CN113835795A

CN113835795A - Dial plate generation method and device, electronic equipment and computer readable storage medium

Info

Publication number: CN113835795A
Application number: CN202010586861.8A
Authority: CN
Inventors: 王多新; 陈德银
Original assignee: Guangdong Oppo Mobile Telecommunications Corp Ltd
Current assignee: Guangdong Oppo Mobile Telecommunications Corp Ltd
Priority date: 2020-06-24
Filing date: 2020-06-24
Publication date: 2021-12-24

Abstract

The application relates to a dial plate generation method, a dial plate generation device, computer equipment and a storage medium. The method comprises the following steps: acquiring historical data generated by triggering each historical dial plate; determining the reference type of the historical dial plate according to the historical data; counting the historical data of each historical dial plate to obtain a statistical result; determining a target type from each reference type based on the statistical result, and determining a target picture corresponding to the target type from a picture library; and acquiring a time element, and generating a recommendation dial plate based on the time element and the target picture. By adopting the method, the recommendation dial plate matched with the user requirement can be generated.

Description

Dial plate generation method and device, electronic equipment and computer readable storage medium

Technical Field

The present application relates to the field of computer technologies, and in particular, to a dial generation method and apparatus, an electronic device, and a computer-readable storage medium.

Background

With the development of mobile technology, many traditional electronic products also start to increase mobile functions, such as watches which can only be used for watching time in the past, and nowadays, they can also be connected to the internet through a smart phone or a home network to display content such as incoming call information, social media chat information, news, weather information, and the like.

On the display interface of electronic equipment such as intelligent wrist-watch or intelligent bracelet, adopt fixed template and colour to arrange usually to generate the dial plate. However, the conventional dial plate generation method has a problem that the generated dial plate does not match the user's needs.

Disclosure of Invention

The embodiment of the application provides a dial plate generation method and device, electronic equipment and a computer readable storage medium, and the accuracy of the generated dial plate can be improved.

A dial generation method, comprising:

acquiring historical data generated by triggering each historical dial plate; determining the reference type of the historical dial plate according to the historical data;

counting the historical data of each historical dial plate to obtain a statistical result;

determining a target type from each reference type based on the statistical result, and determining a target picture corresponding to the target type from a picture library;

and acquiring a time element, and generating a recommendation dial plate based on the time element and the target picture.

A dial plate generation method is applied to wearable equipment and comprises the following steps:

receiving a recommended dial plate sent by electronic equipment; the recommended dial plate is generated by the electronic equipment based on the acquired time elements and target pictures, the target pictures are determined from a picture library according to target types, the target types are determined from reference types of all historical dial plates based on statistical results, the statistical results are obtained by counting historical data of all the historical dial plates, the reference types are determined according to historical data, and the historical data are generated by triggering operation on all the historical dial plates in the electronic equipment;

and displaying the recommended dial plate in a display interface.

A dial generation apparatus comprising:

the historical data acquisition module is used for acquiring historical data generated by triggering each historical dial plate; determining the reference type of the historical dial plate according to the historical data;

the statistical module is used for counting the historical data of each historical dial plate to obtain a statistical result;

the target picture determining module is used for determining a target type from the reference types based on the statistical result and determining a target picture corresponding to the target type from a picture library;

and the recommendation dial plate generation module is used for acquiring time elements and generating a recommendation dial plate based on the time elements and the target picture.

A dial plate generation device is applied to wearable equipment and comprises:

the receiving module is used for receiving the recommended dial plate sent by the electronic equipment; the recommended dial plate is generated by the electronic equipment based on the acquired time elements and target pictures, the target pictures are determined from a picture library according to target types, the target types are determined from reference types of all historical dial plates based on statistical results, the statistical results are obtained by counting historical data of all the historical dial plates, the reference types are determined according to historical data, and the historical data are generated by triggering operation on all the historical dial plates in the electronic equipment;

and the display module is used for displaying the recommendation dial plate in a display interface.

An electronic device comprising a memory and a processor, the memory having stored therein a computer program, the computer program, when executed by the processor, causing the processor to perform the steps of the dial plate generation method as described above.

A wearable device comprising a memory and a processor, the memory having stored therein a computer program that, when executed by the processor, causes the processor to perform the steps of the dial plate generation method as described above.

A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the steps of the method as described above.

The dial plate generation method, the device, the electronic equipment and the computer readable storage medium acquire historical data generated by triggering operation on each historical dial plate, determine the reference type of the historical dial plate according to the historical data, and based on the statistical result of the historical data, can determine the target type matched with the historical data, namely the type of the dial plate favored by a user, from each reference type, thereby acquiring the target picture corresponding to the target type, generating the recommended dial plate matched with the historical data of the user, namely the dial plate favored by the user, and realizing the matching of the generated recommended dial plate with the user requirements.

Drawings

In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present application, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.

FIG. 1 is a diagram of an application environment of a dial plate generation method in one embodiment;

FIG. 2 is a flow diagram of a method for dial generation in one embodiment;

FIG. 3 is a flow chart of a dial generation method in another embodiment;

FIG. 4 is a flow chart of a dial generation method in another embodiment;

FIG. 5 is a flow diagram that illustrates steps in one embodiment for identifying a type of picture taken;

FIG. 6 is a flow chart of a dial generation method in another embodiment;

FIG. 7 is a block diagram showing the structure of a dial plate producing apparatus according to an embodiment;

fig. 8 is a block diagram showing the structure of a dial plate producing apparatus in another embodiment;

fig. 9 is a schematic diagram of an internal structure of an electronic device in one embodiment.

Detailed Description

In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.

Fig. 1 is a schematic diagram of an application environment of the dial plate generation method in one embodiment. As shown in fig. 1, the application environment includes a wearable device 102 and an electronic device 104, and the wearable device 102 and the electronic device 104 communicate over a network. The electronic equipment 104 acquires historical data generated by triggering each historical dial plate; determining the reference type of a historical dial plate according to historical data; counting the historical data of each historical dial plate to obtain a statistical result; determining a target type from all reference types based on the statistical result, and determining a target picture corresponding to the target type from a picture library; the time elements are obtained, a recommendation dial plate is generated based on the time elements and the target picture, and the recommendation dial plate is sent to the wearable device 102 through the network. After the wearable device 102 receives the recommendation dial, the recommendation dial can be displayed on a display interface of the wearable device 102. The wearable device 102 may be one of a smart watch, a smart bracelet, and the like. The electronic device may be a personal computer, a notebook computer, a smart phone, a tablet computer, or an independent server or a server cluster formed by a plurality of servers.

