Smart wardrobe and clothes recommendation method thereof, computer readable storage medium and device

Abstract

The application discloses an intelligent wardrobe, a clothes recommendation method thereof, a computer readable storage medium and equipment. The clothes recommendation method comprises the following steps: obtaining the state of a wardrobe door; detecting user information and clothes information of clothes held by the user based on the state of the wardrobe door being opened, wherein the user information comprises hand movement and identity information, and the clothes information comprises clothes contour and clothes category; associating the hand movement with the clothes information to determine the state of the clothes; and determining the owner of the clothes according to the identity information and the clothes information and providing a clothes recommendation scheme when it is determined that the state of the clothes is to be taken out of the wardrobe. The clothes recommendation method of the application can ensure accurate recommendation results for the user identity and improve the wardrobe use experience by detecting the user information and the clothes information of the clothes held by the user and providing the clothes recommendation scheme according to the identity information and the clothes information when the clothes are taken out.

Description

Technical Field

[0001] This application relates to the field of Internet of Things (IoT) technology, and in particular to a method for recommending clothing in a smart wardrobe, a smart wardrobe, a computer-readable storage medium, and a computer device. Background Technology

[0002] With technological advancements and improved living standards, more and more smart home appliances are entering households, and intelligent technology is impacting every aspect of daily life. Smart homes are based on human-centered design, aiming to provide maximum convenience for homeowners and fostering harmonious interaction between people and furniture / objects. They represent a perfect integration of a meticulously designed intelligent system and a comprehensive home system.

[0003] The emergence of smart wardrobes has provided convenience for people to coordinate their clothing. However, existing smart wardrobes do not take into account that modern home wardrobes store the clothing of an entire family, and that family members may help retrieve clothes, potentially leading to incorrect recommendations. Additionally, there is the issue of clothes being forgotten due to prolonged periods of inactivity. Summary of the Invention

[0004] To address at least one of the aforementioned problems, a first aspect of this application provides a method for recommending clothing in a smart wardrobe, comprising:

[0005] The state of the wardrobe door is determined based on the obtained state information of the wardrobe door;

[0006] Based on the wardrobe door being open, the system detects user information and clothing information of the clothes the user is holding. User information includes hand gestures and identity information, while clothing information includes clothing outlines and clothing categories.

[0007] By associating hand gestures with clothing information, the condition of the clothing can be determined.

[0008] When the status of the clothing is determined to be out of the wardrobe, the owner of the clothing is identified based on the identity information and clothing information, and clothing recommendation options are provided.

[0009] In some optional embodiments, based on the wardrobe door being open, detecting user information and clothing information of the user's held clothing further includes:

[0010] Based on the wardrobe door being open, images of the area in front of the wardrobe are captured, and facial images, hand images, and clothing images are detected within the images.

[0011] Perform facial image recognition to obtain identity information;

[0012] Recognize hand images to obtain hand movements; and

[0013] The clothing outline is extracted from the clothing image and the clothing category is identified.

[0014] In some alternative embodiments,

[0015] When the status of the clothing is determined to be placed in the wardrobe, the clothing information is compared with the clothing information already stored in the wardrobe to obtain the clothing's entry information.

[0016] When clothing is placed in the closet for the first time, its attribute information is identified. The attribute information of clothing includes: the owner of the clothing, applicable weather, clothing style and applicable occasion.

[0017] Update the clothing and its attribute information to the memory.

[0018] In some optional embodiments, when the status of the clothing is determined to be that it has been taken out of the wardrobe, determining the owner of the clothing based on the identity information and clothing information and providing clothing recommendation solutions further includes:

[0019] When the status of the clothing is determined to be "removed from the wardrobe," the attribute information of the clothing is read from the memory based on the clothing information.

[0020] When the owner information in the clothing attribute information matches the identity information, the user is determined to be the actual user. The clothing list of the user is searched in the memory according to the identity information, and clothing matching schemes are recommended to the user according to the clothing attribute information.

[0021] When the owner information in the clothing's attribute information does not match the identity information, the user is determined to be an unauthorized user. Based on the owner information in the clothing's attribute information, the system searches the storage for the clothing list of the clothing owner and recommends clothing matching schemes based on the clothing's attribute information.

[0022] In some optional embodiments, after detecting user information and clothing information of the user's held clothing based on the wardrobe door being open, the method further includes:

[0023] By associating hand gestures with clothing information, the condition of the clothing can be determined.

[0024] Based on the condition that the clothing is not placed in the wardrobe and the clothing information of the held clothing is zero, obtain the weather information;

[0025] Provide clothing recommendations to users based on weather and identity information.

[0026] In some alternative embodiments,

[0027] When clothing is being placed in the closet for the first time, the current placement time is recorded as the first placement time of the clothing. When clothing is not being placed in the closet for the first time, the status of the clothing is marked as "placed".

[0028] In some optional embodiments, after associating hand gestures with clothing information and determining the state of the clothing, the method further includes:

[0029] When the status of the clothing is determined to be removed from the wardrobe, mark the clothing as temporarily removed;

[0030] The system detects when the wardrobe door is closed. If no clothing is detected being placed inside before the door closes, the clothing is marked as retrieved in the memory, the current time is recorded as the last time the clothing was used, and the usage count is incremented by one.

