An interface theme generation method and system, and a storage medium

Abstract

This invention relates to a method and system for generating interface themes, and a storage medium, comprising: receiving interface design condition information and current vehicle location information sent by a vehicle terminal; identifying the user account corresponding to the vehicle terminal; and obtaining pre-stored user personalization information based on the user account; preprocessing the interface design condition information, current vehicle location information, and user personalization information to obtain corresponding multiple digital information; extracting features from the multiple digital information to obtain corresponding feature information; inputting the feature information into a pre-trained deep learning model for processing to generate a corresponding interface theme; and sending the interface theme to the vehicle terminal for setting the interface theme of the in-vehicle information system. This invention addresses the technical problem that existing in-vehicle information system interface theme designs cannot meet users' personalized needs when selecting interface themes, resulting in poor user experience and requiring significant manpower and time costs.

Description

Technical Field

[0001] This invention relates to the field of interface theme generation technology, specifically to an interface theme generation method and system, and a computer-readable storage medium. Background Technology

[0002] The interface themes of existing in-vehicle information systems are mainly designed by HMI designers through interface interaction elements. This design process is heavily influenced by the designer's subjective preferences, which obviously cannot align with the preferences of all users. Different users have different aesthetic tastes and preferences, leading to different preferred interface themes. Although in-vehicle information systems offer a variety of interface themes, they cannot possibly cover all user preferences. Therefore, the current interface theme designs of in-vehicle information systems fail to meet users' personalized needs when choosing an interface theme, resulting in a poor user experience. Furthermore, since the interface theme design is done manually by designers, it requires significant manpower and time costs. Summary of the Invention

[0003] The purpose of this invention is to propose an interface theme generation method and system, and a computer-readable storage medium, in order to solve the technical problems that the interface theme design of existing vehicle information systems cannot meet the personalized needs of users when selecting interface themes, resulting in poor user experience and requiring a lot of manpower and time costs.

[0004] To achieve the above objectives, embodiments of the present invention propose a method for generating an interface theme, comprising the following steps:

[0005] Step S10: Receive interface design condition information and current vehicle location information sent by the vehicle terminal, identify the user account corresponding to the vehicle terminal, and obtain the pre-stored personalized user information based on the user account.

[0006] Step S20: Preprocess the interface design condition information, current vehicle location information, and user personalization information to obtain corresponding multiple digital information;

[0007] Step S30: Extract features from the multiple digital information to obtain corresponding feature information;

[0008] Step S40: Input the feature information into a pre-trained deep learning model for processing to generate the corresponding interface theme;

[0009] Step S50: Send the interface theme to the vehicle terminal for setting the interface theme of the in-vehicle information system.

[0010] Preferably, step S10 further includes:

[0011] Receive user input information sent by the user device while logged into the user account; wherein the user input information is text information and / or image information;

[0012] Step S20 specifically includes:

[0013] When no user input information is received, the interface design condition information, current vehicle location information and user personalized information are preprocessed to obtain corresponding digital information.

[0014] When the user input information is received, the interface design conditions information, current vehicle location information, user personalization information and user input information are preprocessed to obtain corresponding digital information.

[0015] Preferably, in step S20, the current vehicle positioning information is preprocessed to obtain corresponding digital information, specifically including:

[0016] Based on the current vehicle location information, the vehicle's location area information and the weather information of the vehicle's location area are obtained, and the vehicle's location area information and the weather information of the vehicle's location area are preprocessed to obtain corresponding digital information.

[0017] Preferably, in step S20, the user input information is preprocessed to obtain corresponding digital information, specifically including:

[0018] When the user input information includes text information, natural language processing is performed on the text information to extract one or more keywords, and the one or more keywords are converted into corresponding numerical information;

[0019] When the user input information includes image information, the image information is processed to obtain a grayscale image, and the grayscale image is converted into corresponding digital information.

