AI-based business card style one-key replacement method and apparatus, and electronic device

Abstract

The embodiment of the invention provides an AI-based business card style one-key replacement method and device and electronic equipment, and the method comprises the steps: determining the current style of a current business card and the information of a current user through receiving the one-key business card style replacement operation triggered by a user for the current business card; matching a plurality of alternative styles in a predetermined style library based on the information of the current user; taking differences between the characteristic values of the alternative styles and the characteristic value of the current style as style deviations; inputting the style deviation and the current business card into a generative large model to obtain business cards of one or more recommended styles; and displaying the business cards of the plurality of recommended styles on a style change recommendation interface. Through the scheme, the individuation degree of the business card can be remarkably improved, and the generation efficiency is high.

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and in particular, to a method, device and electronic device for one-key changing business card styles based on AI. Background Art

[0002] The replacement of business card styles is usually carried out in the following way: obtaining the personal information of the user, and generating a QR code image according to the personal information; screening at least one candidate template from a preset template set for the user to select according to the age, gender and / or position in the personal information; obtaining a selection instruction, and determining the candidate template corresponding to the selection instruction as a personalized template; generating a personalized business card according to the QR code image and the personalized template.

[0003] However, the personalization of this method is limited by the richness of templates. Generally speaking, the number of templates is limited, and the probability of using the same template is relatively high, and there will also be a situation of similarity when using the same template. Summary of the Invention

[0004] In view of this, the purpose of the present invention is to provide a method, device and electronic device for one-key changing business card styles based on AI.

[0005] In order to achieve the above purpose, the technical solutions adopted in the embodiments of the present invention are as follows:

[0006] In a first aspect, the present invention provides a method for one-key changing business card styles based on AI, including: receiving an operation of one-key changing business card styles triggered by a user for the current business card, and determining the current style of the current business card and the information of the current user; matching a plurality of alternative styles in a pre-determined style library based on the information of the current user; taking the difference between the feature values of the plurality of alternative styles and the feature values of the current style as a style deviation; inputting the style deviation and the current business card into a generative large model to obtain one or more business cards of recommended styles; and displaying the business cards of the plurality of recommended styles on a style replacement recommendation interface.

[0007] In a second aspect, the present invention provides an AI-based device for one-key changing business card styles, including: a receiving module, configured to receive an operation of one-key changing business card styles triggered by a user for the current business card, and determine the current style of the current business card and the information of the current user; a matching module, configured to match multiple alternative styles in a pre-determined style library based on the information of the current user; a determining module, configured to use the difference between the feature values of the multiple alternative styles and the feature values of the current style as the style deviation; a generating module, configured to input the style deviation and the current business card into a generative large model to obtain one or more business cards with recommended styles; and a recommending module, configured to display the business cards with multiple recommended styles on a style change recommendation interface.

[0008] In a third aspect, the present invention provides an electronic device, including a processor and a memory, where the memory stores computer-executable instructions that can be executed by the processor, and the processor executes the computer-executable instructions to implement the method according to any one of the foregoing embodiments.

[0009] The method, device, and electronic device for one-key changing business card styles based on AI provided by the embodiments of the present invention determine the current style of the current business card and the information of the current user by receiving an operation of one-key changing business card styles triggered by a user for the current business card; match multiple alternative styles in a pre-determined style library based on the information of the current user; determine the style deviation based on the multiple alternative styles and the current style; input the style deviation and the current business card into a generative large model to obtain one or more business cards with recommended styles; and display the business cards with multiple recommended styles on a style change recommendation interface. Through the above solutions, the personalization degree of business cards can be significantly improved, and the generation efficiency is high. The styles of the generated business cards not only include the styles in the templates, but also generate richer styles by leveraging the capabilities of the generative large model, thereby reducing the probability of repeated business card styles and enhancing the differentiation.

[0010] To make the above objects, features, and advantages of the present invention more obvious and understandable, the following specifically enumerates preferred embodiments and, in conjunction with the accompanying drawings, provides a detailed description as follows. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] To more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for the embodiments. It should be understood that the following drawings only show some embodiments of the present invention, and therefore should not be regarded as limiting the scope. For those of ordinary skill in the art, other relevant drawings can be obtained based on these drawings without creative efforts.