Fig. 2 is a flow chart of a dial generation method in one embodiment. As shown in fig. 2, the dial plate generation method includes steps 202 to 208.

Step 202, acquiring historical data generated by triggering operation on each historical dial plate; and determining the reference type of the historical dial plate according to the historical data.

The history dial refers to a dial on which the electronic device has been subjected to a trigger operation before the current time. The trigger operation may be click, slide, long press, voice trigger, etc.

The history data refers to data generated when a trigger operation is performed on the history dial. The historical data can comprise at least one of the reference type of the historical dial plate, the identification corresponding to the reference type of the historical dial plate, the triggering time, the triggering times, the triggering time and the like. Wherein the reference type of the history dial refers to the type of the history dial. The reference type of the history dial may include one type, and may also include at least two types. For example, the reference type of the history dial may be at least one of sports, art, landscape, animation, antique, fresher, and the like.

Optionally, the history data may include a reference type of the history dial plate, and may also include an identifier corresponding to the reference type of the history dial plate. And when the historical data comprises the identifier corresponding to the reference type of the historical dial plate, finding the reference type of the historical dial plate from the corresponding relation between the reference type and the identifier according to the identifier. For example, the identifier corresponding to the reference type of the history dial in the history data is a, and the reference type of the history dial can be found from the correspondence between the reference type and the identifier to be the landscape type.

In the electronic device, different user identifications can be logged in the dial application, and the history data can be different between different user identifications. Therefore, when the electronic equipment receives the dial plate generation request, the user identification logged at the current moment can be obtained, and then the corresponding historical data can be searched according to the user identification logged at the current moment. The user identifier refers to an identifier corresponding to the user, and may be at least one of a user name, a serial number, a character string, and the like.

In another embodiment, the electronic device may be further connected to a wearable device, and a dial application in the electronic device may send a dial to be displayed or selected to the wearable device and display the dial in a display interface in the wearable device. And the wearable device may be connected to any of a variety of electronic devices. Obtaining historical data corresponding to the logged-in user identification from a memory; the historical data is generated by triggering each historical dial by the user corresponding to the logged-in user identifier.

In the historical data, the use habits and preferences of the user corresponding to the user identification can be analyzed. For example, when the user identification corresponding to the user frequently occurs at 7 o 'clock to 8 o' clock on a weekday for the time of selecting each history dial, it can be judged that the user is accustomed to selecting the dial before the start of the work. For another example, when most of the reference types of the history dial plate, corresponding to the user identifier, for the user to perform the triggering operation are motion types, it may be determined that the user prefers to move.

And step 204, counting the historical data of each historical dial plate to obtain a statistical result.

The electronic equipment acquires the reference types of the historical dials, and counts historical data of triggering of the historical dials of each reference type by a user corresponding to the user identification to obtain a statistical result.

For example, a user corresponding to the user identifier performs a trigger operation on the history dials A, B, C, D, E and F before the current time, where the reference types of the history dials A, D, E and F are both sports, the reference type of the history dial B is small fresh, and the reference type of the history dial C is animation, then the statistical result may be: the user triggers 4 times to the moving dial plate, 1 time to the small fresh dial plate, and 1 time to the cartoon dial plate.

It can be understood that the more times the user corresponding to the user identifier performs the triggering operation on the history dial plate of the certain reference type, or the longer the duration of the triggering operation performed on the history dial plate of the certain reference type by the user corresponding to the user identifier is, the more the user corresponding to the user identifier is loved by the history dial plate of the reference type.

Step 206, determining a target type from the reference types based on the statistical result, and determining a target picture corresponding to the target type from the picture library.

The target picture refers to a picture used to generate the target dial. The statistical result is the historical data of the historical dial plate corresponding to each reference type, and the statistical result comprises the triggering times of the historical dial plate corresponding to each reference type, the triggering duration of the historical dial plate corresponding to each reference type and the like.

In one embodiment, based on the statistical result, the electronic device may determine, as the target type, a reference type having the largest number of trigger operations or the longest trigger time from among the reference types.

In another embodiment, based on the statistical result, the electronic device may determine, as the target type, a reference type that triggers the operation a number of times or has a long trigger duration from among the reference types.

In other embodiments, based on the statistical result, the electronic device obtains a first parameter corresponding to the number of triggering times and a second parameter corresponding to the triggering duration; for each reference type, multiplying the counted triggering times by a first parameter, multiplying the counted triggering duration by a second parameter, and adding the two products to obtain a reference value corresponding to the reference type; the target type is determined based on the reference values of the respective reference types.

For example, the trigger count counted by the reference type a is 10, the trigger duration is 5s, the trigger count counted by the reference type B is 8, the trigger duration is 6s, the first parameter is 0.4, and the second parameter is 0.6, then the reference value of the reference type a is 10 × 0.4+8 × 0.6 — 8.8, and the reference value of the reference type B is 8 × 0.4+6 × 0.6 — 6.8, based on the reference value of the reference type a and the reference value of the reference type B, the reference type a with the highest reference value may be selected as the target type, and the reference type B with the next highest reference value may also be selected as the target type.

In the picture library, various types of pictures are stored. After the electronic equipment determines the target type, each target picture matched with the target type is searched from the picture library.

And step 208, acquiring a time element, and generating a recommendation dial plate based on the time element and the target picture.

The time element refers to an element including time information. The time elements may include time scales, hour, minute, second, etc. The style of the time element is not limited, as the style of the time element is a cartoon style, a landscape style, an article style, and the like. The time information included in the time element may be either running or static. For example, a time element may be a running clock or a map that includes a clock, the clock in the map being static.

Specifically, the electronic device may perform superposition processing with the target picture as a background picture and the time element as a foreground, so as to generate the recommendation dial.

The dial plate generation method obtains historical data generated by triggering operation on each historical dial plate, determines the reference type of the historical dial plate according to the historical data, can determine the target type matched with the historical data, namely the type of the dial plate favored by a user from each reference type based on the statistical result of the historical data, thereby obtaining the target picture corresponding to the target type, generates the target dial plate matched with the historical data of the user identification, namely the dial plate favored by the user, and realizes that the generated recommendation dial plate is matched with the user requirement.

In one implementation, after acquiring the time element and generating the recommendation dial based on the time element and the target picture, the method further includes: acquiring time elements, and displaying the recommended dial plate in a display interface; and receiving a selection instruction of the recommended dial plate, and taking the recommended dial plate selected by the selection instruction as a target dial plate.

