Map rendering method, apparatus, device, medium, and program product

Abstract

This application provides a map rendering method, apparatus, device, medium, and program product. The method includes: inputting acquired user feature data and map data into a pre-trained deep learning model; generating a map color scheme that matches the input data through the model; and then applying the map color scheme to the corresponding layer of the map software for rendering. The deep learning model can pre-learn the mapping relationship between user features and map color schemes through training based on historical color scheme data, thereby generating more diverse personalized color schemes. This effectively improves the color harmony and user matching of map rendering, reduces user visual fatigue when looking at the map, and enhances travel safety.

Description

Technical Field

[0001] This application relates to the field of map processing technology, and in particular to a map rendering method, apparatus, device, medium and program product. Background Technology

[0002] Map rendering is a crucial step in the map data processing and visualization process, transforming abstract geographic information and route planning results into a visually intuitive interface. With the development of technologies such as mobile navigation and autonomous driving, map rendering quality has become increasingly important, impacting the service quality of map software.

[0003] Currently, most map rendering solutions rely on preset, fixed color templates, such as simply switching the basic color tone based on day / night cycles. These solutions generally have conservative color schemes, resulting in a monotonous visual experience that fails to meet the diverse needs of a large user base. Prolonged use can easily lead to visual fatigue and may affect travel safety. Summary of the Invention

[0004] This application provides a map rendering method, apparatus, device, medium, and program product to enhance the diversity and user adaptability of map rendering.

[0005] In a first aspect, embodiments of this application provide a map rendering method, including:

[0006] Acquire user characteristic data and map data;

[0007] Feature data and map data are input into a pre-trained deep learning model; the deep learning model is trained based on historical color scheme data to learn the mapping relationship between user features and map color schemes.

[0008] A map color scheme that matches the input data is generated using a deep learning model. The map color scheme includes the color values ​​and / or texture parameters of visual elements in the map, including at least one of the following: sky, ground, roads, water bodies, and buildings.

[0009] The corresponding layers in the map software are rendered according to the map's color scheme.

[0010] In some possible implementations, a map color scheme that matches the input data is generated using a deep learning model, including:

[0011] Determine the target style type corresponding to the input feature data from multiple preset color scheme style types;

[0012] Generate a map color scheme that matches the target style type based on the input map data.

[0013] In the above approach, the process of generating color schemes by the model can be divided into two stages. The first stage determines the target style type, and the second stage generates specific color parameters under the constraints of the target style type. This allows the color schemes generated by the model to have a clearer style orientation and higher internal harmony while ensuring diversity, reducing the risk of randomly generating discordant color schemes.

[0014] In some possible implementations, the feature data includes the music style type of the music played by the user, and the target style type corresponding to the input feature data is determined from multiple preset color scheme style types, including:

[0015] The target style type is determined from multiple preset color scheme styles based on the music style type.

[0016] In the above approach, by establishing a cross-modal mapping from music style to map color scheme, the model can perceive the user's auditory preferences and real-time mood, thereby generating a map color scheme that is more in line with the user's current mood in terms of emotional atmosphere, reducing the number of times the user manually adjusts the rendering scheme and ensuring travel safety.

[0017] In some possible implementations, the map data also includes navigation data, rendering the corresponding layers of the map software according to the map color scheme, and also includes:

[0018] Adjust the display status of the navigation panel in the map software based on the navigation data.

[0019] In the above method, by using navigation data as input data for the model, the model can automatically adjust the presentation of the navigation panel according to the user's navigation needs, thereby improving the efficiency and intuitiveness of map information acquisition.

[0020] In some possible implementations, the display state of the navigation panel in the map software is adjusted based on navigation data, including:

[0021] Determine whether the current navigation route is a frequently used route by the user based on navigation data;

[0022] If it is a frequently used route, the navigation panel of the control map software is displayed or hidden in a first style, which includes shrinking the navigation panel and / or increasing the transparency of the navigation panel.

[0023] If the route is not frequently used, the navigation panel of the control map software will be displayed in a second style, which includes enlarging the navigation panel and / or highlighting the navigation panel.

