Theme resource generation method and device, storage medium and electronic device
By analyzing the topic description information entered by the user and using the agent to generate topic resources, the problem that the existing technology cannot generate topics in real time is solved, and the user's personalized needs are met and the theme customization ability is improved.
Patent Information
- Application Number
- CN202410869807.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-06-28
- Publication Date
- 2024-11-26
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
Existing theme generation technology cannot generate or adjust theme resources in real time according to users’ personalized needs, and cannot meet users’ needs to quickly change the device interface according to emotions or occasions.
By analyzing the topic description information entered by the user, obtain scene information and theme replacement types, determine the corresponding detailed information and input it into the agent, so that it generates theme resources, including wallpaper, font and icon resources, and supports complete theme replacement or some elements Replace, consider user preferences and device limitations.
Real-time theme generation of users' personalized needs is realized, the ability to customize and personalize topics is improved, the design process is simplified, the cost is reduced, and the user experience and satisfaction is enhanced.
Smart Images

Figure CN119025103A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of communications, and in particular, to a method and device for generating a subject resource, a storage medium, and an electronic device. Background Art
[0002] In today's digital environment, personalizing and customizing the user interface of computers and mobile devices has become a clear trend. Currently, users usually download and install preset visual themes through theme stores to change the appearance of their device's graphical user interface (GUI). Existing theme generation technologies usually do not support real-time and dynamic theme generation. This means that users cannot quickly generate or adjust themes based on their current emotions or specific occasions. For example, if a user wants to adjust the device interface based on an instant idea or the style of the movie currently being watched, existing technologies cannot immediately meet this demand.
[0003] With regard to the problem that related technologies cannot generate subject resources in real time according to the personalized needs of users, no effective solution has been proposed so far. Summary of the invention
[0004] Embodiments of the present application provide a method and device for generating a theme resource, a storage medium, and an electronic device.
[0005] According to one aspect of an embodiment of the present application, a method for generating a theme resource is provided, comprising: parsing theme description information input by a target object to obtain scene information and a theme change type corresponding to the theme description information; determining first detail information corresponding to the scene information, wherein the first detail information represents dynamic and / or static details of the scene described by the scene information; determining an intelligent agent corresponding to the theme change type, and inputting the first detail information into the intelligent agent, so that the intelligent agent generates a first theme resource according to the first detail information.
[0006] In an exemplary embodiment, the first detail information is input into the intelligent agent so that the intelligent agent generates a first theme resource according to the first detail information, including: when the theme change type is a complete theme change type, generating first prompt information, second prompt information and third prompt information according to the first detail information, wherein the first prompt information includes detail description information related to wallpaper, the second prompt information includes detail description information related to font, and the third prompt information includes detail description information related to color; sending the first prompt information to the wallpaper generation module of the intelligent agent, and sending the second prompt information to the font retrieval module of the intelligent agent, so that the wallpaper generation module generates wallpaper resources according to the first prompt information, and the font retrieval module determines the font resource in the font resource library according to the second prompt information; when the wallpaper generation module generates a target wallpaper resource based on the first prompt information, determining the color information of the target wallpaper corresponding to the target wallpaper resource, and inputting the color information and the third prompt information into the icon generation module of the intelligent agent, so that the icon generation module generates an icon resource according to the color information and the third prompt information, wherein the first theme resource includes: the wallpaper resource, the font resource and the icon resource.
[0007] In an exemplary embodiment, generating first prompt information, second prompt information and third prompt information based on the first detail information includes: determining a text prompt template; inputting the first detail information and preset output information of the wallpaper generation module into the text prompt template to generate the first prompt information, and, inputting the first detail information and the preset output information of the font retrieval module into the text prompt template to generate the second prompt information, and, inputting the first detail information and the preset output information of the wallpaper generation module into the text prompt template to generate the third prompt information.
[0008] In an exemplary embodiment, the icon generation module includes a model for generating icons, and the color information and the third prompt information are input into the icon generation module of the intelligent agent so that the icon generation module generates icon resources according to the color information and the third prompt information, including: updating the low-rank matrix parameters of the model in the icon generation module according to the color information to obtain a fine-tuned model; inputting the third prompt information into the fine-tuned model so that the fine-tuned model generates the icon resources according to the third prompt information.
[0009] In an exemplary embodiment, the first detail information is input into the intelligent agent so that the intelligent agent generates a first theme resource according to the first detail information, including: when the theme change type is a partial theme element change type, generating corresponding fourth prompt information according to the replaced theme element, wherein the theme element includes any at least one of wallpaper, font and icon, and the fourth prompt information contains detailed description information related to the replaced theme element; and at least one of the following: when the theme element to be replaced includes wallpaper and / or font, sending the fourth prompt information to the element generation module corresponding to the theme element to be replaced in the intelligent agent, so that the corresponding element generation module generates or retrieves the corresponding element resource according to the fourth prompt information, wherein the element generation module includes a wallpaper generation module and / or a font retrieval module; when the theme element to be replaced includes wallpaper and icon, determining the color information corresponding to the wallpaper resource generated by the wallpaper generation module, and inputting the color information and the fourth prompt information corresponding to the icon into the icon generation module of the intelligent agent, so that the icon generation module generates the icon resource according to the color information and the fourth prompt information corresponding to the icon.
[0010] In an exemplary embodiment, the first detail information is input into the intelligent agent so that the intelligent agent generates a first theme resource based on the first detail information, including: determining device information of a terminal device that performs theme rendering based on the first theme resource; determining system restriction information corresponding to the device information; and inputting the first detail information and the system restriction information into the intelligent agent so that the intelligent agent generates a first theme resource based on the first detail information and the system restriction information.