[0031] In some optional embodiments, after determining the state of the wardrobe door based on the acquired wardrobe door state information, the method further includes:

[0032] Based on the fact that the wardrobe door is open, obtain voice query information;

[0033] The system retrieves keywords from voice search results and recommends clothing accordingly.

[0034] and / or

[0035] After determining the state of the wardrobe door based on the acquired wardrobe door state information, the method further includes:

[0036] Based on the fact that the wardrobe door is open, an image of the user in front of the wardrobe is captured and displayed in the display unit;

[0037] User image recognition to obtain user identity information;

[0038] Based on the user's identity information, search the memory for the user's clothing items;

[0039] In response to user actions on the display unit, the selected clothing is overlaid on the user image.

[0040] A second aspect of this application provides a smart wardrobe, comprising:

[0041] The sensing unit acquires the status of the wardrobe door;

[0042] The processing unit is configured as follows:

[0043] Determine the status of the wardrobe door based on its status information;

[0044] Based on the wardrobe door being open, the system detects user information and the clothing information of the clothes the user is holding. The user information includes hand gestures and identity information, while the clothing information includes clothing outlines and clothing categories.

[0045] By associating hand gestures with clothing information, the condition of the clothing can be determined.

[0046] When the status of the clothing is determined to be out of the wardrobe, the owner of the clothing is identified based on the identity information and clothing information, and clothing recommendation options are provided.

[0047] A third aspect of this application provides a computer-readable storage medium having a computer program stored thereon that, when executed by a processor, implements the method described above.

[0048] A fourth aspect of this application provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor.

[0049] The processor executes the program to implement the method described above.

[0050] The beneficial effects of this application are as follows:

[0051] This application addresses existing problems by providing a clothing recommendation method for a smart wardrobe, a smart wardrobe itself, a computer-readable storage medium, and a computer device. Specifically, the clothing recommendation method for the smart wardrobe, after obtaining the wardrobe door status, detects user information and the clothing information held by the user. When the clothing is in the "removed" state, it provides clothing recommendation schemes based on the user's identity and clothing information. This ensures accurate recommendations tailored to the owner of the clothing, improves the user experience of the wardrobe, and has broad application potential. Attached Figure Description

[0052] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0053] Figure 1 An exemplary flowchart illustrating a clothing recommendation method for a smart wardrobe according to an embodiment of this application is shown.

[0054] Figure 2 An exemplary block diagram of a smart wardrobe that applies a clothing recommendation method according to an embodiment of this application is shown;

[0055] Figure 3 A detailed flowchart of a clothing recommendation method according to an embodiment of this application is shown;

[0056] Figure 4 A flowchart illustrating a clothing recommendation method according to another embodiment of this application is shown;

[0057] Figure 5 A flowchart illustrating a clothing recommendation method according to another embodiment of this application is shown; and

[0058] Figure 6 This is a schematic diagram of the structure of a computer device according to an embodiment of this application. Detailed Implementation

[0059] To more clearly illustrate this application, the following description, in conjunction with preferred embodiments and accompanying drawings, further clarifies the application. Similar components in the drawings are indicated by the same reference numerals. Those skilled in the art should understand that the specific description below is illustrative rather than restrictive and should not be construed as limiting the scope of protection of this application.

[0060] It should be noted that in the description of this application, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes the element.

[0061] Reference Figure 1 As shown, one embodiment of this application provides a clothing recommendation method for a smart wardrobe, including:

[0062] Step S1: Determine the status of the wardrobe door based on the obtained status information of the wardrobe door;

[0063] Step S2: Based on the wardrobe door being open, detect user information and clothing information of the clothes held by the user. User information includes hand gestures and identity information, and clothing information includes clothing outline and clothing category.

[0064] Step S3: Associate hand movements with clothing information to determine the condition of the clothing;

[0065] Step S4: When the status of the clothing is determined to be taken out of the wardrobe, the owner of the clothing is identified based on the identity information and clothing information, and clothing recommendation solutions are provided.

[0066] In this embodiment, after obtaining the cabinet door status, the system detects user information and the clothing information of the user's clothes. When the clothing is in the "take out" state, the system provides clothing recommendation solutions based on the user's identity and clothing information. This ensures that accurate recommendations are given based on the identity of the person who owns the clothing, thereby improving the user experience of the wardrobe.

[0067] To better understand the clothing recommendation method in this application, firstly, in conjunction with... Figure 2 A schematic structural diagram illustrating a smart wardrobe that applies this clothing recommendation method.

[0068] like Figure 2 As shown, the smart wardrobe 1 includes: a sensing unit 11, an image acquisition unit 12, a processing unit 13, and a display unit 14.