[0024] In the above method, the style of the navigation panel is adaptively adjusted according to whether the navigation route is a frequently used route by the user. This can minimize the interference of the navigation panel on the user's visual interface when driving on familiar roads, and attract the user's attention to the navigation guidance when driving on unfamiliar roads, thus achieving a dynamic balance between navigation safety and ease of use as a whole.

[0025] In some possible implementations, after rendering the corresponding layers of the map software according to the map color scheme, the following steps are also included:

[0026] Obtain user feedback on the rendering results;

[0027] The deep learning model is optimized based on the evaluation.

[0028] In the above approach, optimizing the model based on user feedback enables the model to continuously learn from real-time feedback from real users, thereby achieving a continuous improvement in overall rendering quality.

[0029] In some possible implementations, after rendering the corresponding layers of the map software according to the map color scheme, the following steps are also included:

[0030] Obtain the user's real-time environmental data;

[0031] The color scheme of the rendered map is adjusted based on real-time environmental data.

[0032] The above methods, by introducing real-time environmental data for rendering correction, can solve the problem that the color scheme generated by the model may be out of touch with the actual environment, reduce visual discomfort caused by excessive contrast between the map interface and the external environment, and further reduce potential security risks.

[0033] Secondly, embodiments of this application provide a map rendering apparatus, comprising:

[0034] The acquisition module is used to acquire user feature data and map data;

[0035] The input module is used to input feature data and map data into a pre-trained deep learning model; the deep learning model is trained based on historical color scheme data to learn the mapping relationship between user features and map color schemes.

[0036] The generation module is used to generate a map color scheme that matches the input data through a deep learning model. The map color scheme includes the color values ​​and / or texture parameters of visual elements in the map, and the visual elements include at least one of the sky, ground, roads, water bodies and buildings.

[0037] The rendering module is used to render the corresponding layers of the map software according to the map's color scheme.

[0038] Thirdly, embodiments of this application provide an electronic device, including: a memory and a processor;

[0039] The memory stores instructions that the computer executes;

[0040] The processor executes computer execution instructions stored in memory, causing the processor to perform the first aspect and / or various possible implementations of the first aspect as described above.

[0041] Fourthly, embodiments of this application provide a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, are used to implement the first aspect and / or various possible implementations of the first aspect.

[0042] Fifthly, embodiments of this application provide a computer program product, including a computer program that, when executed by a processor, implements the first aspect and / or various possible implementations of the first aspect.

[0043] The map rendering method, apparatus, device, medium, and program products provided in this application's embodiments input acquired user feature data and map data into a pre-trained deep learning model. The model can generate a map color scheme that matches the input data, and then apply the map color scheme to the corresponding layer of the map software for rendering. The deep learning model can learn the mapping relationship between user features and map color schemes in advance through training based on historical color scheme data, thereby generating more diverse personalized color schemes. This effectively improves the color harmony and user matching of map rendering, reduces user visual fatigue when looking at the map, and improves travel safety. Attached Figure Description

[0044] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0045] Figure 1 A flowchart illustrating a map rendering method provided as an example in this application;

[0046] Figure 2 A schematic diagram of a map rendering effect provided as an example in this application Figure 1 ;

[0047] Figure 3 A schematic diagram of a map rendering effect provided as an example in this application Figure 2 ;

[0048] Figure 4 A schematic diagram of a map rendering effect provided as an example in this application Figure 3 ;

[0049] Figure 5 A schematic diagram of a map rendering effect provided as an example in this application Figure 4 ;

[0050] Figure 6 A schematic diagram of a map rendering interface is provided as an example in this application. Figure 1 ;

[0051] Figure 7 A schematic diagram of a map rendering interface is provided as an example in this application. Figure 2 ;

[0052] Figure 8 This application provides a schematic diagram of the structure of a map rendering apparatus as an example.

[0053] Figure 9 This is a schematic diagram of the structure of an electronic device provided as an example in this application.

[0054] The accompanying drawings illustrate specific embodiments of this application, which will be described in more detail below. These drawings and descriptions are not intended to limit the scope of the concept in any way, but rather to illustrate the concept of this application to those skilled in the art through reference to particular embodiments. Detailed Implementation

[0055] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application as detailed in the appended claims.

