Portal system image configuration generation method and device, equipment and storage medium

Abstract

The invention provides a portal system image configuration generation method and device, equipment and a storage medium, relates to the technical field of computers, and solves the problem that a portal system cannot adapt to personalized and diversified requirements of a user in related technologies. Diversified images can be automatically generated according to user requirements, it is ensured that icon styles meet the user requirements, a portal system interface can be customized according to personalized requirements, manual design and updating are not needed, the updating period of a portal system is shortened, tedious repeated operation is not needed, and the user experience is improved. The personalized and diversified requirements of different users can be quickly responded, and the use experience of the user is improved.

Description

Technical Field

[0001] The present application relates to the field of computer technology, and in particular to a method, device, equipment and storage medium for generating a portal system image configuration. Background Art

[0002] Portal System refers to a portal website system, which is a unified, customizable, and personalized information portal that provides users with a unified access point to obtain various information resources and applications. It integrates various information resources from inside and outside the enterprise (or organization) and provides personalized information services based on user roles, permissions, and needs.

[0003] However, with the increase of personalized and diversified needs of users, the existing portal systems of enterprises and governments (i.e., G-side) have obvious deficiencies in personalization and diversification. Moreover, in related technologies, the design of portal system entry icons and backgrounds usually requires manual design, with a long update cycle and cumbersome operations, making it difficult to quickly respond to the personalized and diversified needs of different users. Summary of the invention

[0004] The present application provides a portal system image configuration generation method, device, equipment and storage medium, which solves the problem in the related art that the portal system cannot adapt to the personalized and diversified needs of users. This solution can quickly obtain images that meet user needs, avoid tedious and repetitive operations, and improve operational efficiency and flexibility.

[0005] In a first aspect, the present application provides a method for generating a portal system image configuration, which includes:

[0006] Obtain the user's configuration information for the portal system;

[0007] Analyze the configuration information in detail to determine the current detailed parameter information;

[0008] Based on the detailed parameter information, determine the application style, and call the LoRA model corresponding to the application style to generate a style image according to the detailed parameter information;

[0009] According to the preset neural network model, the acquired style image is subjected to detail coordination processing according to the detail parameter information, and an output image of the neural network model is acquired;

[0010] The output images of the neural network model are fused to generate the target image.

[0011] In a second aspect, the present application further provides a portal system image configuration generating device, which includes:

[0012] An information acquisition module configured to acquire user configuration information of the portal system;

[0013] A detail parsing module, configured to perform detail parsing on the configuration information to determine current detail parameter information;

[0014] A detail generation module is configured to determine an application style based on the detail parameter information, and call a LoRA model corresponding to the application style to generate a style image according to the detail parameter information;

[0015] A detail coordination module is configured to perform detail coordination processing on the acquired style image according to the detail parameter information based on a preset neural network model, and obtain an output image of the neural network model;

[0016] The image output module is configured to perform fusion processing on the output image of the neural network model to generate a target image.

[0017] In a third aspect, the present application further provides an electronic device, comprising:

[0018] one or more processors;

[0019] a storage device for storing one or more programs,

[0020] When one or more programs are executed by one or more processors, the one or more processors implement the portal system image configuration generation method of the present application.

[0021] In a fourth aspect, the present application further provides a storage medium storing computer executable instructions, which, when executed by a processor, are used to execute the portal system image configuration generation method of the present application.