[0069] The sensing unit 11 is used to sense the angle information of the wardrobe door of the smart wardrobe to determine whether the wardrobe door is open. Optionally, the sensing unit 11 can be an angle sensor, camera, or other device capable of acquiring the angle of the wardrobe door. The image acquisition unit 12 is used to acquire images in front of the smart wardrobe, such as a user image in front of the smart wardrobe after the wardrobe door is open. The image acquisition unit 12 can be a camera installed on the wardrobe door or top of the wardrobe. In the embodiments of this application, the user's head image acquired by the image acquisition unit 12 should include the face area and the hand area, and the acquisition range should be able to capture images of short children and tall adult men. The processing unit 13 is electrically connected to the sensing unit 11 and the image acquisition unit 12 to receive the angle information of the wardrobe door sensed by the sensing unit 11 and the image acquired by the image acquisition unit 12, and to process, analyze, and judge the received angle information and images, and provide clothing recommendations. The processing unit 13 is also electrically connected to the display unit 14, and is used to display clothing recommendation schemes using the display unit 14, such as displaying images of recommended clothing. This process can be achieved by the processing unit 13 sending clothing control information and clothing image information to the display unit 14. In addition... Figure 2 The smart wardrobe 1 shown may further include a communication unit and / or a memory, for connecting to a cloud server via the communication unit to receive weather information, synchronize time display, etc., and for storing clothing records in the wardrobe via the memory. Alternatively, clothing records and other information can also be stored in a cloud memory. In this case, updated clothing records and other data can be read or written to the cloud memory via communication between the communication unit and the cloud memory. It should be noted that when the smart wardrobe 1 includes a communication unit, this communication unit can be a unit connected to the Internet or a local area network via wired or wireless means; the specific communication method is not limited in this application.

[0070] The following is combined with Figure 2 and Figure 3 This application describes a method for recommending clothing in a smart wardrobe, based on one embodiment. Figure 3 This is a detailed flowchart of a clothing recommendation method according to an embodiment of this application.

[0071] In step S1, the state of the wardrobe door is determined based on the obtained state information of the wardrobe door.

[0072] Specifically, when a user needs to use the smart wardrobe, the user stands in front of the wardrobe and opens the wardrobe door. The user's identity could be, for example, the female head of the household. The sensing unit 11 senses the angle information of the wardrobe door. Specifically, for example, if the sensing unit 11 is an angle sensor, then the sensing unit 11 directly senses the angle between the wardrobe door and the wardrobe body, and sends the sensed angle value as angle information to the processing unit 13. The processing unit 13 determines whether the wardrobe door is open based on the acquired angle information. For example, when the angle between the wardrobe door and the wardrobe body is greater than or equal to a preset value, the wardrobe door is determined to be open; if it is less than the preset value, the wardrobe door is not open. This application does not aim to limit the specific value of the preset value; it can be determined according to the specific wardrobe model and size.

[0073] In step S2, based on the fact that the wardrobe door is open, user information and clothing information of the clothes held by the user are detected. The user information includes hand gestures and identity information, and the clothing information includes clothing outline and clothing category.

[0074] Specifically, when processing unit 13 determines that the wardrobe door is open (corresponding to...) Figure 3 When “Y” is displayed, the processing unit 13 acquires the image acquired by the image acquisition unit 12, and detects the user's user information and the clothing information of the clothing held by the user based on the image.

[0075] More specifically, if the image acquisition unit 12 is a camera installed on the top of the wardrobe, and the processing unit 13 determines that the wardrobe door is open, it controls the image acquisition unit 12 to capture images or videos of the area in front of the wardrobe and acquire the images. The processing unit 13 divides the acquired images into regions, detecting and classifying them into face images, hand images, and clothing images.

[0076] For facial images, processing unit 13 performs identity recognition to obtain identity information. Specifically, facial feature information is extracted through feature detection, and this facial feature information is compared with the facial features of each member of the user's family stored in the memory to determine the user's identity information. In this example, the facial feature comparison determines that the user is the female head of the household. Those skilled in the art will understand that when using the smart wardrobe for the first time, the smart wardrobe can provide a user identity information input setting. The user can input the facial images of each family member through image acquisition unit 12 and bind their identities, and then store them in the memory for subsequent identity information detection. This will not be elaborated further here.

[0077] For hand images, processing unit 13 recognizes the hand images and obtains hand movements. Specifically, the images acquired by image acquisition unit 12 can be multiple images that change over time. Processing unit 13 acquires the hand region in these images, detects changes in the hand region, and determines the hand movement. The hand movement can be the direction of hand movement, such as moving towards the wardrobe, moving away from the wardrobe, or moving away from the wardrobe.

[0078] For clothing images, processing unit 12 extracts the clothing outline from the clothing image and identifies the clothing category. Specifically, processing unit 13 acquires the clothing outline and identifies the clothing category based on the clothing image in the clothing area. In the embodiments of this application, the clothing category indicates the age group and gender to which the clothing is suitable, such as whether the clothing is women's or men's, adult or children's. For example, the clothing is an adult women's style.

[0079] It should be noted that those skilled in the art should understand that when detecting clothing information of an image user's clothing, there are two situations: the presence of clothing and the absence of clothing. When there is no clothing information, it means that the result obtained when detecting clothing information is none.

[0080] Therefore, in the embodiments of this application, user information includes hand gestures and identity information, and clothing information includes clothing outline and clothing category.

[0081] In step S3, the hand movements are associated with the clothing information to determine the state of the clothing.

[0082] Specifically, the hand in the hand image is associated with clothing information. More specifically, hand movements can also be associated with clothing information to determine whether the clothing is in the state of being taken out of the wardrobe (i.e., Y) or not (i.e., N). For example, if the hand movement is determined to be moving towards the wardrobe and clothing information is detected, the clothing's state can be determined to be placed in the wardrobe; if the hand movement is determined to be not moving away from the wardrobe, the state can be determined to be not placed in the wardrobe.