[0056] Map rendering is a crucial step in the map data processing and visualization process. Its core function is to transform abstract GIS geographic information data, POI (Point of Interest) data, and route planning results into intuitive and recognizable visual interfaces using graphics and image technology. Map rendering technology can be applied to intelligent navigation systems, human-machine interfaces for autonomous vehicles, and high-precision map visualization.

[0057] Currently, when users view locations using map software, the map interface generally uses a fixed color scheme template for rendering. This fixed color scheme is monotonous and provides a limited visual experience for users. It not only fails to meet diverse user needs but also leads to visual fatigue, inefficient information delivery, and hinders users' ability to quickly identify key map information. Especially when users are driving, prolonged staring at a monotonous map color scheme can easily cause visual fatigue, distract driving attention, and potentially increase safety risks.

[0058] Based on this, a technical concept is proposed: by introducing a deep learning model trained on historical color scheme data, the traditional fixed-template map color scheme configuration method is transformed into a personalized intelligent color scheme generation process. Specifically, the model can learn and establish a mapping relationship from user characteristics to map rendering color schemes based on user feature data. This allows for the real-time generation of map color schemes adapted to different users or different scenarios, thus solving the problems of poor visual experience and security issues caused by the lack of color uniformity and personalization in existing technologies.

[0059] The technical solution of this application and how the technical solution of this application solves the above-mentioned technical problems are described in detail below with specific embodiments. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments. The embodiments of this application will now be described with reference to the accompanying drawings.

[0060] Figure 1 This application provides a schematic flowchart of a map rendering method as an example. Figure 1 As shown, the method includes:

[0061] Step S101: Obtain user feature data and map data.

[0062] User characteristics data may include gender, age, cumulative software usage time, historical mileage, historical navigation habits, destination type, etc. Map data may include roads, buildings, etc., around the user's current location.

[0063] For example, when a user uses map software, the software can obtain the user's age and other characteristics from the map software client after the user's authorization, and can also obtain map data such as the road network around the user from the map library based on the user's current location.

[0064] Step S102: Input the feature data and map data into the pre-trained deep learning model.

[0065] The deep learning model is trained based on historical color scheme data to learn the mapping relationship between user characteristics and map color schemes.

[0066] For example, a large language model or a CNN (Convolutional Neural Network) can be chosen as the base model before training. Training data can include publicly available color scheme datasets and user rating data. Training with a color scheme dataset containing multiple general color schemes allows the model to learn general color harmony rules and style mapping relationships. Using user rating data collected in actual map application scenarios allows the model to learn the color preferences of different user groups in navigation scenarios. Through supervised training and reinforcement learning, the trained model can construct a mapping relationship from multi-dimensional user features and map data to personalized color schemes. Deploying the trained model to the map software application side allows inference using real-time acquired user feature data and map data to generate corresponding color schemes.

[0067] In some possible implementations, besides using historical color scheme data, color harmony algorithms can be introduced as constraints during model training to ensure that the mapping relationships learned by the model can generate color schemes that conform to color principles, maintaining aesthetic consistency. Furthermore, during model training, the model can be guided to associate with some preset color scheme style types (e.g., business, natural, nighttime). These style types can serve as high-dimensional feature labels, enabling the model to first determine the appropriate style category based on the input user characteristics during inference, and then generate specific color values ​​and texture parameters under the constraints of that style, thereby increasing the controllability and interpretability of the generation process.

[0068] Step S103: Generate a map color scheme that matches the input data using a deep learning model.

[0069] The map color scheme includes the color values ​​and / or texture parameters of visual elements in the map, including at least one of the following: sky, ground, roads, water bodies, and buildings.

[0070] For example, a trained deep learning model can be used to generate a personalized color scheme that is adapted to the user. The deep learning model can calculate the input data based on the mapping relationship learned during training to generate specific color parameters that include various visual elements in the map.

[0071] Step S104: Render the corresponding layers of the map software according to the map color scheme.

[0072] For example, the map color scheme generated by the deep learning model can be applied to the corresponding layers of the map through the map rendering engine. When a user opens the map software to view the map or uses navigation, the map rendering engine can call the deep learning model to generate the color scheme, and dynamically color and render the corresponding graphic layers (such as background layer, road layer, and point of interest layer) in the map software according to the parameters in the scheme through the shader program.