[0022] This application scheme is based on deep learning and image generation technology. It can automatically generate diversified images according to user needs and ensure that the icon style meets user needs, so that the portal system interface can be customized according to personalized needs without relying on manual design and updates, thereby shortening the update cycle of the portal system and eliminating the need for tedious repetitive operations. It helps to quickly respond to the personalized and diversified needs of different users and improve the user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Figure 1 A schematic diagram of the steps of a method for generating a portal system image configuration according to an embodiment of the present application;

[0024] Figure 2 A schematic diagram of the steps of generating a style image provided in an embodiment of the present application;

[0025] Figure 3 A schematic diagram of steps for performing detail coordination processing on an image provided by an embodiment of the present application;

[0026] Figure 4 A schematic diagram of the structure of a portal system image configuration device provided in an embodiment of the present application;

[0027] Figure 5 A schematic diagram of the structure of an electronic device provided in one embodiment of the present application. DETAILED DESCRIPTION

[0028] The embodiments of the present application are further described in detail below in conjunction with the accompanying drawings and examples. It is to be understood that the specific embodiments described herein are only used to explain the embodiments of the present application, rather than to limit the embodiments of the present application. It should also be noted that, for ease of description, only the parts related to the embodiments of the present application rather than all structures are shown in the accompanying drawings, and those skilled in the art should be able to think of it after reading the specification of this application that as long as the technical features do not contradict each other, any combination of the technical features can constitute an optional implementation method.

[0029] The terms "first", "second", etc. in the specification and claims of the present application are used to distinguish similar objects, and are not used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable when appropriate, so that the embodiments of the present application can be implemented in an order other than those illustrated or described here, and the objects distinguished by "first", "second", etc. are generally a class, and the number of objects is not limited. For example, the first object can be one or more. In addition, "and / or" in the specification and claims represents at least one of the connected objects, and the character " / " generally represents that the objects associated before and after are in an "or" relationship. In the description of the present application, "multiple" means two or more, and "several" means one or more.

[0030] A portal system refers to a portal website system, which is a unified, customizable, and personalized information portal that provides users with a unified access point to obtain various information resources and applications. With the rapid development of artificial intelligence technology, the demand for intelligence and personalization of G-end portal systems such as enterprise and government is also increasing. However, the existing G-end portal systems have obvious deficiencies in personalization and diversification, such as interface design and user experience, which are difficult to meet user needs. For example, the update of portal system images such as icons and backgrounds usually requires manual design, which has a long update cycle and cumbersome operations, making it difficult to quickly respond to the personalized and diversified needs of different users.

[0031] In this regard, the present application provides a portal system image configuration generation method, which can be applied to servers, computers and other electronic devices, thereby providing users with personalized and diversified configuration generation solutions to generate corresponding images for application in the portal system, such as icons, backgrounds, etc.

[0032] Figure 1 This is a schematic diagram of the steps of a portal system image configuration generation method provided in an embodiment of the present application. The method can be applied to the above-mentioned electronic device, and then the electronic device provides a personalized image configuration generation solution for the user. The specific steps are as follows:

[0033] Step S110: Obtain the user's configuration information for the portal system.

[0034] It is conceivable that the user's configuration information for the portal system can be input on the interactive interface provided by the electronic device, such as an interactive interface provided on the display interface of the electronic device, the interactive interface is used as an interface for providing input to the user, for example, a text input box is provided on the interactive interface, for the user to input the configuration information in text form; for another example, a plurality of corresponding configuration items can be provided on the interactive interface, such as corresponding color, style, type and other details corresponding to different configuration items, and the configuration item is used as a selection box for selecting corresponding parameters, so that the user can click the selection box to determine the specific parameter information of the configuration item. Of course, it should be noted that in some embodiments, the configuration information can also be obtained by the electronic device from other devices through wired, wireless or other means.

[0035] Step S120: parse the configuration information in detail to determine the current detailed parameter information.

[0036] After the corresponding configuration information is determined, the configuration information is further analyzed in detail, that is, the corresponding detailed parameter information, such as color, style, type, etc., is determined from the configuration information. Optionally, in one embodiment, when the configuration information is input through the configuration items provided in the interactive interface, the detailed parameter information is determined according to the input parameters corresponding to the configuration items. It is conceivable that different configuration items correspond to different detail items. For example, corresponding configuration items are provided for detail items such as color, style, type, etc. The user can determine the detailed parameters of the configuration item by selecting the corresponding input parameters for the configuration item. The corresponding detailed parameter information can be determined after all configuration items are configured.

