Theme generation method and device, server, electronic equipment and medium

Abstract

The invention relates to a theme generation method and device, a server, electronic equipment and a medium, and relates to the technical field of display, and the theme generation method comprises the steps that the server generates a target theme and sends the target theme to the electronic equipment based on a pre-stored theme generation model and at least one of target regional information and weather information. The target theme comprises at least one of wallpaper and screensaver, so that the theme of the electronic equipment is more vivid and vivid and has uniqueness, and the weather information of the target regional information can be integrated into the target theme, so that the visual experience of a user is enhanced; moreover, the target theme is generated by the theme generation model according to the weather information, and the generation process does not need manual participation, so that the generation efficiency of the target theme is improved, and time, cost and human resources are saved.

Description

Technical Field

[0001] The present disclosure relates to the technical field of electronic devices, and in particular to a theme generation method, device, server, electronic device and medium. Background Art

[0002] With the popularization of electronic devices and the increase in user personalized needs, the market prospects for wallpapers and screensavers for electronic devices are broad. Wallpapers and screensavers are rich and diverse, covering a variety of themes and styles. Users can choose specific themes, colors, effects, etc. according to their preferences and needs to customize wallpapers and screensavers with personal characteristics. Users can also share their own designed or favorite wallpapers and screensavers with other users through the social sharing and community communication functions provided by wallpaper and screensaver applications, and communicate and interact with other users.

[0003] With the improvement of electronic device display technology, high-definition wallpapers and dynamic wallpapers are becoming more and more popular. High-definition wallpapers can present clear images and details, and dynamic wallpapers can bring vivid visual effects to users. Summary of the invention

[0004] In order to overcome the problems existing in the related art, the present disclosure provides a topic generation method, device, server, electronic device and medium.

[0005] According to a first aspect of an embodiment of the present disclosure, a topic generation method is provided, which is applied to a server, and the topic generation method includes:

[0006] receiving at least one of target area information and weather information, wherein the target area information is at least used to characterize the target area, and the weather information is used to characterize the weather conditions of the target area during a target time period, and the weather information includes a plurality of meteorological data;

[0007] Generate a target theme based on a pre-stored theme generation model and at least one of the target region information and the weather information, wherein the target theme is generated based at least on the weather information of the target region, and the target theme includes at least one of a wallpaper and a screen saver;

[0008] The target topic is sent to an electronic device.

[0009] In some exemplary embodiments of the present disclosure, generating a target topic based on a pre-stored topic generation model and the target region information includes:

[0010] Based on the target area information, obtaining weather information of the target area;

[0011] The weather information is input into the topic generation model to generate the target topic.

[0012] In some exemplary embodiments of the present disclosure, the topic generation method includes establishing the topic generation model, and the method of establishing the topic generation model includes:

[0013] Acquire a plurality of sample meteorological data and a plurality of sample materials associated with each of the sample meteorological data, wherein the sample materials include images, and the images include image features associated with the sample meteorological data;

[0014] The diffusion model is trained based on the multiple sample meteorological data and the multiple sample materials related to each sample meteorological data to obtain the topic generation model, in which the mapping relationship between the sample materials and the meteorological data is stored.

[0015] In some exemplary embodiments of the present disclosure, before training the diffusion model based on the plurality of sample meteorological data and the plurality of sample materials related to each of the sample meteorological data, the method further includes:

[0016] Performing data standardization or normalization processing on the sample meteorological data and the sample material;

[0017] Parameters of the sample material are processed, where the parameters of the sample material include format and image size.

[0018] In some exemplary embodiments of the present disclosure, the topic generation method further includes:

[0019] Receiving a first material sent by an electronic device, where the first material is configured by a user;

[0020] The target theme is generated based on the theme generation model, the weather information and the first material.

[0021] According to a second aspect of an embodiment of the present disclosure, a theme generation method is provided, which is applied to an electronic device, and the theme generation method includes:

[0022] Determine target region information based on the user setting instruction, where the target region information is at least used to characterize the target area;

[0023] Sending at least one of weather information and the target area information to a server, wherein the weather information is determined based on the target area information, the weather information is used to characterize the weather conditions of the target area during a target time period, and the weather information includes a plurality of meteorological data;

[0024] A target theme sent by the server is received, wherein the target theme is generated by a theme generation model pre-stored in the server based at least on weather information of the target area, and the target theme includes at least one of a wallpaper and a screen saver.

[0025] In some exemplary embodiments of the present disclosure, determining the target region information based on the user setting instruction includes:

[0026] Based on the first instruction, determining that the target area is a first area, where the first area is an area where the electronic device is located;

[0027] or,

[0028] Based on the second instruction, the target area is determined to be a second area, the second area is a preset area except the area where the electronic device is located, and the second instruction is used to indicate the second area.

[0029] In some exemplary embodiments of the present disclosure, the method for determining the weather information based on the target area information includes:

[0030] Launching a target application, wherein the target application is a weather-related application;

[0031] Acquire the weather conditions of the target area in the target application during the target time period as the weather information;

[0032] The target time period is the current time or a time after a preset time period from the current time.

[0033] In some exemplary embodiments of the present disclosure, the topic generation method further includes:

[0034] A first material is sent to the server, wherein the first material is configured by a user.

[0035] In some exemplary embodiments of the present disclosure, the topic generation method further includes:

[0036] When the weather information of the target area changes, sending the changed weather information to the server;

[0037] Receive the target theme updated according to the changed weather information.

[0038] According to a third aspect of an embodiment of the present disclosure, a theme generation device is provided, which is applied to a server, and the theme generation device includes:

[0039] A first receiving module is used to receive at least one of target area information and weather information, wherein the target area information is used to characterize at least a target area, and the weather information is used to characterize the weather conditions of the target area during a target time period, and the weather information includes a plurality of meteorological data;

[0040] A generation module, configured to generate a target theme based on a pre-stored theme generation model and at least one of the target region information and the weather information, wherein the target theme is generated based at least on the weather information of the target region, and the target theme includes at least one of a wallpaper and a screen saver;

[0041] The first sending module is used to send the target topic to the electronic device.

[0042] According to a fourth aspect of an embodiment of the present disclosure, a theme generation device is provided, which is applied to an electronic device, and the theme generation device includes:

[0043] A determination module, configured to determine target region information based on a user-set instruction, wherein the target region information is at least used to characterize a target area;

[0044] A second sending module is used to send at least one of weather information and the target area information to a server, wherein the weather information is determined based on the target area information, the weather information is used to characterize the weather conditions of the target area during a target time period, and the weather information includes a plurality of meteorological data;

[0045] The second receiving module is used to receive a target theme sent by the server, wherein the target theme is generated by a theme generation model pre-stored in the server based at least on weather information of the target area, and the target theme includes at least one of wallpaper and screen saver.

[0046] According to a fifth aspect of an embodiment of the present disclosure, a server is provided, the server comprising:

[0047] processor;

[0048] a memory for storing processor-executable instructions;

[0049] Among them, the processor is configured to execute executable instructions in the memory to implement the topic generation method provided in the first aspect of the present disclosure.

[0050] According to a sixth aspect of an embodiment of the present disclosure, a non-temporary computer-readable storage medium is provided, on which executable instructions are stored. When the executable instructions are executed by a processor, the subject generation method provided in the first aspect of the present disclosure is implemented.

[0051] According to a seventh aspect of an embodiment of the present disclosure, an electronic device is provided, the electronic device comprising:

[0052] Display screen;

[0053] processor;

[0054] a memory for storing processor-executable instructions;

[0055] Among them, the processor is configured to execute executable instructions in the memory to implement the topic generation method provided in the second aspect of the present disclosure.