[0073] It's important to note that, in terms of static relationships, the map rendering engine can include resources required for shading and rendering, such as texture mapping units and material libraries. In terms of dynamic relationships, the map rendering engine can update color parameters based on real-time data (such as current time, the user's current navigation route travel time, and distance to the destination), for example, by gradually changing the sky color over time. During real-time color parameter updates, the texture and color of 3D elements such as vehicle models and tree models in the map can be controlled to change synchronously. This approach can replace the original fixed color template rendering scheme, enabling real-time and personalized updates to the interface's visual appearance.

[0074] In the above embodiments, the acquired user feature data and map data are input into a pre-trained deep learning model. The model can generate a map color scheme that matches the input data, and then apply the map color scheme to the corresponding layer of the map software for rendering. The deep learning model can learn the mapping relationship between user features and map color schemes in advance through training based on historical color scheme data, thereby generating more diverse personalized color schemes. This can effectively improve the color harmony and user matching of map rendering, reduce user visual fatigue when looking at the map, and improve travel safety.

[0075] In one embodiment, generating a map color scheme that matches the input data using a deep learning model includes:

[0076] Determine the target style type corresponding to the input feature data from multiple preset color scheme styles; generate a map color scheme that conforms to the target style type based on the input map data.

[0077] In this embodiment, the deep learning model can be configured to perform phased color scheme generation. In the first phase, based on the input user feature data, the model can intelligently match and decide from a predefined, limited style type library (such as "business minimalist," "natural and fresh," and "nighttime eye protection") to select the most suitable target style type for the current user. In the second phase, under the constraint of the selected target style type, the model can combine specific map data (such as roads and water bodies) to generate a specific color scheme that conforms to that style type. This phased guidance approach makes the personalized color scheme generation process more controllable and interpretable, reduces style deviations from random color scheme generation, and ensures the aesthetic consistency of the output scheme.

[0078] In the above embodiments, the model can be configured to generate color schemes in stages. By guiding the model to select a style type from preset style types based on user characteristics as a constraint, the color schemes generated by the model can have a clearer style orientation and higher internal harmony while ensuring diversity. This reduces the risk of randomly generating inconsistent color schemes and also improves the interpretability and interactivity of the color scheme generation process. User preferences can be mapped and adjusted more intuitively through style types, thereby more accurately improving the compatibility between color schemes and users.

[0079] In one embodiment, the feature data includes the music style type of the music played by the user, and determining the target style type corresponding to the input feature data from a plurality of preset color scheme style types includes:

[0080] The target style type is determined from multiple preset color scheme styles based on the music style type.

[0081] In this embodiment, the user's music style preference can be used as an important basis for the model to generate a color scheme. Specifically, the style type (such as rock, folk, electronic music, etc.) of the user's current or historically played music can be obtained from the music software through the API (Application Programming Interface) provided by the user terminal. Then, based on the mapping relationship between the music style type and the map color scheme style type learned during the model training phase, the map color scheme style type corresponding to the user's music style type can be selected.

[0082] In the above embodiments, by establishing a cross-modal mapping from music style to map color scheme style, the model can perceive the user's auditory preferences and real-time mood, thereby determining the map color scheme style type. This can generate map color schemes that are more in sync with the user's current mood in terms of emotional atmosphere, reducing the tediousness of users manually adjusting map color schemes, reducing attention distraction caused by the mismatch between interface visuals and user mood, and ensuring travel safety.

[0083] In one embodiment, the map data further includes navigation data, and the map software renders the corresponding layers according to the map color scheme, and also includes:

[0084] Adjust the display status of the navigation panel in the map software based on the navigation data.

[0085] For example, when rendering map layers, the navigation interface interaction can also be adjusted. Based on key information in the navigation data, a preset decision tree algorithm determines the appropriate display state of the navigation panel in real time, and this determination result is applied in conjunction with an AI-generated color scheme to match the panel's visual appearance (visibility, size, color) with the current navigation scenario and user needs. For instance, if the navigation destination is identified as a "scenic spot," the display state of the navigation panel can be adjusted as the destination approaches, highlighting and enlarging the scenic spots and surrounding POI icons. POIs are data units used in geographic information systems to mark specific locations and can represent entities such as buildings, shops, and bus stops.

