Dial switching method, device, wearable device and storage medium

Abstract

The present application discloses a dial switching method, device, wearable device and storage medium, and relates to the technical field of wearable devices. The dial switching method is applied to wearable devices, and the dial switching method includes: obtaining a wearing image, wherein the wearing image includes at least a part of the clothing area; inputting the clothing area in the wearing image into a pre-trained texture recognition model to obtain the texture type corresponding to the clothing area output by the texture recognition model; obtaining a target dial to be switched based on the texture type; and switching the current dial to the target dial. In this way, by automatically switching the watch dial according to the texture type of the wearing image, the operational complexity of manually switching the dial is greatly reduced, and the user experience is improved.

Description

Technical Field

[0001] The present application relates to the technical field of wearable devices, and more specifically, to a dial switching method, device, wearable device and storage medium. Background Art

[0002] With the continuous development of intelligent technology, in addition to smart phones, more and more smart devices have entered people's lives, bringing great convenience to people. Among them, smart wearable devices (such as smart watches, smart bracelets, etc.) are now more and more widely used smart devices. In order to meet the personalized needs of users, there are usually many different dials in the theme store of smart watches, and users can choose from more different dials according to their preferences. In the related art, users choose their favorite dials from all the dials in the theme store, but the dial search process is cumbersome, resulting in a poor user experience. Summary of the invention

[0003] In view of this, the present application proposes a dial switching method, device, wearable device and storage medium.

[0004] In a first aspect, an embodiment of the present application provides a dial switching method, the method comprising: obtaining a wearing image, the wearing image including at least a partial clothing area; inputting the clothing area in the wearing image into a pre-trained texture recognition model to obtain a texture type corresponding to the clothing area output by the texture recognition model; obtaining a target dial to be switched to based on the texture type; and switching the current dial to the target dial.

[0005] In a second aspect, an embodiment of the present application provides a dial switching device, the device comprising: an image acquisition module, a texture recognition module, a dial acquisition module and a dial switching module. The image acquisition module is used to acquire a wearing image, the wearing image including at least part of a clothing area; the texture recognition module is used to input the clothing area in the wearing image into a pre-trained texture recognition model to obtain a texture type corresponding to the clothing area output by the texture recognition model; the dial acquisition module is used to acquire a target dial to be switched to based on the texture type; and the dial switching module is used to switch the current dial to the target dial.

[0006] In a third aspect, an embodiment of the present application provides a wearable device, comprising: one or more processors; a memory; one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, and the one or more programs are configured to execute the dial switching method provided in the first aspect.

[0007] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, in which a program code is stored. The program code can be called by a processor to execute the dial switching method provided in the first aspect.

[0008] In the solution provided by the present application, a wearing image is obtained, wherein the wearing image includes at least part of the clothing area, the clothing area in the wearing image is input into a pre-trained texture recognition model, the texture type corresponding to the clothing area output by the texture recognition model is obtained, and then the target dial to be switched is obtained based on the texture type, and finally, the current dial is switched to the target dial. In this way, by obtaining the user's wearing image, the dial switching operation is automatically completed, which greatly reduces the complexity of manually switching the dial, and the dial corresponding to the texture type can be determined as the target dial according to the texture type in the wearing image, that is, personalized dial recommendations can be provided according to the user's outfit, which greatly improves the user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For those skilled in the art, other drawings can be obtained based on these drawings without creative work.

[0010] Figure 1 A schematic diagram showing a usage scenario provided by an embodiment of the present application is shown.

[0011] Figure 2 A flow chart of a dial switching method provided in an embodiment of the present application is shown.

[0012] Figure 3 A schematic diagram of a wearing image provided by an embodiment of the present application is shown.

[0013] Figure 4 A schematic diagram of a clothing area provided by an embodiment of the present application is shown.

[0014] Figure 5 A flow chart of a dial switching method provided in another embodiment of the present application is shown.

[0015] Figure 6 A schematic diagram of a face region provided in an embodiment of the present application is shown.

[0016] Figure 7 Shows Figure 5 The flowchart of sub-steps of step S340 in another implementation manner is shown.

[0017] Figure 8A flow chart of a dial switching method provided in yet another embodiment of the present application is shown.

[0018] Fig. 9 A flowchart of a dial switching method provided in yet another embodiment of the present application is shown.

[0019] Fig.10 A flowchart of a dial switching method provided in yet another embodiment of the present application is shown.

[0020] Fig.11 A schematic diagram of sub-areas of a clothing image provided by an embodiment of the present application is shown.

[0021] Fig.12 It is a block diagram of a dial switching device provided according to an embodiment of the present application.

[0022] Fig.13 It is a block diagram of a wearable device according to an embodiment of the present application for executing the dial switching method according to an embodiment of the present application.

[0023] Fig.14 It is a storage unit of an embodiment of the present application for storing or carrying program codes for implementing the dial switching method according to an embodiment of the present application. DETAILED DESCRIPTION

[0024] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application.

[0025] In the related technologies of wearable devices (such as smart watches, smart bracelets, etc.), users usually select their favorite watch faces from all the watch faces in a theme store, but the watch face search process is cumbersome and inconvenient to operate on the smaller screen of the watch, resulting in a poor user experience; alternatively, users select their favorite watch faces on mobile terminals with larger screens, such as mobile phones and tablets. In this way, the dependence on the mobile terminal is relatively large. When the user does not carry the above mobile terminal, the watch face cannot be selected, which still results in a poor user experience.

[0026] In response to the above problems, the inventors propose a dial switching method, apparatus, wearable device and storage medium, which can obtain a user's wearing image, and determine a target dial corresponding to the texture type according to the texture type of the wearing image, and automatically switch the current dial to the target dial. The content is described in detail below.