[0037] Optionally, in one embodiment, when the configuration information is input text, based on a preset semantic analysis algorithm, text features corresponding to the detail parameters are extracted from the configuration information to determine the detail parameter information. It is understandable that for text, the electronic device can use a semantic analysis algorithm to extract text features corresponding to the detail parameters from the configuration information. For example, the text input by the user is "generate an icon with a five-pointed star on a red background", and corresponding text features such as "red background", "five-pointed star", and "icon" can be extracted to determine the corresponding detail parameter information. It should be noted that the semantic analysis algorithm used is an algorithm in the relevant technology, which can be configured according to actual application requirements, and can extract text features corresponding to the detail parameters.

[0038] Therefore, by parsing the configuration information, the electronic device can quickly determine the detailed parameter information in the configuration information, and then determine the user's personalized and diversified needs, so as to better generate images that meet the user's needs, thereby improving the user's usage experience.

[0039] Step S130: determine the application style based on the detail parameter information, and call the LoRA model corresponding to the application style to generate a style image according to the detail parameter information.

[0040] After determining the detail parameter information, the device can determine the application style from the detail parameter information. For example, the detail parameter information includes style parameters corresponding to the application style. Based on the style parameters, the device can determine the corresponding application style. Then, according to the application style, the corresponding LoRA (Low-Rank Adaptation) model is called. It can be understood that the LoRA model is a language model adjusted based on the LoRA technology, which can generate a corresponding image according to the input information and adjust the style of the image to meet the image requirements.

[0041] In this regard, the device calls the LoRA model and then generates a style image according to the detail parameter information. It can be imagined that the detail parameter information is used as the input parameter of the model, and then the LoRA model is used to generate a style image that meets the detail parameter information. For example, the detail parameter information includes various parameters such as "red background", "five-pointed star", "icon" and "animation style". Accordingly, the LoRA model corresponding to the animation style is called to generate a style image with a red background and a five-pointed star in the animation style, which is used as the image used for the icon to be generated.

[0042] Step S140: According to the preset neural network model, detail coordination processing is performed on the acquired style image according to the detail parameter information, and an output image of the neural network model is acquired.

[0043] It is understandable that in order to make the generated image better fit the configuration information input by the user, the device further calls a preset neural network model, which is used to coordinate the details of the image, thereby adjusting the details in the image. In this regard, by calling the neural network model, the neural network model is used to coordinate the details of the acquired style image according to the detail parameter information. It is understandable that the device adjusts the details in the style image through the neural network model so that the style image can better fit the description in the detail parameter information, and then uses the adjusted style image as the output image of the model.

[0044] Step S150: perform fusion processing on the output image of the neural network model to generate a target image.

[0045] It is conceivable that the neural network model can generate corresponding output images for different details during the process of detail adjustment processing. For this, the device also needs to fuse the output images to generate the target image. It should be noted that when fusing images, an image fusion algorithm, such as a Laplace pyramid fusion algorithm, a multi-resolution fusion algorithm, etc., can be used to fuse the images.

[0046] It can be seen from the above scheme that this scheme is based on deep learning and image generation technology, which can automatically generate diversified images according to user needs and ensure that the icon style meets user needs, so that the portal system interface can be customized according to personalized needs without relying on manual design and updates, which shortens the update cycle of the portal system and eliminates the need for tedious repetitive operations, helping to quickly respond to the personalized and diversified needs of different users and improve the user experience.

[0047] During the configuration of the portal system, the device can generate multiple versions of images according to the needs of the user. For this purpose, the device provides a history record function to facilitate backtracking and restoring previous operation configurations, thereby restoring previous versions of images. In some embodiments, during the detailed parsing of the configuration information, the device can use the Checkpoint algorithm to set several save points in the process, and the save points are used to save the detailed parameter information. It can be understood that the Checkpoint algorithm will not suspend the entire parsing process, but save the detailed parameter information during the parsing process and form corresponding save points. It can be imagined that in one embodiment, a save point can be configured each time the detailed parameter information is determined, so that the save point can save the current detailed parameter information.