[0086] In the above embodiments, by using navigation data as model input data, the model can understand the user's real-time intentions and navigation scenario requirements (such as highlighting attractions when approaching a scenic destination) and automatically adjust the presentation of the navigation panel. This improves the efficiency and intuitiveness of map information acquisition, reduces user distraction caused by searching for information or being disturbed by redundant navigation interfaces, and, combined with personalized color schemes, provides users with a more focused and safer driving visual environment.

[0087] In one embodiment, adjusting the display state of the navigation panel in the map software based on navigation data includes:

[0088] Based on the navigation data, determine whether the current navigation route is a frequently used route for the user; if it is a frequently used route, control the map software's navigation panel to display or hide the navigation panel in the first style; if it is not a frequently used route, control the map software's navigation panel to display in the second style.

[0089] The first style can include either shrinking the navigation panel or increasing its transparency. The second style can include either enlarging the navigation panel or highlighting it.

[0090] In this embodiment, the degree of overlap between the current navigation route and the user's historical navigation routes can be used to determine whether it is a frequently used route. For example, if the current navigation route is the same as a route the user has used multiple times previously, then the current navigation route is a frequently used route. If it is a frequently used route, a first style aimed at simplifying or weakening the visual presence of the navigation panel can be adopted, such as shrinking or even hiding the panel. This style aims to minimize the interference of the navigation panel on the user's visual interface. If it is not a frequently used route, a second style aimed at highlighting navigation information can be adopted, such as enlarging the panel or highlighting it. This style aims to attract the user's visual attention and make the user notice the navigation guidance information in a timely manner.

[0091] In the above approach, by adopting a strategy of enhancing guidance on unfamiliar routes and simplifying the interface on familiar routes, unnecessary visual information is reduced on familiar paths. This allows more screen space to be used to present real-time road conditions and the surrounding environment, reducing visual interference from irrelevant information and improving comfort and safety in common scenarios such as commuting. Conversely, on unfamiliar routes, the visual weight of navigation information is strengthened to ensure that key navigation guidance can be obtained quickly and accurately. Overall, by differentiating scenarios related to frequently used routes, a dynamic balance between safety and usability can be achieved while enhancing the personalized experience of map rendering.

[0092] In one embodiment, after rendering the corresponding layers of the map software according to the map color scheme, the method further includes:

[0093] Obtain user feedback on the rendering results; optimize the deep learning model based on the feedback.

[0094] After rendering the map based on the color scheme generated by the deep learning model, subjective or objective evaluation data of users on the current rendering result can be obtained (such as collecting satisfaction ratings, preference selections, or usage time and other interactive behaviors). Subsequently, the collected evaluation data is associated with the corresponding input feature data, map data, and generated color scheme to generate labeled training samples. These newly generated samples are then used to perform incremental learning, parameter fine-tuning, or reinforcement learning on the deep learning model, thereby achieving continuous optimization of the model generation strategy.

[0095] In the above embodiments, by constructing a closed loop from rendering to user feedback to model optimization, the model can continuously learn from real-time feedback from real users, thereby continuously refining and correcting its understanding of individual user preferences and group trends. This can improve the matching accuracy between the generated color scheme and the user's expected visual experience, and achieve a continuous improvement in overall rendering quality.

[0096] In one embodiment, after rendering the corresponding layers of the map software according to the map color scheme, the method further includes:

[0097] Obtain the user's real-time environmental data; adjust the color scheme of the rendered map based on the real-time environmental data.

[0098] Real-time environmental data can include weather conditions (such as sunny, rainy, foggy, etc.), humidity, temperature, and light intensity.

[0099] After the deep learning model generates and applies the initial color scheme to complete the rendering, it can continuously obtain real-time physical data of the user's environment through the user terminal. Then, the rendering engine can dynamically adjust the global or local color parameters of the rendered map according to the preset environment adaptation rules (such as automatically increasing the overall contrast and saturation on rainy or foggy days, and reducing the overall brightness of the map interface under strong light), so that the map display effect on the screen is in harmony with the actual external visual environment around the user.

