second clothing in a certain candidate dressing image is similar to the image of the first user clothing in the user clothing library higher than a second threshold, the candidate dressing image is taken as a first type of target dressing image.

[0016] If the image of the second clothing in a certain candidate dressing image is similar to the image of any user clothing in the user clothing library no higher than a second threshold, the candidate dressing image is taken as a second type of target dressing image.

[0017] In a possible design, after the output of the at least one target dressing image, the method further comprises:

[0018] If the target dressing image is a first type of target dressing image, a storage location of the first user clothing corresponding to the target dressing image is determined, and a prompt message is output according to the storage location; and / or

[0019] If the target dressing image is a second type of target dressing image, purchase information of the second clothing contained in the target dressing image is acquired, and the purchase information is displayed.

[0020] In a possible design, the filtering of the at least one target dressing image from the at least one candidate dressing image according to the similarity between the image of the second clothing and the image of the user clothing in the user clothing library comprises:

[0021] The filtering of the at least one target dressing image from the at least one candidate dressing image according to the similarity between the image of the second clothing and the image of the user clothing in the user clothing library, and a preset filtering factor, wherein the preset filtering factor comprises at least one of weather information, clothing trend information, and user preference information.

[0022] In a possible design, the acquisition of the image of the clothing to be matched comprises:

[0023] acquiring the image of the clothing to be matched by an image acquisition device; or

[0024] receiving a selection instruction of selecting the clothing to be matched from the user clothing library by a user, and acquiring the image of the clothing to be matched from the user clothing library according to the selection instruction.

[0025] In a possible design, the method further comprises:

[0026] An image of the clothes of the user is collected by an image collection device and stored in the clothes library of the user.

[0027] A second aspect of the embodiment of the present application is to provide a clothes matching recommendation device, comprising:

[0028] An acquisition module is configured to acquire an image of clothes to be matched;

[0029] A matching module is configured to match the image of the clothes to be matched with a pre-stored matching image in a matching image library, and acquire at least one alternative matching image, wherein the alternative matching image contains a first piece of clothes with a similarity higher than a first threshold to the image of the clothes to be matched.

[0030] A matching module is configured to determine at least one target matching image according to the at least one alternative matching image and a clothes library of a user, wherein the clothes library of the user pre-stores images of clothes of the user.

[0031] An output module is configured to output the at least one target matching image.

[0032] In a possible design, the matching module is configured to:

[0033] acquire an image of a second piece of clothes in each of the alternative matching images except the first piece of clothes;

[0034] filter at least one target matching image from the at least one alternative matching image according to a similarity between the image of the second piece of clothes and an image of a piece of clothes of the user in the clothes library of the user.

[0035] In a possible design, the target matching image includes a first type of target matching image and a second type of target matching image.

[0036] The matching module is configured to:

[0037] if the image of the second piece of clothes in a certain alternative matching image has a similarity higher than a second threshold to an image of a first piece of clothes of the user in the clothes library of the user, the alternative matching image is taken as the first type of target matching image.

[0038] if the image of the second piece of clothes in a certain alternative matching image has a similarity not higher than the second threshold to an image of any piece of clothes of the user in the clothes library of the user, the alternative matching image is taken as the second type of target matching image.

[0039] In a possible design, the output module is further configured to:

[0040] if the target matching image is the first type of target matching image, determine a storage location of the first piece of clothes corresponding to the target matching image, and output a prompt message according to the storage location; and / or

[0041] If the target dressing image is a second type of target dressing image, the purchase information of a second clothing contained in the target dressing image is acquired, and the purchase information is displayed.

[0042] In a possible design, the dressing module is configured to:

[0043] filter, according to the similarity between the image of the second clothing and the user clothing image in the user clothing library, and a preset filtering factor, at least one target dressing image from the at least one candidate dressing image, where the preset filtering factor includes at least one of weather information, clothing trend information, and user preference information.

[0044] In a possible design, the acquisition module is configured to:

[0045] acquire, by an image acquisition device, the image of the clothing to be dressed; or

[0046] receive a selection instruction of selecting, by a user, the clothing to be dressed from the user clothing library, and acquire, according to the selection instruction, the image of the clothing to be dressed from the user clothing library.