When the number of the determined target pictures is one, a recommendation dial is generated based on the time elements and the target pictures, and the electronic equipment can directly use the recommendation dial as the target dial. When the number of the determined target pictures is at least two, generating at least two recommendation dials based on the time elements and the target pictures, and displaying the at least two recommendation dials on a display interface; and when a selection instruction for the recommended dial plate is received, taking the recommended dial plate selected by the selection instruction as a target dial plate.

In this embodiment, the recommendation dials are displayed in the display interface, one of the recommendation dials can be selected as a target dial, and the type corresponding to the target picture in the target dial is matched with the historical data of the user, so that the target dial favored by the user can be obtained, and the obtained target dial is matched with the user requirement.

In one embodiment, as shown in fig. 3, before receiving a selection instruction for a recommended dial and taking the recommended dial selected by the selection instruction as a target dial, the method further includes:

and step 302, setting buried points in each recommendation dial.

A buried point refers to program code that captures, processes, and transmits for a particular user behavior or event. The number of the buried points provided in the recommendation dial is not limited, and may be one or at least two. The position of the buried point set in the recommendation dial is not limited, and may be the center position of the recommendation dial or any other position of the recommendation dial.

Through the buried point in the recommendation dial plate, the trigger operation of the user can be captured, and trigger data corresponding to the trigger operation is generated. For example, if the user triggers a buried point in the recommendation dial, the buried point may capture data of the trigger time, the trigger duration, the trigger type, and the like of the trigger operation.

Further, after the trigger data corresponding to the trigger operation is generated by the buried point in the recommended dial, the trigger data can be reported to the processor, and then the processor processes the trigger data.

Receiving a selection instruction of the recommended dial plate, and taking the recommended dial plate selected by the selection instruction as a target dial plate, wherein the selection instruction comprises the following steps:

and 304, receiving a selection instruction and trigger data generated by triggering the recommended dial through a buried point in the recommended dial, and taking the recommended dial selected by the selection instruction as a target dial.

When one of the recommendation dials displayed on the display interface is triggered, the buried point arranged in the recommendation dial can receive the trigger operation, so that a selection instruction and trigger data are generated. And the generated selection instruction indicates that the user corresponding to the user identification selects the target dial plate from all recommended dial plates. The trigger data refers to data generated in the process of trigger operation, such as data of the type of a recommended dial plate for trigger operation, trigger time, trigger duration, trigger type and the like.

The method further comprises the following steps:

and step 306, taking the recommended dial plate subjected to the triggering operation as a history dial plate, taking the triggering data as history data, and returning to execute the step of acquiring the history data generated by the triggering operation on each history dial plate.

And after the recommended dial plate selected by the selection instruction is used as the target dial plate, the selected target dial plate is a historical dial plate which is subjected to triggering operation before the current moment, and the triggering data is also historical data generated by triggering operation on the historical dial plate by the user corresponding to the user identification.

And when the dial plate generation request is received again, the electronic equipment executes a step of acquiring historical data generated by triggering operation on each historical dial plate, wherein the target dial plate belongs to one of the historical dial plates, and the triggering data belongs to one part of the historical data.

In this embodiment, the electronic device sets a buried point in each recommended dial, receives a trigger operation of a user on each recommended dial through the buried point, thereby generating trigger data, and when the electronic device generates a dial again, the trigger data can be used as a part of historical data to update the historical data, thereby updating the love degree of the user corresponding to the user identifier on various types of dials, generating a recommended dial more matched with the user requirement, and recommending the recommended dial to the user, thereby obtaining a target dial more meeting the user requirement.

In one embodiment, before receiving a selection instruction for a recommended dial and taking the recommended dial selected by the selection instruction as a target dial, the method further includes: setting buried points in each recommendation dial plate; receiving a selection instruction of the recommended dial plate, and taking the recommended dial plate selected by the selection instruction as a target dial plate, wherein the selection instruction comprises the following steps: receiving a selection instruction and trigger data generated by triggering operation on the recommended dial plate through a buried point in the recommended dial plate, and taking the recommended dial plate selected by the selection instruction as a target dial plate; the method further comprises the following steps: when a dial plate generation request is received, acquiring a candidate picture corresponding to a target type from a picture library; and determining a target picture from the candidate pictures based on the trigger data, returning to execute the step of acquiring a time element, and generating a recommended dial plate based on the time element and the target picture.

It is understood that the types of pictures in the picture library may include one type, or may include at least two types. For example, the type of picture a is landscape, and the type of picture B is sprite and landscape. The candidate picture refers to a picture including a target type.

After the target dial is generated, when a dial generation request is received, namely the dial generation request is received again, candidate pictures containing the target type are obtained from the picture library. Typically, at least two candidate pictures are acquired. The dial plate generation request may be generated by a user performing a preset trigger operation. The preset triggering operation may be clicking a dial generation button in a display interface of the electronic device, inputting a preset voice password, or touching a preset physical key, but is not limited thereto.

The electronic equipment determines a target picture from the candidate pictures based on trigger data generated by the last trigger operation. Specifically, the type of a recommended dial plate for triggering operation is determined according to the triggering data; based on the type of the recommended dial plate of the trigger operation, obtaining the preference degree of the user corresponding to the user identification to each candidate picture; and determining a preset number of target pictures from each candidate picture according to the likeness of each candidate picture.

Optionally, the trigger data may include a type of the recommended dial plate for triggering the operation, or may include an identifier corresponding to the type of the recommended dial plate for triggering the operation, and the type of the recommended dial plate for triggering the operation is determined from a correspondence between the identifier and the type of the dial plate according to the identifier.

It can be understood that the recommendation dial plate selected by the user in the last triggering operation indicates that the user likes the recommendation dial plate, i.e. likes the type of the recommendation dial plate. Therefore, based on the type of the recommended dial plate of the last trigger operation, the preference degree of each candidate picture of the user can be calculated.

For example, the candidate pictures corresponding to the target types obtained from the picture library include A, B and C, the type of the candidate picture a is landscape and fresh, the type of the candidate picture B is a person, the type of the candidate picture C is landscape and a building, and the type of the recommended dial plate of the last trigger operation is landscape and fresh, so that the user's preference for the candidate picture a is highest, the user's preference for the candidate picture C is second, the user's preference for the candidate picture B is lowest, and when the preset number is 2, the candidate pictures a and C can be used as target pictures.

Further, based on the likeness of the user corresponding to the user identifier to each candidate picture, the candidate pictures can be sorted, so that a preset number of candidate pictures with the highest likeness are obtained as target pictures.