[0012] Figure 1 Shows a schematic structural diagram of the electronic device provided by the embodiments of the present invention;

[0013] Figure 2 It is a schematic flowchart of a method for one - key changing business card styles based on AI provided by an embodiment of this application;

[0014] Figure 3 It is a functional module diagram of a device for one - key changing business card styles based on AI provided by an embodiment of the present invention. Detailed implementation manners

[0015] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Usually, the components of the embodiments of the present invention described and illustrated herein can be arranged and designed in various different configurations.

[0016] Therefore, the following detailed description of the embodiments of the present invention provided in the drawings is not intended to limit the scope of the claimed present invention, but merely represents selected embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative efforts belong to the scope of protection of the present invention.

[0017] It should be noted that relational terms such as "first" and "second" are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variant thereof are intended to cover non - exclusive inclusion, so that a process, method, article or device including a series of elements not only includes those elements, but also includes other elements not expressly listed, or also includes elements inherent to such process, method, article or device. Without further limitation, an element defined by the statement "including a..." does not exclude the existence of additional identical elements in the process, method, article or device including the said element.

[0018] Please refer to Figure 1 , which is a block diagram of an electronic device. The electronic device includes a memory, a processor, and a communication module. Each of the memory, the processor, and the communication module is electrically connected directly or indirectly to each other to achieve data transmission or interaction. For example, these elements can be electrically connected to each other through one or more communication buses or signal lines.

[0019] The electronic device 100 includes a processor (CPU) 120, which can perform various appropriate actions and processes according to programs stored in the memory 110. The memory 110 may include a read-only memory (ROM) or a random access memory (RAM). In the RAM, various programs and data required for the operation of the electronic device 100 are also stored. The CPU, ROM, and RAM are connected to each other via a bus. An input / output (I / O) interface is also connected to the bus.

[0020] The following components are connected to the I / O interface: an input part including a keyboard, a mouse, etc.; an output part including a cathode ray tube (CRT), a liquid crystal display (LCD), etc. and a speaker, etc.; a storage part including a hard disk, etc.; and a communication module 130 including a network interface card such as a LAN card, a modem, etc. The communication module 130 performs communication processing via a network such as the Internet. A drive is also connected to the I / O interface as needed. A removable medium, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive as needed so that a computer program read from it can be installed into the storage part as needed.

[0021] Specifically, according to an embodiment of the present disclosure, the processes described with reference to the following flowcharts can be implemented as computer software programs. For example, an embodiment of the present disclosure includes a computer program product including a computer-readable medium carrying instructions. In such an embodiment, the instructions can be downloaded and installed from a network through the communication part, and / or installed from a removable medium. When the instructions are executed by the CPU, the various method steps described in the present invention are executed.

[0022] In some embodiments, the memory 110 is used to store programs or data. The memory may be, but is not limited to, a random access memory (RAM), a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), etc.

[0023] The processor 120 is used to read / write data or programs stored in the memory and execute corresponding functions.

[0024] The communication module 130 is used to establish a communication connection between the electronic device and other communication terminals via a network and is used to transmit and receive data via the network.

[0025] It should be understood that Figure 1 the structure shown is only a schematic diagram of the structure of the electronic device, and the electronic device may also include more or fewer components than those shown in Figure 1 it, or have a configuration different from that shown in Figure 1 it. Figure 1 Each component shown in it can be implemented by hardware, software or a combination thereof.

[0026] Figure 2 FIG. is a schematic flowchart of a method for one - key changing business card styles based on AI provided by an embodiment of the present application. This method can be implemented based on the electronic device shown in Figure 1 it, as shown in Figure 2 it, this method may include:

[0027] S210, receiving an operation of one - key changing the business card style triggered by the user for the current business card, and determining the current style of the current business card and the information of the current user.

[0028] Among them, the style of the business card may include font, color matching, layout, etc. The style of this business card may refer to the visual presentation method of the business card, including font size and type, color combination, layout, etc. These styles can directly affect the aesthetics and practicality of the business card.

[0029] The information of the user may include user personal information, user behavior information, and scene information where the user is located, etc.

[0030] User personal information may refer to data directly related to the user, such as name, position, company name, etc. These information are usually used for displaying the core content of the business card, and the user's preference for styles can also be analyzed through this information.