[0083] Additionally, for items not placed in the wardrobe, when a user stands in front of the smart wardrobe and just opens the door, they will not be holding any clothes for a period of time. In other words, there is an intermediate state of not holding any clothes when the wardrobe is first opened.

[0084] Considering that users may not know the current weather conditions or what clothing is appropriate, and in order to provide convenience so that users do not have to check the weather or think about what to wear, in the embodiments of this application, more preferably, by utilizing the aforementioned intermediate state, clothing recommendations are provided to the user when the user opens the wardrobe but has not yet taken out any clothes.

[0085] Specifically, refer to Figure 4 As shown, after detecting user information and the clothing information of the user's clothes based on the wardrobe door being open, the clothing recommendation method further includes: in step S3', associating hand movements with clothing information to determine the status of the clothing; in step S4', obtaining weather information based on the status of the clothing not being placed in the wardrobe and the clothing information of the held clothing being none; and in step S5', providing clothing recommendation solutions to the user based on the weather information and identity information.

[0086] To further enhance the user experience, embodiments of this application also consider providing voice services, namely, recommending clothing based on the user's voice query information. After determining the wardrobe door's status based on the acquired wardrobe door status information, the method further includes: obtaining voice query information based on the wardrobe door's open status; and extracting keywords from the voice query information and recommending clothing. Specifically, refer to... Figure 3 As shown, the recommendation service can be set up after determining the status of the clothing, that is, when the status of the clothing is determined to be not placed in the closet, the voice query information is obtained through a sound collection unit such as a microphone, such as "What should Dabao wear to the park today?"; the processing unit 13 obtains the keywords "Dabao", "today" and "park" from the voice query information, and searches the memory for clothing recommendations suitable for "Dabao" to wear to "park" today based on the above keywords. Of course, since the keywords involve time, weather information can also be obtained and recommendations can be given, which will not be elaborated here.

[0087] In addition, it should be noted that this application does not limit the specific steps and locations of the voice query recommendation service. In fact, the above recommendation service can be provided by receiving voice information after the wardrobe door is detected to be open.

[0088] Specifically, in this example, when the user opens the wardrobe door, the processing unit 13 determines that the wardrobe door is open. After detecting the user information and the clothing information of the clothes held by the user, it associates the hand movement with the clothing information. When the detected hand movement is moving towards the wardrobe, it determines that the clothing is not placed in the wardrobe. At the same time, if the clothing information of the clothes held is not available, it can be determined that the user is not in the "not placed in" state and has not yet taken out the clothes, and the weather information is obtained. That is to say, if the user is not putting clothes in, after the user opens the wardrobe door, the smart wardrobe connects to the cloud server through the communication unit to obtain the current weather information and sends it to the processing unit 13. For example, if the current weather is "cloudy, temperature is 13℃", the processing unit 13 determines that the current weather is suitable for wearing spring and autumn clothing based on the obtained weather information. The processing unit 13 reads the clothing stored in the memory corresponding to the user based on the user's identity information and provides the user with clothing recommendations based on the clothing of the user that corresponds to the current weather. As for the specific recommendation method, as an example, the processing unit 13 can send an image of the user's clothing that corresponds to the weather to the display unit 14 for display, so as to provide a recommendation reference before the user takes the clothes out of the wardrobe, thereby improving the user experience of the smart wardrobe.

[0089] Furthermore, referring to Figure 3 and Figure 5 As shown, in step S4, when the status of the clothing is determined to be "taken out of the wardrobe", the owner of the clothing is determined based on the identity information and clothing information, and a clothing recommendation plan is provided.

[0090] Specifically, although the smart wardrobe 1 provides clothing recommendations based on the weather when it determines that the clothes are not placed in the wardrobe after the wardrobe door is opened, this is not always what the user needs. One scenario is that the user is not retrieving clothes for themselves, so the smart wardrobe's personalized clothing recommendations may be inappropriate for them. Another scenario is that although the user is retrieving clothes for themselves, and the smart wardrobe 1 has provided various clothing recommendations matching the current weather conditions, it has not provided specific outfit suggestions. The user may choose an item based on these suggestions but need additional styling options for dressing. Yet another scenario is that the user is retrieving clothes for themselves, and the smart wardrobe 1 has provided clothing recommendations matching the current weather conditions, but the user wants to sacrifice warmth or choose clothing for special purposes and occasions regardless of the weather.

[0091] Considering at least the above three situations, the current clothing recommendation scheme based solely on weather conditions cannot fully meet the needs of users. In the embodiments of this application, the smart wardrobe makes further recommendations.

[0092] More specifically, in step S41, when the status of the clothing is determined to be "taken out of the wardrobe," that is, when the user opens the wardrobe door, the processing unit 13 determines, based on the association between the hand movement and the clothing information, that the hand movement is moving away from the wardrobe while the hand is associated with the clothing information, thus determining that the status of the clothing is "taken out of the wardrobe." At this time, the attribute information of the clothing is read from the memory based on the clothing information. This attribute information is the attribute information that the smart wardrobe 1 identifies and stores when the user first puts the clothing into the smart wardrobe 1. The specific process will be described later. The attribute information of the clothing includes: the owner information of the clothing, the applicable weather, the style of the clothing, and the appropriate occasion. For example, for the female homeowner, if she takes out a white bodycon skirt, the processing unit 13 will further extract the features of the clothing based on the clothing image captured in step S2, and further identify it based on the extracted features combined with the attribute information and features stored in the memory, determining that the skirt belongs to the female homeowner, the style of the clothing is a bodycon skirt, the color is, for example, white, suitable for weather around 15°C, and suitable for business attire. Of course, the information about clothing attributes is not limited to the above items, but it is best to include the above items in order to provide better clothing matching solutions.