The electronic equipment can more accurately determine the target picture which better meets the requirements of the user from the picture library based on the trigger data generated by the last trigger operation, so that a recommendation dial plate which better meets the requirements of the user can be generated and recommended to the user, and the generated recommendation dial plate better meets the preference of the user.

In one embodiment, after the recommended dial plate selected by the selection instruction is taken as the target dial plate, the method further includes: sending the target dial plate to the wearable device; the target dial plate is used for indicating the wearable device to show the target dial plate in a display interface of the wearable device.

Wearable devices such as watches, bracelets, and the like. After the wearable device receives the target dial, the target dial can be displayed in the display interface.

It can be understood that, in the electronic equipment execute the tasks that the statistics data, the analysis data and the like are time-consuming and the workload is large, and then the finally determined target dial plate is sent to the wearable equipment, the wearable equipment only needs to show the target dial plate on a display interface, and the operating pressure of the wearable equipment is reduced, so that other functions of the wearable equipment can be better realized.

In another embodiment, the manner of determining the type of the target further comprises: when the shot picture is acquired, identifying the shooting type of the shot picture, taking the shooting type as a target type, and executing a step of determining a target picture corresponding to the target type from a picture library.

The photographed picture may be one of an RGB (Red, Green, Blue) picture, a grayscale picture, and the like. The RGB picture can be obtained by shooting through a color camera. The grey-scale picture can be obtained by shooting through a black-and-white camera.

The electronic equipment calls the camera, shoots through the camera, obtains and shoots the picture. The photographing type of the photographed picture refers to the type of the photographed picture. The type of picture taken is at least one of sports, art, landscape, animation, antique, fresher, etc.

In one embodiment, the method further comprises: acquiring a training image, inputting the training image into a classification model, and training the classification model to obtain a trained classification model; identifying a type of taking of a picture, comprising: and identifying the shooting type of the shot picture through the trained classification model.

The training image refers to an image used for training a classification model. The training image may be one of an RGB (Red, Green, Blue) picture, a grayscale picture, and the like. The training image may be a reference picture in a picture library, and the reference picture carries a tag indicating the type of the reference picture.

Further, the training image includes a desired type; inputting the training image into a classification model, training the classification model to obtain a trained classification model, and the method comprises the following steps: inputting the training image into a convolutional neural network in a classification model, and extracting training characteristics of the training image through the convolutional neural network; inputting the training characteristics into a normalized exponential function or a logistic regression classifier to obtain a training type; determining a cross entropy loss function value between the training type and the expected type based on the training type and the expected type; and adjusting the training parameters of the convolutional neural network based on the cross entropy loss function value until a preset condition is met, and obtaining a trained classification model.

The convolutional neural network is formed by combining a plurality of convolutional layers, a shallow convolutional layer can extract the characteristics of local details such as textures and outlines in a training image, and a high convolutional layer can extract the characteristics of global abstractions such as color and contrast of the training image. The electronic equipment inputs the training image into a convolutional neural network in the classification model, and the training characteristics of the training image are extracted. The electronic device inputs the training features into a normalized exponential function (softmax) or a logistic regression classifier (logistic regression classifier), and classifies the reference pictures to obtain the training types.

The electronic equipment inputs the training type and the expected type into a cross entropy loss function, and calculates an error between the training type and the expected type, namely a cross entropy loss function value. And when the cross entropy loss function value is larger than the loss threshold value, the error between the training type and the expected type is larger, updating the training parameters in the convolutional neural network, and continuing to train the convolutional neural network.

The preset condition may include at least one of that the cross entropy loss function value is less than or equal to a loss threshold value, and that the number of training times reaches a number threshold value.

In one embodiment, the electronic device calculates the gradient using a back propagation algorithm to obtain a cross-entropy loss function value; and when the cross entropy loss function value is less than or equal to the loss threshold value, obtaining the trained classification model.

In one embodiment, as shown in fig. 4, the electronic device executes step 402 to perform a classification process on the reference pictures, that is, to obtain types of the respective reference pictures, and use the types of the respective reference pictures as tags of the reference pictures, so as to generate a classified picture library 404.

The electronic device takes each reference picture in the classified picture library 404 as a training image, and executes step 406 to train the classification model to obtain a trained classification model 408.

The electronic device obtains a shot 410, inputs the shot 410 into the trained classification model 408, and identifies a target type 412 of the shot 410. The electronic device executes step 414 to determine a target picture corresponding to the target type from the picture library, and generates each recommended dial.

The electronic equipment executes step 416 to receive a trigger operation on the recommended dial plate; step 418 is performed to generate a target dial.

Further, a buried point is set in each candidate dial, when the electronic device executes step 416 to receive a trigger operation on the recommended dial, trigger data generated by the trigger operation is acquired, and step 420 is executed to report through the buried point; step 422 is executed again, and trigger data is collected; when a dial plate generation request is received, acquiring a candidate picture corresponding to a target type from a picture library; and determining a target picture from the candidate pictures based on the trigger data, thereby determining a more accurate recommended dial.

In one embodiment, as illustrated in fig. 5, identifying the type of capture of the captured picture comprises:

and 502, extracting shooting characteristics of the shot picture.

The shooting characteristics refer to characteristics of taking a picture. The photographing characteristics may include at least one of local characteristics and global characteristics of the photographed picture. Local features such as texture features, contour features, etc. of the captured picture; global features such as color features, contrast features, etc. of the captured picture.

Alternatively, the shooting characteristics of the shot picture may be represented by a vector.

The electronic equipment inputs the shot picture into the feature extraction model, and the shooting feature of the shot picture is extracted through the trained feature extraction model. Wherein, the feature extraction model is trained by adopting deep learning and metric learning. The deep learning is performed by using a Convolutional Neural Network (CNN). Metric Learning (Metric Learning) is a method of spatial mapping, which can learn a feature (Embedding) space in which all data is converted into a feature vector, and the distance between feature vectors of similar samples is small and the distance between feature vectors of dissimilar samples is large, thereby distinguishing data.

The convolutional neural network in the feature extraction model is formed by combining a plurality of convolutional layers, a shallow convolutional layer can extract features of local details such as textures and outlines in a shot picture, a high convolutional layer can extract globally abstract features such as colors and contrasts, and finally the shot picture is embedded (embedded) into a high-dimensional vector (generally 128-dimensional, 256-dimensional, 512-dimensional and the like) by the whole convolutional neural network and the high-dimensional vector is output. The high-dimensional vector is the shooting feature of the shot picture.