[0031] User behavior information may include browsing behavior, preferences, and other information. For example, it may include the activity records of the user in the system, such as browsing history, click preferences, etc. These data can help the system better understand the user's needs, so as to provide more suitable services.

[0032] The scene information where the user is located may refer to the environment or state where the user is currently located, such as geographical location (whether in a meeting) or information of the system interface. The user may hold multiple roles part - time and assume different roles in different systems, and the current role of the user can be determined according to the system interface where the user is located. These information help to dynamically adjust the style of the business card to adapt to different situations.

[0033] In some embodiments, when the user triggers the "one - click style change" operation (such as clicking an interactive button or using a gesture operation), the position and hierarchical relationship (title / body / contact information) of the business card text area can be extracted through the OCR engine, and the layout feature vectors (such as information density, alignment) can be calculated. Use a CNN model (such as ResNet - 50) to analyze the font type (through a text recognition model), color scheme (HSV color space histogram), and background texture (frequency domain analysis) of the current business card. Combine an NLP model (such as BERT) to perform entity recognition on the business card content, and label industry attributes (such as "finance / technology") and position levels (by matching job keywords with the enterprise VI specification library).

[0034] Structured data such as name, position, company, and industry can also be extracted from the user database.

[0035] The editing frequency of business cards in the past 30 days (such as the number of color scheme modifications / layout switching rate) can also be counted to construct a behavioral time - series sequence.

[0036] The current scenario of the user (such as "mobile office / business meeting") can also be inferred through device sensors (GPS positioning, gyroscope tilt angle) and network status (Wi - Fi SSID).

[0037] The recent business dynamics of the user (such as the industry of newly signed customers) can also be obtained by real - time calling the enterprise API and injected as temporary scenario features.

[0038] In addition, the current style can also be pre - configured information. The information of the current user can also be obtained based on the user's account information or the human resources system.

[0039] For example, the user account information is securely synchronized with the enterprise unified authentication center through the OAuth2.0 protocol, and incremental data updates are performed every hour. The data docking of the human resources system uses the SOAP interface of the enterprise service bus (ESB). When parsing the XML - formatted employee profile data through XPath, sensitive field desensitization processing is automatically performed. The built - in data pre - processing module in the system performs standardized mapping on heterogeneous source data, including job title normalization (such as unifying "VP" to "Vice President") and industry classification code conversion (referring to the GB / T 4754 - 2017 standard). When detecting multi - source data conflicts, the master data of the human resources system is preferred, and at the same time, a log audit event is triggered. The user feature library is implemented by a Redis cluster to achieve millisecond - level real - time query, and an LRU cache eviction mechanism is established to ensure the fast response of frequently accessed data.

[0040] S220, match multiple alternative styles in a pre - determined style library based on the information of the current user.

[0041] Among them, the corresponding relationships between multiple sample styles and user information can be determined in advance; each sample style and the corresponding user information are respectively input into a large language model to obtain the vector representations of each sample style and the vector representations of each user information; a style library is determined based on the vector representations of multiple sample styles, the vector representations of each user information, and the corresponding relationships between the sample styles and the user information.

[0042] The information of the current user can be input into a large language model to obtain the vector representation of the information of the current user; based on the vector representation of the information of the current user, a match is made in the style library to determine the sample styles corresponding to the multiple user information that are the closest as multiple alternative styles.

[0043] In some embodiments, each sample style (such as "minimalist flat style") can be multi-modally encoded. The visual encoder can extract visual feature vectors from the design samples (such as UI interfaces), including key visual elements such as layout, color scheme, and font style. The output is a 512-dimensional dense vector. For example, the embedding vectors of layout, color, and font (dimension 512) can be extracted through a ViT model, the classification layer is removed, and the [CLS] token output by the last layer of the Transformer is extracted as the global visual embedding vector. The ViT (Vision Transformer) model can divide the input image into fixed-size image patches (such as 16x16 pixels), convert them into embedding vectors through linear projection, and add position encoding to preserve the space. Global dependencies between different image patches can also be captured through multiple layers of Transformer encoders, such as the coordination between color scheme and layout. The pre-trained ViT model (such as CLIP-ViT) can also align the visual and text semantic spaces through contrastive learning to enhance the semantic expression ability of visual features.