[0047] In a possible design, the apparatus further includes an uploading module configured to:

[0048] acquire, by an image acquisition device, the image of the user clothing, and store the image into the user clothing library.

[0049] A third aspect of the embodiment of the present application provides a clothing dressing recommendation device, including:

[0050] a memory configured to store a computer program;

[0051] a processor configured to run the computer program stored in the memory to implement the method in the first aspect.

[0052] A fourth aspect of the embodiment of the present application provides a computer readable storage medium having a computer program stored thereon;

[0053] The computer program is executed by a processor to implement the method in the first aspect.

[0054] The method, device, equipment and storage medium for recommending clothes provided by the embodiment of the present application, by acquiring an image of clothes to be matched, matching the image of clothes to be matched with pre-stored matching images in a matching image library, acquiring at least one alternative matching image, the alternative matching image containing first clothes with a similarity higher than a first threshold to the image of clothes to be matched, determining at least one target matching image according to the at least one alternative matching image and a user clothes library, and outputting the at least one target matching image. The embodiment of the present application matches the clothes to be matched with the matching image library to acquire an alternative matching image containing the same or similar clothes to the clothes to be matched, and then determines a target matching image in combination with the user clothes library, so that the user can match clothes according to the target matching image, meet the user demand, and improve the user experience. BRIEF DESCRIPTION OF DRAWINGS

[0055] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiments or prior art description. Obviously, the drawings in the following description are only some embodiments of the present application, and for those skilled in the art, other drawings can also be obtained from these drawings without creative labor.

[0056] Figure 1 The flow chart of the method for recommending clothes provided by the embodiment of the present application is provided.

[0057] Figure 2 The flow chart of the method for recommending clothes provided by another embodiment of the present application is provided.

[0058] Figure 3 The interface schematic diagram of the method for recommending clothes provided by an embodiment of the present application is provided.

[0059] Figure 4 The interface schematic diagram of the method for recommending clothes provided by another embodiment of the present application is provided.

[0060] Figure 5 The structure diagram of the device for recommending clothes provided by the embodiment of the present application is provided.

[0061] Figure 6 The structure diagram of the device for recommending clothes provided by the embodiment of the present application is provided. DETAILED DESCRIPTION

[0062] With reference to the accompanying drawings, the technical solutions in the embodiments of the present application will be clearly and completely described below, obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without creative efforts belong to the protection scope of the present application.

[0063] In the prior art, when a user needs to match a certain clothing item, the user usually queries how to match the clothing item through the network, fashion magazines and other ways, which is time-consuming and laborious, and sometimes the user cannot determine the appropriate matching method, which cannot meet the user's demand. In order to solve the above problems, in the embodiments of the present application, the target matching image is obtained according to the clothing to be matched, and the user is guided to match the clothing based on the target matching image.

[0064] Specifically, the image of the clothing to be matched is matched with the pre-stored matching image in the matching image library to obtain at least one alternative matching image, wherein the alternative matching image contains a first clothing with a similarity higher than a first threshold to the image of the clothing to be matched; at least one target matching image is determined according to the at least one alternative matching image and the user clothing library, wherein the image of the user clothing is pre-stored in the user clothing library; and the at least one target matching image is output. The present application matches the clothing to be matched with the matching image library to obtain an alternative matching image containing the same or similar clothing to the clothing to be matched, and then determines the target matching image in combination with the user clothing library, so that the user can match the clothing according to the target matching image, meet the user's demand, and improve the user experience.

[0065] The clothing matching recommendation method provided in the embodiments of the present application can be applied to some terminal devices, such as smart phones, tablet computers, wearable devices, smart closets, smart televisions and the like. Specifically, the clothing matching recommendation method can be executed by a terminal device, wherein the matching image library and the user clothing library can be stored locally in the terminal device, or can be downloaded in advance from a server to the local terminal device.

[0066] In another optional embodiment, the terminal device and the server can also interact to jointly complete the clothing matching recommendation method, for example, the terminal device obtains the image of the clothing to be matched, and then sends the clothing to be matched to the server, the server matches the image of the clothing to be matched with the pre-stored matching image in the matching image library to obtain at least one alternative matching image, and determines at least one target matching image according to the at least one alternative matching image and the user clothing library, and then sends the at least one target matching image to the terminal device, which is displayed to the user by the terminal device.