[0011] In an exemplary embodiment, determining first detail information corresponding to the scene information includes: obtaining a user portrait of the target object, and determining preference information of the target object based on the user portrait, wherein the preference information includes at least one of the following: color information, style information; determining second detail information having an association with the scene information, and adjusting the second detail information based on the preference information to obtain the first detail information, wherein the second detail information includes preliminary description information for describing the scene details.
[0012] In an exemplary embodiment, after the first detail information is input into the intelligent agent so that the intelligent agent generates a first topic resource based on the first detail information, the method further includes: upon receiving feedback information input by the target object, determining the correlation between the feedback information and the topic description information; when the correlation is greater than or equal to a preset threshold, parsing the feedback information to obtain the sub-topic to be adjusted and the adjustment type of the sub-topic to be adjusted; inputting the sub-topic to be adjusted and the adjustment type into the intelligent agent so that the intelligent agent generates a second topic resource based on the sub-topic to be adjusted and the adjustment type.
[0013] In an exemplary embodiment, the theme resource includes an element for representing an interactive object, wherein the interactive object element represents a virtual object that interacts with the target object, and the interactive object element has multiple dynamic effects corresponding to multiple interactive states of the target object.
[0014] According to another aspect of an embodiment of the present application, a device for generating a theme resource is also provided, including: a parsing module for parsing theme description information input by a target object to obtain scene information and a theme change type corresponding to the theme description information; a determination module for determining first detail information corresponding to the scene information, wherein the first detail information represents dynamic and / or static details of the scene described by the scene information; a generation module for determining an intelligent agent corresponding to the theme change type, and inputting the first detail information into the intelligent agent, so that the intelligent agent generates a first theme resource based on the first detail information.
[0015] According to another aspect of the embodiments of the present application, a computer-readable storage medium is provided, in which a computer program is stored, wherein the computer program is configured to execute the above-mentioned method for generating theme resources when running.
[0016] According to another aspect of an embodiment of the present application, an electronic device is provided, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the method for generating the subject resource through the computer program.
[0017] According to another aspect of the embodiments of the present application, a computer program product is provided, including a computer program, and when the computer program is executed by a processor, the method for generating the above-mentioned subject resources is implemented.
[0018] Through this application, the subject description information input by the target object is parsed to obtain the scene information and subject change type corresponding to the subject description information; the first detail information corresponding to the scene information is determined; the intelligent agent corresponding to the subject change type is determined, and the first detail information is input into the intelligent agent, so that the intelligent agent generates the first subject resource according to the first detail information. That is, this application generates the corresponding first detail information according to the description information input by the user, and generates the subject corresponding to the first detail information through the intelligent agent; the above technical solution solves the problem in the related technology that the subject resources cannot be generated in real time according to the personalized needs of the user, thereby improving the subject customization and personalization capabilities. BRIEF DESCRIPTION OF THE DRAWINGS
[0019] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The exemplary embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:
[0020] Figure 1 It is a hardware structure block diagram of a computer terminal of the method for generating subject resources of an embodiment of the present application;
[0021] Figure 2 is a flowchart of a method for generating a subject resource according to an embodiment of the present application;
[0022] Figure 3 is a schematic diagram of a display interface according to an embodiment of the present application;
[0023] Figure 4 is a schematic diagram of a method for generating a subject resource according to an embodiment of the present application (I);
[0024] Figure 5 is a schematic diagram of a method for generating a subject resource according to an embodiment of the present application (II);
[0025] Figure 6 It is a structural block diagram of a device for generating subject resources according to an embodiment of the present application. DETAILED DESCRIPTION
[0026] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present application.
[0027] It should be noted that the terms and "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.
[0028] The method embodiments provided in the embodiments of the present application can be executed in a computer terminal or a similar computing device. Taking running on a computer terminal as an example, Figure 1 1 is a hardware structure block diagram of a computer terminal for generating a subject resource according to an embodiment of the present application. Figure 1 As shown, the computer terminal may include one or more ( Figure 1 Only one is shown in the figure) processor 102 (processor 102 may include but is not limited to a microprocessor (Microprocessor Unit, referred to as MPU) or a programmable logic device (Programmable logic device, referred to as PLD)) and a memory 104 for storing data. In an exemplary embodiment, the computer terminal may also include a transmission device 106 and an input / output device 108 for communication functions. It can be understood by those skilled in the art that Figure 1 The structure shown is only for illustration and does not limit the structure of the above-mentioned computer terminal. Figure 1 More or fewer components as shown, or with Figure 1 Equivalent functions or comparisons shown Figure 1 A different configuration with more features is shown.
[0029] The memory 104 can be used to store computer programs, for example, software programs and modules of application software, such as the computer program corresponding to the method for generating the subject resource in the embodiment of the present application. The processor 102 executes various functional applications and data processing by running the computer program stored in the memory 104, which is equivalent to implementing the above method. The memory 104 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 104 may further include a memory remotely arranged relative to the processor 102, and these remote memories may be connected to the computer terminal via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.
[0030] The transmission device 106 is used to receive or send data via a network. The above-mentioned network specific example may include a wireless network provided by a communication provider of a computer terminal. In one example, the transmission device 106 includes a network adapter (Network Interface Controller, referred to as NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device 106 can be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.
[0031] In this embodiment, a method for generating a theme resource is provided, which is applied to the above-mentioned computer terminal. Figure 2 : is a flowchart of a method for generating a subject resource according to an embodiment of the present application, and the process includes the following steps:
[0032] Step S202, parsing the subject description information input by the target object to obtain scene information and subject change type corresponding to the subject description information;
[0033] Step S204, determining first detail information corresponding to the scene information, where the first detail information represents dynamic and / or static details of the scene described by the scene information;
[0034] Step S206, determining an agent corresponding to the theme change type, and inputting the first detail information into the agent, so that the agent generates a first theme resource according to the first detail information.