Furthermore, the electronic equipment can also perform denoising, wrinkle removal and other processing on the shot picture, and then perform feature extraction on the processed shot picture, so that more accurate shooting features can be extracted.

Step 504, obtaining a reference picture in the picture library and a reference feature of the reference picture.

The reference picture refers to a picture matched with a photographed picture. The reference feature refers to a feature of a reference picture. Likewise, the reference feature may also include at least one of a local feature and a global feature of the reference picture. Local features such as texture features, contour features, etc. of the reference picture; global features such as color features, contrast features, etc. of the reference picture. Alternatively, the reference features of the reference picture may be represented by a vector.

In one embodiment, the electronic device may extract reference features from the reference picture in advance. In another embodiment, the electronic device may also extract the reference features from the reference picture after the reference picture is acquired.

And the electronic equipment inputs the reference picture into the feature extraction model, and extracts the reference feature of the reference picture through the trained feature extraction model. Wherein, the feature extraction model is trained by adopting deep learning and metric learning. The deep learning is performed by using a Convolutional Neural Network (CNN). Metric Learning (Metric Learning) is a method of spatial mapping, which can learn a feature (Embedding) space in which all data is converted into a feature vector, and the distance between feature vectors of similar samples is small and the distance between feature vectors of dissimilar samples is large, thereby distinguishing data.

The convolutional neural network in the feature extraction model is formed by combining a plurality of convolutional layers, a shallow convolutional layer can extract features of local details such as textures and outlines in a reference picture, a high convolutional layer can extract globally abstract features such as colors and contrasts, and finally the reference picture is embedded (embedded) into a high-dimensional vector (generally 128-dimensional, 256-dimensional, 512-dimensional and the like) by the whole convolutional neural network and the high-dimensional vector is output. The high-dimensional vector is the reference feature of the reference picture.

Furthermore, the electronic device can also perform denoising, wrinkle removal and other processing on the reference picture, and then perform feature extraction on the processed reference picture, so that more accurate reference features can be extracted.

Step 506, matching the shooting characteristics with the reference characteristics of each reference picture respectively, and determining the similarity between the shot picture and each reference picture.

It is to be understood that similar pictures have similar representations of features. The higher the similarity between the shot picture and the reference picture is, the closer the shot feature representing the shot picture is to the reference feature of the reference picture.

Specifically, the electronic device calculates a cosine distance between the photographed feature and the reference feature as a similarity between the photographed picture and the reference picture. The cosine distance, also called cosine similarity, is a measure for measuring the difference between two individuals by using the cosine value of the included angle between two vectors in the vector space.

And step 508, determining the type of the shot picture based on the similarity between the shot picture and each reference picture.

Alternatively, the number of the determined taken pictures may be one, or may be at least two.

In one embodiment, the electronic device may determine a reference picture with the highest similarity, acquire a type of the reference picture with the highest similarity, and determine the type of the reference picture with the highest similarity as the type of the taken picture.

In another embodiment, the electronic device may also determine the first two reference pictures with the highest similarity, acquire the types of the first two reference pictures with the highest similarity, and determine the types of the first two reference pictures with the highest similarity as the types of the taken pictures.

In other embodiments, the electronic device may further determine a plurality of reference pictures with the highest similarity, acquire a type with the highest occurrence frequency among the plurality of reference pictures with the highest similarity, and determine the type as the type of the shot picture.

In the embodiment, the shooting characteristics of the shot picture are matched with the reference characteristics of the reference picture, so that the more accurate type of the shot picture can be determined based on the similarity between the shot picture and the reference picture.

In one embodiment, as shown in fig. 6, after the captured picture is acquired, the method further includes:

step 602, determining a shooting area from the shot picture, and obtaining a sub-picture according to the shooting area.

The photographing region refers to a region selected from a photographed picture. The shape of the imaging region is not limited, and may be circular, rectangular, triangular, irregular, or the like.

The sub-picture refers to a picture generated from a photographing region. In one embodiment, the electronic device may take the capture area as a sub-picture. In another embodiment, the electronic device may capture a sub-picture from the capture area. For example, the photographing region is an irregular shape, and the largest rectangular region can be determined from the photographing region as a sub-picture. The specific embodiment of obtaining the sub-picture according to the shooting area is not limited, and may be set according to the user's needs.

Extracting shooting characteristics of a shot picture, comprising:

step 604, extracting sub-features of the sub-picture.

Alternatively, the sub-features of the sub-picture may be represented by vectors.

And the electronic equipment inputs the sub-picture into the feature extraction model, and extracts the sub-features of the sub-picture through the trained feature extraction model. Wherein, the feature extraction model is trained by adopting deep learning and metric learning. The deep learning is performed by using a Convolutional Neural Network (CNN). Metric Learning (Metric Learning) is a method of spatial mapping, which can learn a feature (Embedding) space in which all data is converted into a feature vector, and the distance between feature vectors of similar samples is small and the distance between feature vectors of dissimilar samples is large, thereby distinguishing data.

The convolutional neural network in the feature extraction model is formed by combining a plurality of convolutional layers, a shallow convolutional layer can extract features of local details such as textures and outlines in a sub-picture, a high convolutional layer can extract globally abstract features such as colors and contrasts, and finally the sub-picture is embedded (embedded) into a high-dimensional vector (generally 128-dimensional, 256-dimensional, 512-dimensional and the like) by the whole convolutional neural network and the high-dimensional vector is output. The high-dimensional vector is the sub-feature of the sub-picture.

Furthermore, the electronic equipment can also perform denoising, wrinkle removal and other processing on the sub-picture, and then perform feature extraction on the processed sub-picture, so that more accurate sub-features can be extracted.

Matching the shooting characteristics with the reference characteristics of each reference picture respectively, and determining the similarity between the shot picture and each reference picture, wherein the method comprises the following steps:

and 606, respectively matching the sub-features with the reference features of the reference pictures, and determining the similarity between the sub-pictures and each reference picture.

The higher the similarity between the sub-picture and the reference picture, the closer the sub-feature representing the sub-picture is to the reference feature of the reference picture.

Specifically, the electronic device calculates a cosine distance between the sub-feature and the reference feature, and takes the cosine distance as a similarity between the sub-picture and the reference picture. The cosine distance, also called cosine similarity, is a measure for measuring the difference between two individuals by using the cosine value of the included angle between two vectors in the vector space.

Determining the type of the shot picture based on the similarity between the shot picture and each reference picture, wherein the determining comprises the following steps:

and step 608, determining the type of the sub-picture based on the similarity between the sub-picture and each reference picture, and taking the type of the sub-picture as the type of the shot picture.