[0020] Preferably, step S30 includes:

[0021] The multiple digital information is filtered in the same group to obtain multiple corresponding information features, and the multiple information features are encapsulated to obtain feature information; wherein, each information feature is a 1-row N-column digital matrix, and the feature information is an M-column M-row square digital matrix; wherein, N>0, M≥N.

[0022] Preferably, step S50 further includes:

[0023] After sending the interface theme to the vehicle, wait to receive the response information from the vehicle.

[0024] When the response information indicates that the user has confirmed the application of the interface theme, the interface theme generation process ends.

[0025] When the response information indicates that the user has confirmed a request for a new interface theme, the deep learning model is used to reprocess the feature information to obtain a new interface theme, and the new interface theme is sent to the vehicle.

[0026] Preferably, the user personalization information includes user preference information and user characteristic information, wherein the user preference information includes a set of positive preference feedback information and a set of negative preference feedback information;

[0027] Step S50 further includes:

[0028] When the response information indicates that the user has confirmed the application of the interface theme, the interface theme is recorded as positive feedback information of the user's preference and added to the set of positive feedback information for storage.

[0029] When the response information indicates that the user has confirmed a request to obtain a new interface theme, the interface theme is recorded as the user's negative feedback information and added to the negative feedback information set for storage.

[0030] Embodiments of the present invention also propose an interface theme generation system, comprising:

[0031] The information acquisition unit is used to identify the user account corresponding to the vehicle terminal when receiving interface design condition information and current vehicle location information sent by the vehicle terminal, and to obtain pre-stored user personalized information based on the user account.

[0032] The preprocessing unit is used to preprocess the interface design condition information, current vehicle positioning information and user personalized information respectively to obtain corresponding multiple digital information.

[0033] A feature extraction unit is used to extract features from the multiple digital information to obtain corresponding feature information;

[0034] The topic generation unit is used to input the feature information into a pre-trained deep learning model for processing, and generate corresponding interface topics; and

[0035] The theme sending unit is used to send the interface theme to the vehicle terminal for generating the interface theme of the vehicle information system.

[0036] Preferably, the information acquisition unit is further configured to receive user input information sent by the user device while logged into the user account; wherein the user input information is text information and / or image information;

[0037] The preprocessing unit is specifically used for:

[0038] When the information acquisition unit does not receive the user input information, it preprocesses the interface design condition information, the current vehicle location information and the user personalized information to obtain the corresponding digital information.

[0039] When the information acquisition unit receives the user input information, it preprocesses the interface design condition information, current vehicle location information, user personalization information, and user input information to obtain corresponding digital information.

[0040] Embodiments of the present invention also propose a computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the steps of the interface theme generation method described in the above embodiments.

[0041] The embodiments of the present invention have at least the following beneficial effects:

[0042] This invention can be implemented by a cloud server, used to provide interface theme generation services for in-vehicle information systems to multiple vehicle terminals. The cloud server establishes communication and interacts with multiple vehicle terminals, receiving information sent by them. When the cloud server receives interface design condition information and current vehicle location information from a particular vehicle terminal, it identifies the user account corresponding to that vehicle terminal and retrieves pre-stored user personalization information based on the user account. Each user account is bound to user personalization information and stored on the cloud server. User personalization information can be set by the user at any time or obtained by the cloud server based on user behavior. Further, the cloud server processes the interface design condition information, current vehicle location information, and user personalization information... The information is preprocessed to obtain multiple corresponding digital information, and features are extracted from these multiple digital information to obtain corresponding feature information. Finally, the feature information is input into a pre-trained deep learning model for processing to generate a corresponding interface theme, which is then sent to a specific vehicle for setting the interface theme of the in-vehicle information system. In this embodiment of the invention, the interface theme of the in-vehicle information system is generated by the deep learning model based on the feature information input to the model. This process can be understood as an interface theme design, which does not require manual design by designers, thus reducing labor and time costs. Moreover, it can generate interface themes based on user-personalized information, meeting users' personalized needs when selecting interface themes and improving user experience.