[0067] The clothing matching recommendation process will be explained and described in detail below with reference to specific embodiments.

[0068] Figure 1 The flow chart of the clothes matching recommendation method provided in the embodiment of the present application. The embodiment provides a clothes matching recommendation method, and the specific steps are as follows:

[0069] S101, acquiring an image of a clothes to be matched.

[0070] In the embodiment, first, the clothes to be matched need to be determined, for example, when a user needs to match a top with a lower garment, the top is determined as the clothes to be matched, and then the image of the clothes to be matched is acquired.

[0071] In an alternative embodiment, the image of the clothes to be matched can be acquired by an image acquisition device, for example, the user can issue a photographing instruction through a touch screen, voice interaction or a remote controller, and the terminal device acquires the image of the clothes to be matched through the image acquisition device after receiving the photographing instruction of the user, wherein the clothes to be matched can be clothes hung on a clothes hanger or clothes laid flat, or can be clothes currently worn by the user. Further, if the clothes to be matched are clothes currently worn by the user, the current dressing image of the user can be acquired by the image acquisition device, and then the instruction of the user selecting the clothes to be matched from the current dressing image is accepted, and the clothes to be matched in the current dressing image is determined according to the instruction. Alternatively, when the current dressing image of the user is acquired by the image acquisition device, the user stands in front of the image acquisition device and controls the shooting through the remote controller or voice, or a delay time is set for shooting, for example, the user says "take a photo" and the shooting is delayed for 3 seconds.

[0072] In another alternative embodiment, some images of clothes owned by the user can also be stored in the user's clothes library in advance, for example, the images of the clothes of the user are acquired by the image acquisition device and stored in the user's clothes library; and then the user can select the clothes to be matched from the user's clothes library, and the terminal device acquires the image of the clothes to be matched from the user's clothes library according to the selection instruction of the user selecting the clothes to be matched from the user's clothes library.

[0073] Of course, the image of the clothes to be matched can also be acquired through other ways, for example, when the user needs to determine whether he has clothes to match with the clothes to be purchased before purchasing a piece of clothes, the image of the clothes to be matched can also be acquired from the purchase interface.

[0074] S102, matching the image of the clothes to be matched with the pre-stored dressing image in the dressing image library to acquire at least one alternative dressing image, wherein the alternative dressing image contains a first clothes with a similarity higher than a first threshold to the image of the clothes to be matched.

[0075] In the embodiment, the image library includes pre-stored dressing images, which can be matching images of a stylist or popular images among users. Each pre-stored dressing image includes at least two pieces of clothing, such as a coat, a top, a bottom, and shoes.

[0076] In the embodiment, the image of the clothing to be matched is matched with the pre-stored dressing images in the dressing image library, and pre-stored dressing images in the dressing image library that include the same or similar clothing (denoted as first clothing) as the clothing to be matched are selected as candidate dressing images, where the same or similar is determined based on a similarity of the images being higher than a first threshold. For example, the first threshold can be 70%. For example, if the clothing to be matched is a specific top, pre-stored dressing images that include the same or similar top are obtained from the dressing image library as candidate dressing images.

[0077] Of course, whether the clothing is the same or similar can be further determined based on the image similarity being higher than the first threshold and some attribute information of the clothing, where the attribute information can include at least one of a type, a style, a model, a material, and the like.

[0078] S103, determining at least one target dressing image based on the at least one candidate dressing image and a user clothing library, where the user clothing library pre-stores images of clothing of a user.

[0079] In the embodiment, since there is at least one candidate dressing image, a target dressing image of a suitable user can be determined based on the user clothing library. Optionally, a strategy for determining the target dressing image can be that the user clothing library has the same or similar clothing for the matched clothing, that is, the user has the same or similar clothing, or that the user has a possibility of purchasing the clothing although the user does not have the same or similar clothing. Of course, other strategies can also be used, which are not described herein.

[0080] S104, outputting the at least one target dressing image.

[0081] In the embodiment, after the at least one target dressing image is obtained, the at least one target dressing image can be outputted, for example, displayed on a display interface, so as to guide the user to match the clothing.