[0027] See also Figure 1 , showing a schematic diagram of a usage scenario of the dial switching method provided by the implementation of the present application, the usage scenario includes a wearable device 100.

[0028] In this embodiment, the wearable device 100 may be an electronic device such as a smart watch or a smart bracelet, and this embodiment does not limit this. The wearable device 100 may capture the user's wearing image through its own camera, and may display the captured wearing image; and the wearable device 100 may identify the texture type of the clothing area in the collected wearing image, and use the dial corresponding to the texture type as the dial to be switched to and switch, thereby reducing the complexity of dial switching operations and realizing personalized recommendations for dials.

[0029] Please refer to Figure 2 , Figure 2 A flowchart of a dial switching method provided in an embodiment of the present application is applied to a wearable device. Figure 2 The dial switching method provided in the embodiment of the present application is described in detail. The dial switching method may include the following steps:

[0030] Step S210: Acquire a wearing image, where the wearing image includes at least a portion of a clothing area.

[0031] In the embodiment of the present application, the wearing image may be an image of the user's clothing, which may include at least a portion of the clothing area. Of course, the wearing image may also include a portion of the clothing area and the user's face area (i.e., the user's upper body image), which is not limited in the present embodiment.

[0032] In some implementations, taking the wearable device as a smart watch as an example, the wearing image can be taken by the user through the camera on the smart watch worn by the user. Figure 3 As shown, the image may include a portion of the clothing area and the user's face area (i.e., the user's upper body image). Optionally, when the user selects a button for automatically switching the dial on the smart watch, the dial interface may display a prompt message, prompting the user to take a photo through the camera on the smart watch to obtain the user's wearing image.

[0033] As an implementation method, the wearable device may monitor its current posture through a gyroscope, an accelerometer, etc.; when the current posture of the wearable device meets the preset posture condition, the distance of the wearable device relative to the user is obtained, and if the distance is greater than the distance threshold, the wearing image is collected through the camera. Among them, the preset posture condition can be determined according to the posture of the wearable device collecting the wearing image through the camera. For example, if the camera is set on one side of the screen, the screen of the wearable device may be perpendicular to the ground or parallel to the user's face. The specific preset posture condition may not be limited in this embodiment. When it is detected that the current posture meets the preset posture condition, the distance of the wearable device relative to the user can be further obtained. When the distance is greater than the distance threshold, the wearable device collects the wearing image through the camera. It can be understood that when a user wears a wearable device, if the user needs to switch the dial by collecting the wearing image, the wearable device can be made to enter the corresponding posture. In this posture, the user may just check the display content of the wearable device on a daily basis, or the camera is close to the user, and does not really want to switch the dial; therefore, when the wearable device meets the preset posture condition, the distance relative to the user can be further detected, and when the distance is greater than the distance threshold, the wearing image is collected for switching, thereby avoiding the mistaken dial switching. And if the distance is too small, the collected image may be incomplete, and then the dial switching according to the collected image may be inaccurate. Therefore, the integrity of the wearing image collected by the camera can be ensured by judging whether the distance is greater than the distance threshold. Through the above method, the user can make the posture of the wearable device meet the preset posture condition, and when the distance of the wearable device relative to the user is greater than the distance threshold, the wearing image can be automatically collected and the dial can be switched according to the wearing image later, thereby improving the user experience.

[0034] In other implementations, the user can pre-import or pre-photograph images of multiple pieces of clothing that the user may wear on the smart watch, and store the images of the multiple pieces of clothing. Based on this, the wearing image can be an image randomly selected by the smart watch from the stored images of multiple pieces of clothing, or can be an image selected by the user from the stored images of multiple pieces of clothing, which is not limited in this embodiment.

[0035] Step S220: inputting the clothing region in the wearing image into a pre-trained texture recognition model to obtain a texture type corresponding to the clothing region output by the texture recognition model.

[0036] In this embodiment, after acquiring the wearing image, the wearable device can identify the texture type corresponding to the clothing area in the wearing image through a pre-trained texture recognition model, so as to switch the dial according to the texture type.

[0037] In some embodiments, the texture recognition model can be trained based on a large number of sample clothing images labeled with texture types. Texture types can refer to types corresponding to clothing patterns, such as circles, Chinese characters, English characters, digital characters, other characters, zebra patterns, stripes, plaids, solid colors, patterns, leopard prints, camouflage, and other types. The texture recognition model can be a deep neural network, etc., and the specific type of the texture recognition model may not be limited.

[0038] In some embodiments, the texture recognition model may be pre-stored locally in the wearable device, and the wearable device may directly call the texture recognition model locally and input the clothing area in the wearing image into the texture recognition model.

[0039] In other embodiments, the texture recognition model may also be stored in a cloud server, and the wearable device may call the texture recognition model from the cloud server when it needs to identify the clothing area in the wearing image. For example, the clothing area in the wearing image may be sent to the cloud server to instruct the cloud server to input the clothing area in the wearing image into the texture recognition model to identify the texture type.

[0040] In this embodiment, since the texture type of the clothes needs to be identified, a designated area can be selected from the acquired clothing image as the area to be identified, wherein the clothing area can be selected by randomly selecting a part of the clothing image, or the user can decide to select the clothing area he needs, which is not limited in this embodiment. Figure 4 As shown, the box area is the clothing area to be identified.

[0041] The wearable device can perform processing such as cropping, scaling, and normalization on the clothing area to be identified, and then input the clothing area in the wearing image into a pre-trained texture recognition model to obtain the texture type corresponding to the clothing area output by the texture recognition model.