[0100] In the above embodiments, by incorporating real-time environmental data for post-rendering correction, the problem of color schemes generated by the model potentially being out of sync with the actual environment can be solved (for example, during a sudden downpour, color schemes originally suitable for sunny days may become glaring). This dynamic adjustment ensures that the map interface maintains a harmonious visual effect with the surrounding environment under various lighting and weather conditions, reducing visual discomfort caused by excessive contrast between the map interface and the external environment, and further reducing potential safety risks.

[0101] Based on the map rendering methods of the above embodiments, this application also provides a map rendering system. This system may include a map color scheme resource generation module, a map theme recommendation module, a user feature input parameter module, a UI intervention module, a POI recommendation module, a travel feature module, an HMI recommendation service module, a map rendering engine module, and a user feedback module.

[0102] The map color scheme generation module can deploy the deep learning model trained in the above embodiments. The user feature input parameter module can be used to manage user feature data (such as user gender, age, etc.) input to the deep learning model. The map theme recommendation module can be used to store and recommend several specific color scheme styles to users. The UI (User Interface) intervention module can be used to manage interface controls such as navigation panels presented in the map software. The POI recommendation module can be used to manage POI markers displayed in the map software. The travel feature module can be used to manage user-related navigation data. The map rendering engine can call the deep learning model to generate a color scheme that matches user characteristics and then render it.

[0103] In one example, the map rendering system described above is applied when users A, B, and C use map software for navigation. Based on the personal characteristic data and map navigation data of users A, B, and C, the model processes the data to obtain the following characteristic labels: User A is female, young, novice driver, familiar with the road; User B is male, middle-aged, aggressive experienced driver, familiar with the road; and User C is male, elderly, steady experienced driver, unfamiliar with the road.

[0104] Figure 2A schematic diagram of a map rendering effect provided as an example in this application Figure 1 . Figure 3 A schematic diagram of a map rendering effect provided as an example in this application Figure 2 . Figure 4 A schematic diagram of a map rendering effect provided as an example in this application Figure 3 .

[0105] Figure 2 , Figure 3 and Figure 4 These are renderings generated by the map rendering system for users A, B, and C when they use the map software for navigation, as described above. For example... Figure 2 As shown, by learning from historical color schemes, the model can generate dopamine-inspired color schemes for young female users. Furthermore, since user A is a familiar driver and navigates to frequently used routes, pink, red, and color gradient effects can be used to provide a richer visual experience. Figure 3 As shown, the model can generate a sporty color scheme for middle-aged male users, using green tones to render buildings and greenery, thus improving visual comfort. Figure 4 As shown, the model can generate a more minimalist color scheme for elderly male users. Since user C is not familiar with the roads and the navigation route is not a frequently used route, a general color scheme can be used for rendering to reduce the overall color richness of the map, allowing the user to concentrate on driving.

[0106] In one example, user A launched the map software but did not use the navigation function, and it was detected that user A was playing music through the car's infotainment system; the music style was upbeat and lively. Figure 5 As shown, in this scenario, the system can completely hide the navigation panel, automatically update and render the surrounding map based on the user's location, and can also generate cartoon-style clouds and suns on the map based on the type of music the user is playing (e.g., ...). Figure 5 The map interface features a smiling sun emoji, ensuring the visual effect aligns with the user's mood and enhancing the user experience.

[0107] Figure 6 A schematic diagram of a map rendering interface is provided as an example in this application. Figure 1 .like Figure 6 As shown, the HMI (Human Machine Interface) recommendation service module can add AI-generated map recommendation UI controls (such as...) to the user's map software interface. Figure 6 The blue box-shaped UI in the lower right corner is used to recommend the map interface rendered with a color scheme generated based on the model to the user.

[0108] Figure 7A schematic diagram of a map rendering interface is provided as an example in this application. Figure 2 .like Figure 7 As shown, the user feedback module can add UI controls for evaluating rendering satisfaction to the map software interface, for example... Figure 7 The blue UI in the lower right corner can collect user feedback on the color rendering results generated by the AI ​​model. Users can choose to like or dislike it, and this feedback can be used for incremental training of the AI ​​model.