[0035] For example, if the user says that he wants a theme suitable for spring, the algorithm in the intelligent agent will help the user describe the various dynamic and / or static details of the spring scene, such as blooming flowers, green grass, and flying butterflies. The intelligent agent will then generate corresponding theme resources based on "blooming flowers, green grass, and flying butterflies" as the corresponding detail information.
[0036] Through the above steps, the subject description information input by the target object is parsed to obtain the scene information and subject change type corresponding to the subject description information; the first detail information corresponding to the scene information is determined; the intelligent agent corresponding to the subject change type is determined, and the first detail information is input into the intelligent agent, so that the intelligent agent generates the first subject resource according to the first detail information. That is, the present application generates the corresponding first detail information according to the description information input by the user, and generates the subject corresponding to the first detail information through the intelligent agent; the above technical solution solves the problem in the related technology that the subject resources cannot be generated in real time according to the personalized needs of the user, thereby improving the subject customization and personalization capabilities.
[0037] Optionally, determining the intelligent agent corresponding to the theme change type includes: when the theme change type is a design replacement of a complete theme, determining the intelligent agent that calls the complete theme replacement; when the theme change type is a wallpaper replacement, determining the intelligent agent that calls the wallpaper replacement; when the theme change type is an icon replacement, determining the intelligent agent that calls the icon replacement; when the theme change type is a font replacement, determining the intelligent agent that calls the font replacement; when the theme change type is a theme rollback, determining the intelligent agent that calls the subject rollback.
[0038] In an embodiment of the present application, different agents are scheduled to complete corresponding generation tasks according to the parsed theme change type. Since different theme change types correspond to different agents, the generated theme resources are more accurate.
[0039] Optionally, a better understanding of the above-mentioned step S206 can be achieved in the following manner, including: when the theme change type is a complete theme change type, generating a first prompt information, a second prompt information and a third prompt information according to the first detail information, the first prompt information including detail description information related to the wallpaper, the second prompt information including detail description information related to the font, and the third prompt information including detail description information related to the color; sending the first prompt information to the wallpaper generation module of the intelligent body, and sending the second prompt information to the font retrieval module of the intelligent body, so that the wallpaper generation module generates wallpaper resources according to the first prompt information, and the font retrieval module determines the font resources in the font resource library according to the second prompt information; when the wallpaper generation module generates the target wallpaper resource based on the first prompt information, determining the color information of the target wallpaper corresponding to the target wallpaper resource, and inputting the color information and the third prompt information into the icon generation module of the intelligent body, so that the icon generation module generates the icon resource according to the color information and the third prompt information, wherein the first theme resource includes: the wallpaper resource, the font resource and the icon resource.
[0040] The intelligent body corresponding to the complete theme change type includes: a wallpaper generation module, a font retrieval module and an icon generation module. Before the corresponding resources are generated by the wallpaper generation module, the font retrieval module and the icon generation module, it is necessary to generate the corresponding first prompt information, the second prompt information and the third prompt information according to the detail information; when the wallpaper generation module generates the target wallpaper resource according to the first prompt information, in order to make the icon resource visually consistent with the target wallpaper resource, it is necessary to parse the color information of the target wallpaper corresponding to the target wallpaper resource, and then send the parsed color information and the third prompt information to the icon generation module, so that the icon generation module generates the icon resource.
[0041] In an embodiment of the present application, after generating the target wallpaper resource, the color information of the target wallpaper is parsed so that the icon generation module generates the icon resource according to the color information and the prompt information. Since the color information of the target wallpaper is taken into consideration when generating the icon resource, the style and color of the target wallpaper resource and the icon resource can be kept consistent.
[0042] Optionally, the font retrieval module determines the font resource in the font resource library according to the second prompt information, including: determining the feature information in the second prompt information, and determining the first feature vector corresponding to the feature information; determining the second feature vector of each resource in the font resource library; determining the vector similarity between the first feature vector and each second feature vector; determining the vector similarity with the largest value among multiple vector similarities, and determining the resource corresponding to the vector similarity with the largest value as the font resource.
[0043] Optionally, the embodiment of the present application further provides another method for generating a first subject resource, including:
[0044] In the case where the theme change type is a complete theme change type, first prompt information, second prompt information and third prompt information are generated according to the first detail information; the first prompt information is sent to the wallpaper generation module of the intelligent body, and the second prompt information is sent to the font retrieval module of the intelligent body, and the third prompt information is sent to the target wallpaper resource of the intelligent body, so that the wallpaper generation module generates wallpaper resources according to the first prompt information, the font retrieval module determines the font resources in the font resource library according to the second prompt information, and the icon generation module generates icon resources according to the third prompt information.
[0045] In the present application, the first theme resource can be generated in parallel by multiple element generation modules, or in serial by multiple element generation modules. Here, the element generation module can include: one or more of: a wallpaper generation module, a font retrieval module, and an icon generation module.
[0046] Optionally, generating first prompt information, second prompt information and third prompt information based on the first detail information includes: determining a text prompt template; inputting the first detail information and the preset output information of the wallpaper generation module into the text prompt template to generate the first prompt information, and inputting the first detail information and the preset output information of the font retrieval module into the text prompt template to generate the second prompt information, and inputting the first detail information and the preset output information of the wallpaper generation module into the text prompt template to generate the third prompt information.
[0047] It should be noted that the first prompt information, the second prompt information and the third prompt information are generated based on the same text prompt template, that is, the visual consistency of the entire theme style is controlled through the consistent text prompt template.