[0042] Step S230: Obtain a target dial to be switched to based on the texture type.

[0043] In this embodiment, there is a mapping relationship between texture types and dials. The mapping relationship includes multiple texture types and dials corresponding to each texture type, and the mapping relationship can be established based on empirical data, that is, the dial types used by users wearing clothes of various texture types are counted, and the dial type with the highest usage rate (that is, the highest user preference) is used as the dial corresponding to the texture type. Based on this, the dial corresponding to the texture type of the clothing area can be determined according to the above mapping relationship, and the dial is determined as the target dial to be switched to. The texture type can include multiple types, such as: circle, Chinese characters, English characters, digital characters, other characters, zebra patterns, stripes, plaids, solid colors, patterns, leopard prints, camouflage and other types, and correspondingly, each texture type can also correspond to a dial type. The above mapping relationship can be stored in a wearable device or in a server, and there is no limitation on this.

[0044] Step S240: Switch the current watch dial to the target watch dial.

[0045] In this embodiment, after the target dial to be switched is acquired based on the texture type, the wearable device automatically switches the current dial to the target dial.

[0046] In some implementations, the color of the clothing area in the wearing image may be acquired, a target dial to be switched to may be acquired based on the color, and then the current dial may be switched to the target dial.

[0047] In other embodiments, the texture type of the clothing area in the wearing image and the base color of the clothing area can also be obtained, and the target dial to be switched to is obtained based on the texture type of the clothing area and the base color of the clothing area, and then the current dial is switched to the target dial.

[0048] In some embodiments, after the wearable device successfully switches the target dial automatically, if a dial switching operation is received within a preset time, the current dial is switched from the target dial to the second dial in response to the dial switching operation. Based on the second dial, the correspondence between the texture type and the dial is updated, wherein in the updated correspondence, the texture type corresponds to the second dial.

[0049] Specifically, the target dial that the wearable device automatically switches according to the texture type of the clothes worn by the user may not be the user's favorite dial. Based on this, the user can manually switch the target dial again and select the second dial that he likes. Correspondingly, the wearable device receives the second dial and switches the current dial to the second dial selected by the user. In addition, the wearable device can update the correspondence between the texture type and the dial based on the second dial, that is, update the mapping relationship of the above dial, and in the more detailed mapping relationship of the dial, the texture type corresponds to the second dial. In this way, after the user manually selects the dial corresponding to a certain texture type, the mapping relationship of the dial is updated, and the current dial can be more accurately switched to the dial that the user wearing clothes of the texture type likes, thereby improving the user experience.

[0050] In this embodiment, by acquiring a wearing image, and then inputting the clothing area in the wearing image into a pre-trained texture recognition model, the texture type corresponding to the clothing area output by the texture recognition model is obtained; further, based on the texture type, the target dial to be switched to is obtained, and the current dial is switched to the target dial. In this way, by acquiring the user's wearing image, the dial switching operation is automatically completed, which greatly reduces the complexity of manually switching the dial, and can determine the dial corresponding to the texture type as the target dial according to the texture type in the wearing image, that is, it can provide personalized dial recommendations based on the user's outfit, greatly improving the user experience.

[0051] Please refer to Figure 5 , Figure 5 A flowchart of a dial switching method provided in another embodiment of the present application is applied to a wearable device. Figure 5 The dial switching method provided in the embodiment of the present application is described in detail. The dial switching method may include the following steps:

[0052] Step S310: Acquire a wearing image, where the wearing image includes at least a portion of a clothing area.

[0053] Step S320: inputting the clothing region in the wearing image into a pre-trained texture recognition model to obtain a texture type corresponding to the clothing region output by the texture recognition model.

[0054] In the embodiment of the present application, steps S310-S320 may refer to the contents of steps S210-S220 in the aforementioned embodiment, which will not be repeated here.

[0055] Step S330: inputting the face region in the clothing image into a pre-trained face attribute recognition model to obtain face attribute information output by the face attribute recognition model.

[0056] Among them, the facial attribute information may include the user's gender, age, skin color, expression, etc. The clothing image may also include the face area, such as Figure 6 As shown, the box area is the face area to be recognized.

[0057] In this embodiment, the wearable device can perform processing such as cropping, scaling, and normalization on the face region to be identified, and then input the face region in the wear image into a pre-trained face attribute recognition model to obtain face attribute information corresponding to the face region output by the face attribute recognition model. The face attribute recognition model can be trained by a large number of training samples. The training samples can include multiple face images marked with gender and age.

[0058] In some embodiments, the facial attribute recognition model may be pre-stored locally in the wearable device, and the wearable device may directly call the facial attribute recognition model locally and input the facial area in the wearing image into the facial attribute recognition model.

[0059] In other embodiments, the facial attribute recognition model may also be stored in a cloud server, and the wearable device may call the facial attribute recognition model from the cloud server when it needs to recognize the facial area in the wearing image. For example, the facial area in the wearing image may be sent to the cloud server to instruct the cloud server to input the facial area in the wearing image into the facial attribute recognition model to recognize the facial attribute information.

[0060] Step S340: Based on the texture type and the facial attribute information, obtain the target dial to be switched to.

[0061] In this embodiment, there is a mapping relationship between the texture type and the facial attribute information and the dial, wherein the mapping relationship includes multiple texture types, multiple facial attribute information, and a dial corresponding to each texture type and each facial attribute information, and the mapping relationship can be established based on empirical data. Based on this, after determining the texture type of the clothing area and the facial attribute information of the user, the dial corresponding to the texture type and the facial attribute information can be determined based on the mapping relationship. The above mapping relationship can be stored in the wearable device or in the server, and there is no limitation on this.