[0044] The information text encoder encodes the design description text (such as "suitable for the financial industry") into a semantic vector, capturing the style description and industry requirement keywords in the text. The design description text (such as "suitable for the financial industry") can be encoded through a RoBERTa model, and the [CLS] token output by the last layer of the Transformer is taken as the global text representation. The text encoder encodes the design description text (such as "suitable for the financial industry") into a semantic vector, capturing the style description and industry requirement keywords in the text. The style keywords (such as "minimalist") and industry attributes (such as "finance") in the text are associated with visual features through an attention mechanism.

[0045] The fusion matrix is responsible for mapping visual and text embedding vectors into a unified semantic space to enhance cross-modal feature complementarity. The distributions of visual and text vectors are adjusted through a learnable weight matrix (such as MLP or cross-attention). It is possible to combine early fusion (concatenating visual and text vectors) and late fusion (weighted summation), and optimize the fusion weights through backpropagation. Fusion strategy: . Among them, can be the fusion style vector, is the learnable fusion matrix, which is optimized through backpropagation to learn the weight assignment of visual and text features. Assuming the fusion style vector is 256-dimensional, then has a dimension of 1024×256. By minimizing the loss function of downstream tasks (such as style classification, generation tasks), the fused can retain both visual and text semantic information at the same time.

[0046] The user profile vector is generated by aggregating the user's multi-dimensional information (such as personal information, behavior sequence, scene context) into a 256-dimensional low-dimensional representation for personalized recommendation. The GraphSAGE model can be used to aggregate the user's multi-dimensional information (personal information nodes, behavior sequence edges, scene context nodes) to generate a low-dimensional dense vector (dimension 256). GraphSAGE is an inductive learning model based on graph neural networks. It generates node embeddings by sampling neighbor nodes and aggregating their features (such as mean, LSTM or attention), and then models the user nodes (personal information), behavior edges (click sequence), and scene nodes (usage environment) as a heterogeneous graph, capturing complex interactions through hierarchical aggregation.

[0047] A heterogeneous graph can be constructed with the user as the central node, connecting the behavior logs (edges) and scene context (nodes).

[0048] Multi-hop neighbors (such as behavior sequences within 2 hops) can be randomly sampled to balance computational efficiency and information integrity.

[0049] The neighbor features can be fused using mean aggregation or attention mechanism, and the model can be optimized through link prediction or classification tasks.

[0050] S230, taking the difference between the feature values of multiple alternative styles and the feature values of the current style as the style deviation.

[0051] The current style can be input into a large language model to obtain the vector representation of the current style; based on the vector representation of the current style and the vector representations of multiple alternative styles, the style deviation is determined. Among them, the feature value of the style can be the vector representation of the style, or other values that can reflect the style features or the differences between styles.

[0052] The sub - deviation between the vector representation of the current style and the vector representations of each alternative style can be determined based on the following formula:

[0053] ;

[0054] where U is the vector representation of the current style;

[0055] Si is the vector representation of the i - th alternative style;

[0056] ; , and the covariance matrix Σ is estimated by sample covariance;

[0057] used to constrain the matching of discrete features (such as font type);

[0058] the denominator's prevents the similarity from being dominated by extreme values.

[0059] Among them, the style deviation is the difference between the mean of the eigenvalues of multiple alternative styles and the eigenvalue of the current style; or, the style deviation includes the differences between the eigenvalues of multiple alternative styles and the eigenvalue of the current style respectively, that is, the style deviation can be a set of multiple differences.

[0060] S240, input the style deviation and the current business card into the generative large - model to obtain one or more business cards of recommended styles.

[0061] A prompt template is predetermined. The prompt template includes the first content to be input and the second content to be input. The first content to be input is used to input the vector representation of the current style, and the second content to be input is used to input the style deviation.

[0062] The prompt template is as follows: "You are a senior graphic designer and need to generate a business card solution based on the following constraints:

[0063] Must follow the current style features: [CLS] current vector representation [SEP];

[0064] Need to balance the following deviation: [CLS] deviation vector description [SEP];

[0065] The output needs to meet:

[0066] Brand specification: Corporate VI color swatch ΔE < 5, font copyright compliance;

[0067] User preference: Elements frequently used in the past 7 days (such as dark background accounting for 60%);

[0068] Scene adaptation: The current scene is [scene type];

[0069] [Generation requirements];

[0070] Provide 3 design options, with focuses on respectively:

[0071] Option 1: Extreme professionalism (suitable for the finance / legal industries);

[0072] Option 2: Innovative visual expression (suitable for the technology / creative industries);

[0073] Option 3: High information density (suitable for the sales / consulting industries).