[0109] The map rendering system provided in this application overcomes the shortcomings of current high-precision map rendering, such as lack of personalized adaptation, fixed and disharmonious color schemes, rigid navigation elements, and lack of user feedback, thereby improving visual experience and navigation safety. The map rendering engine module generates harmonious color schemes by calling models for rendering, which can significantly improve user satisfaction ratings, reduce visual fatigue warnings and navigation errors. The rendering engine supports millisecond-level real-time updates, ensuring smooth navigation and maintaining personalized adaptation of map rendering effects to user characteristics.

[0110] Figure 8 This application provides an exemplary structural diagram of a map rendering apparatus, such as... Figure 8 As shown, the map rendering device 800 provided in this embodiment includes:

[0111] The acquisition module 801 is used to acquire user feature data and map data;

[0112] The input module 802 is used to input feature data and map data into a pre-trained deep learning model; the deep learning model is trained based on historical color scheme data to learn the mapping relationship between user features and map color schemes.

[0113] The generation module 803 is used to generate a map color scheme that matches the input data through a deep learning model. The map color scheme includes color values ​​and / or texture parameters of visual elements in the map. The visual elements include at least one of sky, ground, road, water and building.

[0114] Rendering module 804 is used to render the corresponding layers of the map software according to the map color scheme.

[0115] In some possible implementations, the generation module 803 can also be used to: determine the target style type corresponding to the input feature data from multiple preset color scheme style types; and generate a map color scheme that conforms to the target style type based on the input map data.

[0116] In some possible implementations, the generation module 803 can also be used to: determine the corresponding target style type from multiple preset color scheme style types based on the music style type.

[0117] In some possible implementations, the rendering module 804 can also be used to: adjust the display state of the navigation panel in the map software based on navigation data.

[0118] In some possible implementations, the rendering module 804 can also be used to: determine whether the current navigation route is a frequently used route by the user based on the navigation data; if it is a frequently used route, control the navigation panel of the map software to display or hide the navigation panel in a first style, the first style including shrinking the navigation panel and / or increasing the transparency of the navigation panel; if it is not a frequently used route, control the navigation panel of the map software to display in a second style, the second style including enlarging the navigation panel and / or highlighting the navigation panel.

[0119] In some possible implementations, the rendering module 804 can also be used to: obtain user feedback on the rendering results; and optimize the deep learning model based on the feedback.

[0120] In some possible implementations, the rendering module 804 can also be used to: acquire the user's real-time environmental data; and adjust the color scheme of the rendered map based on the real-time environmental data.

[0121] The map rendering device provided in this embodiment can execute the method provided in the above method embodiment. Its implementation principle and technical effect are similar, and will not be described in detail here.

[0122] Figure 9 This is a schematic diagram of the structure of an electronic device provided in this application. Figure 9 As shown, the electronic device 90 provided in this embodiment includes at least one processor 901 and a memory 902. Optionally, the device 90 further includes a communication component 903. The processor 901, memory 902, and communication component 903 are connected via a bus 904.

[0123] In a specific implementation, at least one processor 901 executes computer execution instructions stored in memory 902, causing at least one processor 901 to perform the above-described method.

[0124] The specific implementation process of processor 901 can be found in the above method embodiments, and its implementation principle and technical effect are similar. It will not be repeated here.

[0125] In the above embodiments, it should be understood that the processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), etc. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in this invention can be directly implemented by a hardware processor, or implemented by a combination of hardware and software modules within the processor.

[0126] The memory may include random access memory (RAM) and may also include non-volatile memory (NVM), such as at least one disk storage device.

[0127] The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. Buses can be categorized as address buses, data buses, control buses, etc. For ease of illustration, the buses shown in the accompanying drawings are not limited to a single bus or a single type of bus.

[0128] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the above-described method.

[0129] This application also provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the above-described method.

[0130] The aforementioned readable storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk. The readable storage medium can be any available medium accessible to a general-purpose or special-purpose computer.

[0131] An exemplary readable storage medium is coupled to a processor, enabling the processor to read information from and write information to the readable storage medium. Of course, the readable storage medium can also be a component of the processor. The processor and the readable storage medium can reside in an Application Specific Integrated Circuit (ASIC). Alternatively, the processor and the readable storage medium can exist as discrete components in the device.