[0062] In some embodiments, see Figure 7 , step S340 may include:

[0063] Step S341: Send a dial acquisition request to the server, wherein the dial acquisition request carries the texture type and the face attribute information.

[0064] In this embodiment, since the local storage space of the wearable device is limited, if you want to provide more types of dials, you can store a remote dial mapping relationship containing more dial types in the server in advance. On the premise that the wearable device is connected to the network and can communicate data with the server, send a dial acquisition request to the server to obtain more types of dials from the server.

[0065] Optionally, the remote dial mapping relationship can be established based on empirical data, and the remote dial mapping relationship includes the user's clothing texture type, age and gender classification, and the corresponding dial. In the remote dial mapping relationship, there is a mapping relationship between the texture type, age and gender classification, and the dial. After the texture type and age and gender classification are obtained, the corresponding dial can be determined according to the remote dial mapping relationship. Among them, the age and gender classification can include multiple types. In some embodiments, gender and a certain age stage are used as a category, for example, [Male, 0-10 years old], [Female, 0-10 years old], [Male, 11-15 years old], [Female, 11-15 years old], [Male, 16-20 years old], [Female, 16-20 years old], [Male, 21-25 years old], [Female, 21-25 years old], [Male, 26-30 years old], [Female, 26-30 years old], [Male, 31-35 years old], [ [Female, 31-35 years old], [Male, 36-40 years old], [Female, 36-40 years old], [Male, 41-45 years old], [Female, 41-45 years old], [Male, 46-50 years old], [Female, 46-50 years old], [Male, 51-55 years old], [Female, 51-55 years old], [Male, 56-60 years old], [Female, 51-60 years old], [Male, 61-70 years old], [Female, 61-70 years old], [Male, over 70 years old] and [Female, over 70 years old]. In another embodiment, gender and age are used as a category, for example, [Male, 5 years old], [Female, 5 years old], [Male, 10 years old], [Female, 10 years old], [Male, 18 years old], [Female, 18 years old], etc.

[0066] Furthermore, after receiving the watch face acquisition request sent by the wearable device, the server can obtain the corresponding target watch face from the remote watch face mapping relationship according to the texture type, age and gender classification and the above mapping relationship carried by the wearable device.

[0067] Step S342: receiving a target dial returned by the server, wherein the target dial corresponds to the texture type and the facial attribute information.

[0068] In this embodiment, after the server obtains the target watch dial, it will feed back the target watch dial to the wearable device, and correspondingly, the wearable device receives the target watch dial.

[0069] Step S350: Switch the current watch dial to the target watch dial.

[0070] In the embodiment of the present application, step S350 can refer to the content of step S240 in the aforementioned embodiment, which will not be repeated here.

[0071] In this embodiment, by acquiring a wearing image, and then inputting the clothing area in the wearing image into a pre-trained texture recognition model, the texture type corresponding to the clothing area output by the texture recognition model is obtained; and the face area in the wearing image is input into a pre-trained face attribute recognition model, and the face attribute information output by the face attribute recognition model is obtained. Further, based on the texture type and face attribute information, the target dial to be switched is acquired, and the current dial is switched to the target dial. In this way, by acquiring the user's wearing image, the dial switching operation is automatically completed, which greatly reduces the complexity of manually switching the dial. In addition, the corresponding dial can be determined as the target dial according to the texture type in the wearing image and the user's gender and age classification, that is, personalized dial recommendations can be provided according to the user's outfit, age and gender, which greatly improves the user experience.

[0072] Please refer to Figure 8 , Figure 8 A flowchart of a dial switching method provided in another embodiment of the present application is applied to a wearable device. Figure 8 The dial switching method provided in the embodiment of the present application is described in detail. The dial switching method may include the following steps:

[0073] Step S510: Acquire a wearing image, where the wearing image includes at least a portion of a clothing area.

[0074] Step S520: inputting the clothing region in the wearing image into a pre-trained texture recognition model to obtain a texture type corresponding to the clothing region output by the texture recognition model.

[0075] In the embodiment of the present application, steps S510-S520 may refer to the contents of steps S210-S220 in the aforementioned embodiment, which will not be repeated here.

[0076] Step S530: Obtain current network information.

[0077] Step S540: Determine whether the current network information meets the preset network condition.

[0078] Step S550: If the current network information meets the preset network conditions, the face area in the clothing image is input into a pre-trained face attribute recognition model to obtain the face attribute information output by the face attribute recognition model.

[0079] In this embodiment, the wearable device can obtain its own current network information, and determine whether the current network information meets the preset network conditions, and select different methods of obtaining the target dial according to the determination result.

[0080] In some embodiments, the current network information may be the network status of the current network. Correspondingly, the preset network condition is whether the network status is available. If the network status of the current network is available, it is determined that the current network information meets the preset network condition; if the network status of the current network is disabled, it is determined that the current network information does not meet the preset network condition.

[0081] In other embodiments, the current network information may be the transmission rate of the current network. Correspondingly, the preset network condition may be to determine whether the transmission rate of the current network reaches the standard transmission rate. If the transmission rate of the current network is lower than the standard transmission rate, it is determined that the current network information does not meet the preset network condition; if the transmission rate of the current network is greater than or equal to the standard transmission rate, it is determined that the current network information does not meet the preset network condition.

[0082] In some other embodiments, the current network information may also be a packet loss rate. Correspondingly, the preset network condition may be to determine whether the packet loss rate of the current network is lower than a packet loss rate threshold. If the packet loss rate of the current network is lower than the packet loss rate threshold, it is determined that the current network information meets the preset network condition; if the packet loss rate of the current network is greater than or equal to the packet loss rate threshold, it is determined that the current network information does not meet the preset network condition.