[0074] For S250, display business cards of multiple recommended styles on the style replacement recommendation interface.

[0075] After the recommendation interface is displayed, it can respond to the style selection instruction triggered by the user on the recommendation interface and perform dynamic rendering and multi-terminal synchronization of the business card style. Specifically in implementation, the rendering engine can use WebGL 2.0 to achieve GPU-accelerated rendering, and perform anti-aliasing processing based on the SDF signature on vector elements (such as corporate logos). When the user clicks on a certain recommended style, the system calls the image processing module compiled by WASM to perform real-time style transfer, and uses the CycleGAN model to adapt the original business card visual elements to the new style while retaining the readability of the text. In terms of the synchronization mechanism, a duplex communication channel is established through WebSocket, and the Operational Transformation algorithm is used to solve multi-device editing conflicts. The style change records are persistently stored in the blockchain node in the JSON Patch format to ensure that the operations are traceable.

[0076] It is also possible to build a closed-loop optimization of the style library driven by user feedback. Embed an implicit feedback collection module in the recommendation interface: record the dwell time of the user on each recommended style (accurate to milliseconds), the scaling operation trajectory (fitting the gesture path through a Bezier curve), and the favorite folder addition behavior. Explicit feedback collects design satisfaction through a five-point Likert scale, and calculates the visual focus heat map in combination with eye movement tracking data (pupil coordinates collected by the front camera). After the feedback data is feature-extracted, it is input into a reinforcement learning model (PPO algorithm) to dynamically adjust the weight parameters in the style matching strategy. Perform incremental updates of the style library at a fixed time every week: eliminate styles with zero exposure in 30 days, perform data enhancement on styles with high conversion rates (including 12 image transformations such as hue offset ±15°, kerning fine-tuning ±2%, etc.), and new styles need to pass the aesthetic evaluation model (based on the NIMA architecture) with a score exceeding 8.5 points before being stored in the library.

[0077] Cross-media style compatibility can also be ensured. When it is detected that the user enables the AR business card function, the 3D style adaptation pipeline is automatically activated: a 3D reconstruction model of the business card is generated through NeRF technology, and the material properties are recalculated using a physically based rendering (PBR) workflow. For the printed matter scenario, the color management module is called to perform CMYK color separation calibration, and G7-certified color matching is implemented based on the ICC profile. A 1mm bleed and a 300dpi print preprocessing file are generated synchronously. The responsive layout engine monitors the DPI parameters of the display medium in real time. When switching to a small-screen device such as a smartwatch, it automatically triggers the reconstruction of the information hierarchy - the core information (name / position) is identified through a CRF conditional random field model, and the secondary information (company introduction QR code) is progressively folded.

[0078] In some embodiments, a style matching matrix can also be constructed based on multi-dimensional features to generate a personalized recommendation candidate set. The layout feature vector (0.78, 0.12, 0.65), color histogram (#3F88C5 main color ratio 32%), texture complexity coefficient (DCT frequency domain energy 0.45) and user feature vector are tensor-concatenated through a feature fusion layer and input into a deep cross network (DCN) to calculate the style adaptation degree score. The responsive grid parameters of an enterprise-level design system (such as Ant Design) are used, combined with the spacing ratio specification of Material Design, to dynamically generate an accessible color scheme that meets the WCAG 2.1 AA standard. For users in the financial industry, the visual weight of security identification elements (such as shield icons) is automatically enhanced, while for technology users, the placeholder area of the dynamic data visualization module is increased.

[0079] In some embodiments, a real-time feedback closed-loop can also be established to optimize the recommendation strategy. When the user selects a new style, implicit feedback data such as dwell time (≥5s triggers a valid event) and edit rollback rate (number of undo operations) are collected through data points. A user behavior event time window is constructed through the Flink stream processing engine, and the user preference model is updated every 5 minutes. When designing the multi-objective optimization function, the compliance with the enterprise VI specification (weight 0.6) and the personalized innovation index (weight 0.4) are balanced, and the NSGA-II algorithm is used to solve the Pareto optimal solution set. For high-frequency modification users (≥3 operations per day), the reinforcement learning mechanism is started to dynamically adjust the exploration / exploitation ratio, and potential preference combinations are mined from the style library through the Q-learning algorithm.