[0048] For example, when the first detail information mentioned above is “flowers are blooming, green grass is glittering, and butterflies are flying”, and the preset output information of the wallpaper generation module is to generate wallpaper resources, the first prompt information may be to generate wallpaper resources based on “flowers are blooming, green grass is glittering, and butterflies are flying”; when the first detail information mentioned above is “flowers are blooming, green grass is glittering, and butterflies are flying”, and the preset output information of the font retrieval module is to generate font resources, the second prompt information may be to generate font resources based on “flowers are blooming, green grass is glittering, and butterflies are flying”; when the first detail information mentioned above is “flowers are blooming, green grass is glittering, and butterflies are flying”, and the preset output information of the icon generation module is to generate icon resources, the third prompt information may be to generate icon resources based on “flowers are blooming, green grass is glittering, and butterflies are flying”.
[0049] Optionally, the color information and the third prompt information are input into the icon generation module of the intelligent agent so that the icon generation module generates icon resources according to the color information and the third prompt information, including: updating the low-rank matrix parameters of the model in the icon generation module according to the color information to obtain a fine-tuned model; inputting the third prompt information into the fine-tuned model so that the fine-tuned model generates the icon resources according to the third prompt information.
[0050] Among them, the icon generation module generates icon resources based on the model. In order to improve the model's adaptability to tasks without significantly increasing the complexity of the model, a low-rank matrix is added to a specific layer of the model in the icon generation module, wherein the specific layer is one of the following: a convolutional layer, a fully connected layer; when color information is obtained, the low-rank matrix parameters are updated according to the color information, and other parameters of the model are kept unchanged or only slightly updated, and then the icon resources are generated according to the fine-tuned model.
[0051] In addition, to prevent overfitting, you may need to apply regularization techniques (such as L2 regularization) and optimization techniques (such as momentum, Adam, etc.); during fine-tuning, regularly evaluate the performance of the model on the validation set. Based on performance feedback, you may need to adjust the fine-tuning strategy, such as changing the rank of the low-rank matrix, adjusting the learning rate, or optimizing other hyperparameters.
[0052] In the embodiments of the present application, by adding a low-rank matrix in a convolutional layer or a fully connected layer, more abstract features can be captured, while the number of parameters can be reduced, and the output effect can be made more suitable for various devices.
[0053] In some embodiments, the theme replacement type is a partial theme element replacement type. In this case, the first theme resource may be generated in the following manner:
[0054] Generate corresponding fourth prompt information according to the replaced theme element, wherein the theme element includes at least one of wallpaper, font and icon, and the fourth prompt information includes detailed description information related to the replaced theme element; and at least one of the following:
[0055] In the case where the theme element to be replaced includes wallpaper and / or font, sending the fourth prompt information to the element generation module corresponding to the theme element to be replaced in the agent, so that the corresponding element generation module generates or retrieves corresponding element resources according to the fourth prompt information, wherein the element generation module includes a wallpaper generation module and / or a font retrieval module;
[0056] In the case where the theme elements to be replaced include wallpapers and icons, the color information corresponding to the wallpaper resources generated by the wallpaper generation module is determined, and the color information and the fourth prompt information corresponding to the icon are input into the icon generation module of the intelligent body, so that the icon generation module generates icon resources according to the color information and the fourth prompt information corresponding to the icon.
[0057] When the target object expects to replace only some elements in the theme, such as only the wallpaper, or only the font and wallpaper, etc., only the modules corresponding to the elements to be replaced can be called, such as only the wallpaper generation module, or only the font retrieval module and the wallpaper generation module to achieve the replacement of the corresponding element resources. At this time, the generated fourth prompt information can correspondingly only contain detailed description information related to the elements to be replaced. In this way, the user can freely select the theme elements to be replaced, and the user's theme change needs can be more flexibly met.
[0058] Optionally, in order to increase user satisfaction and device usage experience, system restriction information needs to be added when generating theme resources, specifically including: determining the device information of the terminal device for theme rendering according to the first theme resource; determining the system restriction information corresponding to the device information; inputting the first detail information and the system restriction information into the intelligent agent, so that the intelligent agent generates the first theme resource based on the first detail information and the system restriction information.
[0059] For example, when generating theme resources for a car machine, the system restriction information includes:
[0060] 1) Screen size: The screen size, resolution, and aspect ratio of a car computer may be different from that of a mobile phone or tablet. When designing a theme, you need to ensure that the resources perform well on screens of different sizes.
[0061] 2) User interface design: The user interface design of the car computer should follow the principles of simplicity and intuitiveness to avoid distracting the driver.
[0062] 3) Ease of operation: Considering the driver's safety during driving, the theme resources of the car computer should support an easy-to-operate interface, such as large buttons, clear icons, and a simple menu structure.
[0063] 4) Impact of ambient light: The car computer is used under different lighting conditions, and the subject needs to consider the visibility of the screen, such as high contrast and anti-reflection design.
[0064] The car computer will add color controls that affect safe driving; when generating mobile phone theme resources, the system limits the following information:
[0065] 1) Screen size and resolution: Different phone models have different screen sizes and resolutions. When designing a theme, you need to ensure that the resources can be displayed correctly on devices of various sizes and resolutions.
[0066] 2) Operating system and version: Different operating systems (such as Android and iOS) and their versions may have different design guidelines and APIs. Theme resources need to be adapted to the target operating system and its version.
[0067] 3) Hardware performance: Consider the hardware performance of different phones, such as processor speed, memory, and graphics processing capabilities. Avoid using overly complex visual effects that may affect performance and battery life.
[0068] In order to better understand the above step S204, determining the first detail information corresponding to the scene information includes: obtaining a user portrait of the target object, and determining preference information of the target object based on the user portrait, wherein the preference information includes at least one of the following: color information, style information; determining second detail information that is associated with the scene information, and adjusting the second detail information based on the preference information to obtain the first detail information, wherein the second detail information includes preliminary description information for describing the scene details.
[0069] Adjusting the second detail information according to the preference information includes: deleting and / or adding the second detail information according to the preference information.