[0048] Moreover, the electronic device also associates all save points through the corresponding management interface. Then, when the user needs to query the historical records, the user can trigger the query operation of the corresponding historical records by touching the electronic device or through an external device such as a mobile terminal, and then in response to the received query operation, the electronic device calls the management interface to display all save points on the interactive interface for the user to select the target save point. Therefore, by setting the save point, this solution can provide users with the backtracking and recovery of historical records to meet the user's personalized and diversified configuration requirements for the portal system, so that the user can restore the specified version or restore the initialization as needed, thereby improving efficiency and flexibility.

[0049] Figure 2A schematic diagram of the steps for generating a style image provided by an embodiment of the present application. In one embodiment, the detail parameter information includes image style, image color, special features and image content. The LoRA model called by the device needs to generate a corresponding style image according to the above-mentioned detail parameter information. The specific steps include steps S210-S220:

[0050] Step S210: According to the image style, a target LoRA model whose application style matches the image style is selected from a plurality of preset LoRA models.

[0051] Step S220: Based on the target LoRA model, both the image color and the special symbols are applied to the style image generation process, and a style image corresponding to the image content is generated.

[0052] It can be understood that the image style in the detail parameter information corresponds to an application style, and different LoRA models also correspond to different application styles. Therefore, after determining the image style, a model whose application style matches the image style is selected from the preset multiple LoRA models as the target LoRA model. Then, the target LoRA model is called to apply both the image color and special symbols to the generation process of the style image, and a style image corresponding to the image content is generated, so that the generated style image can meet the requirements of image color and special symbols.

[0053] It can be imagined that the LoRA model is a language model adjusted based on the LoRA technology, which can generate corresponding images according to the input information and adjust the style of the image to meet the image requirements. After the model is trained, the model has the ability to generate images and understand text, and can also adjust the model parameters so that the model can better adapt to specific image generation requirements, such as making the generated image meet the requirements of specific styles, characters, scenes, etc. Furthermore, in the process of generating the output image of the model, the target LoRA model will generate an image that meets the requirements of the input information, that is, the above-mentioned output image, based on the input information (that is, the above-mentioned detailed parameter information) and the adjustment effect brought by the model.

[0054] Therefore, this solution uses the LoRA model, which can expand the style types of generated images to generate corresponding style images, so as to quickly obtain images that meet user needs and meet the user's personalized and diversified needs.

[0055] Figure 3A schematic diagram of steps for performing detail coordination processing on an image provided by an embodiment of the present application. In one embodiment, the neural network model used is a ControlNet model. The device performs detail coordination processing on the style image by calling the ControlNet model to semantically control and adjust the details of the image. The specific steps include steps S310-S330:

[0056] Step S310: extract input condition features from configuration information.

[0057] Step S320: Based on the Canny module in the ControlNet model, contour processing is performed on the style image according to the input conditional features to adjust the contour graphics of the style image.

[0058] Step S330: Based on the Depth module in the ControlNet model, the style image is deeply processed according to the input conditional features to adjust the spatial relationship between the elements in the style image.

[0059] It is understandable that the ControlNet model includes a Canny module and a Depth module, wherein the Canny module is used to perform edge detection on the image to extract the contour lines in the image and adjust the contour lines in the image; and the Depth module is used to control the depth of field effect in the image and adjust the spatial relationship between different elements in the image. In this regard, after generating the style image, the input condition features are extracted from the configuration information. For example, if the user's requirement is to generate an icon with a red background and a five-pointed star with a sense of hierarchy on the icon, the features that can be extracted from the configuration information include but are not limited to "red background", "sense of hierarchy", and "five-pointed star", and these are used as input condition features.