[0043] Other features and advantages of the present invention will be set forth in the following description. Attached Figure Description

[0044] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0045] Figure 1 This is a flowchart illustrating an interface theme generation method according to an embodiment of the present invention.

[0046] Figure 2 This is a schematic diagram of the structure of an interface theme generation system according to another embodiment of the present invention. Detailed Implementation

[0047] The various exemplary embodiments, features, and aspects of this disclosure will now be described in detail with reference to the accompanying drawings. Furthermore, numerous specific details are set forth in the following detailed embodiments to better illustrate the invention. Those skilled in the art will understand that the invention can be practiced without certain specific details. In some instances, means well known to those skilled in the art have not been described in detail in order to highlight the spirit of the invention.

[0048] See Figure 1 One embodiment of the present invention proposes an interface theme generation method, which can be implemented by a cloud server to provide interface theme generation services for in-vehicle information systems to multiple vehicle terminals. The cloud server establishes communication and interacts with multiple vehicle terminals, for example, through a vehicle network communication connection. The method includes the following steps:

[0049] Step S10: Receive interface design condition information and current vehicle location information sent by the vehicle terminal, identify the user account corresponding to the vehicle terminal, and obtain the pre-stored personalized user information based on the user account.

[0050] Specifically, the vehicle interacts with the cloud server through the in-vehicle information system. When a user starts the vehicle, they need to log in to the in-vehicle information system with their user account in order to interact with the cloud server. For each user account, the cloud server pre-stores the corresponding user's personalized information. The user's personalized information can be entered and customized by the vehicle user, or it can be identified and extracted by the cloud server based on the user's behavior data in the in-vehicle information system.

[0051] The interface design condition information refers to the design parameters of the system interface of the vehicle information system, such as system size and resolution characteristics, control style specifications in the interface, color specification range of each UI component module of the system design theme, interface background design specification range, icon and text style specifications, etc. All interface themes need to be designed and generated based on the interface design condition information given by the vehicle side in order to be applicable to the vehicle information system of the corresponding vehicle side. It can be understood that the interface design condition information is the constraint or basic framework for generating interface themes.

[0052] In this embodiment, when the vehicle starts, the vehicle user logs into their user account in the vehicle information system. After successful login, the vehicle information system automatically obtains the pre-set interface design conditions and the current vehicle location information, and sends them to the cloud server to automatically initiate the generation of the interface theme.

[0053] Step S20: Preprocess the interface design condition information, current vehicle location information, and user personalization information to obtain corresponding multiple digital information;

[0054] Specifically, since different types of information have different forms of representation, in order to facilitate subsequent information processing, all types of information are preprocessed in step S20 and uniformly converted into digital information.

[0055] Step S30: Extract features from the multiple digital information to obtain corresponding feature information;

[0056] Specifically, there are many ways to extract features, and this embodiment of the invention is not specifically limited to one or more methods.

[0057] Step S40: Input the feature information into a pre-trained deep learning model for processing to generate the corresponding interface theme;

[0058] In this embodiment of the invention, the interface theme of the vehicle information system is generated by a deep learning model based on the feature information input to the model. This process can be understood as an interface theme design work, which does not require manual design by designers. Therefore, it can reduce labor and time costs. Moreover, it can generate the interface theme based on user personalized information, which can meet the personalized needs of users when selecting interface themes and improve user experience.

[0059] Step S50: Send the interface theme to the vehicle terminal for setting the interface theme of the in-vehicle information system;

[0060] Specifically, when the vehicle's in-vehicle information system receives the interface theme, it can directly apply the interface theme, or preview the interface theme and prompt the user whether to apply the interface theme.

[0061] In some embodiments, step S10 further includes:

[0062] Receive user input information sent by the user device while logged into the user account; wherein the user input information is text information and / or image information;

[0063] Specifically, the user device is, for example, a mobile smart terminal such as a mobile phone. For instance, the mobile phone has a client installed, and the user logs in to the client on the mobile phone using their user account.