[0093] In step S42, when the owner information in the clothing attribute information matches the identity information, the user is determined to be the actual user. The clothing list of the user is searched in the memory according to the identity information, and clothing matching schemes are recommended to the user according to the clothing attribute information.

[0094] Specifically, the processing unit 13 compares the owner information of the clothing with the detected user identity information. When they match, it can be determined that the user is picking up clothing for themselves. The processing unit then searches the memory for all clothing items matching the identity information and recommends clothing items that match the attributes of the currently retrieved clothing. For example, the memory may store multiple matching options suitable for the white bodycon skirt, such as a light-colored shirt with stockings, a light-colored shirt with a short blazer and stockings, and a light-colored printed shirt with a cardigan and stockings. The processing unit 13 displays these matching options as images on the display unit 14 to facilitate user selection and improve user experience.

[0095] Alternatively, as a clothing combination recommendation, the suitable temperature for the outfit can be displayed below the recommendation or in other locations so that users can make a reasonable choice based on the current weather conditions. This will not be elaborated further here.

[0096] Next, in step S43, when the owner information in the clothing attribute information does not match the identity information, it is determined that the user is not the actual user. Based on the owner information in the clothing attribute information, the clothing list of the clothing owner is searched in the memory, and clothing matching schemes are recommended based on the clothing attribute information.

[0097] Specifically, the processing unit 13 compares the owner information of the retrieved clothing with the detected user's identity information. When the two do not match, it can be determined that the user is retrieving clothing for someone else in the household. The processing unit then searches the memory for all clothing items with the same owner information and recommends clothing combinations that match the attributes of the retrieved item. For example, if the user is the female homeowner and the retrieved item is a men's black jacket, and the owner information of the men's black jacket is identified as the male homeowner, the processing unit 13 searches the processor for all of the male homeowner's clothing items and provides clothing combination recommendations based on multiple combinations stored in the memory that match the black jacket. For example, dark casual pants, a sweater, and the men's black jacket could be used as clothing combination options, and these combinations could be displayed as images on the display unit 14 to facilitate user selection and improve the user experience.

[0098] Similarly, as a clothing outfit recommendation, the suitable temperature for that outfit can be displayed below the corresponding recommendation or in other locations so that users can make a reasonable choice based on the current weather conditions. This will not be elaborated further here.

[0099] The above settings detect user and clothing information when the wardrobe door is opened, associate hand gestures with clothing information to determine the status of the clothing, and when the status of the clothing is determined to be taken out of the wardrobe, provide clothing recommendations to the user based on user and clothing information. This can take into account the specific user who takes out the clothing when recommending clothing, thereby improving the accuracy of clothing recommendations and enhancing the user experience.

[0100] Considering that wardrobes typically contain a large number of clothes, but users only think about wearing a small number, many items purchased earlier or rarely worn are easily forgotten in daily outfits. In other words, frequently worn items often indicate higher user preference, and these items should be prioritized or highlighted in clothing recommendations. Therefore, the frequency of item retrieval and usage becomes a crucial benchmark.

[0101] In an optional embodiment, the frequency of use of each piece of clothing taken out is statistically analyzed.

[0102] Specifically, after associating hand movements with clothing information and determining the state of the clothing, the method further includes:

[0103] When the status of clothing is determined to be taken out of the wardrobe, the clothing is temporarily taken out. For example, the memory can set a storage area for each stored clothing to record the number of times it has been taken out, take_times. Therefore, the number of times the clothing has been taken out, take_times, can be incremented by one as a temporary take-out mark.

[0104] The system detects when the wardrobe door closes. If no clothing is detected being placed inside before the door closes, the clothing's status in the memory is marked as retrieved. The current time is recorded as the last time the clothing was used, and the usage count is incremented. For example, the memory can set a storage area for each stored garment to record the usage count (use_times). Therefore, the usage count (use_times) of the garment can be incremented as a retrieved flag. Specifically, if take_times is "1" when the door closes, the usage count (use_times) is incremented. Conversely, if the same garment is detected being placed inside before the door closes, it is determined that the garment was not actually retrieved and used. The retrieval count (take_times) is decremented, and the retrieved status is canceled. At this point, take_times is "0", indicating that the garment was neither retrieved nor placed inside. Furthermore, if the garment is detected being placed inside immediately after the door opens before it closes, it is directly marked as placed inside. Those skilled in the art should understand that only one of the three flags—retrieval flag, temporary retrieval flag, and placement flag—is retained in the garment's retrieved status. Furthermore, in this embodiment, the current time does not need to be strictly limited to a specific moment; any time within the current clothing retrieval process is acceptable. Typically, for convenience, the time when the processing unit 13 determines that the clothing has not been returned after the wardrobe door is closed can be counted as the current time. Additionally, when recommending clothing, clothing with a take_times of 1 is not recommended; when clothing is first placed in the wardrobe, take_times is 0.