[0083] In some further embodiments, the current network information may also be a transmission delay value. Correspondingly, the preset network condition may be to determine whether the transmission delay value of the current network is lower than a transmission delay threshold. If the transmission delay value of the current network is lower than the transmission delay threshold, it is determined that the current network information meets the preset network condition; if the transmission delay value of the current network is greater than or equal to the transmission delay threshold, it is determined that the current network information does not meet the preset network condition.

[0084] In some other embodiments, the current network information may also be a transmission delay change value. Correspondingly, the preset network condition may be to determine whether the transmission delay change value of the current network is lower than the transmission delay change threshold. If the transmission delay change value of the current network is lower than the transmission delay change threshold, it is determined that the current network information meets the preset network condition; if the transmission delay change value of the current network is greater than or equal to the transmission delay change threshold, it is determined that the current network information does not meet the preset network condition.

[0085] In this embodiment, the current network information may also be other parameter values, which is not limited in this embodiment.

[0086] Step S560: Based on the texture type and the facial attribute information, obtain the target dial to be switched to.

[0087] In the embodiment of the present application, after the current network information meets the preset network conditions, the specific contents of steps S550-S560 can refer to the contents of steps S330-S340 in the aforementioned embodiment, which will not be repeated here.

[0088] Step S570: If the current network information does not meet the preset network condition, obtain a target dial corresponding to the texture type from the local dial.

[0089] In this embodiment, after the current network information does not meet the preset network condition, the specific content of step S570 can refer to the content of step S230 in the above embodiment, which will not be repeated here.

[0090] Step S580: Switch the current watch dial to the target watch dial.

[0091] In this implementation, step S580 may refer to the content of step S240 in the aforementioned embodiment, which will not be described in detail here.

[0092] In this embodiment, by acquiring a wearing image, and then inputting the clothing area in the wearing image into a pre-trained texture recognition model, the texture type corresponding to the clothing area output by the texture recognition model is obtained; when the current network information meets the preset network condition, the face area in the wearing image is input into the pre-trained face attribute recognition model, the face attribute information output by the face attribute recognition model is obtained, and then based on the texture type and the face attribute information, the target dial to be switched to is obtained, and the current dial is switched to the target dial; when the current network information does not meet the preset network condition, the target dial corresponding to the texture type is obtained from the local dial. In this way, when the current network information meets the preset network condition, the target dial is determined based on the texture type and the gender and age classification of the user; when the current network information meets the preset network condition, the target dial is determined from the local dial based on the texture type. In this way, the smoothness of switching the dial can be guaranteed, and the problem of dial switching being stuck due to poor current network information will not be caused, and personalized dial recommendations can still be provided to users, thereby improving user experience.

[0093] Please refer to Fig. 9 , Fig. 9 A flowchart of a dial switching method provided in another embodiment of the present application is applied to a wearable device. Fig. 9 The dial switching method provided in the embodiment of the present application is described in detail. The dial switching method may include the following steps:

[0094] Step S610: Acquire a wearing image, where the wearing image includes at least a portion of a clothing area.

[0095] Step S620: inputting the clothing region in the wearing image into a pre-trained texture recognition model to obtain a texture type corresponding to the clothing region output by the texture recognition model.

[0096] Step S630: Obtain a target dial to be switched to based on the texture type.

[0097] In the embodiment of the present application, steps S610-S630 may refer to the contents of steps S210-S230 in the aforementioned embodiment, which will not be repeated here.

[0098] Step S640: If there are multiple target watch faces, obtain the current power value of the wearable device.

[0099] In this embodiment, there can be multiple target dials obtained based on the texture type. The target dial can be a static dial or a dynamic dial. It can be understood that a dynamic dial may accelerate the power consumption of the wearable device. Therefore, when there are multiple target dials, the current power of the wearable device can be obtained, and which target dial to select can be considered based on the current power.

[0100] Step S650: If the current power value is less than the power threshold, a dial whose rated power consumption meets a preset power consumption condition is obtained from multiple target dials as the first dial.

[0101] The power threshold may be a factory setting of the wearable device or may be set in advance by the user, which is not limited in this embodiment. If the current power is less than the power threshold, it may be determined whether the rated power consumption of multiple target dials meets the preset power consumption condition, and the dial that meets the preset power consumption condition is used as the first dial. The preset power consumption condition may be preset in advance.

[0102] In some embodiments, the preset power consumption condition may be that the power consumed by the dial per unit time is lower than a preset power threshold. If there is a dial among multiple target dials whose power consumption is lower than the preset power threshold, the target dial is selected as the first dial.

[0103] In other embodiments, if none of the multiple target dials meets the preset power consumption conditions, the dial with the lowest rated power consumption among the multiple target dials can be selected as the first dial to ensure that when the current battery level of the wearable device is low, the dial with the slowest power consumption is selected as the target dial to reduce the power consumption of the wearable device.

[0104] Step S660: Switch the current dial to the first dial.

[0105] In this embodiment, after the first dial is determined based on the current power level of the wearable device, the wearable device automatically switches the current dial to the first dial.