[0064] It should be noted that the user account of the vehicle information system is the same as the user account logged in on the mobile client; the user can generate image information by taking a picture with the mobile phone or selecting a picture from the mobile phone album, or generate text information by entering a piece of text. While logged in with the user account, the user can operate the mobile phone to send text information and / or image information to the cloud server.

[0065] Step S20 specifically includes:

[0066] When no user input information is received, the interface design condition information, current vehicle location information and user personalized information are preprocessed to obtain corresponding digital information.

[0067] When the user input information is received, the interface design conditions information, current vehicle location information, user personalization information and user input information are preprocessed to obtain corresponding digital information.

[0068] In some embodiments, in step S20, the current vehicle positioning information is preprocessed to obtain corresponding digital information, specifically including:

[0069] Based on the current vehicle location information, the vehicle's location area information and the weather information of the vehicle's location area are obtained, and the vehicle's location area information and the weather information of the vehicle's location area are preprocessed to obtain corresponding digital information.

[0070] Specifically, in this embodiment, when designing and generating the interface theme, the location information of the vehicle user is considered, such as Tianhe District of Guangzhou City, China, or Chaoyang District of Beijing City, China. Weather information of the vehicle user's location is obtained through a weather service application, such as sunny, cloudy, and rain showers. The city where the vehicle user is located is often where the vehicle user lives and works, and the weather conditions may affect the user's mood; therefore, in this embodiment, the city area and weather are used as one of the materials for the interface theme.

[0071] In some embodiments, in step S20, preprocessing the user input information to obtain corresponding digital information specifically includes:

[0072] When the user input information includes text information, perform natural language processing on the text information, extract one or more keywords, and convert the one or more keywords into corresponding digital information; for example, when a user inputs "I'm lovelorn today" through a user device, use natural language processing technology for automatic word segmentation to obtain "today / I / lovelorn /

[0073] 了". Through semantic analysis, the keyword of this text information can be identified as "lovelorn", then "lovelorn" is used as one of the materials for interface theme design, and the finally generated interface theme will be a low-mood interface theme related to "lovelorn"; another example, when a user inputs "The sky is very blue today" through a user device, then perform word segmentation as "today / sky / very blue". Through semantic analysis, the keywords of this text information can be identified as "sky" and "very blue", then "sky" and "blue" are used as one of the materials for interface theme design, and the finally generated interface theme is related to the sky and blue elements.

[0074] When the user input information includes picture information, perform grayscale processing on the picture information to obtain a grayscale image, and convert the grayscale image into corresponding digital information; specifically, that is, convert each pixel point of the picture into a number between 0 and 1, where 0 is white and 1 is black for representation; then use the pre-trained GoogleNet model to perform convolution processing on the grayscale image to extract a digital matrix of a key feature, that is, the digital information corresponding to the conversion of the grayscale image; here, the processing of the grayscale image by the GoogleNet model can be understood as the recognition of the emotion of the image, and the final image emotion is represented by a matrix; of course, in this embodiment, the recognition of the image emotion can also be implemented by other recognition models, and only an example is given here; among them, when a user selects or takes a picture, the picture is related to the user's current mood or the expected interface design theme to be generated. For example, if the picture is a sea view picture, then the sea can be used as one of the materials for interface theme design, and the finally generated interface theme is related to sea elements.

[0075] In some embodiments, step S30 includes:

[0076] Perform peer group filtering (PGF) on the multiple digital information to obtain corresponding multiple information features, and perform encapsulation processing on the multiple information features to obtain feature information; where each information feature is a 1-row N-column digital matrix, and the feature information is an M-column M-row square digital matrix; where N>0, M≥N.

[0077] Specifically, the steps involve using PGF filtering for feature extraction. Each piece of digital information forms a 1-row, N-column digital matrix after PGF filtering, which represents the features of different information such as city areas, weather, images, and text. Furthermore, to facilitate subsequent convolution calculations by the deep learning network model, the features of multiple digital matrices are encapsulated into an M-column, M-row square digital matrix feature.