[0056] According to an eighth aspect of an embodiment of the present disclosure, a non-temporary computer-readable storage medium is provided, on which executable instructions are stored. When the executable instructions are executed by a processor, the subject generation method provided in the second aspect of the present disclosure is implemented.

[0057] The above method of the present disclosure has the following beneficial effects: the theme generation method of the present disclosure is that the server generates a target theme based on a pre-stored theme generation model and at least one of target area information and weather information, and sends the target theme to the electronic device, wherein the target theme includes at least one of wallpaper and screen saver, thereby making the wallpaper and screen saver of the electronic device more vivid, vivid, and unique; because the weather information of the target area information can be integrated into the target theme, the user's visual experience is enhanced; and because the target theme received by the electronic device can be continuously changed according to the weather information, the target theme generation process can be performed without human participation, thereby improving the generation efficiency of the target theme and saving time, cost and human resources.

[0058] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0059] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and, together with the description, serve to explain the principles of the present disclosure.

[0060] Figure 1 The figure is a flowchart of a method for generating a topic according to an exemplary embodiment.

[0061] Figure 2 It is a schematic diagram of a target subject according to an exemplary embodiment.

[0062] Figure 3 The figure is a flowchart of a method for generating a topic according to an exemplary embodiment.

[0063] Figure 4 The figure is a flowchart of a method for generating a topic according to an exemplary embodiment.

[0064] Figure 5 It is a schematic diagram of a target subject according to an exemplary embodiment.

[0065] Figure 6 The figure is a flowchart of a method for generating a topic according to an exemplary embodiment.

[0066] Figure 7 The figure is a flowchart of a method for generating a topic according to an exemplary embodiment.

[0067] Figure 8 The figure is a block diagram of a theme generating device according to an exemplary embodiment.

[0068] Fig. 9 The figure is a block diagram of a theme generating device according to an exemplary embodiment.

[0069] Fig.10 is a block diagram of a server according to an exemplary embodiment. DETAILED DESCRIPTION

[0070] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present disclosure. Instead, they are merely examples of devices and methods consistent with some aspects of the present disclosure as detailed in the appended claims.

[0071] The present disclosure provides a theme generation method, in which an electronic device sends the weather information of a target area or sends the target area to a server, and the server determines the weather information of the target area according to the received target area information or directly generates a target theme through a pre-stored theme generation model according to the received weather information, and sends the target theme to the electronic device for display, so that the electronic device can display weather-related theme content such as wallpapers and screen savers, thereby improving the interactive emotional expression between the electronic device and the user, and improving the real-time, personalized and uniqueness of the theme of the electronic device. Since the theme generated by the server can be combined with the weather information, the visualization effect of the weather information is achieved, the visual effect of the electronic device is enhanced, and the user experience is improved.

[0072] The exemplary embodiment of the present disclosure provides a topic generation method, which is applied to a server for generating a target topic, such as Figure 1 As shown, the subject generation method shown in the present disclosure includes:

[0073] S101, receiving at least one of target area information and weather information;

[0074] S102, generating a target theme based on a pre-stored theme generation model and at least one of target region information and weather information;

[0075] S103, sending the target topic to the electronic device.

[0076] In step S101, the target area information represents the target area. The target area information can be a target area directly set by the user of the electronic device through input. For example, the user directly enters specific city information such as Beijing, Dali, Los Angeles, etc. in the relevant application, and can also enter longitude and latitude information, and can also enter scenic spot information; the target area information can also be the real-time position of the electronic device directly determined by the electronic device through a communication connection with a positioning device such as GPS.

[0077] The weather information represents the weather conditions in the target time period of the target area, wherein the weather information includes multiple meteorological data, such as temperature, humidity, ultraviolet intensity, precipitation, wind direction, wind speed, etc.; the target time period refers to the specific time period for which the user wants to know the weather information, which can be the current time or the time after a preset time period from the current time. For example, the target area information determines that the target area is Beijing, the current time is 12:00, and the preset time period is half an hour. The weather information is the weather conditions in Beijing at 12:30 in the target time period. The received weather information is determined to be that the temperature in Beijing at 12:30 is 40°C, the humidity is 26%, the precipitation is 0.0mm, and the ultraviolet index is level 11.

[0078] The server generating the target theme receives at least one of the target area information and the weather information sent by the electronic device. In one example, the server generating the target theme may only receive the target area information sent by the electronic device, and then the server generating the target theme may communicate with the weather-related server to obtain the weather information of the target area. In another example, the server generating the target theme may also only receive the weather information sent by the electronic device, and then the weather information may be directly used when the target theme is subsequently formed. In yet another example, the server generating the target theme may also receive the target area information and the weather information at the same time, so that when the target theme is generated using the pre-stored theme generation model, the generated target theme not only includes the weather information, but also includes the characteristic scenery or characteristic buildings of the target area represented by the target area information, so as to further enhance the uniqueness, diversity and personalization of the target theme, and better help to express and communicate emotions with users.

[0079] In step S102, a theme generation model is pre-stored in the server. The theme generation model is trained by a neural network model using sample meteorological data and sample materials. Since the mapping relationship between sample materials and weather information is stored in the theme generation model, the server can use the theme generation model to output a target theme related to weather information based on weather information. The theme generation model can be trained and generated using a diffusion model. By training using sample meteorological data and sample materials related to meteorological data during the training process, a vertical model related to weather can be obtained. When using the trained theme generation model (that is, the trained vertical model related to weather), weather-related pictures, icons, or animated pictures and other theme contents can be quickly generated according to the weather information received by the server. Since the generated target theme is automatically and randomly generated by the theme generation model, there is no need to worry about using pictures involving copyright issues, and there is no copyright risk. At the same time, the target theme is automatically generated using the theme generation model, and the target theme can be adjusted and updated in real time according to weather changes, giving users a more novel and varied visual experience.

[0080] It should be noted here that if the server receives target area information sent by an electronic device, the server needs to first obtain the corresponding weather information based on the target area information, and then use the topic generation model to generate the target topic. The target area information cannot be directly input into the topic generation model.

[0081] Among them, the target theme includes at least one of wallpaper and screen saver. Wallpaper refers to the image or animated picture displayed on the interface background of the electronic device when the electronic device is turned on. The screen saver refers to the image or animated picture displayed on the interface of the electronic device when the electronic device is in the lock screen state. The target theme can be displayed on the main screen interface of the electronic device as a wallpaper; the target theme can also be displayed on the lock screen interface of the electronic device as a screen saver; the target theme can also be displayed on the main screen interface and the lock screen interface at the same time. For example, the user is currently traveling in Beijing, it is daytime and the weather is sunny. If the server that generates the target theme receives the weather information sent by the electronic device, the server can generate a wallpaper showing the sun; for another example, the user sets the target area to Shanghai and wants to know the weather information in 2 hours. The server that generates the target theme can search for the weather information of Shanghai in 2 hours in the weather-related server based on the received target area information. It is rainstorm, and the server can generate a screen saver showing rain.

[0082] Of course, it is understandable that the target theme may include not only wallpapers, screen savers, etc., but also input method input box images, icons of various applications, and other graphics and animated graphics-related content that can enhance the visual experience.

[0083] In step S103, the server sends the generated target theme to the electronic device, and the electronic device displays the target theme as a wallpaper or screen saver on the electronic device, so that the user can view weather information in real time and enjoy a personalized display experience. The server can automatically update the target theme on the electronic device according to the change of weather information, and can also remind the user to change the target theme by sending a reminder message when the target theme needs to be changed, and then change it after the user agrees.

[0084] In order to better illustrate the effect of the method involved in the present disclosure, firstly, the relevant contents of the subject of the electronic device are described.