[0060] Then the device calls the ControlNet model to adjust the contour and depth of the style image according to the input conditional features, so that the image can meet the needs of the user. For example, the Canny module in the ControlNet model is used to process the contour of the style image to adjust the contour graphics of the style image. For example, the edge detection is performed on the generated five-pointed star to extract the contour line corresponding to the five-pointed star. Then, the Depth module in the ControlNet model is used to process the image in depth. For example, based on the above-mentioned layered condition, the spatial relationship between the five-pointed star and the red background is adjusted to form a layered sense between the five-pointed star and the red background in the image.

[0061] Therefore, this solution adjusts the image through the ControlNet model to coordinate the details on the image, which helps to generate an image that is more in line with the configuration information provided by the user to meet the user's needs.

[0062] In one embodiment, after the style image is processed for contour and depth, the corresponding contour detail image and depth detail image can be obtained. In this regard, the device fuses the above images based on a preset image fusion algorithm to obtain a target image corresponding to the user's needs. It can be understood that in the process of image fusion, contour information is obtained from the contour detail image and depth information is obtained from the depth detail image. Then, based on the contour information, depth information and image fusion algorithm, when the contour detail image and the depth detail image are fused, the contour information and depth information are used as references to fuse the contour detail image and the depth detail image to form a target image. In this regard, after adjusting the details in the image through the ControlNet model, the images generated in different processing processes are fused by this solution to generate an image that is more in line with the configuration information provided by the user, thereby meeting the user's needs.

[0063] In some embodiments, after generating a target image according to the configuration information provided by the user, the device can display the target image to the user through an interactive interface. Accordingly, the device also provides a function of regenerating the image, such as providing a touchable virtual button in the interactive interface, so that the user can touch the virtual button to generate a corresponding instruction to make the device regenerate the image. In this regard, after the user touches the virtual button, the device can receive the corresponding re-generated instruction, and then the device re-calls the LoRA model corresponding to the application style, so that it generates a new style image according to the detailed parameter information, referring to Figure 1 , that is, starting again from step S130, and then after generating the style image, inputting the style image into the neural network model, so that the image is coordinated in detail by the neural network model, and then the generated image is fused to obtain a new target image.

[0064] Figure 4 This is a schematic diagram of the structure of a portal system image configuration device provided in an embodiment of the present application. The device is used to execute the above-mentioned portal system image configuration method and has functional modules and beneficial effects for executing the method. Figure 4 As shown, the device includes an information acquisition module 401, a detail analysis module 402, a detail generation module 403, a detail coordination module 404 and an image output module 405.

[0065] Among them, the information acquisition module 401 is configured to obtain the user's configuration information for the portal system; the detail analysis module 402 is configured to perform detail analysis on the configuration information to determine the current detail parameter information; the detail generation module 403 is configured to determine the application style based on the detail parameter information, and call the LoRA model corresponding to the application style to generate a style image according to the detail parameter information; the detail coordination module 404 is configured to perform detail coordination processing on the acquired style image according to the detail parameter information based on a preset neural network model, and obtain the output image of the neural network model; the image output module 405 is configured to perform fusion processing on the output image of the neural network model to generate a target image.

[0066] Based on the above embodiment, the detail analysis module 402 is specifically configured as follows:

[0067] When the configuration information is input through the configuration items provided in the interactive interface, the detailed parameter information is determined according to the input parameters corresponding to the configuration items, and different configuration items correspond to different detailed items;

[0068] In the case where the configuration information is input text, text features corresponding to the detail parameters are extracted from the configuration information based on a preset semantic analysis algorithm to determine the detail parameter information.

[0069] On the basis of the above embodiment, the device further includes a history record module, and the history record module is specifically configured as follows:

[0070] Based on the Checkpoint algorithm, several save points are set in the process of detailed parsing of configuration information. The save points are used to save detailed parameter information.

[0071] When a query operation corresponding to the query history record is received, a management interface for displaying all save points is called to allow the user to select a target save point.