[0080] In some embodiments, cross-terminal style synchronization and version control can also be implemented. After the mobile device completes the style change, it synchronizes to the PC-side enterprise email signature via a WebSocket long connection, and calls the Jira API to update the user identity in the collaboration tool. The Git version management scheme is adopted to record the style modification history, supporting differential comparison and rollback operations based on timestamps (accurate to milliseconds) or semantic tags (such as "business official version_v2.1.3"). When deeply integrated with WeCom, a style change description card is automatically generated, rendering the modification details (adjusting the kerning from 1.5 to 1.8, hue shift +15°) through Markdown syntax, and @-mentioning relevant approvers for compliance confirmation.

[0081] To execute the corresponding steps in the above embodiments and each possible manner, the following presents an implementation of a device for one-key changing business card styles based on AI. Optionally, the device for one-key changing business card styles based on AI can adopt the device structure of the electronic device shown above. Further, please refer to Figure 1 shown in Figure 3 , Figure 3 which is a functional module diagram of a device for one-key changing business card styles based on AI provided by an embodiment of the present invention. It should be noted that the basic principle and the technical effects generated by the device for one-key changing business card styles based on AI provided in this embodiment are the same as those in the above embodiments. For a brief description, for parts not mentioned in this embodiment, reference can be made to the corresponding content in the above embodiments. The device for one-key changing business card styles based on AI includes:

[0082] A receiving module 301, configured to receive an operation of one-key changing the business card style triggered by a user for the current business card, and determine the current style of the current business card and the information of the current user;

[0083] A matching module 302, configured to match multiple alternative styles in a pre-determined style library based on the information of the current user;

[0084] A determining module 303, configured to use the difference between the feature values of the multiple alternative styles and the feature values of the current style as the style deviation;

[0085] A generating module 304, configured to input the style deviation and the current business card into a generative large model to obtain one or more business cards with recommended styles;

[0086] A recommending module 305, configured to display the one or more business cards with recommended styles on a style change recommendation interface.

[0087] In some embodiments, the style of the business card includes font, color matching, and layout; the user information includes user personal information, user behavior information, and the scenario information where the user is located.

[0088] In some embodiments, the style deviation is the difference between the average of the feature values ​​of the multiple candidate styles and the feature value of the current style; or, the style deviation includes the difference between the feature values ​​of the multiple candidate styles and the feature value of the current style.

[0089] In some embodiments, the device also includes an establishment module, which is used to: predetermine the correspondence between multiple sample styles and user information; input each sample style and the corresponding user information into a large language model to obtain a vector representation of each sample style and a vector representation of each user information; wherein the characteristic value of the style is the vector representation of the style; determine the style library based on the vector representation of multiple sample styles, the vector representation of each user information and the correspondence between the sample style and the user information.

[0090] In some embodiments, the matching module 302 is specifically used to: input the current user's information into the large language model to obtain a vector representation of the current user's information; match the vector representation of the current user's information in the style library to determine the sample styles corresponding to the closest multiple user information as multiple alternative styles.

[0091] In some embodiments, the determination module 303 is specifically used to: input the current style into the large language model to obtain a vector representation of the current style; and determine the style deviation based on the vector representation of the current style and the vector representations of multiple candidate styles.

[0092] In some embodiments, a prompt word template is predetermined, and the prompt word template includes a first content to be input and a second content to be input, the first content to be input is used to input a vector representation of the current style, and the second content to be input is used to input a style deviation.

[0093] Optionally, the above modules can be stored in the form of software or firmware. Figure 1 The memory shown in the figure may be solidified in the operating system (OS) of the AI-based one-key business card style change, and can be Figure 1 Meanwhile, the data and program codes required for executing the above modules can be stored in the memory.

[0094] In several embodiments provided in this application, it should be understood that the disclosed devices and methods can also be implemented in other ways. The device embodiments described above are merely illustrative. For example, the flowcharts and block diagrams in the accompanying drawings show the possible architectures, functions, and operations of devices, methods, and computer program products according to multiple embodiments of the present invention. In this regard, each block in the flowchart or block diagram can represent a module, a program segment, or a part of code, and the module, program segment, or part of code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order than that marked in the accompanying drawings. For example, two consecutive blocks can actually be executed substantially in parallel, and they can sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block in the block diagram and / or flowchart, as well as the combination of blocks in the block diagram and / or flowchart, can be implemented by a dedicated hardware-based system for performing the specified functions or actions, or can be implemented by a combination of dedicated hardware and computer instructions.