[0085] Currently, the production of wallpapers and screensavers requires designers to create them based on their creativity or purchase material images from external websites, and then manually adjust the size and resolution of the material images to make them suitable for different models of electronic devices. These two steps are mainly completed manually, which requires a lot of time and labor costs. In addition, wallpapers and screensavers are usually automatically replaced based on random push notifications, and their content will not change with changes in the user's environment, and cannot provide users with intelligent services.

[0086] The general steps for generating and using wallpapers and screen savers are: 1) Designers use drawing tools to design image materials, or purchase image materials from the Internet and other channels; 2) Adjust the size and resolution of the image materials according to different electronic devices; 3) Upload the adjusted image materials to the server for users to download and use; 4) Users select and download their favorite image materials in the app store or wallpaper-related applications, store the image materials locally and use them as wallpapers or screen savers; 5) Some wallpaper-related applications have an automatic wallpaper changing function, which automatically and randomly changes the wallpaper of electronic devices at a fixed time.

[0087] The above-mentioned method of generating and using wallpapers and screen savers has the following problems: 1) High time and cost: Manually producing image materials requires a lot of time and human resources, and purchasing image materials externally will increase product costs; 2) Low consistency and efficiency: Different designers will produce different styles and quality levels, resulting in a lack of consistency between materials, and the speed and efficiency of manually producing image materials will be limited by the designer's personal limitations. External purchase of image materials requires negotiation, purchase and delivery with suppliers, which may cause project time delays and affect progress and efficiency; 3) Poor scalability and customization: Manually produced or externally purchased image materials have certain limitations in large-scale and customization. When a large number of image materials are required or they need to be customized according to different needs, manual production or external purchase may not meet the needs and will face time and cost challenges; 4) Slow update and iteration: If the product needs to frequently update and iterate image materials, the update speed will be slowed down and the demand for fast iteration of image materials will not be met; 5) Lack of uniqueness: External purchase of image materials may cause multiple products or brands to use the same or similar materials, lacking uniqueness and personalization, affecting product differentiation and market competitiveness.

[0088] Compared to the above-mentioned wallpaper and screen saver problems, the target theme involved in the method in the above embodiment of the present disclosure is automatically generated by the server. The server can use the pre-stored theme generation model to generate a target theme related to the weather information of the target area. When the server receives the target area information or weather information or a combination of the target area information and weather information, the multiple sample materials stored in the theme generation model can be integrated according to the weather information, thereby randomly generating a new static image or dynamic image. Different weather information is often associated with specific emotions and atmospheres. Generating wallpapers and screen savers associated with meteorological data based on weather information can better express and convey emotions. For example, sunny weather can bring pleasant and energetic wallpapers, while rainy weather can present a screen saver with a tranquil atmosphere, so that users can obtain a unique and personalized theme experience based on their region and weather conditions, or the region and weather conditions that users care about.

[0089] In one example, the screen saver or wallpaper may include a weather symbol, temperature, and a cartoon character that reflects the weather conditions, such as Figure 2 As shown in (a), when the weather information of the target area is a sunny day with a temperature of 40°C, the server generates a target theme related to the weather conditions of the target area during the target time period. The target theme contains a sunny sun logo, text of a temperature of 40°C, a cartoon character, and the feeling that the weather conditions are "too hot". Figure 2As shown in (b), when the weather information of the target area is a rainy day with a temperature of 26°C, the server generates a target theme related to the weather conditions of the target area during the target time period. The target theme includes a rainy day sun logo, text of a temperature of 26°C, a cartoon character, and the feeling of the weather condition being "really cool".

[0090] In another example, when the user is traveling in Wuzhen, the elements displayed on the screensaver or wallpaper may include the small bridges, flowing water and other characteristic attractions of Wuzhen. If it is daytime and the weather is clear, the elements such as small bridges, flowing water and sunshine can be displayed on the screensaver or wallpaper. If it is daytime but it is raining, the landscapes such as stone bridges, misty rain, foggy, and black-sailed boats can be displayed on the screensaver or wallpaper. Since users are prone to sadness on rainy days, the input box of the input method of the electronic device can be changed to a melancholy blue with raindrops falling, so as to match the user's mood. If it is night and the moon can be seen, the screensaver or wallpaper shows the night of lights in Wuzhen, with a full moon hanging high in the sky and a few clouds floating, so that the user can still feel the beauty of Wuzhen when using the electronic device, and be completely immersed in the beauty of the scenery of Wuzhen. In addition, the elements of the black-sailed boat can also be generated on the input box of the input method of the electronic device, so as to bring users a full range of experience.

[0091] In another example, when the user's family went to the Maldives for vacation, the user was very concerned about the weather in the Maldives, so that the user could input the Maldives as the target area into the electronic device, and send the current weather information related to the Maldives obtained from the weather application to the server storing the theme generation model. The server generates wallpapers and screensavers according to the weather information of the Maldives sent by the received electronic device and the information that the target area is the Maldives. The wallpapers and screensavers contain elements such as the sea and sailboats. If the weather in the Maldives is clear, light blue water, bright sunshine and beaches, and leisurely swimming fish are displayed. If the weather in the Maldives is not good, the rolling waves, clouds in the air, and other elements are displayed in the screensaver or wallpaper. Although the user did not travel to the Maldives with his family, he was able to feel the weather in the Maldives through wallpapers or screensavers, and there was a sense of empathy, which improved the user's experience.

[0092] In the present disclosure, the server generates a target theme based on a pre-stored theme generation model and at least one of the target area information and weather information, and creates unique wallpapers and screensavers related to the weather information, so that the wallpapers and screensavers of the electronic device are more vivid and vivid. This innovation can bring novel and interesting wallpaper and screensaver options to users, attracting the interest of users, and the target theme can be continuously changed according to the weather information without relying on manual design or purchase, making the target theme diverse and personalized, improving the generation efficiency of the target theme, and reducing the generation cost of the target theme.

[0093] According to an exemplary embodiment, Figure 3 As shown, the topic generation method in this embodiment includes:

[0094] S301, receiving at least one of target area information and weather information;

[0095] S302, based on the target region information, obtaining weather information of the target region;

[0096] S303, inputting weather information into a topic generation model to generate a target topic;

[0097] S304: Send the target topic to the electronic device.

[0098] Among them, steps S301 and S304 are the same as those in the above embodiment and will not be described again.

[0099] In step S302, if the server generating the target topic only receives the target region information, the server generating the target topic obtains the weather information of the target area by interacting with the weather-related server based on the target region information. For example, the electronic device sends the target region information to the server generating the target topic, and after receiving the target region information, the server generating the target topic can determine that the target area is Beijing, and the server generating the target topic obtains the weather information of Beijing by interacting with the weather-related server.

[0100] In step S303, a theme generation model is pre-stored in the server generating the target theme. Since the theme generation model is a neural network model that has been trained and stores the mapping relationship between sample materials and meteorological data, the weather information is input into the theme generation model, and the theme generation model can generate a target theme related to the weather information of the target area. For example, the sample materials corresponding to rainy days in the theme generation model include dark sky, raindrops, dark clouds, large trees with raindrops, and swamps with water, and the sample materials corresponding to sunny days include the sun, sunshine, dry grass, reflective pools, etc. When the weather information input into the theme generation model is rainy days, the theme generation model can integrate the sample materials corresponding to rainy days to generate a wallpaper with sky, raindrops, dark clouds, and large trees with raindrops.

[0101] In some embodiments, the topic generation method includes establishing a topic generation model, and the method of establishing the topic generation model includes:

[0102] Acquire a plurality of sample meteorological data and a plurality of sample materials related to each sample meteorological data, wherein the sample materials include images, and the images include image features related to the sample meteorological data;

[0103] The diffusion model is trained based on multiple sample meteorological data and multiple sample materials related to each sample meteorological data to obtain a topic generation model, in which the mapping relationship between the sample materials and the meteorological data is stored.