[0072] Based on the above embodiment, the detail parameter information includes image style, image color, special symbols and image content. The detail generation module 403 is specifically configured as follows:

[0073] According to the image style, select a target LoRA model whose application style matches the image style from multiple preset LoRA models;

[0074] Based on the target LoRA model, both image colors and special symbols are applied to the style image generation process, and a style image corresponding to the image content is generated.

[0075] Based on the above embodiment, the neural network model is a ControlNet model, and the detail coordination module 404 is specifically configured as follows:

[0076] Extracting input condition features from configuration information;

[0077] Based on the Canny module in the ControlNet model, the style image is processed according to the input conditional features to adjust the contour graphics of the style image;

[0078] Based on the Depth module in the ControlNet model, the style image is deeply processed according to the input conditional features to adjust the spatial relationship between the elements in the style image.

[0079] Based on the above embodiment, the image output module 405 is specifically configured as follows:

[0080] Obtaining a contour detail image after contour processing is performed on the style image and a depth detail image after depth processing is performed on the style image, and determining corresponding contour information and depth information;

[0081] Based on the contour information, the depth information and a preset image fusion algorithm, the contour detail image and the depth detail image are fused to generate a target image.

[0082] On the basis of the above embodiment, the device further includes a regeneration module, and the regeneration module is specifically configured as follows:

[0083] After fusing the output images of the neural network model to generate the target image, the method further includes:

[0084] When it is determined that a corresponding re-generation instruction has been received, the LoRA model corresponding to the application style is re-called to generate a new style image according to the detailed parameter information, and the new style image is input into the neural network model to generate a new target image.

[0085] It is worth noting that in the embodiment of the above-mentioned device, the modules included are only divided according to functional logic, but are not limited to the above-mentioned division, as long as the corresponding functions can be achieved; in addition, the specific names of the modules are only for the convenience of distinguishing each other, and are not used to limit the protection scope of the embodiments of the present application.

[0086] Figure 5The structural diagram of an electronic device provided in an embodiment of the present application is used to execute the portal system image configuration method provided in the above embodiment, and has the functional modules and beneficial effects corresponding to the execution method. As shown in the figure, the electronic device includes a processor 501, a memory 502, an input device 503 and an output device 504. The number of processors 501 can be one or more, and one processor 501 is taken as an example in the figure; the processor 501, the memory 502, the input device 503 and the output device 504 can be connected by a bus or other means, and the figure takes the connection through the bus as an example. The memory 502, as a computer-readable storage medium, can be used to store software programs, computer executable programs and modules, such as the program instructions / modules corresponding to the portal system image configuration method in the embodiment of the present application. The processor 501 executes the corresponding various functional applications and data processing by running the software programs, instructions and modules stored in the memory 502, that is, the above-mentioned portal system image configuration method is realized.

[0087] The memory 502 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system and at least one application required for a function; the data storage area may store data recorded or created during use, etc. In addition, the memory 502 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other non-volatile solid-state storage device. In some embodiments, the memory 502 may further include a memory remotely arranged relative to the processor 501, and these remotely arranged memories may be connected to the device 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.

[0088] The input device 503 can be used to input corresponding digital or character information to the processor 501, and to generate key signal input related to the user settings and function control of the device; the output device 504 can be used to send or display key signal output related to the user settings and function control of the device.

[0089] The embodiment of the present application also provides a storage medium storing computer executable instructions, which, when executed by a processor, are used to perform relevant operations in the portal system image configuration method provided in any embodiment of the present application.

[0090] Computer-readable storage media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer-readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device.

[0091] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0092] Note that the above are only preferred embodiments of the present application and the technical principles used. Those skilled in the art will understand that the present application is not limited to the specific embodiments described herein, and that various obvious changes, readjustments and substitutions can be made by those skilled in the art without departing from the scope of protection of the present application. Therefore, although the present application is described in more detail through the above embodiments, the present application is not limited to the above embodiments, and may include more other equivalent embodiments without departing from the concept of the present application, and the scope of the present application is determined by the scope of the appended claims.

