Method and electronic device for changing business card style based on information synchronization

Abstract

The present invention provides a method and electronic device for changing business card styles based on information synchronization, relating to the field of computer technology. The method comprises: receiving an update message for the current user's basic information; determining a degree score using a pre-trained degree model; inputting the current user's current style definition, modified first basic information, unmodified first basic information, degree score, and degree score definition into a generative model to obtain multiple alternative styles; and displaying the multiple alternative styles so that the current user can select a target style from the alternative styles. The degree model maps the basic information update to a style difference score, driving the generative model to output the alternative style, and completing the update upon user selection.

Description

Technical Field

[0001] The present disclosure relates to the field of computer technology, and more particularly, to a method and electronic device for changing a business card style based on information synchronization. Background Art

[0002] Changing the business card style is usually done in the following way: obtaining the user's personal information and generating a QR code image based on the personal information; screening at least one candidate template from the preset template set for the user to select based on 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; and generating a personalized business card based on 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, the probability of using the same template is relatively high, and the use of the same template may also result in similar situations. Summary of the Invention

[0004] In view of this,

[0005] In a first aspect, the present invention provides a method for changing a business card style based on information synchronization, comprising:

[0006] Receiving an update message of the basic information of the current user, the update message including the modified first basic information and the first basic information before the modification;

[0007] Based on the modified first basic information and the first basic information before modification, a degree score is determined using a pre-trained degree model. The degree model is used to predict the degree score corresponding to the current update message based on historical update messages, the degree scores corresponding to each historical update message, and the updated style. The degree score is used to indicate the difference between styles. The style of a business card includes attributes and patterns. The degree score includes an attribute difference score and a pattern difference score. The attribute difference score is used to quantify the impact of changes in text fields in the basic information on style attributes. The pattern difference score quantifies the impact of changes in visual fields in the basic information on the style pattern.

[0008] Inputting the current style definition of the current user, the modified first basic information, the first basic information before modification, the degree score, and the definition of the degree score into a generative large model to obtain a plurality of candidate styles;

[0009] A plurality of candidate styles are displayed so that the current user can select a target style from the candidate styles.

[0010] In an optional embodiment, the attributes include fonts and layouts; the user's basic information includes user personal information, user behavior information, and user scenario information, the user's personal information includes position information, the first basic information before modification includes the position information before modification, and the first basic information after modification includes the position information after modification.

[0011] In an optional embodiment, the final degree score takes the maximum value of the attribute difference score and the pattern difference score, and both scores are constrained by a dynamic threshold of the historical pattern sequence.

[0012] In an optional embodiment, determining the degree score by a pre-trained degree model based on the modified first basic information and the first basic information before the modification further includes:

[0013] Determine the historical target style sequence;

[0014] Based on the historical target style sequence, the modified first basic information, and the first basic information before modification, a degree score is determined by a pre-trained degree model.

[0015] In an optional embodiment, the degree model is trained by the following steps:

[0016] Obtain historical data sets: including user basic information update messages, corresponding historical style change sequences, and updated target styles;

[0017] Extract style features: For each style in the historical style sequence, extract attribute features and pattern features;

[0018] Construct training samples: Take the pre-modification value of each information update, the post-modification value of the information update, the corresponding style sequence features, and the manual annotation degree score between the new and old styles as samples;

[0019] Training a dual-path model: the first path learns attribute difference scores; the second path learns pattern difference scores.

[0020] In an optional embodiment, the dynamic threshold constraint is implemented in the following manner:

[0021] Calculate the average attribute difference and average pattern difference of consecutive styles in the historical style sequence;

[0022] If the current attribute difference score is greater than the historical average attribute difference × 1.5, it will be suppressed to 60% of the original value;

[0023] If the current pattern difference score is greater than the historical average pattern difference × 1.8, it will be suppressed to 40% of the original value.

[0024] In an optional embodiment, the input of the generative large model further includes:

[0025] Attribute Difference Score Definition: Describes the mapping relationship between the score and the font and layout adjustment range;

[0026] Definition of pattern difference score: describes the mapping relationship between the score and the degree of color and layout adjustment;

[0027] Among them, the large model generates adjustment plans for the attribute dimension and pattern dimension based on the two scores, and then combines them into a complete alternative style.

[0028] In an optional embodiment, the weight distribution of the attribute difference score and the pattern difference score is dynamically adjusted according to the user scenario:

[0029] When basic information updates involve business and social scenarios, the weight of the pattern difference score is increased;

[0030] When the update involves recruitment and job-seeking scenarios, the weight of attribute difference scores is increased.