[0104] The topic generation model can be a diffusion model generated by training based on weather information and topic materials. The diffusion model receives multiple sample meteorological data and multiple sample materials related to each sample meteorological data, wherein the sample meteorological data includes meteorological data of various weather conditions such as sunny days, rainy days, cloudy days, snowy days, etc., and can also include meteorological data of the four seasons of spring, summer, autumn, and winter. The sample materials include images, texts, icons, characters, etc., wherein the images include image features related to the sample meteorological data, such as color, lines, structure, etc., and the images corresponding to sunny days have a yellowish hue, and the images corresponding to rainy days have a bluish hue.

[0105] The diffusion model is trained using multiple sample meteorological data and multiple sample materials related to each sample meteorological data. The diffusion model selects several sample materials corresponding to the sample meteorological data from all sample materials, and generates a target topic through integration. The diffusion model can use the LoRA (Low-Rank Adaption) fine-tuning technology to fine-tune a vertical model that generates a target topic related to weather information. If the diffusion model can generate a target topic related to the sample meteorological data based on the sample meteorological data, it means that the diffusion model training is complete, and the trained diffusion model can be used as a topic generation model and stored in the server. Since the diffusion model learns the relationship between meteorological data and materials, the mapping relationship between sample materials and meteorological data is stored in the topic generation model, so the server can generate target topics related to weather information based on weather information.

[0106] In some embodiments, before training the diffusion model based on the plurality of sample meteorological data and the plurality of sample materials related to each sample meteorological data, the method further includes:

[0107] Perform data standardization or normalization on sample meteorological data and sample materials;

[0108] The parameters of the sample material are processed, and the parameters of the sample material include format and image size.

[0109] Before using multiple sample meteorological data and multiple sample materials related to each sample meteorological data to train the diffusion model, the sample meteorological data and sample materials need to be processed. Since the acquired sample meteorological data and sample materials are random and diverse, in order to ensure the consistency and availability of the samples, the sample meteorological data and sample materials are subjected to data standardization or normalization, and the parameters of the sample materials need to be processed. The parameters of the sample materials include the format and image size, and in addition, the image pixels and other parameters may also be included. For example, all images in the sample materials are uniformly adjusted to jpg format, all images in the sample materials are uniformly adjusted to a size of 16:9, and all data formats in the sample materials are adjusted to a unified format, so that the sample materials can adapt to the resolution and size of electronic devices. When the topic generation model is used later, it is easy to quickly merge multiple materials, improve generation efficiency and data versatility.

[0110] The diffusion model is a mathematical model used for image processing and computer vision tasks. The diffusion model is inspired by non-equilibrium thermodynamics. It first defines a Markov chain of diffusion steps to gradually add random noise to the data, and then learns the reverse diffusion process to construct the required data samples from the noise. The diffusion model is essentially a set of probability distributions, that is, random samples are taken from a certain data P_data independently and identically to form a training data set, and then a distribution P_theta closest to P_data is found from the generative model (probability distribution).

[0111] The diffusion model includes a forward process and a reverse process. The forward process is to continuously add noise to any distribution so that it eventually becomes a pure noise distribution N(0, I), which can be understood as continuously adding noise to a clear picture, so as to finally obtain an image that is all noise; the reverse process is to generate an image by reversely diffusing pure noise, which can be understood as removing the noise from an image that is all noise, so as to obtain a clear image. For example, the sample is a clear image, and the forward process is to add noise with various image features to the clear image step by step, so that a blurred image with a lot of noise is finally generated. The reverse process is to deconstruct the blurred image, remove the noise on the blurred image step by step, so that a clear image is finally generated. Through the above forward process and reverse process, the various parameters involved in the process of adding noise to make the clear image become pure noise can be known, and then when the trained model is used to generate a clear image in the future, the above parameters can be used for the denoising step to obtain a clear image.

[0112] The forward process is to add Gaussian noise to the real image samples x0~q(x) by T times accumulation to obtain x1, x2, ..., x T , where the step size of each diffusion step is a hyperparameter of the variance of a series of Gaussian distributions The hyperparameter determines how much noise is added at each step. Since each moment t in the forward process is only related to the moment t-1, it can also be regarded as a Markov process, which corresponds to the following formula (1). In the forward process, as t increases, x t is getting closer and closer to pure noise. When T→∞, x T It is a complete Gaussian noise. The following formula (2) is the multiplication of each step of adding noise. The process formula is as follows, where I is the adjustment coefficient of the hyperparameter, that is, in the process of accumulating noise at each step, the adjustment coefficient I can be used to adjust according to different samples.

[0113]

[0114]

[0115] The reverse process is to reverse the above process, which can be understood as x t As input, predict the mean and variance of the Gaussian distribution, and then randomly sample based on the predicted distribution to get x t-1 , through continuous prediction and sampling process, finally generate a real picture x0. That is, for q(x t-1 |x t ) is sampled from Gaussian noise x T ~N(0,I) restores the original image distribution x0~q(x). The process formula is as follows, where μ represents the mean and ∑ represents the variance, that is, at time t, the noise x t The corresponding mean parameter μ θ and variance parameter ∑ θ .

[0116]

[0117]

[0118] The diffusion model mainly consists of three parts, namely Text Encoder, Image Information Creator and Image Decoder. Among them, the Text Encoder module is responsible for converting text input (such as weather information) into data encoding that can be understood by computers. Text Encoder is mainly composed of the CLIPText model. The training set of this model consists of 400 million images and their descriptions. During training, the images and texts are encoded separately, and then the generated embeddings are compared using cosine similarity. Through training, the encoder can finally generate embeddings similar to images and descriptions. The Text Encoder module puts the data into a matrix and transmits it to the Image Information Creator module. The Image Information Creator module is responsible for combining text to gradually remove noise from pure noise and generate image latent variables, where the image latent variables are various feature information of the image. The image latent variables are placed in a matrix and transmitted to the Image Decoder. The Image Information Creator is mainly composed of the UNet model and Scheduler. At each step, the input latent information is operated to generate another latent information. The generated latent information contains the fusion information of the input text information and the visual information obtained by the model from the image training set. Image Decoder is mainly composed of the Decoder part of the VAE model. Image Decoder is responsible for decoding the image latent variables and generating images.

[0119] The training process of the diffusion model includes two processes: training and sampling. The training process is the noise adding process mentioned above, and the sampling process is the noise reducing process mentioned above. The pseudo code of the training process is as follows:

[0120] Algorithm 1 Training

[0121] 1: repeat

[0122] 2: x0~q(x)

[0123] 3: t~Uniform({1,…,T})

[0124] 4:

[0125] 5: Take gradient descent step on

[0126]

[0127] 6: until converged

[0128] x0 is a clear image, and its training process is to sample a noise from a standard Gaussian distribution That is, any image feature in the image, such as color, line, structure, etc. ∈ θ is a function of the guidance noise intensity, It is the hyperparameter at time t. The generated noise is compared with the original noise. If the square result is smaller, it means that the generated noise is close to the original noise, that is, the loss is minimized or stabilized to a fixed value through gradient descent. The training is carried out until convergence. Due to the long training time, T can be set to 1000 in the code.

[0129] The pseudo code of the sampling process is as follows:

[0130] Algorithm 2Sampling

[0131] 1:

[0132] 2: for t = T, ..., 1 do

[0133] 3: else z=0

[0134] 4:

[0135] 5: end for

[0136] 6: until x0

[0137] x T is a blurred image with noise, x t-1 Indicates the noise map of the previous moment. The sampling process is to sample a noise from the standard Gaussian distribution. It starts from time step T and iterates forward diffusion to time step 1. If the time step is not 1, a noise is sampled from the standard Gaussian distribution, that is, there is still noise and it needs to be removed. Otherwise, z = 0. The noise map of each time step t is calculated according to the Gaussian distribution.