In the embodiment, the shooting area is determined from the shot picture, the sub-picture is obtained according to the shooting area, and the sub-features of the sub-picture are matched with the reference features of the reference picture, so that the features of all the areas of the shot picture are avoided being obtained, the features of all the areas of the shot picture are also avoided being matched, the resources of the electronic equipment are saved, the feature matching efficiency is improved, and the type of the target picture can be determined more quickly.

In one embodiment, extracting sub-features of the sub-picture comprises: acquiring a target scale; adjusting the size of the sub-picture to a target scale; normalizing the pixel value of each pixel point in the sub-picture of the target scale; and performing feature extraction on the sub-picture after the normalization processing to obtain the sub-features of the sub-picture.

It can be understood that, from the shooting area determined in the shooting picture, the sub-picture is obtained according to the shooting area, and the size of the sub-picture may be different from that of the reference picture, so that the size of the sub-picture is adjusted to the target size. The target dimension can be set according to the needs of the user. When the target dimension is larger than the original dimension of the sub-picture, expanding the sub-picture; and when the target scale is smaller than the original scale of the sub-picture, reducing the sub-picture.

For example, if the target scale is (224 × 224 pixels), the sub-picture is resized to the target scale (224 × 224 pixels).

Normalization refers to mapping data into a range of 0-1, and processing can be performed more conveniently and rapidly. Specifically, the pixel value of each pixel point in the sub-picture of the target scale is obtained, and the pixel value is mapped to the range of 0-1 from 0-255.

In this embodiment, the size of the sub-picture is adjusted to a target scale; the pixel values of all the pixel points in the target scale sub-picture are normalized, so that the sub-picture after normalization can be conveniently processed subsequently.

In one embodiment, acquiring a reference picture in a picture library and a reference feature of the reference picture comprises: acquiring a reference picture in a picture library; adjusting the size of the reference picture to a target scale; normalizing the pixel value of each pixel point in the reference picture of the target scale; and performing feature extraction on the normalized reference picture to obtain the reference features of the reference picture.

It can be understood that, by adjusting the sizes of the reference picture and the sub-picture to the target scale, the reference picture and the sub-picture can be subjected to feature matching under the same condition, and the similarity between the sub-picture and the reference picture can be obtained more accurately, so that the type of the shot picture can be determined more accurately. Moreover, the pixel values of all the pixel points in the reference picture are normalized, so that the reference picture can be conveniently processed subsequently.

In one embodiment, acquiring a time element, and generating a recommendation dial based on the time element and a target picture comprises: acquiring a target style corresponding to the target type; and acquiring time elements of the target style, and generating a recommendation dial plate based on the target picture and the time elements of the target style.

In the electronic device, at least one style corresponding to each type may be stored in advance. When the electronic equipment acquires the target type, the target type is matched with each stored type, and therefore the target style corresponding to the target type is acquired. Target styles such as cartoon styles, landscape styles, architectural styles, and the like.

For example, if the target type is "building", various styles of the type "building", such as "cantonese tower" style, "world window" style, "yellow crane building" style, etc., are retrieved from the memory of the electronic device.

In this embodiment, a time element of a target style corresponding to the target type is obtained, the time element is more matched with the target picture, the degree of engagement is higher, and a more accurate recommendation dial can be generated based on the target picture and the time element of the target style.

In another embodiment, a dial plate generation method is provided, which is applied to a wearable device, and includes: receiving a recommended dial plate sent by electronic equipment; the recommendation dial plate is generated by the electronic equipment based on the acquired time elements and the target picture, the target picture is determined from the picture library according to the target type, the target type is determined from the reference type of each history dial plate based on the statistical result, the statistical result is obtained by counting the history data of each history dial plate, the reference type is determined according to the history data, and the history data is generated by triggering each history dial plate in the electronic equipment to display the recommendation dial plate in the display interface.

The process of generating the recommended dial plate needs to execute tasks which are time-consuming and large in workload, such as statistical data, analysis data and the like, and the tasks are executed in the electronic equipment; and wearable equipment only needs to receive the recommendation dial plate sent by the electronic equipment and displays the recommendation dial plate in a display interface, so that the operating pressure of the wearable equipment is reduced, and other functions of the wearable equipment can be better realized.

It should be understood that, although the steps in the flowcharts of fig. 2 to 5 and fig. 6 are shown in order as indicated by the arrows, the steps are not necessarily performed in order as indicated by the arrows. The steps are not performed in the exact order shown and described, and may be performed in other orders, unless explicitly stated otherwise. Moreover, at least some of the steps in fig. 2-5 and 6 may include multiple sub-steps or multiple stages, which are not necessarily performed at the same time, but may be performed at different times, and the order of performing the sub-steps or stages is not necessarily sequential, but may be performed alternately or alternatingly with other steps or at least some of the sub-steps or stages of other steps.

Fig. 7 is a block diagram showing the structure of a dial plate generation device according to an embodiment. As shown in fig. 7, there is provided a dial plate generation apparatus 700 including: a historical data acquisition module 702, a statistics module 704, a target picture determination module 706, and a recommendation dial generation module 708, wherein:

a historical data obtaining module 702, configured to obtain historical data generated by performing a triggering operation on each historical dial; and determining the reference type of the historical dial plate according to the historical data.

And the counting module 704 is used for counting the historical data of each historical dial plate to obtain a counting result.

And a target picture determining module 706, configured to determine a target type from the reference types based on the statistical result, and determine a target picture corresponding to the target type from the picture library.

And the target recommendation dial plate generation module 708 is configured to obtain the time element, and generate a recommendation dial plate based on the time element and the target picture.

The dial plate generation device acquires the historical data generated by triggering each historical dial plate, determines the reference type of the historical dial plate according to the historical data, and can determine the target type matched with the historical data, namely the type of the dial plate favored by a user from each reference type based on the statistical result of the historical data, thereby acquiring the target picture corresponding to the target type, generating the recommendation dial plate matched with the historical data of the user, namely the dial plate favored by the user, and realizing the matching of the generated recommendation dial plate with the user requirement.

In one embodiment, the dial plate generation device further comprises a selection module, configured to display the recommended dial plate in a display interface; and receiving a selection instruction of the recommended dial plate, and taking the recommended dial plate selected by the selection instruction as a target dial plate.