[0078] In some embodiments, step S50 further includes:

[0079] After sending the interface theme to the vehicle, wait to receive the response information from the vehicle; when the response information indicates that the user has confirmed the application of the interface theme, the interface theme generation process ends; when the response information indicates that the user has confirmed a request to obtain a new interface theme, use the deep learning model to reprocess the feature information to obtain a new interface theme, and send the new interface theme to the vehicle.

[0080] Specifically, the vehicle's in-vehicle information system receives an interface theme from the cloud server, previews it, and prompts the user whether to apply the theme. The user then enters the response information. The in-vehicle information system sends the response information to the cloud server and applies the theme or waits to receive the next theme generated by the cloud server, repeating this process until the vehicle user confirms the application of the theme generated by the cloud server.

[0081] In some embodiments, the user personalization information includes user preference information and user characteristic information, wherein the user preference information includes a set of positive preference feedback information and a set of negative preference feedback information;

[0082] The user characteristic information includes, for example, age, zodiac sign, occupation, and other information that can characterize user traits; in order to generate interface themes based on user characteristic information.

[0083] The positive feedback information set stores information about vehicle user preferences, such as preferred theme types, preferred colors, preferred music styles, and frequently visited entertainment venues. The negative feedback information set is the opposite of the positive feedback information set, containing information such as disliked theme types, disliked colors, disliked music styles, and infrequently visited entertainment venues.

[0084] Step S50 further includes:

[0085] When the response information indicates that the user has confirmed the application of the interface theme, the interface theme is recorded as positive feedback information of the user's preference and added to the set of positive feedback information for storage.

[0086] When the response information indicates that the user has confirmed a request to obtain a new interface theme, the interface theme is recorded as the user's negative feedback information and added to the negative feedback information set for storage.

[0087] As described in the above embodiments, this invention proposes a technology for generating interface themes for in-vehicle information systems using a cloud server. A pre-trained deep learning model is deployed on the cloud server. This deep learning model can generate interface themes suitable for in-vehicle information systems based on given interface design conditions, combined with elements such as city area, weather, and user personal preferences. The generated themes are then sent to the in-vehicle information system for application. This effectively addresses the conflict between the human resource costs, timeliness, user preferences, and the subjective factors of designers when manually designing interface themes, by introducing artificial intelligence technology. The deep learning model automatically generates interface design themes that meet user preferences based on different inputs.

[0088] It should be noted that the deep learning model described in this embodiment is not limited to a certain model type / structure. As for the deep learning model, it has the ability to learn and can realize the function of generating interface design themes through training. For example, the deep learning model can be an LSTM+FCN network model composed of a Long Short-Term Memory Network (LSTM) and a Fully Convolutional Network (FCN).

[0089] See Figure 2 Another embodiment of the present invention also proposes an interface theme generation system, which is applied to a cloud server and can be used to implement the interface theme generation system method described in the above embodiments. The system of this embodiment includes:

[0090] Information acquisition unit 1 is used to identify the user account corresponding to the vehicle terminal when receiving interface design condition information and current vehicle location information sent by the vehicle terminal, and to obtain pre-stored user personalized information based on the user account.

[0091] Preprocessing unit 2 is used to preprocess the interface design condition information, current vehicle positioning information and user personalized information respectively to obtain corresponding multiple digital information;

[0092] Feature extraction unit 3 is used to extract features from the multiple digital information to obtain corresponding feature information;

[0093] Theme generation unit 4 is used to input the feature information into a pre-trained deep learning model for processing, and generate corresponding interface themes; and

[0094] The theme sending unit 5 is used to send the interface theme to the vehicle terminal for generating the interface theme of the vehicle information system.