[0138] According to an exemplary embodiment, Figure 4 As shown, the topic generation method in this embodiment includes:

[0139] S401, receiving at least one of target area information and weather information;

[0140] S402, based on the target region information, obtaining weather information of the target region;

[0141] S403, receiving a first material sent by an electronic device, where the first material is configured by a user;

[0142] S404, generating a target theme based on the theme generation model, weather information and the first material;

[0143] S405: Send the target topic to the electronic device.

[0144] Among them, steps S401, S402, and S405 are the same as those in the above embodiment and will not be repeated here.

[0145] In step S403, the server may receive a first material sent by the electronic device, wherein the first material is configured by the user and may include scenery and buildings of the target area, text, cartoon patterns, etc. For example, the first material may be a font that the user likes, scenery of the target area that the user likes, or a cartoon character that the user likes. The user may also use a personal photo as the first material.

[0146] In addition to adding weather information to the generated target theme, the present invention also allows users to add personal favorite patterns, texts and other content to make the target theme more personal. In step S404, when the server that generates the target theme receives the weather information and the first material, the server that generates the target theme can use the theme generation model to generate a target theme related to the weather information that contains the first material. For example, a user can send his or her own photo or his or her own name to the server as the first material, so that when the theme generation model generates the target theme, the photo or name sent by the user through the electronic device can be integrated into the target theme, thereby further enhancing the personalization and uniqueness of the target theme.

[0147] For another example, if the first material is the scenery and buildings of the target area, the generated Figure 5 (c) and Figure 5The target theme shown in (d) displays not only the sample material related to the weather information, but also the first material related to the target area. For example, the server generating the target theme receives the target area information and weather information. The target area information shows that the user is in Guangzhou and it is currently a sunny day with a temperature of 35°C. The server inputs the first material of a small waist and the weather information into the theme generation model. The theme generation model fuses the sample material and the first material that have a corresponding relationship with the weather information, and outputs a target theme showing the sun and a small waist. For another example, the server generating the target theme receives the target area information of Inner Mongolia, and the received weather information is a cloudy day with a temperature of 26°C. It also receives the first material containing a grassland pattern. The server inputs the above information into the theme generation model. The theme generation model fuses the sample material and the first material that have a corresponding relationship with the weather information, and outputs a target theme showing cloudy skies and grassland.

[0148] In the present disclosure, the target topics randomly generated based on the topic generation model and weather information can easily achieve the function of continuous updating and iteration, and high-quality and non-repetitive target topics can be generated by utilizing existing resources to meet the personalized and diverse needs of users without any copyright risks.

[0149] The exemplary embodiment of the present disclosure provides a theme generation method, which is applied to an electronic device, and the electronic device may be a smart electronic device with a display screen, such as a mobile phone, a tablet computer, and a smart wearable device. Figure 6 As shown, the display method shown in the present disclosure includes:

[0150] S601, determining target region information based on a user setting instruction;

[0151] S602, sending at least one of weather information and target area information to a server;

[0152] S603: Receive the target topic sent by the server.

[0153] In step S601, the user setting instruction may be, for example, an instruction input through a display screen of an electronic device, an instruction input by a user through voice, or an instruction input by selecting an option displayed on a display screen through touch.

[0154] In one example, the user setting instruction can be, for example, a target area directly set by the user through input, such as the user directly inputs specific city information such as Beijing, Dali, Los Angeles, etc. in the relevant application, or inputs latitude and longitude information, and also inputs scenic spot information, such as the Leshan Giant Buddha, etc. Thus, the user can arbitrarily select the weather information of the target area that he wants to know, so as to obtain the subject related to the weather information of the target area that he wants to know when forming the target theme later. For example, the real-time location of the electronic device used by the user is Beijing, but the user is about to leave for Shanghai. At this time, the user can set the target area to Shanghai through the user setting instruction, and the target area information obtained in step S601 is Shanghai. Among them, the application used by the user can be an application pre-installed when the electronic device leaves the factory, or it can be an application downloaded by the user later.

[0155] In another example, the user setting instruction may be an instruction for instructing to determine the target area information through a communication connection with a positioning device such as GPS. After the user setting instruction is input, the real-time location information of the electronic device automatically located by a positioning device such as GPS on the electronic device will be used as a reference to obtain the weather information of the real-time location of the electronic device. For example, if a user takes a flight from Beijing to Shanghai, after getting off the plane and turning on the electronic device, the positioning device such as GPS of the electronic device will update the real-time location of the electronic device, so that the target area information obtained in step S601 is Shanghai.

[0156] The target area information represents the target area. After obtaining the target area information, the electronic device can directly send the target area information to the server. The server pre-stores a trained neural network model, so that after receiving the target area information, it can further obtain weather information related to the target area information, and then use the weather information to automatically generate the target theme. For example, the display screen displays an icon representing the location. When the user applies touch pressure to the icon representing the location, the electronic device automatically updates the location and obtains the GPS location information, and determines the target area information from the location information.

[0157] In addition, the user setting instruction can also be a voice instruction. The electronic device obtains the voice content input by the user through the microphone. When the voice content input by the user is consistent with the voice instruction content preset in the electronic device, the voice content will be used to trigger the user setting instruction. For example, the voice instruction preset in the electronic device is "determine the current location", then when the electronic device receives the user input voice content of "determine the current location" through the microphone, the user setting instruction is triggered, and the electronic device determines the target geographical information. The user setting instruction can also be a gesture instruction. The electronic device obtains the user's gesture through the gesture tracking sensor. When the user's gesture is consistent with the gesture preset in the electronic device, the electronic device will use the gesture to trigger the user setting instruction. For example, the gesture preset in the electronic device to determine the current location is to approach the display screen from far to near with the display screen as a reference. Then, when the electronic device receives the user's gesture from far to near through the gesture tracking sensor, the setting instruction is triggered, and the electronic device determines the target geographical information.

[0158] In step S602, after determining the target region information, the electronic device can directly query the weather information of the target region involved in the target region information by using a weather application program, etc., wherein the weather information is used to characterize the weather conditions of the target time period of the target region; the target time period can be the current time, or the time after a preset time period from the current time, and the user can set the target time period according to actual needs; the weather conditions can include information such as temperature, humidity, precipitation, and ultraviolet index. For example, the target region information determines that the target region is Beijing, the current time is 12:00, and the preset time period is half an hour, then the weather information is the weather conditions of Beijing at 12:30 in the target time period, and the weather information determined by the server is that the temperature of Beijing at 12:30 is 40°C, the humidity is 26%, the precipitation is 0.0mm, and the ultraviolet index is 11 levels.

[0159] After the electronic device obtains the target area information, it can send the target area information to a weather-related server, and obtain weather information related to the target area information from the weather-related server. Then the electronic device can send the weather information to a model for generating a target theme that has a pre-stored neural network model, so that the server that has a pre-stored neural network model can generate a target theme related to the weather and then send it to the electronic device for display.

[0160] For example, the electronic device can also obtain weather information of the target area based on the weather-related application carried by the electronic device itself, and the electronic device can send the weather information to the server used to generate the target topic. The server used to generate the target topic can directly generate the target topic corresponding to the weather information after receiving the weather information sent by the electronic device. For example, the electronic device obtains the API key of the weather-related application, writes code in a programming language to call the API, obtains the weather information of the target area by accessing the website of the weather data service provider, and converts it into text and sends it to the server used to generate the target topic.