[0070] For example, if the user says that he wants a theme suitable for spring, the algorithm will help the user describe the various details of the spring scene, such as blooming flowers, green grass, and flying butterflies. If the user likes the two-dimensional world, the detail information can be adjusted to: cartoon version of blooming flowers, green grass, and flying butterflies; if the user likes a cool style, the detail information can be adjusted to: cartoon version of blooming flowers and green grass.
[0071] When generating the first detail information, the user's preference information is taken into consideration so that the generated detail information can better meet the user's needs.
[0072] Optionally, when the theme corresponding to the generated first theme resource does not meet the user's needs, the user can also make targeted adjustments through dialogue, which is implemented as follows: when receiving feedback information input by the target object, determine the correlation between the feedback information and the theme description information; when the correlation is greater than or equal to a preset threshold, parse the feedback information to obtain the sub-theme to be adjusted, and the adjustment type of the sub-theme to be adjusted; input the sub-theme to be adjusted and the adjustment type into the intelligent agent, so that the intelligent agent generates a second theme resource according to the sub-theme to be adjusted and the adjustment type.
[0073] When the correlation between the feedback information and the topic description information is greater than or equal to a preset threshold, it means that the information input by the user this time is information for adjusting the current topic, and then the feedback information is parsed, and the corresponding intelligent agent is called again based on the user's adjustment information to generate a second topic resource.
[0074] For example, adaptively control the color of the theme, or replace and modify the details in the theme. Specifically, if the icon does not match the overall style, the icon can be adjusted.
[0075] In some embodiments, the theme resource includes an element for representing an interactive object, wherein the interactive object element represents a virtual object that interacts with the target object, and the interactive object element has multiple animations corresponding to multiple interactive states of the target object. When generating theme resources, the agent can synchronously generate interactive object elements that match the theme resources. The interactive object element can be displayed in the display interface of the terminal device, such as Figure 3 The circular element on the left side shown represents the object that is communicating with the user. The interactive object element represented by this circular shape can have any abstract or concrete graphic form, such as stacked cubes, a little girl, a small animal, etc.
[0076] Furthermore, when receiving the user's theme description information, the form of the interactive object element can also be determined based on the user's theme description information and the user's preference information. For example, when the user is a business person and the user's theme description information is: generate a concise and clear theme, the form of the interactive object element can be Figure 3The circular element on the left is shown; if the user is an animal lover and the user's theme description information is: "I need a spring theme with grass and sunshine", the interactive object element can be in the form of a small animal.
[0077] Interactive object elements can have multiple animations. In different interactive states of the target object, the interactive object element can present the animation corresponding to the interactive state. For example, when the target object is speaking, the interactive object element presents a slow light and shadow change animation, while when the interactive object represented by the interactive object element outputs feedback information to the target object, it can present a fast light and shadow change animation.
[0078] Obviously, the above-described embodiments are only a part of the embodiments of the present application, not all of the embodiments. In order to better understand the above-mentioned method for generating subject resources, the above-mentioned process is described below in conjunction with the embodiments, but it is not intended to limit the technical solutions of the embodiments of the present application, specifically:
[0079] In an optional embodiment, a method for generating a theme resource is provided, such as Figure 4 As shown, Figure 4 1 is a schematic diagram of a method for generating a theme resource according to an embodiment of the present application (I), which is as follows:
[0080] Step 1: The user communicates with the topic agent through voice and inputs the user's topic description information;
[0081] Step 2: Convert the voice topic description information input by the user into text topic description information;
[0082] Step 3: The topic agent identifies the text topic description information and determines whether the user needs to replace the design of the entire topic or the design of part of the topic resources;
[0083] Step 4: According to the intention recognition results, different sub-agents are dispatched to complete their respective design tasks. During this period, the subject agent will understand and transform the user's design requirements, and expand and optimize the user's design requirements through algorithms;
[0084] Optionally:
[0085] a) Collect and generate a large amount of descriptive data about wallpaper design and conduct training;
[0086] b) The training results are applied to the theme agent, which can understand the user's simple description and convert it into a professional picture design description (for example, if the user says that he wants a theme suitable for spring, the algorithm will help the user describe the various details of the spring theme, such as blooming flowers, green grass, and flying butterflies, while adding restrictions from different systems, such as adding color control that affects safe driving on the car computer);
[0087] c) In the process of generating wallpapers and icons, the generation results are controlled by means of lora, so that the output effect is more suitable for various devices;
[0088] d) According to the result of intent recognition, different sub-agents (equivalent to the intelligent agents in the above embodiment) are dispatched to complete their respective design tasks, including: when the intent recognition result is a design replacement of a complete theme, determining to call a sub-agent for complete theme replacement; when the intent recognition result is a wallpaper replacement, determining to call a sub-agent for wallpaper replacement; when the intent recognition result is an icon replacement, determining to call a sub-agent for icon replacement; when the intent recognition result is a font replacement, determining to call a sub-agent for font replacement; when the intent recognition result is a subject rollback, determining to call a sub-agent for subject rollback.
[0089] In the case where the intention recognition result is a design replacement of a complete theme, after determining the sub-agent for calling the complete theme replacement, the method further includes:
[0090] When the sub-agent of the complete topic replacement generates a topic resource, such as Figure 4 As shown, the implementation is as follows:
[0091] Call the wallpaper replacement tool to generate wallpaper resources according to design requirements, and call the font retrieval tool to determine the font resources in the font resource library according to design requirements; and when generating wallpaper resources, determine the color information of the wallpaper corresponding to the wallpaper resources, and then input the color information into the icon generation tool, so that the icon generation tool generates icon resources according to the design requirements and color information, wherein the theme resources include: wallpaper resources, font resources and icon resources.