In one embodiment, the dial plate generation apparatus further includes a buried point setting module, configured to set a buried point in each candidate dial plate; the recommended dial plate generation module 708 is further configured to receive a selection instruction and trigger data generated by performing a trigger operation on the recommended dial plate through a buried point in the recommended dial plate, and use the recommended dial plate selected by the selection instruction as a target dial plate; the historical data obtaining module 702 is further configured to use the recommended dial plate for performing the triggering operation as a historical dial plate, use the triggering data as historical data, and return to the step of obtaining the historical data generated by performing the triggering operation on each historical dial plate.

In one embodiment, the buried point setting module is further configured to set buried points in each candidate dial; the recommended dial plate generation module 708 is further configured to receive a selection instruction and trigger data generated by performing a trigger operation on the recommended dial plate through a buried point in the recommended dial plate, and use the recommended dial plate selected by the selection instruction as a target dial plate; the target picture determining module 706 is further configured to obtain a candidate picture corresponding to the target type from the picture library when receiving the dial plate generation request; and determining a target picture from the candidate pictures based on the trigger data, executing the steps of acquiring a time element through a recommendation dial generation module 708, and generating a recommendation dial based on the time element and the target picture.

In one embodiment, the dial plate generation apparatus further includes a sending module, configured to send the target dial plate to the wearable device; the target dial plate is used for indicating the wearable device to show the target dial plate in a display interface of the wearable device.

In an embodiment, the dial plate generating apparatus further includes a type identifying module, configured to identify a shooting type of the shot picture when the shot picture is acquired, use the shooting type as a target type, and execute a step of determining, by the target picture determining module 706, a target picture corresponding to the target type from the picture library.

In one embodiment, the type identification module is further configured to extract shooting characteristics of the shot picture; acquiring a reference picture in a picture library and reference characteristics of the reference picture; matching the shooting characteristics with the reference characteristics of each reference picture respectively, and determining the similarity between the shooting picture and each reference picture; and determining the type of the shot picture based on the similarity between the shot picture and each reference picture.

In one embodiment, the dial plate generation device further includes a sub-picture acquisition module, configured to determine a shooting area from the shot picture, and obtain a sub-picture according to the shooting area; the type identification module is also used for extracting the sub-features of the sub-pictures; matching the sub-features with the reference features of each reference picture respectively, and determining the similarity between the sub-pictures and each reference picture; and determining the type of the sub-picture based on the similarity between the sub-picture and each reference picture, and taking the type of the sub-picture as the type of the shot picture.

In one embodiment, the type identification module is further configured to obtain a target scale; adjusting the size of the sub-picture to a target scale; normalizing the pixel value of each pixel point in the sub-picture of the target scale; and performing feature extraction on the sub-picture after the normalization processing to obtain the sub-features of the sub-picture.

In one embodiment, the type identification module is further configured to obtain a reference picture in a picture library; adjusting the size of the reference picture to a target scale; normalizing the pixel value of each pixel point in the reference picture of the target scale; and performing feature extraction on the normalized reference picture to obtain the reference features of the reference picture.

In one embodiment, the dial plate generation apparatus further includes a training module, configured to obtain a training image, input the training image into a classification model, and train the classification model to obtain a trained classification model; the type identification module is also used for identifying the shooting type of the shot picture through the trained classification model.

In one embodiment, the training image includes a desired type; the training module is also used for inputting the training image into a convolutional neural network in the classification model and extracting the training characteristics of the training image through the convolutional neural network; inputting the training characteristics into a normalized exponential function or a logistic regression classifier to obtain a training type; determining a cross entropy loss function value between the training type and the expected type based on the training type and the expected type; and adjusting the training parameters of the convolutional neural network based on the cross entropy loss function value until a preset condition is met, and obtaining a trained classification model.

In an embodiment, the target dial plate generation module 708 is further configured to obtain a target style corresponding to the target type; and acquiring time elements of the target style, and generating a recommendation dial plate based on the target picture and the time elements of the target style.

Fig. 8 is a block diagram showing the structure of a dial plate generation device according to an embodiment. As shown in fig. 8, there is provided a dial producing apparatus 800 including: a receiving module 802 and a presentation module 804, wherein:

a receiving module 802, configured to receive a recommendation dial sent by an electronic device; the recommended dial plates are generated by the electronic equipment based on the acquired time elements and the target pictures, the target pictures are determined from the picture library according to target types, the target types are determined from reference types of all historical dial plates based on statistical results, the statistical results are obtained by counting historical data of all the historical dial plates, the reference types are determined according to historical data, and the historical data are generated by triggering operation on all the historical dial plates in the electronic equipment.

And the display module 804 is used for displaying the recommendation dial plate in the display interface.

According to the dial plate generation device, the electronic equipment acquires historical data generated by triggering operation on each historical dial plate by a user corresponding to the user identification, and determines a target type matched with the historical data of the user identification based on a statistical result of the historical data, namely the type of the dial plate favored by the user, so that a target picture corresponding to the target type is acquired, a recommended dial plate is generated, and the recommended dial plate is sent to the wearable equipment.

The process of generating the recommended dial plate needs to execute tasks which are time-consuming and large in workload, such as statistical data, analysis data and the like, and the tasks are executed in the electronic equipment; and wearable equipment only need receive the recommendation dial plate that electronic equipment sent, show the recommendation dial plate in showing interface can, alleviateed wearable equipment's operating pressure to can realize other functions of wearable equipment better.

The division of the modules in the dial generation device is merely for illustration, and in other embodiments, the dial generation device may be divided into different modules as needed to complete all or part of the functions of the dial generation device.

For specific limitations of the dial generation apparatus, reference may be made to the above limitations of the dial generation method, which are not described herein again. The respective modules in the dial plate generation apparatus described above may be implemented in whole or in part by software, hardware, and a combination thereof. The modules can be embedded in a hardware form or independent from a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.

Fig. 9 is a schematic diagram of an internal structure of an electronic device in one embodiment. As shown in fig. 9, the electronic device includes a processor and a memory connected by a system bus. Wherein, the processor is used for providing calculation and control capability and supporting the operation of the whole electronic equipment. The memory may include a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The computer program can be executed by a processor to implement a dial generation method provided in the following embodiments. The internal memory provides a cached execution environment for the operating system computer programs in the non-volatile storage medium. The electronic device may be any terminal device such as a mobile phone, a tablet computer, a PDA (Personal Digital Assistant), a Point of Sales (POS), a vehicle-mounted computer, and a wearable device.

The respective modules in the dial plate generation apparatus provided in the embodiments of the present application may be implemented in the form of a computer program. The computer program may be run on a terminal or a server. Program modules constituted by such computer programs may be stored on the memory of the electronic device. Which when executed by a processor, performs the steps of the method described in the embodiments of the present application.