[0161] In step S603, the electronic device receives the target theme generated and sent by the server pre-stored with the neural network model. The target theme includes at least one of wallpaper and screen saver. The electronic device can display the received target theme on the main screen interface of the electronic device as wallpaper; the electronic device can also display the received target theme on the lock screen interface of the electronic device as a screen saver; the electronic device can also display the target on both the main screen interface and the lock screen interface at the same time.

[0162] In the present disclosure, an electronic device obtains weather information corresponding to a target time period of the target area information based on target area information, and displays a received target theme related to the weather information, wherein the target theme includes at least one of wallpaper and screen saver, thereby making the wallpaper and screen saver of the electronic device more vivid, vivid, and unique. Since the weather information of the target area information can be integrated into the target theme, the user's visual experience is enhanced; and since the theme received by the electronic device can be continuously changed according to the weather information, the target theme generation process can be performed without human participation, thereby improving the generation efficiency of the target theme and saving time and human resources.

[0163] In some embodiments, step S601 determines the target region based on the user setting instruction, including:

[0164] Based on the first instruction, determining that the target area is a first area, where the first area is an area where the electronic device is located;

[0165] The first instruction may be a touch instruction. The electronic device maintains a communication connection with the display screen to obtain the user's touch operation on the display screen. When the user clicks and applies pressure on the set virtual button on the display screen, the display screen sends the first instruction to the electronic device. Based on the first instruction, the electronic device automatically determines the area where the electronic device is located using a positioning device such as GPS, and uses the area where the electronic device is located as the target area. The electronic device uses the target area determined based on the first instruction as the first area, and sends the first regional information to a weather-related server for subsequent acquisition of weather information of the first area from the weather-related server. For example, the electronic device is currently in Beijing. When the electronic device receives a touch operation from the user acting on the display screen for positioning, the electronic device obtains the current positioning information of the GPS, determines the first regional information from the positioning information, and the target area is the Beijing area where the electronic device is currently located. In addition, the first instruction may also be a voice instruction, a gesture instruction, etc., and a voice instruction or a gesture instruction is used to trigger the electronic device to determine the first area.

[0166] In the present disclosure, when the target area is the area where the electronic device is located, the electronic device can receive and display a target theme corresponding to the weather information of the area where the electronic device is located. The target theme can reflect the current weather conditions in real time, so that the user can understand the current weather through the wallpaper, including temperature, weather status, etc., to enhance the perception and understanding of the local weather.

[0167] In some embodiments, step S601 determines the target region based on the user setting instruction, including:

[0168] Based on the second instruction, the target area is determined to be the second area, the second area is a preset area except the area where the electronic device is located, and the second instruction is used to indicate the second area.

[0169] The second instruction can be a voice instruction. The electronic device uses a microphone to obtain the voice content input by the user. When the voice content input by the user is consistent with the voice instruction content preset in the electronic device, the electronic device will use the voice content to trigger the second instruction. Based on the second instruction, the electronic device determines a preset area other than the area where the electronic device is located, and the electronic device uses the preset area as the target area. Among them, the preset area can be pre-stored in the electronic device by the user, or it can be selected and determined by the user in real time. For example, the user is currently in Beijing, and the user has previously stored Shanghai as a preset area in the electronic device, so Shanghai can be directly determined as the target area based on the second instruction. The user can also directly enter the name of the city he wants to know, such as Dali, and Dali can be determined as the target area based on the second instruction. The electronic device uses the target area determined based on the second instruction as the second area, and sends the second regional information to a weather-related server for subsequent acquisition of weather information in the second area. In addition, the second instruction can also be a touch instruction, a gesture instruction, etc., and the touch instruction or gesture instruction is used to trigger the electronic device to determine the second area.

[0170] In the present disclosure, when the target area is a preset area other than the area where the electronic device is located, the server can generate a target theme corresponding to the weather information of the preset area. When the electronic device displays the target theme, it is convenient for users to understand the weather conditions in other places, allowing users to contact family or friends in other places in time, issue weather reminders, and improve user experience.

[0171] According to an exemplary embodiment, Figure 7 As shown, the display method in this embodiment includes:

[0172] S701, determining target region information based on a user setting instruction;

[0173] S702, starting a target application, where the target application is a weather-related application;

[0174] S703, obtaining the weather conditions of the target area and the target time period displayed in the target application as weather information;

[0175] S704: Receive the target topic sent by the server.

[0176] Among them, steps S701 and S704 are the same as those in the above embodiment and will not be described again.

[0177] In step S702, the electronic device starts a target application related to weather, and the target application may record the weather conditions of various regions in the world at the current time and within seven days after the current time. The target application may be a weather-related application that comes with the electronic device's operating system, such as Xiaomi Weather; the target application may also be a weather-related application that the electronic device downloads from an application store, such as Moji Weather.

[0178] In step S703, the electronic device determines the target area based on the user-set instruction, and then determines the target time period based on the time requirement, where the target time period is the current moment or the moment after a preset time period from the current moment. After determining the target area and target time period, the electronic device obtains the weather conditions of the target time period of the target area through the target application and uses it as weather information. For example, if the target area is determined to be Beijing, the Xiaomi Weather application can obtain that the current temperature in Beijing is 40°C, and the temperature for 2 hours after the current moment is 40°C. If the preset time period set by the user is 1 hour, the electronic device will obtain the weather conditions of Beijing in Xiaomi Weather after one hour from the current moment, and use the temperature of 40°C as weather information.

[0179] In some embodiments, the topic generation method further includes:

[0180] The first material is sent to the server, wherein the first material is configured by the user.

[0181] The electronic device sends a first material to a server, wherein the first material is configured by the user and may include scenery and buildings of the target area, text, cartoon patterns, etc. For example, the first material may be a font that the user likes, scenery of the target area that the user likes, or a cartoon character that the user likes. The user may also use a personal photo as the first material. A target theme may be generated based on weather information and the first material, so that the target theme displayed by the electronic device can reflect the weather conditions of the target area, so that the user can know the weather conditions based on the target theme, and can also reflect personal characteristics. When the first material is scenery and target buildings, the target theme may be generated based on weather information and the target scenery and target buildings of the target area, integrating the scene characteristics of the target area so that the target theme has regional characteristics. The user may directly know the specific location of the target area through the target theme, while enhancing the user's viewing experience. Figure 5 As shown in (c), the target area is Beijing, the weather information is sunny and the temperature is 40℃, and the target theme is generated based on the weather information and the first material including the target building. Therefore, in addition to the sunny sun logo, the text of the temperature of 40℃, the cartoon character and the feeling of the weather condition "too hot", the generated target theme also has an image of the target building, the Great Wall. Figure 5As shown in (d), the target area is the Xiaoxi Scenic Area in Chongqing, the weather information is rainy and the temperature is 26°C, and the target theme is generated based on the weather information and the first material including the target scenery. Therefore, in addition to the rainy sun logo, the text of the temperature 26°C, the cartoon character and the feeling of the weather condition "really cool", the generated target theme also has an image of the target scenery creek.

[0182] In the present disclosure, the target theme can be generated based on at least one of the weather information, target scenery and target building of the target area, which brings diverse choices for the generation of the target theme, makes the target theme unique, and brings visual beauty and artistry. The generated wallpaper can create attractive visual effects through elements such as color, light and texture, thereby increasing the interest of users.

[0183] In some embodiments, the topic generation method further includes:

[0184] When the weather information of the target area changes, the changed weather information is sent to the server;

[0185] Receive the updated target topic according to the changed weather information.