[0106] In some embodiments, if there are multiple target dials, historical dials corresponding to the texture type can be obtained, and the similarities between the multiple target dials and the historical dials can be obtained respectively. The target dial whose similarity reaches a preset threshold is determined as the second dial, and the current dial is switched to the second dial. In practical applications, different users wearing the same texture type may prefer to use different dials. Correspondingly, there may be a one-to-many mapping relationship between the texture type and the dial. Therefore, there may be multiple target dials determined according to the texture type. Based on this, when there are multiple target dials, the historical dials used by users wearing clothes of the texture type can be obtained. By judging the similarities between the multiple target dials and the historical dials, the target dial whose similarity reaches a preset threshold or has the highest similarity is determined as the second dial, and then the current dial is switched to the second dial. In this way, the current dial can be more accurately switched to the dial that the user wearing clothes of the texture type likes, thereby improving the user experience.

[0107] In this embodiment, by acquiring a wearing image, and then inputting the clothing area in the wearing image into a pre-trained texture recognition model, the texture type corresponding to the clothing area output by the texture recognition model is obtained; further, based on the texture type, the target dial to be switched to is obtained. If there are multiple target dials, and when the current power of the wearable device is less than the power threshold, the dial with a rated power consumption that meets the preset power consumption condition is used as the first dial, and the current dial is switched to the first dial. In this way, on the basis of determining multiple target dials according to the texture type of the user's wearing image, the dial with the lowest power consumption is selected as the first dial to be switched, which can provide personalized dial recommendations based on the user's outfit, age and gender, improve the user experience, and also reduce the power consumption of the wearable device.

[0108] Please refer to Fig.10 , Fig.10 A flowchart of a dial switching method provided in another embodiment of the present application is applied to a wearable device. Fig.10 The dial switching method provided in the embodiment of the present application is described in detail. The dial switching method may include the following steps:

[0109] Step S710: Acquire a wearing image, where the wearing image includes at least a portion of a clothing area.

[0110] In the embodiment of the present application, step S710 may refer to the content of step S210 in the aforementioned embodiment, which will not be repeated here.

[0111] Step S720: Divide the clothing image into a plurality of sub-areas.

[0112] In this embodiment, after acquiring the wearing image, the wearable device may divide the wearing image into multiple sub-areas, such as Fig.11 As shown, the clothing image is divided into 12 sub-regions.

[0113] Step S730: displaying designated prompt information, wherein the designated prompt information is used to prompt the user to select any sub-area from the multiple sub-areas.

[0114] Furthermore, after the clothing image is divided into a plurality of sub-regions, a specified prompt message such as “Please select a region as the clothing region to be identified” may be displayed to prompt the user to select any sub-region from the plurality of sub-regions.

[0115] Step S740: In response to the region selection operation, the target sub-region selected by the region selection operation is determined as the clothing region.

[0116] Optionally, after the user selects the area, the wearable device receives the selection operation input by the user, responds to the area selection operation, and determines the target sub-area selected by the area selection operation as the clothing area. Fig.11 For example, if the target sub-region selected by the user is the sub-region labeled 8, the sub-region labeled 8 is correspondingly determined as the clothing region.

[0117] In some embodiments, the clothing area can also be selected by the user by drawing on the display screen of the wearable device. The user can draw a closed area in the wearing image, and correspondingly, the wearable device uses the closed area as the clothing area.

[0118] In this embodiment, there may be multiple ways to determine the clothing area, which is not limited in this embodiment.

[0119] Step S750: inputting the clothing region in the wearing image into a pre-trained texture recognition model to obtain a texture type corresponding to the clothing region output by the texture recognition model.

[0120] Step S760: Obtain a target dial to be switched to based on the texture type.

[0121] Step S770: Switch the current watch dial to the target watch dial.

[0122] In the embodiment of the present application, steps S750-S770 may refer to the contents of steps S220-S240 in the aforementioned embodiment, which will not be repeated here.

[0123] In this embodiment, a clothing image is obtained and divided into multiple sub-areas, and a specified prompt message is displayed to prompt the user to select any sub-area from the multiple sub-areas; in response to the area selection operation, the target sub-area selected by the area selection operation is determined as the clothing area, and then the clothing area in the clothing image is input into a pre-trained texture recognition model to obtain the texture type corresponding to the clothing area; finally, the target dial to be switched to is obtained based on the texture type, and the current dial is switched to the target dial. In this way, the user can select his favorite clothing area and determine the target dial according to the texture type determined by the clothing area, which better realizes the provision of personalized dial recommendations based on the user's favorite outfits, greatly improving the user experience.

[0124] Please refer to Fig.12 , which shows a structural block diagram of a dial switching device 800 provided in an embodiment of the present application. The device 800 may include: an image acquisition module 810, a texture recognition module 820, a dial acquisition module 830 and a dial switching module 840.

[0125] The image acquisition module 810 is used to acquire a wearing image, where the wearing image includes at least a portion of a clothing area.

[0126] The texture recognition module 820 is used to input the clothing area in the wearing image into a pre-trained texture recognition model to obtain the texture type corresponding to the clothing area output by the texture recognition model.

[0127] The dial acquisition module 830 is used to acquire a target dial to be switched to based on the texture type.

[0128] The dial switching module 840 is used to switch the current dial to the target dial.

[0129] In some embodiments, the wearing image further includes a face area, and before acquiring the target dial to be switched to based on the texture type, the dial switching device 800 may include: a face recognition module. The face recognition module may be used to input the face area in the wearing image into a pre-trained face attribute recognition model to obtain face attribute information output by the face attribute recognition model.

[0130] In this implementation, the watch face acquisition module 830 may be specifically configured to acquire a target watch face to be switched to based on the texture type and the facial attribute information.

[0131] In this implementation, the dial acquisition module 830 may include: a request sending unit and a dial receiving unit. The request sending unit may be used to send a dial acquisition request to a server, wherein the dial acquisition request carries the texture type and the face attribute information. The dial receiving unit may be used to receive a target dial returned by the server, wherein the target dial corresponds to the texture type and the face attribute information.