[0095] In some embodiments, the information acquisition unit 1 is further configured to receive user input information sent by the user device while logged into the user account; wherein the user input information is text information and / or image information;

[0096] The preprocessing unit 2 is specifically used for:

[0097] When the information acquisition unit 1 does not receive the user input information, it preprocesses the interface design condition information, current vehicle location information and user personalized information to obtain the corresponding digital information.

[0098] When the information acquisition unit 1 receives the user input information, it preprocesses the interface design condition information, current vehicle location information, user personalization information, and user input information to obtain corresponding digital information.

[0099] In some embodiments, the topic sending unit 5 is further configured to:

[0100] After sending the interface theme to the vehicle, wait to receive the response information from the vehicle.

[0101] When the response information indicates that the user has confirmed the application of the interface theme, the system ends the interface theme generation process; when the response information indicates that the user has confirmed a request to obtain a new interface theme, the theme generation unit 4 uses the deep learning model to reprocess the feature information to obtain a new interface theme, and sends the new interface theme to the vehicle terminal.

[0102] The systems described in the embodiments above are merely illustrative. 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 modules can be selected to achieve the purpose of the system solution in the embodiments, depending on actual needs.

[0103] It should be noted that the system in the above embodiments corresponds to the method in the above embodiments. Therefore, the parts of the system in the above embodiments that are not described in detail can be obtained by referring to the content of the method in the above embodiments. That is, the specific steps recorded in the method in the above embodiments can be understood as the functions that the system in the above embodiments can achieve, and will not be described again here.

[0104] Embodiment Six of the present invention also proposes a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the steps of the interface theme generation method described in Embodiments One, Three, or Five above.

[0105] Specifically, the computer-readable storage medium may include any entity or recording medium capable of carrying the computer program instructions, such as a USB flash drive, portable hard drive, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signals, telecommunication signals, and software distribution media.

[0106] The various embodiments of the present invention have been described above. These descriptions are exemplary and not exhaustive, nor are they limited to the disclosed embodiments. Many modifications and variations will be apparent to those skilled in the art without departing from the scope and spirit of the described embodiments. The terminology used herein is chosen to best explain the principles, practical application, or technical improvements to the embodiments in the market, or to enable others skilled in the art to understand the embodiments disclosed herein.

Claims

1. A method for generating interface themes, applied to a cloud server, characterized in that, The steps include the following: Step S10: Receive interface design condition information and current vehicle location information sent by the vehicle terminal, identify the user account corresponding to the vehicle terminal, and obtain pre-stored user personalized information based on the user account; the user personalized information includes user preference information and user characteristic information, and the user preference information includes a set of positive preference feedback information and a set of negative preference feedback information; wherein, the process of the cloud server receiving the interface design condition information and current vehicle location information sent by the vehicle terminal is as follows: when the vehicle starts, the vehicle user logs into their user account in the vehicle information system. After successful login, the vehicle information system automatically obtains the pre-set interface design condition information and current vehicle location information, and sends them to the cloud server to automatically initiate the generation of the interface theme; Step S20: Preprocess the interface design condition information, current vehicle location information, and user personalization information to obtain corresponding multiple digital information; Step S30: Extracting features from the plurality of digital information to obtain corresponding feature information, including: performing equal-group filtering on the plurality of digital information to obtain corresponding multiple information features, and encapsulating the plurality of information features to obtain feature information; wherein, each information feature is a 1-row N-column digital matrix, and the feature information is an M-column M-row square digital matrix; N>0, M≥N; Step S40: Input the feature information into a pre-trained deep learning model for processing to generate the corresponding interface theme; Step S50: Send the interface theme to the vehicle terminal for setting the interface theme of the in-vehicle information system, and receive the response information from the vehicle terminal; when the response information indicates that the user confirms the application of the interface theme, the interface theme is recorded as positive feedback information of the user's preference and added to the set of positive feedback information for storage; when the response information indicates that the user confirms the request to obtain a new interface theme, the interface theme is recorded as negative feedback information of the user's preference and added to the set of negative feedback information for storage.