[0186] The electronic device and the server that generates the target theme can receive weather information of the target area sent by the weather-related server in real time. When it is determined that the weather information of the target area has changed, the server that generates the target theme will update the target theme based on the changed weather information, and send the updated target theme to the electronic device. The electronic device receives the target theme that has been updated according to the changed weather information, so that the wallpaper or screen saver displayed by the electronic device can always truly reflect the weather conditions of the target area. For example, the electronic device determines that the target area is Beijing, and the target time period is the current time. The electronic device and the server that generates the target theme receive the current weather information of Beijing at 14:00, which is sunny and the temperature is 40°C, and generate the following: Figure 2 (a) shows the target subject, the electronic device receives and displays Figure 2 (a) target theme; at 20:00, the electronic device and the server generating the target theme receive weather information of rainy day and temperature 26°C, then the server generating the target theme will update the target theme according to the changed weather information, generating Figure 2 (b) The target subject shown, the electronic device receives and displays Figure 2 (b) The target topic is updated according to the changed weather information.

[0187] In the present disclosure, an electronic device receives and displays a target theme that is updated according to changed weather information, so that the target theme can reflect the weather conditions of the target area in real time, and generates personalized target themes based on the weather information. The diversified target themes can meet the different needs and preferences of users, and the generation of the target themes does not require human participation, which saves time and cost and improves the efficiency of target theme generation.

[0188] The exemplary embodiment of the present disclosure provides a theme generation device, which is applied to a server. Figure 8 As shown, a block diagram of a topic generating device shown in the present disclosure.

[0189] The block diagram includes: a first receiving module 81, a generating module 82, and a first sending module 83. The first receiving module 81 is used to receive at least one of target area information and weather information, the target area information is used to characterize the target area at least, the weather information is used to characterize the weather conditions of the target area in the target time period, and the weather information includes multiple meteorological data; the generating module 82 is used to generate a target theme based on a pre-stored theme generation model and at least one of the target area information and weather information, the target theme is generated at least based on the weather information of the target area, and the target theme includes at least one of wallpaper and screen saver; the first sending module 83 is used to send the target theme to the electronic device.

[0190] In an exemplary embodiment of the present disclosure, the generation module 82 is further used to: obtain weather information of the target area based on the target area information; and input the weather information into the topic generation model to generate a target topic.

[0191] In an exemplary embodiment of the present disclosure, the first receiving module 81 is also used to: obtain multiple sample meteorological data and multiple sample materials related to each sample meteorological data, the sample materials including images, and the images including image features related to the sample meteorological data; train a diffusion model based on the multiple sample meteorological data and the multiple sample materials related to each sample meteorological data to obtain a topic generation model, which stores the mapping relationship between the sample materials and the meteorological data.

[0192] In an exemplary embodiment of the present disclosure, before training the diffusion model based on multiple sample meteorological data and multiple sample materials related to each sample meteorological data, the first receiving module 81 is also used to: perform data standardization or normalization on the sample meteorological data and the sample materials; and process the parameters of the sample materials, wherein the parameters of the sample materials include format and image size.

[0193] In an exemplary embodiment of the present disclosure, the generation module 82 is further used to: receive a first material sent by an electronic device, where the first material is configured by a user; and generate a target theme based on the theme generation model, weather information and the first material.

[0194] Regarding the theme generation device in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.

[0195] The exemplary embodiment of the present disclosure provides a theme generation device, which is applied to an electronic device. Fig. 9 As shown, a block diagram of a topic generating device shown in the present disclosure.

[0196] The block diagram includes: a determination module 91, a second sending module 92, and a second receiving module 93. The determination module 91 is used to determine the target region information based on the user setting instruction, and the target region information is at least used to characterize the target region; the second sending module 92 is used to send at least one of weather information and target region information to the server, wherein the weather information is determined based on the target region information, and the weather information is used to characterize the weather conditions of the target region in the target time period, and the weather information includes multiple meteorological data; the second receiving module 93 is used to receive the target theme sent by the server, wherein the target theme is generated by the theme generation model pre-stored in the server based on at least the weather information of the target region, and the target theme includes at least one of wallpaper and screen saver.

[0197] In an exemplary embodiment of the present disclosure, the determination module 91 is further configured to: based on the first instruction, determine that the target area is a first area, where the first area is an area where the electronic device is located.

[0198] In an exemplary embodiment of the present disclosure, the determination module 91 is further used to: based on the second instruction, determine that the target area is a second area, the second area is a preset area except the area where the electronic device is located, and the second instruction is used to indicate the second area.

[0199] In an exemplary embodiment of the present disclosure, the determination module 91 is also used to: start a target application, which is a weather-related application; obtain the weather conditions of a target time period in a target area in the target application as weather information; wherein the target time period is the current moment or the moment after a preset time period from the current moment.

[0200] In an exemplary embodiment of the present disclosure, the second sending module 92 is further used to: send the first material to the server, wherein the first material is configured by the user.

[0201] In an exemplary embodiment of the present disclosure, the second receiving module 93 is further used for: when the weather information of the target area changes, sending the changed weather information to the server; and receiving the target theme updated according to the changed weather information.

[0202] Regarding the theme generation device in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.

[0203] Fig.10 1 is a block diagram of a server 1000 according to an exemplary embodiment. For example, the server 1000 may be a mobile phone, a computer, a digital broadcast terminal, a messaging device, a game console, a tablet device, a medical device, a fitness device, a personal digital assistant, etc.

[0204] Reference Fig.10 The server 1000 may include one or more of the following components: a processing component 1002 , a memory 1004 , a power component 1006 , a multimedia component 1008 , an audio component 1010 , an input / output (I / O) interface 1012 , a sensor component 1014 , and a communication component 1016 .

[0205] The processing component 1002 generally controls the overall operation of the server 1000, such as operations associated with display, phone calls, data communications, camera operations, and recording operations. The processing component 1002 may include one or more processors 1020 to execute instructions to complete all or part of the steps of the above-mentioned method. In addition, the processing component 1002 may include one or more modules to facilitate the interaction between the processing component 1002 and other components. For example, the processing component 1002 may include a multimedia module to facilitate the interaction between the multimedia component 1008 and the processing component 1002.

[0206] The memory 1004 is configured to store various types of data to support operations on the server 1000. Examples of such data include instructions for any application or method operating on the server 1000, contact data, phone book data, messages, pictures, videos, etc. The memory 1004 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk.

[0207] The power supply component 1006 provides power to various components of the server 1000. The power supply component 1006 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power to the server 1000.

[0208] The multimedia component 1008 includes a screen that provides an output interface between the server 1000 and the user. In some embodiments, the screen may include a liquid crystal display (LCD) and a touch panel (TP). If the screen includes a touch panel, the screen may be implemented as a touch screen to receive input signals from the user. The touch panel includes one or more touch sensors to sense touch, slide, and gestures on the touch panel. The touch sensor may not only sense the boundaries of the touch or slide action, but also detect the duration and pressure associated with the touch or slide operation. In some embodiments, the multimedia component 1008 includes a front camera and / or a rear camera. When the server 1000 is in an operating mode, such as a shooting mode or a video mode, the front camera and / or the rear camera may receive external multimedia data. Each front camera and the rear camera may be a fixed optical lens system or have a focal length and optical zoom capability.

[0209] The audio component 1010 is configured to output and / or input audio signals. For example, the audio component 1010 includes a microphone (MIC), and when the server 1000 is in an operation mode, such as a call mode, a recording mode, and a speech recognition mode, the microphone is configured to receive an external audio signal. The received audio signal can be further stored in the memory 1004 or sent via the communication component 1016. In some embodiments, the audio component 1010 also includes a speaker for outputting audio signals.

[0210] I / O interface 1012 provides an interface between processing component 1002 and peripheral interface modules, such as keyboards, click wheels, buttons, etc. These buttons may include but are not limited to: a home button, a volume button, a start button, and a lock button.