[0082] The method for recommending clothes provided in the embodiment comprises the following steps: obtaining an image of clothes to be matched; matching the image of the clothes to be matched with pre-stored clothes matching images in a clothes matching image library to obtain at least one candidate clothes matching image, the candidate clothes matching image containing a first piece of clothes having a similarity higher than a first threshold with the image of the clothes to be matched; determining at least one target clothes matching image according to the at least one candidate clothes matching image and a user clothes library in which images of user clothes are pre-stored; and outputting the at least one target clothes matching image. The clothes to be matched are matched with the clothes matching image library to obtain a candidate clothes matching image containing the same or similar clothes as the clothes to be matched, and then the target clothes matching image is determined in combination with the user clothes library, so that the user can match clothes according to the target clothes matching image, meet the user demand, and improve the user experience.

[0083] As a further improvement of the above-mentioned embodiments, as shown in Figure 2 The step of determining at least one target clothes matching image according to the at least one candidate clothes matching image and a user clothes library can comprise the following steps:

[0084] S201: obtaining an image of a second piece of clothes in each of the candidate clothes matching images except the first piece of clothes.

[0085] In the embodiment, since the candidate clothes matching image contains the first piece of clothes and at least one second piece of clothes matched with the first piece of clothes, and the first piece of clothes is the same as or similar to the clothes to be matched, the image of the second piece of clothes except the first piece of clothes can be obtained as a candidate piece of clothes matched with the clothes to be matched.

[0086] S202: screening at least one target clothes matching image from the at least one candidate clothes matching image according to the similarity between the image of the second piece of clothes and the image of the user clothes in the user clothes library.

[0087] In the embodiment, since the second piece of clothes in a certain candidate clothes matching image can be the same as or similar to the user clothes in the user clothes library, the similarity between the image of the second piece of clothes and the image of the user clothes in the user clothes library can be obtained, and then whether the candidate clothes matching image can be used as the target clothes matching image can be determined according to the similarity.

[0088] Optionally, the target clothes matching image comprises a first type of target clothes matching image and a second type of target clothes matching image; the first type of target clothes matching image is a candidate clothes matching image in which the second piece of clothes is the same as or similar to the user clothes in the user clothes library, and the user can directly match clothes from the clothes owned by himself according to the first type of target clothes matching image; and the second type of target clothes matching image is a candidate clothes matching image in which the second piece of clothes is not the same as or similar to the user clothes in the user clothes library, and the user can purchase new clothes to match according to the second type of target clothes matching image.

[0089] Further, the filtering, at S202, of the at least one target dressing image from the at least one candidate dressing image according to the similarity between the image of the second clothing and the image of the user clothing in the user clothing library can specifically include:

[0090] If the similarity between the image of the second clothing in a certain candidate dressing image and the image of the first user clothing in the user clothing library is higher than the second threshold value, the candidate dressing image is taken as the first type of target dressing image.

[0091] If the similarity between the image of the second clothing in a certain candidate dressing image and the image of any user clothing in the user clothing library is not higher than the second threshold value, the candidate dressing image is taken as the second type of target dressing image.

[0092] In the embodiment, when filtering the target dressing image from the candidate dressing image, the similarity between the second clothing in each candidate dressing image and each user clothing in the user clothing library can be calculated. If the similarity between the second clothing in the candidate dressing image and a certain user clothing (denoted as the first user clothing) in the user clothing library is higher than the second threshold value, the candidate dressing image is taken as the first type of target dressing image, i.e., the second clothing is the same as or similar to the first user clothing. If the similarity between the second clothing in the candidate dressing image and the image of any user clothing in the user clothing library is not higher than the second threshold value, the candidate dressing image is taken as the second type of target dressing image, i.e., there is no clothing in the user clothing library that is the same as or similar to the second clothing. Optionally, the second threshold value in the embodiment can be 70%.

[0093] Of course, it can also be determined whether the clothing is the same or similar on the basis of the image similarity being higher than the second threshold value by further using some attribute information of the clothing. The attribute information can include at least one of the type, style, style, material, and other attributes of the clothing.

[0094] Optionally, when outputting the target dressing image, the first type of target dressing image and the second type of target dressing image can be displayed according to a preset quantity ratio and / or a preset priority. For example, the total number of the first type of target dressing image and the second type of target dressing image can be limited to a set value, for example, 20, the first type of target dressing image is prior to the second type of target dressing image, and the quantity ratio between the first type of target dressing image and the second type of target dressing image is less than 3:1, i.e., the first type of target dressing image is less than 15, and the remaining is supplemented by the second type of target dressing image.