2. The method of claim 1, wherein, Step S10 further includes: Receive user input information sent by the user device while logged into the user account; wherein the user input information is text information and / or image information; Step S20 specifically includes: When no user input information is received, the interface design condition information, current vehicle location information and user personalized information are preprocessed to obtain corresponding digital information. When the user input information is received, the interface design conditions information, current vehicle location information, user personalization information and user input information are preprocessed to obtain corresponding digital information.

3. The method of claim 2, wherein, In step S20, the current vehicle positioning information is preprocessed to obtain corresponding digital information, specifically including: Based on the current vehicle location information, the vehicle's location area information and the weather information of the vehicle's location area are obtained, and the vehicle's location area information and the weather information of the vehicle's location area are preprocessed to obtain corresponding digital information.

4. The method of claim 2, wherein, In step S20, the user input information is preprocessed to obtain corresponding digital information, specifically including: When the user input information includes text information, natural language processing is performed on the text information to extract one or more keywords, and the one or more keywords are converted into corresponding numerical information; When the user input information includes image information, the image information is processed to obtain a grayscale image, and the grayscale image is converted into corresponding digital information.

5. The method according to any one of claims 1 to 4, characterized in that, Step S50 further includes: When the response information indicates that the user has confirmed the application of the interface theme, the interface theme generation process ends. When the response information indicates that the user has confirmed a request for a new interface theme, the deep learning model is used to reprocess the feature information to obtain a new interface theme, and the new interface theme is sent to the vehicle.

6. A UI theme generation system, applied to a cloud server, characterized in that, include: The information acquisition unit is used to identify the user account corresponding to the vehicle terminal when receiving interface design condition information and current vehicle location information sent by the vehicle terminal, and to obtain pre-stored user personalized information based on the user account; the user personalized information includes user preference information and user feature information, and the user preference information includes a set of positive preference feedback information and a set of negative preference feedback information; wherein, the process of the cloud server receiving interface design condition information and current vehicle location information is as follows: when the vehicle starts, the vehicle user logs in to his / her user account in the vehicle information system. After successful login, the vehicle information system automatically obtains the pre-set interface design condition information and current vehicle location information, and sends them to the cloud server to automatically initiate the generation of the interface theme; The preprocessing unit is used to preprocess the interface design condition information, current vehicle positioning information and user personalized information respectively to obtain corresponding multiple digital information. A feature extraction unit is used to extract features from the plurality of digital information to obtain corresponding feature information. Specifically, the feature extraction unit is used to perform equal-group filtering on the plurality of digital information to obtain corresponding multiple information features, and to encapsulate the multiple information features to obtain feature information. Each information feature is a 1-row N-column digital matrix, and the feature information is an M-column M-row square digital matrix; N>0, M≥N. The topic generation unit is used to input the feature information into a pre-trained deep learning model for processing, and generate corresponding interface topics; and The theme sending unit is used to send the interface theme to the vehicle terminal for generating the in-vehicle information system interface theme, and to receive response information from the vehicle terminal; when the response information indicates that the user confirms the application of the interface theme, the interface theme is recorded as positive feedback information of the user's preference and added to the set of positive feedback information for storage; when the response information indicates that the user confirms a request to obtain a new interface theme, the interface theme is recorded as negative feedback information of the user's preference and added to the set of negative feedback information for storage.

7. The system of claim 6, wherein, The information acquisition unit is further configured to receive user input information sent by the user device while logged into the user account; wherein the user input information is text information and / or image information; The preprocessing unit is specifically used for: When the information acquisition unit does not receive the user input information, it preprocesses the interface design condition information, the current vehicle location information and the user personalized information to obtain the corresponding digital information. When the information acquisition unit receives the user input information, it preprocesses the interface design condition information, current vehicle location information, user personalization information, and user input information to obtain corresponding digital information.

8. A computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the steps of the interface theme generation method according to any one of claims 1 to 5.

Images