[0211] The sensor assembly 1014 includes one or more sensors for providing various aspects of status assessment for the server 1000. For example, the sensor assembly 1014 can detect the open / closed state of the server 1000, the relative positioning of components, such as the display and keypad of the server 1000, and the sensor assembly 1014 can also detect the position change of the server 1000 or a component of the server 1000, the presence or absence of user contact with the server 1000, the orientation or acceleration / deceleration of the server 1000, and the temperature change of the server 1000. The sensor assembly 1014 may include a proximity sensor configured to detect the presence of nearby objects without any physical contact. The sensor assembly 1014 may also include an optical sensor, such as a CMOS or CCD image sensor, for use in imaging applications. In some embodiments, the sensor assembly 1014 may also include an acceleration sensor, a gyroscope sensor, a magnetic sensor, a pressure sensor, or a temperature sensor.

[0212] The communication component 1016 is configured to facilitate wired or wireless communication between the server 1000 and other devices. The server 1000 can access a wireless network based on a communication standard, such as WiFi, 2G or 3G, or a combination thereof. In an exemplary embodiment, the communication component 1016 receives a broadcast signal or broadcast-related information from an external broadcast management system via a broadcast channel. In an exemplary embodiment, the communication component 1016 also includes a near field communication (NFC) module to facilitate short-range communication. For example, the NFC module can be implemented based on radio frequency identification (RFID) technology, infrared data association (IrDA) technology, ultra-wideband (UWB) technology, Bluetooth (BT) technology and other technologies.

[0213] In an exemplary embodiment, the server 1000 may be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components to perform the above methods.

[0214] In an exemplary embodiment, a non-transitory computer-readable storage medium including instructions is also provided, such as a memory 1004 including instructions, and the instructions can be executed by the processor 1020 of the server 1000 to complete the above-mentioned theme generation method. For example, the non-transitory computer-readable storage medium can be a ROM, a random access memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, etc.

[0215] A non-transitory computer-readable storage medium, when instructions in the storage medium are executed by a processor of a server, enables a processing device of the server to execute a theme generation method provided by an exemplary embodiment of the present disclosure.

[0216] Those skilled in the art will readily appreciate other embodiments of the present disclosure after considering the specification and practicing the disclosure disclosed herein. This application is intended to cover any variations, uses, or adaptations of the present disclosure that follow the general principles of the present disclosure and include common knowledge or customary techniques in the art that are not disclosed in the present disclosure. The description and examples are intended to be exemplary only, and the true scope and spirit of the present disclosure are indicated by the following claims.

[0217] It should be understood that the present disclosure is not limited to the exact structures that have been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.

Claims

1. A topic generation method, characterized in that: Applied to the server, the topic generation method includes: receiving at least one of target area information and weather information, wherein the target area information is at least used to characterize the target area, and the weather information is used to characterize the weather conditions of the target area during a target time period, and the weather information includes a plurality of meteorological data; Generate a target theme based on a pre-stored theme generation model and at least one of the target region information and the weather information, wherein the target theme is generated based at least on the weather information of the target region, and the target theme includes at least one of a wallpaper and a screen saver; The target topic is sent to an electronic device.

2. The topic generation method according to claim 1, characterized in that: Generating a target topic based on a pre-stored topic generation model and the target region information includes: Based on the target area information, obtaining weather information of the target area; The weather information is input into the topic generation model to generate the target topic.

3. The topic generation method according to claim 1, characterized in that: The topic generation method includes establishing the topic generation model, and the method for establishing the topic generation model includes: Acquire a plurality of sample meteorological data and a plurality of sample materials associated with each of the sample meteorological data, wherein the sample materials include images, and the images include image features associated with the sample meteorological data; The diffusion model is trained based on the multiple sample meteorological data and the multiple sample materials related to each sample meteorological data to obtain the topic generation model, in which the mapping relationship between the sample materials and the meteorological data is stored.

4. The topic generation method according to claim 3, characterized in that: Before training the diffusion model based on the plurality of sample meteorological data and the plurality of sample materials related to each of the sample meteorological data, the method further includes: Performing data standardization or normalization processing on the sample meteorological data and the sample material; Parameters of the sample material are processed, where the parameters of the sample material include format and image size.

5. The topic generation method according to any one of claims 1 to 4, characterized in that: The topic generation method also includes: Receiving a first material sent by an electronic device, where the first material is configured by a user; The target theme is generated based on the theme generation model, the weather information and the first material.

6. A topic generation method, characterized in that: Applied to electronic equipment, the theme generation method includes: Determine target region information based on the user setting instruction, where the target region information is at least used to characterize the target area; Sending at least one of weather information and the target area information to a server, wherein the weather information is determined based on the target area information, the weather information is used to characterize the weather conditions of the target area during a target time period, and the weather information includes a plurality of meteorological data; A target theme sent by the server is received, wherein the target theme is generated by a theme generation model pre-stored in the server based at least on weather information of the target area, and the target theme includes at least one of a wallpaper and a screen saver.

7. The topic generation method according to claim 6, characterized in that: The determining of the target region information based on the user setting instruction includes: Based on the first instruction, determining that the target area is a first area, where the first area is an area where the electronic device is located; or, Based on the second instruction, the target area is determined to be a second area, the second area is a preset area except the area where the electronic device is located, and the second instruction is used to indicate the second area.

8. The topic generation method according to claim 6, characterized in that: Based on the target area information, the method for determining the weather information includes: Launching a target application, wherein the target application is a weather-related application; Acquire the weather conditions of the target area in the target application during the target time period as the weather information; The target time period is the current time or a time after a preset time period from the current time.

9. The topic generation method according to any one of claims 6 to 8, characterized in that: The topic generation method also includes: A first material is sent to the server, wherein the first material is configured by a user.

10. The topic generation method according to any one of claims 6 to 8, characterized in that: The topic generation method also includes: When the weather information of the target area changes, sending the changed weather information to the server; Receive the target theme updated according to the changed weather information.

11. A theme generating device, characterized in that: Applied to a server, the theme generating device comprises: A first receiving module is used to receive at least one of target area information and weather information, wherein the target area information is used to characterize at least a target area, and the weather information is used to characterize the weather conditions of the target area during a target time period, and the weather information includes a plurality of meteorological data; A generation module, configured to generate a target theme based on a pre-stored theme generation model and at least one of the target region information and the weather information, wherein the target theme is generated based at least on the weather information of the target region, and the target theme includes at least one of a wallpaper and a screen saver; The first sending module is used to send the target topic to the electronic device.

12. A theme generating device, characterized in that: Applied to electronic equipment, the theme generating device comprises: A determination module, configured to determine target region information based on a user-set instruction, wherein the target region information is at least used to characterize a target area; A second sending module is used to send at least one of weather information and the target area information to a server, wherein the weather information is determined based on the target area information, the weather information is used to characterize the weather conditions of the target area during a target time period, and the weather information includes a plurality of meteorological data; The second receiving module is used to receive a target theme sent by the server, wherein the target theme is generated by a theme generation model pre-stored in the server based at least on weather information of the target area, and the target theme includes at least one of wallpaper and screen saver.

13. A server, characterized in that: The server comprises: a processor; a memory for storing processor-executable instructions; The processor is configured to execute executable instructions in the memory to implement the topic generation method according to any one of claims 1 to 5.

14. A non-transitory computer-readable storage medium having executable instructions stored thereon, characterized in that: When the executable instruction is executed by a processor, the topic generation method according to any one of claims 1 to 5 is implemented.

15. An electronic device, characterized in that: The electronic device comprises: Display screen; processor; a memory for storing processor-executable instructions; The processor is configured to execute executable instructions in the memory to implement the topic generation method as described in any one of claims 6 to 10.

16. A non-transitory computer-readable storage medium having executable instructions stored thereon, characterized in that: When the executable instruction is executed by a processor, the topic generation method according to any one of claims 6 to 10 is implemented.

Images