[0092] like Figure 5 As shown in FIG. 1 , another implementation method of generating topic resources by a sub-agent for complete topic replacement is also given, including:
[0093] Determine color information according to design requirements;
[0094] Calling a wallpaper replacement tool to enable the wallpaper replacement tool to generate wallpaper resources according to design requirements; calling a font retrieval tool to enable the font retrieval tool to determine font resources in a font resource library according to design requirements; and calling an icon generation tool to enable the icon generation tool to generate icon resources according to design requirements and color information, wherein theme resources include: wallpaper resources, font resources and icon resources.
[0095] After the wallpaper resources, font resources and icon resources are generated, the wallpaper replacement tool, font replacement tool and icon replacement tool are called to replace the wallpaper, font and icon.
[0096] Optionally, user feedback information may also be received in the embodiment of the present application.
[0097] Users can roll back or schedule sub-agents to make adjustments through dialogue.
[0098] The embodiments of the present application can achieve the following effects:
[0099] 1) Simplified theme creation process: Users can use simple natural language descriptions, such as "I want a mobile phone interface with a summer beach theme", to instantly generate complete theme resources, including wallpapers, application icons, fonts, colors, sound effects, and animations. This approach significantly simplifies the traditional complex design process that requires the participation of professional designers.
[0100] 2) Accelerate the application and replacement of themes: It not only supports the rapid design of themes, but also enables instant replacement of existing themes, greatly improving the efficiency of user customization and theme replacement. Users can change themes at any time according to their mood or occasion, enhancing the personalization and fun of device use.
[0101] 3) Reduce design costs and barriers: Traditional theme design and generation usually involve high design fees and long development cycles, while this technology allows users to create professional-level themes without any design background. This not only reduces costs, but also enables non-professional users to enjoy the fun of creation and customization.
[0102] 4) Enhanced user experience and satisfaction: Users can design unique interface themes based on their specific needs and preferences. This high degree of personalization significantly improves user satisfaction and device experience.
[0103] Through the description of the above implementation methods, those skilled in the art can clearly understand that the method according to the above embodiment can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes a number of instructions for a terminal device (which can be a mobile phone, computer, server, or network device, etc.) to execute the methods of each embodiment of the present application.
[0104] In the present embodiment, a generation device of a theme resource is also provided, and the device is used to implement the above-mentioned embodiment and preferred implementation mode, and the description has been made no further. As used below, the term "module" can implement a combination of software and / or hardware of a predetermined function. Although the equipment described in the following embodiments is preferably implemented with software, the implementation of hardware, or a combination of software and hardware is also possible and conceived.
[0105] Figure 6 : is a structural block diagram of a device for generating a theme resource according to an embodiment of the present application, the device comprising:
[0106] The parsing module 62 is used to parse the subject description information input by the target object to obtain the scene information and the subject change type corresponding to the subject description information;
[0107] A determination module 64, configured to determine first detail information corresponding to the scene information, wherein the first detail information represents dynamic and / or static details of the scene described by the scene information;
[0108] The generation module 66 is used to determine the intelligent agent corresponding to the theme change type, and input the first detail information into the intelligent agent, so that the intelligent agent generates a first theme resource according to the first detail information.
[0109] Through this application, the subject description information input by the target object is parsed to obtain the scene information and subject change type corresponding to the subject description information; the first detail information corresponding to the scene information is determined; the intelligent agent corresponding to the subject change type is determined, and the first detail information is input into the intelligent agent, so that the intelligent agent generates the first subject resource according to the first detail information. That is, this application generates the corresponding first detail information according to the description information input by the user, and generates the subject corresponding to the first detail information through the intelligent agent; the above technical solution solves the problem in the related technology that the subject resources cannot be generated in real time according to the personalized needs of the user, thereby improving the subject customization and personalization capabilities.
[0110] In an exemplary embodiment, a generation module 66 is used to generate first prompt information, second prompt information and third prompt information according to the first detail information when the theme change type is a complete theme change type, wherein the first prompt information includes detail description information related to the wallpaper, the second prompt information includes detail description information related to the font, and the third prompt information includes detail description information related to the color; send the first prompt information to the wallpaper generation module of the intelligent body, and send the second prompt information to the font retrieval module of the intelligent body, so that the wallpaper generation module generates wallpaper resources according to the first prompt information, and the font retrieval module determines the font resources in the font resource library according to the second prompt information; when the wallpaper generation module generates a target wallpaper resource based on the first prompt information, determine the color information of the target wallpaper corresponding to the target wallpaper resource, and input the color information and the third prompt information into the icon generation module of the intelligent body, so that the icon generation module generates an icon resource according to the color information and the third prompt information, wherein the first theme resource includes: the wallpaper resource, the font resource and the icon resource.
[0111] In an exemplary embodiment, a generation module 66 is used to determine a text prompt template; input the first detail information and the preset output information of the wallpaper generation module into the text prompt template to generate the first prompt information, and input the first detail information and the preset output information of the font retrieval module into the text prompt template to generate the second prompt information, and input the first detail information and the preset output information of the wallpaper generation module into the text prompt template to generate the third prompt information.
[0112] In an exemplary embodiment, the generation module 66 is used to update the low-rank matrix parameters of the model in the icon generation module according to the color information to obtain a fine-tuned model; and input the third prompt information into the fine-tuned model so that the fine-tuned model generates the icon resource according to the third prompt information.