The embodiment of the application also provides a computer readable storage medium. One or more non-transitory computer-readable storage media containing computer-executable instructions that, when executed by one or more processors, cause the processors to perform the steps of a dial generation method.

A computer program product containing instructions which, when run on a computer, cause the computer to perform a dial generation method.

Any reference to memory, storage, database, or other medium used herein may include non-volatile and/or volatile memory. Non-volatile memory can include read-only memory (ROM), Programmable ROM (PROM), Electrically Programmable ROM (EPROM), Electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM), which acts as external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms, such as Static RAM (SRAM), Dynamic RAM (DRAM), Synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), Enhanced SDRAM (ESDRAM), synchronous Link (Synchlink) DRAM (SLDRAM), Rambus Direct RAM (RDRAM), direct bus dynamic RAM (DRDRAM), and bus dynamic RAM (RDRAM).

The above-mentioned embodiments only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the present application. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present patent shall be subject to the appended claims.

Claims

1. A dial generation method, comprising:

2. The method of claim 1, further comprising, after the obtaining a time element, generating a recommendation dial based on the time element and the target picture:

displaying the recommended dial plate in a display interface;

and receiving a selection instruction of the recommended dial plate, and taking the recommended dial plate selected by the selection instruction as a target dial plate.

3. The method of claim 2, wherein before receiving a selection instruction for the recommended dial, and taking the recommended dial selected by the selection instruction as a target dial, the method further comprises:

setting buried points in each recommendation dial plate;

the receiving of the selection instruction of the recommended dial plate and the taking of the recommended dial plate selected by the selection instruction as the target dial plate comprise:

receiving a selection instruction and trigger data generated by triggering operation on the recommended dial plate through a buried point in the recommended dial plate, and taking the recommended dial plate selected by the selection instruction as a target dial plate;

the method further comprises the following steps:

and taking the recommended dial plate subjected to the triggering operation as a history dial plate, taking the triggering data as history data, and returning to execute the step of acquiring the history data generated by triggering operation on each history dial plate.

4. The method of claim 2, wherein before receiving a selection instruction for the recommended dial, and taking the recommended dial selected by the selection instruction as a target dial, the method further comprises:

setting buried points in each recommendation dial plate;

the method further comprises the following steps:

when a dial plate generation request is received, acquiring a candidate picture corresponding to the target type from the picture library;

and determining a target picture from the candidate pictures based on the trigger data, returning to execute the step of acquiring a time element, and generating a recommended dial plate based on the time element and the target picture.

5. The method according to claim 2, wherein after the recommended dial selected by the selection instruction is used as the target dial, the method further comprises:

sending the target dial plate to a wearable device; the target dial plate is used for indicating the wearable equipment to display the target dial plate in a display interface of the wearable equipment.

6. The method of claim 1, wherein determining the target type further comprises:

when a shot picture is acquired, identifying the shooting type of the shot picture, taking the shooting type as a target type, and executing the step of determining the target picture corresponding to the target type from the picture library.

7. The method of claim 6, wherein the identifying the type of capture of the captured picture comprises:

extracting shooting characteristics of the shot picture;

acquiring a reference picture in the picture library and reference characteristics of the reference picture;

matching the shooting characteristics with the reference characteristics of the reference pictures respectively, and determining the similarity between the shooting pictures and each reference picture;

and determining the shooting type of the shot picture based on the similarity between the shot picture and each reference picture.

8. The method of claim 7, wherein after the obtaining the captured picture, further comprising:

determining a shooting area from the shooting picture, and obtaining a sub-picture according to the shooting area;

the extracting of the shooting characteristics of the shot picture comprises:

extracting sub-features of the sub-picture;

the matching the shooting characteristics with the reference characteristics of the reference pictures respectively to determine the similarity between the shooting pictures and each reference picture comprises:

matching the sub-features with the reference features of the reference pictures respectively to determine the similarity between the sub-pictures and each reference picture;

the determining the shooting type of the shot picture based on the similarity between the shot picture and each reference picture comprises the following steps:

and determining the type of the sub-picture based on the similarity between the sub-picture and each reference picture, and taking the type of the sub-picture as the shooting type of the shot picture.

9. The method of claim 8, wherein the extracting sub-features of the sub-picture comprises:

acquiring a target scale;

adjusting the size of the sub-picture to a target scale;

normalizing the pixel value of each pixel point in the sub-picture of the target scale;

and performing feature extraction on the sub-picture after the normalization processing to obtain the sub-features of the sub-picture.

10. The method according to claim 9, wherein the obtaining the reference picture in the picture library and the reference feature of the reference picture comprises:

acquiring a reference picture in the picture library;

resizing the reference picture to the target scale;

normalizing the pixel value of each pixel point in the reference picture of the target scale;

and performing feature extraction on the normalized reference picture to obtain the reference features of the reference picture.

11. The method of claim 6, further comprising:

acquiring a training image, inputting the training image into a classification model, and training the classification model to obtain a trained classification model;

the identifying of the shooting type of the shot picture comprises:

and identifying the shooting type of the shot picture through the trained classification model.

12. The method of claim 11, wherein the training image comprises a desired type;

inputting the training image into a classification model, training the classification model, and obtaining a trained classification model, including:

inputting the training image into a convolutional neural network in a classification model, and extracting training characteristics of the training image through the convolutional neural network;

inputting the training characteristics into a normalized exponential function or a logistic regression classifier to obtain a training type;

determining a cross-entropy loss function value between the training type and the desired type based on the training type and the desired type;

and adjusting the training parameters of the convolutional neural network based on the cross entropy loss function value until a preset condition is met, and obtaining a trained classification model.

13. The method of claim 1, wherein obtaining a time element, generating a recommendation dial based on the time element and the target picture, comprises:

acquiring a target style corresponding to the target type;

and acquiring the time element of the target style, and generating a recommendation dial plate based on the target picture and the time element of the target style.

14. A dial plate generation method is applied to wearable equipment and comprises the following steps:

and displaying the recommended dial plate in a display interface.

15. A dial generating apparatus, comprising:

16. A dial generation device, applied to a wearable device, includes:

17. An electronic device comprising a memory and a processor, the memory having stored therein a computer program, characterized in that the computer program, when executed by the processor, causes the processor to carry out the steps of the dial generation method according to any one of claims 1 to 13.

18. A wearable device comprising a memory and a processor, the memory having stored therein a computer program, wherein the computer program, when executed by the processor, causes the processor to perform the steps of the dial generating method of claim 14.

19. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method according to any one of claims 1 to 14.