[0105] In addition, considering the frequency of use, when clothes are taken out for the first time after the door is opened, the system will identify the clothes belonging to the current owner (e.g., the female homeowner) that have been used the least, taken out the least, and whose last use was more than a preset threshold time_thr. The system will then remind the current user that these clothes may have been forgotten or are no longer needed, thus improving the flow and effectiveness of the clothes in the smart wardrobe 1.

[0106] In another optional embodiment, in order to further improve the user experience and reduce the trouble of users frequently dressing and undressing, the embodiments of this application utilize the display unit 14 to provide a dressing mirror function.

[0107] Specifically, the display unit 14 installed on the wardrobe door can serve as a virtual dressing mirror. Specifically, after determining the state of the wardrobe door based on the acquired state information, the method further includes:

[0108] Based on the wardrobe door being open, capture the image of the user in front of the wardrobe and display it in the display unit;

[0109] User image recognition to obtain user identity information;

[0110] Based on the user's identity information, search the memory for the user's clothing items;

[0111] In response to user actions on the display unit, the selected clothing is overlaid on the user image.

[0112] In this specific example, after opening the wardrobe door, the user can stand in front of the wardrobe and face the camera installed on the wardrobe door. Clicking a specific button on the display unit 14 or a specific icon on the touchscreen will activate the virtual fitting mirror function. At this time, the processing unit 13 acquires the user's image in front of the wardrobe through the image acquisition unit 12 and displays it on the display unit 14; it identifies the user's identity information based on the user image and searches for and displays the user's clothing items based on that information. The user can drag and select from currently recommended clothing images or choose their preferred clothing from the storage. In response to these user actions, the processing unit 13 overlays the clothing onto the user's image for a simulated try-on.

[0113] This setting can effectively improve the user's fitting experience and increase efficiency.

[0114] In another optional embodiment, the clothing recommendation method of this application also provides an inclusion management function.

[0115] Optionally, refer to Figure 3 As shown, when new clothes are added, the smart wardrobe performs an initial data entry, specifically:

[0116] When the status of the clothing is determined to be placed in the wardrobe, the clothing information is compared with the clothing information already stored in the wardrobe to obtain the clothing's entry information.

[0117] When clothing is placed in the closet for the first time, its attribute information is identified. This attribute information includes: the owner of the clothing, applicable weather, clothing style, and suitable occasion. For example, by extracting features from the clothing image, various attribute information of the clothing is obtained and compared with all clothing attribute information stored in the memory. If no information about the clothing being placed in the closet is found in the memory, it is determined to be clothing placed in the closet for the first time. For example, the attribute information includes: the owner is the male or female head of the household, a boy, or a girl; the applicable weather is autumn, winter, 10℃ to 15℃, or below 0℃; the clothing style is a trench coat, T-shirt, dress, skirt, jacket, or shirt; and the suitable occasion is running, leisure, business, or shopping. If any of the attribute information does not match the record in the memory, it can be determined that the clothing is being placed in the closet for the first time.

[0118] Update the clothing and its attribute information to the memory.

[0119] In addition, considering that some neutral clothing may have errors in identifying the owner information when identifying the clothing attribute information, and may also have errors in identifying the style of clothing, the embodiments of this application also provide a manual modification function. When the user confirms that the attribute information is identified incorrectly, he / she can operate on the display unit 14 to complete the manual modification.

[0120] In addition to managing clothing leaving the closet, the status management of each time clothing is put back into the closet should also be considered. Specifically, when clothing is being put into the closet for the first time, the current time of placement should be recorded as the first time the clothing was put in. When clothing is not being put into the closet for the first time, the status of the clothing should be marked as "put in".

[0121] This setting allows for a clear record of how each garment is stored in the closet, providing accurate results when determining the frequency of use and retrieval of clothing, thus facilitating subsequent suggestions for discarding items and recommending new garments.

[0122] Corresponding to the clothing recommendation method of the smart wardrobe mentioned above, continue to combine Figure 2 As shown, one embodiment of this application also provides a smart wardrobe, including:

[0123] Sensing unit 11 acquires the status of the wardrobe door;

[0124] Processing unit 13 is configured as follows:

[0125] The state of the wardrobe door is determined based on the state information of the wardrobe door.

[0126] Based on the fact that the wardrobe door is open, user information and clothing information of the clothes held by the user are detected. The user information includes hand gestures and identity information, and the clothing information includes clothing outline and clothing category.

[0127] The hand gestures are associated with the clothing information to determine the state of the clothing;

[0128] When the status of the clothing is determined to be taken out of the wardrobe, the owner of the clothing is identified based on the identity information and the clothing information, and a clothing recommendation solution is provided.

[0129] In addition to the above units, the smart wardrobe may also include an image acquisition unit 12, a communication unit (not shown), a sound acquisition unit (not shown), etc. The specific functions of these units have been described in detail in the description of the above clothing recommendation method, and will not be repeated here.

[0130] In this embodiment, the state of the wardrobe door is obtained through a sensing unit, and after obtaining the wardrobe door state through a processing unit, user information and clothing information of the user are detected. When the clothing is in the "removed clothing" state, clothing recommendation schemes are provided based on the user's identity information and clothing information. This ensures accurate recommendation results based on the identity of the clothing owner, improves the user experience of the wardrobe, and has broad applications. The specific implementation method of this embodiment is the same as the previous embodiment, and will not be repeated here.