[0113] In an exemplary embodiment, a generation module 66 is used to generate a corresponding fourth prompt information according to the replaced theme element when the theme change type is a partial theme element change type, wherein the theme element includes any at least one of wallpaper, font and icon, and the fourth prompt information contains detailed description information related to the replaced theme element; and at least one of the following: when the theme element to be replaced includes wallpaper and / or font, sending the fourth prompt information to the element generation module corresponding to the theme element to be replaced in the intelligent body, so that the corresponding element generation module generates or retrieves the corresponding element resource according to the fourth prompt information, wherein the element generation module includes a wallpaper generation module and / or a font retrieval module; when the theme element to be replaced includes wallpaper and icon, determining the color information corresponding to the wallpaper resource generated by the wallpaper generation module, and inputting the color information and the fourth prompt information corresponding to the icon into the icon generation module of the intelligent body, so that the icon generation module generates the icon resource according to the color information and the fourth prompt information corresponding to the icon.
[0114] In an exemplary embodiment, a generation module 66 is used to determine device information of a terminal device that performs theme rendering based on the first theme resource; determine system restriction information corresponding to the device information; and input the first detail information and the system restriction information into the intelligent agent so that the intelligent agent generates a first theme resource based on the first detail information and the system restriction information.
[0115] In an exemplary embodiment, the determination module 64 is used to obtain a user portrait of the target object, and determine preference information of the target object based on the user portrait, wherein the preference information includes at least one of the following: color information, style information; determine second detail information that is associated with the scene information, and adjust the second detail information based on the preference information to obtain the first detail information, wherein the second detail information includes preliminary description information for describing the scene details.
[0116] In an exemplary embodiment, the generation module 66 is used to determine the correlation between the feedback information and the topic description information when receiving feedback information input by the target object; when the correlation is greater than or equal to a preset threshold, parse the feedback information to obtain the sub-topic to be adjusted and the adjustment type of the sub-topic to be adjusted; input the sub-topic to be adjusted and the adjustment type into the intelligent agent, so that the intelligent agent generates a second topic resource according to the sub-topic to be adjusted and the adjustment type.
[0117] In an exemplary embodiment, the theme resource includes an element for representing an interactive object, wherein the interactive object element represents a virtual object that interacts with the target object, and the interactive object element has multiple animations corresponding to multiple interactive states of the target object.
[0118] An embodiment of the present application further provides a computer-readable storage medium, in which a computer program is stored, wherein the computer program is configured to execute the steps of any of the above method embodiments when running.
[0119] Optionally, in this embodiment, the storage medium may be configured to store a computer program for performing the following steps:
[0120] S1, parsing the subject description information input by the target object to obtain the scene information and the subject change type corresponding to the subject description information;
[0121] S2, determining first detail information corresponding to the scene information, wherein the first detail information represents dynamic and / or static details of the scene described by the scene information;
[0122] S3, determining an agent corresponding to the theme change type, and inputting the first detail information into the agent, so that the agent generates a first theme resource according to the first detail information.
[0123] In an exemplary embodiment, the computer-readable storage medium may include, but is not limited to, various media that can store computer programs, such as a USB flash drive, a read-only memory (ROM), a random access memory (RAM), a mobile hard disk, a magnetic disk or an optical disk.
[0124] For specific examples in this embodiment, reference may be made to the examples described in the above embodiments and exemplary implementation modes, and this embodiment will not be described in detail herein.
[0125] An embodiment of the present application further provides an electronic device, including a memory and a processor, wherein a computer program is stored in the memory, and the processor is configured to run the computer program to execute the steps in any one of the above method embodiments.
[0126] Optionally, in this embodiment, the processor may be configured to perform the following steps through a computer program:
[0127] S1, parsing the subject description information input by the target object to obtain the scene information and the subject change type corresponding to the subject description information;
[0128] S2, determining first detail information corresponding to the scene information, wherein the first detail information represents dynamic and / or static details of the scene described by the scene information;
[0129] S3, determining an agent corresponding to the theme change type, and inputting the first detail information into the agent, so that the agent generates a first theme resource according to the first detail information.
[0130] In an exemplary embodiment, the electronic device may further include a transmission device and an input / output device, wherein the transmission device is connected to the processor, and the input / output device is connected to the processor.
[0131] An embodiment of the present application further provides a computer program product, which includes a computer program. When the computer program is executed by a processor, the steps in any one of the above method embodiments are implemented.
[0132] An embodiment of the present application further provides another computer program product, including a non-volatile computer-readable storage medium, wherein the non-volatile computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps in any of the above method embodiments are implemented.
[0133] An embodiment of the present application also provides a computer program, which includes computer instructions, which are stored in a computer-readable storage medium; a processor of a computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device performs the steps in any one of the above method embodiments.
[0134] Optionally, in this embodiment, the computer program product may be configured to store a computer program for performing the following steps:
[0135] S1, parsing the subject description information input by the target object to obtain the scene information and the subject change type corresponding to the subject description information;
[0136] S2, determining first detail information corresponding to the scene information;
[0137] S3, determining an agent corresponding to the theme change type, and inputting the first detail information into the agent, so that the agent generates a first theme resource according to the first detail information.
[0138] For specific examples in this embodiment, reference may be made to the examples described in the above embodiments and exemplary implementation modes, and this embodiment will not be described in detail herein.
[0139] Obviously, those skilled in the art should understand that the above modules or steps of the present application can be implemented by a general computing device, they can be concentrated on a single computing device, or distributed on a network composed of multiple computing devices, they can be implemented by a program code executable by a computing device, so that they can be stored in a storage device and executed by the computing device, and in some cases, the steps shown or described can be executed in a different order from that herein, or they can be made into individual integrated circuit modules, or multiple modules or steps therein can be made into a single integrated circuit module for implementation. Thus, the present application is not limited to any specific combination of hardware and software.
[0140] The above description is only the preferred embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the principles of the present application shall be included in the protection scope of the present application.
Claims
1. A method for generating a subject resource, characterized in that: include: Parsing the subject description information input by the target object to obtain the scene information and the subject change type corresponding to the subject description information; Determine first detail information corresponding to the scene information, wherein the first detail information represents dynamic and / or static details of the scene described by the scene information; An agent corresponding to the theme change type is determined, and the first detail information is input into the agent, so that the agent generates a first theme resource according to the first detail information.