[0095] Optionally, when there are multiple target dressing images of the first type, the target dressing images of the first type can be sorted according to some sorting rules, for example, according to user preferences. The user can set a preference degree parameter for each user clothing in the user clothing library in advance, and then when sorting the target dressing images of the first type, the target dressing images of the first type can be sorted in descending order of the preference degree parameters of the first user clothing corresponding to the target dressing images of the first type. Of course, the target dressing images of the first type can also be sorted according to their popularity.

[0096] On the basis of any of the above embodiments, after outputting the at least one target dressing image, different operations can be performed according to the target dressing image.

[0097] In an optional embodiment, if the target dressing image is a target dressing image of the first type, a storage location of the first user clothing corresponding to the target dressing image is determined, and a prompt message is output according to the storage location. In this embodiment, the storage location of each user clothing can be determined in advance. Specifically, the user can upload the storage location of the clothing to the terminal device when storing the clothing, and then the storage location of the first user clothing corresponding to the target dressing image can be queried. Of course, the terminal device can also be connected with a smart wardrobe, and the storage location of the first user clothing can be obtained through the smart wardrobe or through other methods. After determining the storage location of the first user clothing, the storage location can be displayed to prompt the user, or other means can be used to output a prompt message to prompt the user.

[0098] In another optional embodiment, if the target dressing image is a target dressing image of the second type, purchase information of the second clothing included in the target dressing image is obtained, and the purchase information is displayed. In this embodiment, the purchase link, price, brand, and other information of the second clothing can be obtained and displayed to facilitate the user to purchase.

[0099] On the basis of any of the above embodiments, S202 can further include:

[0100] S202 can further include: filtering at least one target dressing image from the at least one candidate dressing image according to the similarity between the image of the second clothing and the image of the user clothing in the user clothing library and a preset filtering factor, wherein the preset filtering factor includes at least one of weather information, clothing trend information, and user preference information.

[0101] In the embodiment, in addition to considering the image similarity, some preset screening factors can be further considered in screening the target dressing image, for example, considering the weather information, the local temperature and weather condition can be obtained, so that a more reasonable target dressing image is screened out.

[0102] For example, considering the weather information, the clothes to be matched is a short-sleeved shirt, and if it is summer and the temperature is very high, a cooler dressing in the candidate dressing image is selected as the target dressing image, for example, the second clothes can be shorts, skirts, etc.; and if the current temperature is low, a warmer dressing in the candidate dressing image is selected as the target dressing image, for example, the second clothes can be pants, coats, etc.

[0103] For another example, considering the fashion trend information of the clothes, the current clothes are more popular with pleats and tuck elements, and the clothes to be matched is pants, and a target dressing image containing pleats and tuck elements can be selected from the candidate dressing image, for example, the second clothes can be a shirt with pleats and tuck elements.

[0104] Based on the above embodiment, a specific application scenario is provided as an example in the embodiment, the terminal device is a television set, the television set is connected with a server in the cloud, and the television set can also have an image acquisition device, the television set is configured with a clothes dressing recommendation program, Figure 3 which is an interface schematic diagram.

[0105] The user can enter the clothes dressing recommendation program through the touch screen, voice interaction or remote control, and then select the photographing function in the interface, for example, click the photographing matching button 301 in Figure 3 , enter the photographing mode, and control the shooting through the remote control or voice while standing in front of the image acquisition device, so as to acquire the current dressing image of the user and display it in the display area 302 in the interface. If the image is blurred or the user is not satisfied, the user can return to retake the image.

[0106] Further, the user can select the clothes to be matched from the current dressing image, for example, the user can select the upper garment, lower garment and shoes as the clothes to be matched through the selection button 303 in Figure 3 . In addition, after the user selects the clothes to be matched, the user can identify the clothes to be matched. If the clothes to be matched can be identified, the attribute information of the clothes to be matched is acquired, such as the category, style, color, material, type and style of the clothes, and the attribute information of the clothes to be matched is displayed; if the clothes to be matched cannot be identified, a prompt of reacquiring the image of the clothes to be matched is issued.

[0107] After the user selects the clothes to be matched, the TV can obtain the image of the clothes to be matched from the current dressing image, and obtain the target dressing image through the above-mentioned clothes matching recommendation method, and then display it in the interface.