[0131] Another embodiment of this application provides a computer-readable storage medium having a computer program stored thereon. When executed by a processor, the program performs the following: determining the state of the wardrobe door based on acquired wardrobe door state information; detecting user information and clothing information of the clothing held by the user, based on the wardrobe door being open, the user information including hand gestures and identity information, and the clothing information including clothing outlines and clothing categories; associating the hand gestures with the clothing information to determine the state of the clothing; and when the state of the clothing is determined to be that it has been taken out of the wardrobe, determining the owner of the clothing based on the identity information and the clothing information and providing clothing recommendation solutions.

[0132] In practical applications, a computer-readable storage medium can take any combination of one or more computer-readable media. A computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. A computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of computer-readable storage media (a non-exhaustive list) include: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this embodiment, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.

[0133] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. Computer-readable signal media may also be any computer-readable medium other than computer-readable storage media, capable of sending, propagating, or transmitting programs for use by or in connection with an instruction execution system, apparatus, or device.

[0134] Program code contained on a computer-readable medium may be transmitted using any suitable medium, including but not limited to wireless, wire, optical fiber, RF, etc., or any suitable combination thereof.

[0135] Computer program code for performing the operations of this application can be written in one or more programming languages ​​or a combination thereof. Programming languages ​​include object-oriented programming languages—such as Java, Smalltalk, and C++—as well as conventional procedural programming languages—such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0136] like Figure 6As shown, another embodiment of this application provides a structural schematic diagram of a computer device. Figure 6 The computer device 10 shown is merely an example and should not impose any limitation on the functionality and scope of use of the embodiments of this application.

[0137] like Figure 6 As shown, the computer device 10 is presented in the form of a general-purpose computing device. The components of the computer device 10 may include, but are not limited to: one or more processors or processor units 16, system memory 28, and bus 18 connecting different system components (including system memory 28 and processor unit 16).

[0138] Bus 18 represents one or more of several bus architectures, including a memory bus or memory controller, a peripheral bus, a graphics acceleration port, a processor, or a local bus using any of the various bus architectures. For example, these architectures include, but are not limited to, the Industry Standard Architecture (ISA) bus, the Micro Channel Architecture (MAC) bus, the Enhanced ISA bus, the Video Electronics Standards Association (VESA) local bus, and the Peripheral Component Interconnect (PCI) bus.

[0139] Computer device 10 typically includes a variety of computer system readable media. These media can be any available media that can be accessed by computer device 10, including volatile and non-volatile media, removable and non-removable media.

[0140] System memory 28 may include computer system readable media in the form of volatile memory, such as random access memory (RAM) 30 and / or cache memory 32. Computer device 10 may further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, storage system 34 may be used to read and write non-removable, non-volatile magnetic media (…). Figure 6 Not shown; usually referred to as a "hard drive"). Although Figure 6 Not shown, a disk drive for reading and writing to a removable non-volatile disk (e.g., a "floppy disk") and an optical disk drive for reading and writing to a removable non-volatile optical disk (e.g., a CD-ROM, DVD-ROM, or other optical media) may be provided. In these cases, each drive may be connected to bus 18 via one or more data media interfaces. Memory 28 may include at least one program product having a set (e.g., at least one) of program modules configured to perform the functions of the embodiments of this application.

[0141] A program / utility 40 having a set (at least one) of program modules 42 may be stored, for example, in memory 28. Such program modules 42 include, but are not limited to, an operating system, one or more application programs, other program modules, and program data. Each or some combination of these examples may include an implementation of a network environment. Program modules 42 typically perform the functions and / or methods described in the embodiments of this application.

[0142] Computer device 10 can also communicate with one or more external devices 15 (e.g., keyboard, pointing device, display 24, etc.), and with one or more devices that enable a user to interact with the computer device 10, and / or with any device that enables the computer device 10 to communicate with one or more other computing devices (e.g., network card, modem, etc.). This communication can be performed through input / output (I / O) interface 22. Furthermore, computer device 10 can also communicate with one or more networks (e.g., local area network (LAN), wide area network (WAN), and / or public networks, such as the Internet) via network adapter 20. Figure 6 As shown, network adapter 20 communicates with other modules of computer device 10 via bus 18. It should be understood that, although... Figure 6 As not shown, other hardware and / or software modules may be used in conjunction with computer device 10, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0143] The processor unit 16 executes various functional applications and data processing by running programs stored in the system memory 28, such as implementing the clothing recommendation method for the smart wardrobe provided in the embodiments of this application.

[0144] This application addresses existing problems by providing a clothing recommendation method for a smart wardrobe, a smart wardrobe itself, a computer-readable storage medium, and a computer device. Specifically, the clothing recommendation method for the smart wardrobe, after obtaining the wardrobe door status, detects user information and the clothing information held by the user. When the clothing is in the "removed" state, it provides clothing recommendation schemes based on the user's identity and clothing information. This ensures accurate recommendations tailored to the owner of the clothing, improves the user experience of the wardrobe, and has broad application potential.