2. The method for generating a theme resource according to claim 1, characterized in that: Inputting the first detail information into the agent so that the agent generates a first subject resource according to the first detail information includes: In the case where the theme change type is a complete theme change type, first prompt information, second prompt information, and third prompt information are generated according to the first detail information, wherein the first prompt information includes detail description information related to wallpaper, the second prompt information includes detail description information related to fonts, and the third prompt information includes detail description information related to colors; Sending a first prompt message to a wallpaper generation module of the intelligent agent, and sending a second prompt message to a font retrieval module of the intelligent agent, so that the wallpaper generation module generates wallpaper resources according to the first prompt message, and the font retrieval module determines font resources in a font resource library according to the second prompt message; When the wallpaper generation module generates the target wallpaper resource based on the first prompt information, the color information of the target wallpaper corresponding to the target wallpaper resource is determined, and the color information and the third prompt information are input into the icon generation module of the intelligent body, so that the icon generation module generates the icon resource according to the color information and the third prompt information, wherein the first theme resource includes: the wallpaper resource, the font resource and the icon resource.
3. The method for generating a theme resource according to claim 2, characterized in that: Generating first prompt information, second prompt information and third prompt information according to the first detail information includes: Determine the text prompt template; inputting the first detail information and the preset output information of the wallpaper generation module into the text prompt template to generate the first prompt information, and, inputting the first detail information and the preset output information of the font retrieval module into the text prompt template to generate the second prompt information, and, The first detail information and the preset output information of the wallpaper generation module are input into the text prompt template to generate the third prompt information.
4. The method for generating a theme resource according to claim 2, characterized in that: The icon generation module includes a model for generating an icon, and the color information and the third prompt information are input into the icon generation module of the agent so that the icon generation module generates an icon resource according to the color information and the third prompt information, including: updating the low-rank matrix parameters of the model in the icon generation module according to the color information to obtain a fine-tuned model; The third prompt information is input into the fine-tuned model, so that the fine-tuned model generates the icon resource according to the third prompt information.
5. The method for generating a theme resource according to claim 1, characterized in that: Inputting the first detail information into the agent so that the agent generates a first subject resource according to the first detail information includes: In the case where the theme change type is a partial theme element change type, corresponding fourth prompt information is generated according to the changed theme element, wherein the theme element includes any at least one of wallpaper, font and icon, and the fourth prompt information includes detailed description information related to the changed theme element; and at least one of the following: In the case where the theme element to be replaced includes wallpaper and / or font, sending the fourth prompt information to the element generation module corresponding to the theme element to be replaced in the agent, so that the corresponding element generation module generates or retrieves corresponding element resources according to the fourth prompt information, wherein the element generation module includes a wallpaper generation module and / or a font retrieval module; In the case where the theme elements to be replaced include wallpapers and icons, the color information corresponding to the wallpaper resources generated by the wallpaper generation module is determined, and the color information and the fourth prompt information corresponding to the icon are input into the icon generation module of the intelligent body, so that the icon generation module generates icon resources according to the color information and the fourth prompt information corresponding to the icon.
6. The method for generating a theme resource according to claim 1, characterized in that: Inputting the first detail information into the agent so that the agent generates a first subject resource according to the first detail information includes: Determine device information of a terminal device that performs theme rendering according to the first theme resource; Determine system restriction information corresponding to the device information; The first detail information and the system restriction information are input into the agent, so that the agent generates a first theme resource according to the first detail information and the system restriction information.
7. The method for generating a theme resource according to claim 1, characterized in that: Determining first detail information corresponding to the scene information includes: Acquire a user portrait of the target object, and determine preference information of the target object according to the user portrait, wherein the preference information includes at least one of the following: color information and style information; Determine second detail information associated with the scene information, and adjust the second detail information according to the preference information to obtain the first detail information, wherein the second detail information includes preliminary description information for describing the scene details.
8. The method for generating a theme resource according to claim 1, characterized in that: After inputting the first detail information into the agent so that the agent generates a first subject resource according to the first detail information, the method further includes: In case of receiving feedback information input by the target object, determining the relevance between the feedback information and the subject description information; When the correlation degree is greater than or equal to a preset threshold, the feedback information is parsed to obtain the sub-topic to be adjusted and the adjustment type of the sub-topic to be adjusted; the sub-topic to be adjusted and the adjustment type are input into the intelligent agent so that the intelligent agent generates a second topic resource according to the sub-topic to be adjusted and the adjustment type.
9. The method for generating a subject resource according to any one of claims 1 to 8, characterized in that: The theme resource includes an element for representing an interactive object, wherein the interactive object element represents a virtual object that interacts with the target object, and the interactive object element has a plurality of animations corresponding to a plurality of interactive states of the target object.
10. A device for generating a theme resource, characterized in that: include: A parsing module, used to parse the subject description information input by the target object to obtain the scene information and the subject change type corresponding to the subject description information; A determination module, configured to determine first detail information corresponding to the scene information, wherein the first detail information represents dynamic and / or static details of the scene described by the scene information; A generation module is used to determine the intelligent agent corresponding to the theme change type, and input the first detail information into the intelligent agent so that the intelligent agent generates a first theme resource according to the first detail information.
11. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored program, wherein the program executes the method described in any one of claims 1 to 9 when executed.
12. An electronic device comprising a memory and a processor, characterized in that: A computer program is stored in the memory, and the processor is configured to execute the method according to any one of claims 1 to 9 through the computer program.
13. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the method according to any one of claims 1 to 9 is implemented.
Citation Information
Cited By
Emotion theme generation method and electronic device
WO2026188956A1