[0108] The target dressing image includes the first type of target dressing image 304 and the second type of target dressing image 305 described above. The first type of target dressing image 304 and the second type of target dressing image 305 can be displayed according to a preset number ratio and / or a preset priority. For example, the total number of the first type of target dressing image 304 and the second type of target dressing image 305 can be limited to a set value, for example, 20 (only 3 are taken as an example in the figure) Figure 3 The first type of target dressing image 304 is preferred to the second type of target dressing image 305, and the number ratio between the first type of target dressing image 304 and the second type of target dressing image 305 is 2:1, that is, there are 2 first type of target dressing images and 1 second type of target dressing image.

[0109] Based on the displayed target dressing image, the user can perform further operations. For example, for the first type of target dressing image, the user can select a certain first type of target dressing image through the touch screen, voice interaction or remote control. According to the user's selection instruction, the storage location of the clothes matched in the first type of target dressing image can be displayed to facilitate the user to find; for the second type of target dressing image, the user can select a certain second type of target dressing image, and then display the purchase information of the matched clothes, such as purchase link, price, brand and other information.

[0110] Optionally, the user can also trigger the add to dressing image library button 307 in the interface to upload the current dressing image to the dressing image library to provide reference for other users to match clothes.

[0111] Optionally, the user can also add the clothes to be matched to the above-mentioned user clothes library through the add to user clothes library button 306. Specifically, the image, attribute information, user preference degree parameter and the like of the clothes to be matched can be added; in addition, the user can also view and manage the user clothes in the user clothes library. As shown in the figure, Figure 4 The user clothes library includes the image 311 of the user clothes, and the user can also classify the user clothes. The classification can include coat, top, bottom, suit, shoes and recently added, etc.; the user can also call the instruction of adding clothes from the display interface of the user clothes library, that is, by triggering the add clothes button 312, the image acquisition device is started to acquire and identify the image of the clothes, and the clothes are added to the user clothes library.

[0112] Figure 5A structural diagram of a clothes matching recommendation device is provided in the embodiment of the present application. The clothes matching recommendation device provided in the embodiment can execute the processing flow provided in the clothes matching recommendation method embodiment, as shown in Figure 5 The clothes matching recommendation device 500 includes an acquisition module 501, a matching module 502, a matching module 503, and an output module 504.

[0113] The acquisition module 501 is configured to acquire an image of clothes to be matched.

[0114] The matching module 502 is configured to match the image of the clothes to be matched with a pre-stored matching image in a matching image library, and acquire at least one alternative matching image, wherein the alternative matching image contains a first piece of clothes with a similarity higher than a first threshold to the image of the clothes to be matched.

[0115] The matching module 503 is configured to determine at least one target matching image according to the at least one alternative matching image and a user clothes library, wherein the user clothes library pre-stores images of user clothes.

[0116] The output module 504 is configured to output the at least one target matching image.

[0117] In a possible design, the matching module 503 is configured to:

[0118] acquire an image of a second piece of clothes in each of the alternative matching images except the first piece of clothes;

[0119] filter at least one target matching image from the at least one alternative matching image according to a similarity between the image of the second piece of clothes and an image of a user clothes in the user clothes library.

[0120] In a possible design, the target matching image includes a first type of target matching image and a second type of target matching image.

[0121] The matching module 503 is configured to:

[0122] if the image of the second piece of clothes in a certain alternative matching image has a similarity higher than a second threshold to an image of a first piece of user clothes in the user clothes library, the alternative matching image is taken as the first type of target matching image.

[0123] if the image of the second piece of clothes in a certain alternative matching image has a similarity not higher than the second threshold to an image of any piece of user clothes in the user clothes library, the alternative matching image is taken as the second type of target matching image.

[0124] In a possible design, the output module 504 is further configured to:

[0125] If the target dressing image is a first type of target dressing image, a storage position of the first user clothes corresponding to the target dressing image is determined, and a prompt message is output according to the storage position; and / or

[0126] If the target dressing image is a second type of target dressing image, purchase information of a second clothes included in the target dressing image is acquired, and the purchase information is displayed.