Claims

1. A method for generating a portal system image configuration, characterized in that: include: Obtain the user's configuration information for the portal system; Analyze the configuration information in detail to determine the current detailed parameter information; Based on the detailed parameter information, determine the application style, and call the LoRA model corresponding to the application style to generate a style image according to the detailed parameter information; According to a preset neural network model, performing detail coordination processing on the acquired style image according to the detail parameter information, and acquiring an output image of the neural network model; The output image of the neural network model is fused to generate a target image.

2. The portal system image configuration generation method according to claim 1, characterized in that: The detailed analysis of the configuration information to determine the current detailed parameter information includes: In the case where the configuration information is input through configuration items provided in an interactive interface, the detailed parameter information is determined according to input parameters corresponding to the configuration items, and different configuration items correspond to different detailed items; In the case where the configuration information is input text, text features corresponding to detail parameters are extracted from the configuration information based on a preset semantic analysis algorithm to determine the detail parameter information.

3. The portal system image configuration generation method according to claim 1 or 2, characterized in that: The method further comprises: Based on the Checkpoint algorithm, a number of save points are set in the process of detailed parsing of the configuration information, and the save points are used to save detailed parameter information; When a query operation corresponding to the query history record is received, a management interface for displaying all save points is called to allow the user to select a target save point.

4. The portal system image configuration generation method according to claim 1, characterized in that: The detailed parameter information includes image style, image color, special symbols and image content. The determining of the application style based on the detailed parameter information and calling the LoRA model corresponding to the application style to generate a style image according to the detailed parameter information include: According to the image style, a target LoRA model whose application style matches the image style is selected from a plurality of preset LoRA models; Based on the target LoRA model, the image color and the special symbol are both applied to the generation process of the style image, and a style image corresponding to the image content is generated.

5. The portal system image configuration generation method according to claim 1, characterized in that: The neural network model is a ControlNet model, and the acquired style image is subjected to detail coordination processing according to the preset neural network model to determine the output image of the neural network model, including: Extracting input condition features from the configuration information; Based on the Canny module in the ControlNet model, contour processing is performed on the style image according to the input condition feature to adjust the contour graphic of the style image; Based on the Depth module in the ControlNet model, the style image is deeply processed according to the input condition features to adjust the spatial relationship between the elements in the style image.

6. The portal system image configuration generation method according to claim 5, characterized in that: The step of fusing the output image of the neural network model to generate a target image includes: Acquire a contour detail image after contour processing is performed on the style image and a depth detail image after depth processing is performed on the style image, and determine corresponding contour information and depth information; Based on the contour information, the depth information and a preset image fusion algorithm, the contour detail image and the depth detail image are fused to generate the target image.

7. The portal system image configuration generation method according to claim 1, characterized in that: After the output image of the neural network model is fused to generate a target image, the method further includes: When it is determined that a corresponding re-generation instruction has been received, the LoRA model corresponding to the application style is re-called to generate a new style image according to the detailed parameter information, and the new style image is input into the neural network model to generate a new target image.

8. A portal system image configuration generating device, characterized in that: include: An information acquisition module configured to acquire user configuration information of the portal system; A detail analysis module, configured to perform detail analysis on the configuration information to determine current detail parameter information; A detail generation module is configured to determine an application style based on the detail parameter information, and call a LoRA model corresponding to the application style to generate a style image according to the detail parameter information; A detail coordination module is configured to perform detail coordination processing on the acquired style image according to the detail parameter information based on a preset neural network model, and acquire an output image of the neural network model; The image output module is configured to perform fusion processing on the output image of the neural network model to generate a target image.

9. An electronic device, characterized in that: include: one or more processors; The storage device is used to store one or more programs. When the one or more programs are executed by the one or more processors, the one or more processors implement the portal system image configuration generation method according to any one of claims 1 to 7.

10. A storage medium storing computer executable instructions, characterized in that: When the computer executable instructions are executed by a processor, they are used to execute the portal system image configuration generating method according to any one of claims 1 to 7.

Images