[0132] The division of units is merely a logical functional division; in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be indirect coupling or communication connection through some interfaces, devices, or units, and may be electrical, mechanical, or other forms.

[0133] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0134] In addition, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0135] If a function is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0136] Those skilled in the art will understand that all or part of the steps of the above-described method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When executed, the program performs the steps of the above-described method embodiments; and the aforementioned storage medium includes various media capable of storing program code, such as ROM, RAM, magnetic disks, or optical disks.

[0137] Finally, it should be noted that other embodiments of the invention will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This invention is intended to cover any variations, uses, or adaptations of the invention that follow the general principles of the invention and include common knowledge or customary techniques in the art not disclosed herein, and is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of the invention is limited only by the appended claims.

Claims

1. A map rendering method, characterized in that, include: Acquire user characteristic data and map data; The feature data and the map data are input into a pre-trained deep learning model; The deep learning model is trained based on historical color scheme data to learn the mapping relationship between user characteristics and map color schemes; The deep learning model generates a map color scheme that matches the input data. The map color scheme includes color values ​​and / or texture parameters of visual elements in the map, and the visual elements include at least one of sky, ground, roads, water bodies and buildings. The corresponding layers of the map software are rendered according to the map color scheme.

2. The method according to claim 1, characterized in that, The process of generating a map color scheme that matches the input data using the deep learning model includes: Determine the target style type corresponding to the input feature data from multiple preset color scheme style types; Generate a map color scheme that matches the target style type based on the input map data.

3. The method according to claim 2, characterized in that, The feature data includes the music style type of the music played by the user. Determining the target style type corresponding to the input feature data from multiple preset color scheme style types includes: The target style type is determined from multiple preset color scheme style types based on the music style type.

4. The method according to any one of claims 1 to 3, characterized in that, The map data also includes navigation data, and the rendering of the corresponding layers of the map software according to the map color scheme further includes: Based on the navigation data, adjust the display status of the navigation panel in the map software.

5. The method according to claim 4, characterized in that, Adjusting the display state of the navigation panel in the map software based on the navigation data includes: Based on the navigation data, determine whether the current navigation route is the user's frequently used route; If it is a frequently used route, the navigation panel of the map software is controlled to be displayed or hidden in a first style, the first style including shrinking the navigation panel and / or increasing the transparency of the navigation panel; If the route is not frequently used, the navigation panel of the map software is controlled to be displayed in a second style, which includes enlarging the navigation panel and / or highlighting the navigation panel.

6. The method according to any one of claims 1 to 3, characterized in that, After rendering the corresponding layers of the map software according to the map color scheme, the process also includes: Obtain the user's evaluation of the rendering results; The deep learning model is optimized based on the evaluation.

7. The method according to any one of claims 1 to 3, characterized in that, After rendering the corresponding layers of the map software according to the map color scheme, the process also includes: Obtain the user's real-time environmental data; The color scheme of the rendered map is adjusted based on the real-time environmental data.

8. A map rendering device, characterized in that, include: The acquisition module is used to acquire user feature data and map data; An input module is used to input the feature data and the map data into a pre-trained deep learning model; The deep learning model is trained based on historical color scheme data to learn the mapping relationship between user characteristics and map color schemes; A generation module is used to generate a map color scheme that matches the input data through the deep learning model. The map color scheme includes color values ​​and / or texture parameters of visual elements in the map. The visual elements include at least one of sky, ground, road, water body and building. The rendering module is used to render the corresponding layers of the map software according to the map color scheme.

9. An electronic device, characterized in that, include: A processor, and a memory communicatively connected to the processor; The memory stores computer-executed instructions; The processor executes computer execution instructions stored in the memory to implement the method as described in any one of claims 1 to 7.

10. A computer-readable storage medium / computer program product, characterized in that, The computer-readable storage medium stores computer-executable instructions, which, when executed by a processor, are used to implement the method as described in any one of claims 1 to 7; and / or, The computer program product includes a computer program that, when executed by a processor, implements the method of any one of claims 1 to 7.

Images