[0132] In some embodiments, before inputting the face area in the wearing image into a pre-trained face attribute recognition model, obtaining the face attribute information output by the face attribute recognition model, and obtaining the target watch face to be switched based on the texture type and the face attribute information, the watch face switching device 800 may further include: a network acquisition module. The network acquisition module may be used to obtain current network information.

[0133] In this embodiment, the dial acquisition module 830 can be specifically used to execute the input of the face area in the wearing image into a pre-trained face attribute recognition model if the current network information meets the preset network conditions, obtain the face attribute information output by the face attribute recognition model, and obtain the target dial to be switched based on the texture type and the face attribute information; if the current network information does not meet the preset network conditions, obtain the target dial corresponding to the texture type from the local dial.

[0134] In some embodiments, the dial switching module 840 may include: a power acquisition unit, a dial acquisition unit, and a first dial switching unit. The power acquisition unit may be used to acquire the current power value of the wearable device if there are multiple target dials. The dial acquisition unit may be used to acquire a dial whose rated power consumption meets a preset power consumption condition from multiple target dials as a first dial if the current power value is less than a power threshold. The first dial switching unit may be used to switch the current dial to the first dial.

[0135] In some embodiments, after the current dial is switched to the target dial, the dial switching device 800 may further include: a second dial switching module and a dial updating module. The second dial switching module may be configured to, if a dial switching operation is received within a preset time period, respond to the dial switching operation and switch the current dial from the target dial to the second dial. The dial updating module may be configured to update the correspondence between the texture type and the dial based on the second dial, wherein in the updated correspondence, the texture type corresponds to the second dial.

[0136] In some embodiments, before the clothing area in the wearing image is input into a pre-trained texture recognition model to obtain the texture type corresponding to the clothing area output by the texture recognition model, the dial switching device 800 may also include: an image division module, a display module, and a response module. The image division module can be used to divide the wearing image into multiple sub-areas. The display module can be used to display specified prompt information, and the specified prompt information is used to prompt the user to select any sub-area from the multiple sub-areas. The response module can be used to respond to the area selection operation and determine the target sub-area selected by the area selection operation as the clothing area.

[0137] In some embodiments, the wearable device includes a camera, and before acquiring the wearing image, the dial switching device 800 may further include: a distance acquisition module. The distance acquisition module may be used to acquire the distance of the wearable device relative to the user when the current posture of the wearable device meets a preset posture condition.

[0138] In this implementation, the image acquisition module 810 may be specifically configured to capture the wearing image through the camera if the distance is greater than a distance threshold.

[0139] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described devices and modules can refer to the corresponding processes in the aforementioned method embodiments, and will not be repeated here.

[0140] In several embodiments provided in the present application, the coupling between modules may be electrical, mechanical or other forms of coupling.

[0141] In addition, each functional module in each embodiment of the present application can be integrated into a processing module, or each module can exist physically separately, or two or more modules can be integrated into one module. The above integrated modules can be implemented in the form of hardware or software functional modules.

[0142] In summary, in the solution provided by the embodiment of the present application, by acquiring a wearing image and inputting the clothing area in the wearing image into a pre-trained texture recognition model, the texture type corresponding to the clothing area output by the texture recognition model is obtained, and then the target dial to be switched to is obtained based on the texture type, and finally, the current dial is switched to the target dial. In this way, by acquiring the user's wearing image, the dial switching operation is automatically completed, which greatly reduces the complexity of manually switching the dial, and the dial corresponding to the texture type can be determined as the target dial according to the texture type in the wearing image, that is, personalized dial recommendations can be provided according to the user's outfit, which greatly improves the user experience.

[0143] A wearable device provided in this application will be described below with reference to the figures.

[0144] Reference Fig.13 , Fig.13 A structural block diagram of a wearable device 900 provided in an embodiment of the present application is shown, and the dial switching method provided in an embodiment of the present application can be executed by the wearable device 900.

[0145] The wearable device 900 in the embodiment of the present application may include one or more of the following components: a processor 901, a memory 902, and one or more applications, wherein the one or more applications may be stored in the memory 902 and configured to be executed by one or more processors 901, and the one or more programs are configured to execute the method described in the aforementioned method embodiment.

[0146] The processor 901 may include one or more processing cores. The processor 901 uses various interfaces and lines to connect the various parts of the entire wearable device 900, and executes various functions and processes data of the wearable device 900 by running or executing instructions, programs, code sets or instruction sets stored in the memory 902, and calling data stored in the memory 902. Optionally, the processor 901 can be implemented in at least one hardware form of digital signal processing (Digital Signal Processing, DSP), field programmable gate array (Field-Programmable Gate Array, FPGA), and programmable logic array (Programmable Logic Array, PLA). The processor 901 can integrate one or a combination of a central processing unit (Central Processing Unit, CPU), a graphics processing unit (Graphics Processing Unit, GPU) and a modem. Among them, the CPU mainly processes the operating system, user interface and application programs; the GPU is responsible for rendering and drawing display content; and the modem is used to process wireless communications. It can be understood that the above-mentioned modem can also be integrated into the processor 901 and implemented separately through a communication chip.

[0147] The memory 902 may include a random access memory (RAM) or a read-only memory (ROM). The memory 902 may be used to store instructions, programs, codes, code sets, or instruction sets. The memory 902 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for implementing at least one function (such as a touch function, a sound playback function, an image playback function, etc.), instructions for implementing the following various method embodiments, etc. The data storage area may also store data created by the wearable device 900 during use (such as the various corresponding relationships described above), etc.