[0127] In a possible design, the dressing module 503 is configured to:

[0128] The at least one target dressing image is selected from the at least one candidate dressing image according to a similarity between an image of the second clothes and a user clothes image in the user clothes library, and a preset screening factor, the preset screening factor including at least one of weather information, clothes trend information, and user preference information.

[0129] In a possible design, the acquisition module 501 is configured to:

[0130] acquire, by an image acquisition apparatus, an image of the clothes to be dressed; or

[0131] receive a selection instruction of selecting, by a user, clothes to be dressed from the user clothes library, and acquire, according to the selection instruction, the image of the clothes to be dressed from the user clothes library.

[0132] In a possible design, the apparatus further includes an uploading module configured to:

[0133] acquire, by an image acquisition apparatus, an image of user clothes, and store the image into the user clothes library.

[0134] The dressing recommendation apparatus provided by the embodiment of the present application can be specifically used to execute the above Figures 1-2 The method embodiment is provided, and specific functions are not described herein again.

[0135] The clothes matching recommendation device provided by the embodiment of the present application comprises the following steps: obtaining an image of clothes to be matched; matching the image of the clothes to be matched with a pre-stored matching image in a matching image library to obtain at least one alternative matching image, the alternative matching image comprising a first piece of clothes with a similarity higher than a first threshold to the image of the clothes to be matched; determining at least one target matching image according to the at least one alternative matching image and a user clothes library, the image of the user clothes being pre-stored in the user clothes library; and outputting the at least one target matching image. The clothes to be matched are matched with the matching image library to obtain an alternative matching image comprising the same or similar clothes to the clothes to be matched, and then the target matching image is determined in combination with the user clothes library, so that the user can match clothes according to the target matching image, the user demand is met, and the user experience is improved.

[0136] Figure 6 The clothes matching recommendation device provided by the embodiment of the present application comprises the following steps: obtaining an image of clothes to be matched; matching the image of the clothes to be matched with a pre-stored matching image in a matching image library to obtain at least one alternative matching image, the alternative matching image comprising a first piece of clothes with a similarity higher than a first threshold to the image of the clothes to be matched; determining at least one target matching image according to the at least one alternative matching image and a user clothes library, the image of the user clothes being pre-stored in the user clothes library; and outputting the at least one target matching image. The clothes to be matched are matched with the matching image library to obtain an alternative matching image comprising the same or similar clothes to the clothes to be matched, and then the target matching image is determined in combination with the user clothes library, so that the user can match clothes according to the target matching image, the user demand is met, and the user experience is improved. Figure 6

[0137] Figure 6 The clothes matching recommendation device of the embodiment shown can be used to execute the technical solutions of the method embodiments, and the implementation principles and technical effects are similar, which will not be described here.

[0138] In addition, the embodiment also provides a computer readable storage medium, which stores a computer program, and the computer program is executed by a processor to implement the clothes matching recommendation method described in the above embodiments.

[0139] In several embodiments provided by the present application, it should be understood that the disclosed device and method can be implemented in other ways. For example, the device embodiments described above are only schematic. The division of the units is only a logical function division. There can be another division during actual implementation. For example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the displayed or discussed mutual couplings or direct couplings or communication connections can be indirect couplings or communication connections through some interfaces, devices or units, and can be electrical, mechanical or other forms.

[0140] ​The units described as separate components may or may not be physically separate, and the components displayed as units may or may not be physical units, i.e. may be located in one place, or may be distributed on multiple network units. Part or all of the units may be selected according to actual needs to achieve the purpose of the embodiment.

[0141] In addition, each functional unit in each embodiment of the embodiment of the application can be integrated in one processing unit, or each unit can exist physically, or two or more units can be integrated in one unit. The integrated unit can be realized in the form of hardware or in the form of hardware plus software functional unit.

[0142] The integrated unit realized in the form of software functional unit can be stored in a computer readable storage medium. The software functional unit is stored in a storage medium, including a plurality of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) or a processor to execute part of the steps of the method described in each embodiment of the application. The foregoing storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and various program code storage media.

[0143] Those skilled in the art can clearly understand that, for the convenience and brevity of description, only the division of the above functional modules is exemplified, and in actual application, the above functions can be completed by different functional modules according to needs, i.e. the internal structure of the device is divided into different functional modules to complete all or part of the functions described above. The specific working process of the device described above can refer to the corresponding process in the foregoing method embodiments, which will not be described here.