[0095] In addition, each functional module in various embodiments of the present invention can be integrated together to form an independent part, or each module can exist alone, or two or more modules can be integrated to form an independent part.

[0096] If the above-mentioned functions are implemented in the form of software functional modules and sold or used as an independent product, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or a part of this 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 for causing a computer device (which can be a personal computer, an electronic device, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of the present invention. The aforementioned storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memories (ROMs), random access memories (RAMs), magnetic disks, or optical discs that can store program codes.

[0097] The above are only the preferred embodiments of the present invention and are not used to limit the present invention. For those skilled in the art, the present invention can have various changes and modifications. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A method for one-key changing business card styles based on AI, characterized in that, Including: Receiving an operation by the user to trigger one - key replacement of the business card style for the current business card, and determining the current style of the current business card and the information of the current user; Based on the information of the current user, matching multiple alternative styles in a pre - determined style library; Taking the difference between the feature values of the multiple alternative styles and the feature values of the current style as the style deviation; Inputting the style deviation and the current business card into a generative large - model to obtain one or more business cards with recommended styles; Displaying the business cards with multiple recommended styles on the style replacement recommendation interface.

2. The method according to claim 1, characterized in that The style of the business card includes font, color matching, and layout; the user's information includes user personal information, user behavior information, and the scenario information where the user is located.

3. The method according to claim 2, wherein The style deviation is the difference between the mean of the feature values of the multiple alternative styles and the feature values of the current style; Or, the style deviation includes the differences between the feature values of the multiple alternative styles and the feature values of the current style respectively.

4. The method according to claim 1, wherein The method further includes: Pre - determining the correspondence between multiple sample styles and user information; Inputting each of the sample styles and the corresponding user information into a large - language model to obtain the vector representation of each sample style and the vector representation of each user information; wherein, the feature value of a style is the vector representation of the style; Determining the style library based on the vector representations of the multiple sample styles, the vector representations of each user information, and the correspondence between the sample styles and the user information.

5. The method according to claim 4, wherein Based on the information of the current user, matching multiple alternative styles in a pre - determined style library, including: Inputting the information of the current user into a large - language model to obtain the vector representation of the information of the current user; Based on the vector representation of the information of the current user, performing matching in the style library to determine the sample styles corresponding to the most similar multiple user information as multiple alternative styles.

6. The method according to claim 5, characterized in that The determining the style deviation based on the multiple alternative styles and the current style includes: Inputting the current style into a large - language model to obtain the vector representation of the current style; Based on the vector representation of the current style and the vector representations of the multiple alternative styles, determining the style deviation.

7. The method according to claim 6, characterized in that, Determining the sub - deviation between the vector representation of the current style and the vector representation of each alternative style based on the following formula: ； Wherein, U is the vector representation of the current style; Si is the vector representation of the i - th alternative style; ; , the covariance matrix Σ is estimated by sample covariance; For constraining the matching of discrete features; Of the denominator To prevent the similarity from being dominated by extreme values.

8. The method according to claim 4, wherein There is a pre - determined prompt - word template, which includes a first content to be input and a second content to be input. The first content to be input is used to input the vector representation of the current style, and the second content to be input is used to input the style deviation.

9. An AI-based device for one-key changing business card styles, characterized in that, Including: A receiving module, configured to receive an operation by the user to trigger one - key replacement of the business card style for the current business card, and determine the current style of the current business card and the information of the current user; A matching module, configured to match multiple alternative styles in a pre - determined style library based on the information of the current user; A determining module, configured to take the difference between the feature values of the multiple alternative styles and the feature values of the current style as the style deviation; A generation module, configured to input the style deviation and the current business card into a generative large model to obtain one or more business cards with recommended styles; A recommendation module, configured to display the business cards with multiple recommended styles on a style replacement recommendation interface.

10. An electronic device, characterized in that, It includes a processor and a memory, the memory stores computer executable instructions that can be executed by the processor, and the processor executes the computer executable instructions to implement the method according to any one of claims 1 to 7.

Images