[0145] Obviously, the above embodiments of this application are merely examples for clearly illustrating this application, and are not intended to limit the implementation of this application. For those skilled in the art, other variations or modifications can be made based on the above description. It is impossible to exhaustively list all implementation methods here. Any obvious variations or modifications derived from the technical solutions of this application are still within the protection scope of this application.

Claims

1. A method for recommending clothing in a smart wardrobe, characterized in that, include: The state of the wardrobe door is determined based on the acquired state information of the wardrobe door; Based on the fact that the wardrobe door is open, user information and clothing information of the clothes held by the user are detected. The user information includes hand gestures and identity information, and the clothing information includes clothing outline and clothing category. The hand gestures are associated with the clothing information to determine the state of the clothing; When the status of the clothing is determined to be "removed from the wardrobe," the attribute information of the clothing is read from the memory based on the clothing information. When the owner information in the attribute information of the clothing matches the identity information, the user is determined to be the actual user. The user's clothing list is searched in the memory according to the identity information, and clothing matching schemes are recommended to the user according to the attribute information of the clothing. When the owner information in the clothing's attribute information does not match the identity information, the user is determined to be an unauthorized user. Based on the owner information in the clothing's attribute information, the system searches the storage for the clothing list of the clothing owner and recommends clothing matching schemes based on the clothing's attribute information. The step of detecting user information and clothing information of the user based on the wardrobe door being open further includes: Based on the fact that the wardrobe door is open, an image of the area in front of the wardrobe is captured, and facial images, hand images, and clothing images are detected in the image; The facial image is used for identity recognition to obtain the identity information; The hand image is recognized to obtain the hand movement; and The outline of the clothing is extracted from the clothing image, and the clothing category is identified.

2. The clothing recommendation method according to claim 1, characterized in that, When the status of the clothing is determined to be placed in the wardrobe, the clothing information is compared with the clothing information already stored in the wardrobe to obtain the clothing's entry information. When the clothing is placed in the cabinet for the first time, the attribute information of the clothing is identified. The attribute information of the clothing includes: the owner information of the clothing, applicable weather, clothing style and applicable occasion; Update the clothing and its attribute information to the memory.

3. The clothing recommendation method according to claim 1, characterized in that, After detecting user information and clothing information of the user's belongings based on the wardrobe door being open, the method further includes: The hand gestures are associated with the clothing information to determine the state of the clothing; Based on the fact that the clothing is not placed in the wardrobe and the clothing information of the held clothing is zero, obtain the weather information; Based on the weather information and the user's identity information, the system provides clothing recommendations.

4. The clothing recommendation method according to claim 2, characterized in that, When the garment is being placed in the closet for the first time, the current placement time is recorded as the first placement time of the garment. When the garment is not being placed in the closet for the first time, the status of the garment is marked as "placed".

5. The clothing recommendation method according to claim 1, characterized in that, After associating the hand movements with the clothing information and determining the state of the clothing, the method further includes: When the status of the clothing is determined to be removed from the wardrobe, the clothing is temporarily marked as removed. If the wardrobe door is closed and no clothing is detected being placed inside before the door closes, the clothing is marked as removed from the memory, the current time is recorded as the last time the clothing was used, and the usage count is incremented by one.

6. The clothing recommendation method according to claim 1, characterized in that, After determining the state of the wardrobe door based on the acquired wardrobe door state information, the method further includes: Based on the fact that the wardrobe door is open, obtain voice query information; Keywords are extracted from the voice query information to recommend clothing items. and / or After determining the state of the wardrobe door based on the acquired wardrobe door state information, the method further includes: Based on the fact that the wardrobe door is open, an image of the user in front of the wardrobe is captured and displayed in the display unit; The user's identity information is obtained by recognizing the user's image; Based on the identity information, search the memory for the user's clothing items; In response to the user's operation on the display unit, the selected clothing is overlaid on the user image.

7. A smart wardrobe, characterized in that, include: The sensing unit acquires the status of the wardrobe door; The processing unit is configured as follows: The state of the wardrobe door is determined based on the state information of the wardrobe door. Based on the fact that the wardrobe door is open, user information and clothing information of the clothes held by the user are detected. The user information includes hand gestures and identity information, and the clothing information includes clothing outline and clothing category. The hand gestures are associated with the clothing information to determine the state of the clothing; When the status of the clothing is determined to be "removed from the wardrobe," the attribute information of the clothing is read from the memory based on the clothing information. When the owner information in the attribute information of the clothing matches the identity information, the user is determined to be the actual user. The user's clothing list is searched in the memory according to the identity information, and clothing matching schemes are recommended to the user according to the attribute information of the clothing. When the owner information in the clothing's attribute information does not match the identity information, the user is determined to be an unauthorized user. Based on the owner information in the clothing's attribute information, the system searches the storage for the clothing list of the clothing owner and recommends clothing matching schemes based on the clothing's attribute information. The step of detecting user information and clothing information of the user based on the wardrobe door being open further includes: Based on the fact that the wardrobe door is open, an image of the area in front of the wardrobe is captured, and facial images, hand images, and clothing images are detected in the image; The facial image is used for identity recognition to obtain the identity information; The hand image is recognized to obtain the hand movement; and The outline of the clothing is extracted from the clothing image, and the clothing category is identified.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the method as described in any one of claims 1-6.

9. A computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the method as described in any one of claims 1-6.

Images