[0144] Finally, it should be pointed out that: the above embodiments are only used to illustrate the technical solutions of the embodiments of the application, and not to limit them; although the embodiments of the application have been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that: they can still modify the technical solutions recorded in the foregoing embodiments, or make equivalent replacement for part or all of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the scope of the technical solutions of the embodiments of the application.

Claims

1. A method of recommending clothes to wear, characterized by, The method comprises the following steps: acquiring images of clothes of a user through an image acquisition device and storing the images into a user clothes library; acquiring images of clothes to be matched through the image acquisition device; or receiving a selection instruction of the user selecting clothes to be matched from the user clothes library, and acquiring images of the clothes to be matched from the user clothes library according to the selection instruction; matching the images of the clothes to be matched with pre-stored dressing images in a dressing image library to obtain at least one alternative dressing image, the alternative dressing image containing a first piece of clothes with a similarity higher than a first threshold to the images of the clothes to be matched, and any of the pre-stored dressing images including at least two pieces of clothes; determining at least one target dressing image according to the at least one alternative dressing image and the user clothes library, the images of the user clothes being pre-stored in the user clothes library; outputting the at least one target dressing image; the step of determining at least one target dressing image according to the at least one alternative dressing image and the user clothes library comprises the following steps: acquiring images of second clothes other than the first piece of clothes in each of the alternative dressing images; screening at least one target dressing image from the at least one alternative dressing image according to similarities of the images of the second clothes to images of the user clothes in the user clothes library and a preset screening factor, wherein the preset screening factor comprises at least one of weather information, fashion trend information of clothes, and user preference information.

2. The method of claim 1, wherein, The target dressing image comprises a first type of target dressing image and a second type of target dressing image. The step of screening at least one target dressing image from the at least one alternative dressing image according to similarities of the images of the second clothes to images of the user clothes in the user clothes library comprises the following steps: if the similarity of the images of the second clothes in a certain alternative dressing image to the images of a first piece of user clothes in the user clothes library is higher than a second threshold, the alternative dressing image is taken as a first type of target dressing image; if the similarity of the images of the second clothes in a certain alternative dressing image to the images of any piece of user clothes in the user clothes library is not higher than the second threshold, the alternative dressing image is taken as a second type of target dressing image.

3. The method of claim 2, wherein, After the step of outputting the at least one target dressing image, the method further comprises the following steps: if the target dressing image is a first type of target dressing image, determining a storage location of the first piece of user clothes corresponding to the target dressing image, and outputting a prompt message according to the storage location; and / or if the target dressing image is a second type of target dressing image, acquiring purchase information of the second clothes contained in the target dressing image, and displaying the purchase information.

4. A clothes recommendation device, characterized by, The method comprises the following steps: an acquiring module, configured to acquire images of clothes of a user through an image acquisition device and store the images into a user clothes library; acquiring images of clothes to be matched through the image acquisition device; or receiving a selection instruction of the user selecting clothes to be matched from the user clothes library, and acquiring images of the clothes to be matched from the user clothes library according to the selection instruction; The matching module is configured to match the image of the clothes to be matched with a pre-stored dressing image in a dressing image library, and obtain at least one candidate dressing image, the candidate dressing image including a first piece of clothes with a similarity higher than a first threshold to the image of the clothes to be matched, and any pre-stored dressing image including at least two pieces of clothes; The matching module is configured to determine at least one target dressing image according to the at least one candidate dressing image and a user clothes library in which images of user clothes are pre-stored; The output module is configured to output the at least one target dressing image; The matching module is specifically configured to obtain an image of a second piece of clothes in each candidate dressing image except the first piece of clothes, and screen at least one target dressing image from the at least one candidate dressing image according to a similarity between the image of the second piece of clothes and an image of user clothes in the user clothes library and a preset screening factor, wherein the preset screening factor includes at least one of weather information, popular trend information of clothes, and user preference information.

5. A clothing recommendation device, characterized by, The computer program is stored in the memory and includes a computer program product; The processor is configured to run the computer program stored in the memory to implement the method in any one of claims 1-3. The computer program is stored in the memory and includes a computer program product; 6. A computer-readable storage medium, characterized in that, The computer program is stored in the memory and includes a computer program product; ​

Images