[0148] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described devices and modules can refer to the corresponding processes in the aforementioned method embodiments, and will not be repeated here.

[0149] In several embodiments provided in the present application, the coupling or direct coupling or communication connection between the modules shown or discussed may be an indirect coupling or communication connection through some interfaces, devices or modules, which may be electrical, mechanical or other forms.

[0150] In addition, each functional module in each embodiment of the present application can be integrated into a processing module, or each module can exist physically separately, or two or more modules can be integrated into one module. The above integrated modules can be implemented in the form of hardware or software functional modules.

[0151] Please refer to Fig.14 , which shows a structural block diagram of a computer-readable storage medium provided in an embodiment of the present application. The computer-readable medium 1000 stores program codes, which can be called by a processor to execute the method described in the above method embodiment.

[0152] The computer readable storage medium 1000 may be an electronic memory such as a flash memory, an EEPROM (electrically erasable programmable read-only memory), an EPROM, a hard disk, or a ROM. Optionally, the computer readable storage medium 1000 includes a non-transitory computer-readable storage medium. The computer readable storage medium 1000 has storage space for program code 1010 that performs any method step of the above method. These program codes can be read from or written to one or more computer program products. The program code 1010 can be compressed, for example, in an appropriate form.

[0153] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A dial switching method, characterized in that: Applied to a wearable device, the wearable device includes a camera, and the method includes: When the current posture of the wearable device satisfies a preset posture condition, obtaining a distance of the wearable device relative to the user, wherein the preset posture condition is that the screen of the wearable device is in a posture parallel to the face of the user; If the distance is greater than the distance threshold, collecting a wearing image through the camera, wherein the wearing image includes at least a part of the clothing area; Inputting the clothing region in the wearing image into a pre-trained texture recognition model to obtain a texture type corresponding to the clothing region output by the texture recognition model; Get the current network transmission rate; If the current network transmission rate is greater than or equal to the standard transmission rate, the face area in the clothing image is input into a pre-trained face attribute recognition model to obtain face attribute information output by the face attribute recognition model, wherein the face attribute information includes the user's gender, age, skin color and expression, and the face attribute recognition model is stored in a cloud server; Based on the mapping relationship, the texture type and the face attribute information, a target dial to be switched to is obtained, wherein the mapping relationship includes multiple texture types, multiple face attribute information, and dials corresponding to each texture type and each face attribute information; If the transmission rate of the current network is lower than the standard transmission rate, obtaining a target watch face corresponding to the texture type from a local watch face; Switch the current watch face to the target watch face.

2. The method according to claim 1, characterized in that The acquiring a target dial to be switched to based on the mapping relationship, the texture type, and the face attribute information includes: Sending a dial acquisition request to a server, wherein the dial acquisition request carries the texture type and the face attribute information; Receive a target watch face returned by the server, wherein the target watch face corresponds to the texture type and the facial attribute information.

3. The method according to claim 1, characterized in that The step of switching the current dial to the target dial includes: If there are multiple target watch faces, obtain the current power value of the wearable device; If the current power value is less than the power threshold, a dial whose rated power consumption meets a preset power consumption condition is obtained from multiple target dials as a first dial; Switch the current dial to the first dial.

4. The method according to any one of claims 1 to 3, characterized in that: After switching the current dial to the target dial, the method further includes: If a dial switching operation is received within a preset time period, in response to the dial switching operation, the current dial is switched from the target dial to the second dial; Based on the second dial, the correspondence between the texture type and the dial is updated, wherein in the updated correspondence, the texture type corresponds to the second dial.

5. The method according to any one of claims 1 to 3, characterized in that: Before inputting the clothing region in the wearing image into a pre-trained texture recognition model to obtain a texture type corresponding to the clothing region output by the texture recognition model, the method further includes: dividing the clothing image into a plurality of sub-regions; Displaying specified prompt information, wherein the specified prompt information is used to prompt the user to select any sub-area from the multiple sub-areas; In response to the region selection operation, the target sub-region selected by the region selection operation is determined as the clothing region.

6. A dial switching device, characterized in that: Applied to a wearable device, the wearable device includes a camera, and the device includes: A distance acquisition module, configured to obtain the distance of the wearable device relative to the user when the current posture of the wearable device satisfies a preset posture condition, wherein the preset posture condition is that the screen of the wearable device is in a posture parallel to the face of the user; An image acquisition module, configured to acquire a wearing image through the camera if the distance is greater than a distance threshold, wherein the wearing image includes at least a portion of a clothing area; A texture recognition module, used for inputting the clothing region in the wearing image into a pre-trained texture recognition model, and obtaining a texture type corresponding to the clothing region output by the texture recognition model; The network acquisition module is used to obtain the current network transmission rate; A face recognition module, for inputting the face region in the clothing image into a pre-trained face attribute recognition model to obtain face attribute information output by the face attribute recognition model if the current network transmission rate is greater than or equal to the standard transmission rate, wherein the face attribute information includes the user's gender, age, skin color and expression, and the face attribute recognition model is stored in the cloud server; A dial acquisition module, used to acquire a target dial to be switched to based on a mapping relationship, the texture type and the face attribute information, wherein the mapping relationship includes multiple texture types, multiple face attribute information, and dials corresponding to each texture type and each face attribute information; if the current network transmission rate is lower than the standard transmission rate, the target dial corresponding to the texture type is acquired from a local dial; The dial switching module is used to switch the current dial to the target dial.

7. A wearable device, characterized in that: include: one or more processors; Memory; One or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, and the one or more programs are configured to execute the method according to any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores program code, and the program code can be called by a processor to execute the method according to any one of claims 1 to 5.

Images