[0031] In an optional implementation, when multiple basic information fields are updated simultaneously:

[0032] Calculate attribute difference scores and pattern difference scores independently for each field;

[0033] When a scoring conflict is detected, the arbitration strategy is activated;

[0034] Arbitration strategies include:

[0035] Prioritize responding to changes with fields that have higher weights, or take the geometric mean of conflicting field scores as the final value.

[0036] In a second aspect, the present invention provides an electronic device, comprising:

[0037] one or more processors;

[0038] a memory for storing one or more programs,

[0039] When the one or more programs are executed by the one or more processors, the one or more processors execute the method as described in any one of the aforementioned embodiments.

[0040] The present invention provides a method and electronic device for changing business card styles based on information synchronization. The method comprises receiving an update message for the current user's basic information, the update message including modified first basic information and pre-modified first basic information; determining a degree score based on the modified first basic information and pre-modified first basic information using a pre-trained degree model, the degree score including an attribute difference score and a pattern difference score. The attribute difference score is used to quantify the impact of changes in text fields in the basic information on style attributes, and the pattern difference score is used to quantify the impact of changes in visual fields in the basic information on style patterns; inputting the current user's current style definition, the modified first basic information, the pre-modified first basic information, the degree score, and the definition of the degree score into a generative model to obtain multiple alternative styles; and displaying the multiple alternative styles so that the current user can select a target style from the alternative styles. The degree model maps the basic information update to a style difference score, driving the generative model to output an alternative style, and completing the update upon user selection. An automated closed loop from information change to style update has been achieved. While traditional solutions require manual style adjustments, the degree model automatically responds to information changes. The degree score quantifies the intensity of the change requirement to avoid over-design or insufficient adjustment, reducing user cognitive load. Users only need to choose from a limited number of alternatives generated by AI, reducing decision-making time. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] Figure 1 A flowchart of a method for changing a business card style based on information synchronization provided in an embodiment of the present application;

[0042] Figure 2 A schematic diagram of the structure of a device for changing business card styles based on information synchronization provided in an embodiment of the present application;

[0043] Figure 3 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0044] Hereinafter, embodiments of the present disclosure will be described with reference to the accompanying drawings. However, it should be understood that these descriptions are merely illustrative and are not intended to limit the scope of the present disclosure. In addition, in the following description, descriptions of well-known structures and technologies are omitted to avoid unnecessary confusion of the concepts of the present disclosure.

[0045] The terms used herein are intended only to describe specific embodiments and are not intended to limit the present disclosure. The terms "a," "an," and "the" as used herein also include "plurality" and "multiples," unless the context clearly indicates otherwise. Furthermore, the terms "comprise," "include," and "includes" as used herein indicate the presence of the described features, steps, operations, and / or components, but do not preclude the presence or addition of one or more other features, steps, operations, or components.

[0046] All terms used herein (including technical and scientific terms) have the meanings commonly understood by those skilled in the art unless otherwise defined. It should be noted that the terms used herein should be interpreted as having a meaning consistent with the context of this specification and should not be interpreted in an idealized or overly rigid manner.

[0047] Figure 1 This is a flow chart of a method for changing the business card style based on information synchronization provided by an embodiment of the present application. Figure 1 As shown, the method includes:

[0048] S110: Receive a current update message of the basic information of the current user, wherein the current update message includes the modified first basic information and the first basic information before the modification.

[0049] The style of a business card includes attributes and patterns. Attributes include fonts and layouts. The basic information of a user includes personal information, behavior information, and the scenario in which the user is located. Personal information of the user includes position information. Updated information includes changes in position information.

[0050] Basic information can also refer to various basic information related to the user, including personal information, behavioral habits, and current environment or scene information.

[0051] Business card style refers to the design form of an electronic or physical business card, including visual elements such as fonts and layout, which is used to display the user's identity or related information.

[0052] Position information is part of a user's personal information and is used to describe the user's role or title in an organization or scenario, such as "manager" or "engineer."

[0053] Update messages refer to notifications received by the system about changes in user information, including specific content before and after the modification for comparison and record keeping.

[0054] User behavior information refers to the user's operation records or habit data on a certain system or platform, such as click preferences, browsing history, etc., which is used to analyze user behavior patterns.

[0055] S120: Determine a degree score based on the modified first basic information and the first basic information before and after modification using a pre-trained degree model. The degree model is used to predict the degree score corresponding to the current update message based on historical update messages, the degree scores corresponding to each historical update message, and the updated style. The degree score indicates the difference between styles. The style of a business card includes attributes and patterns. The degree score includes an attribute difference score and a pattern difference score. The attribute difference score quantifies the impact of changes in text fields in the basic information on style attributes, and the pattern difference score quantifies the impact of changes in visual fields in the basic information on the style pattern.

[0056] The final degree score takes the maximum value of the attribute difference score and the pattern difference score, and both scores are constrained by the dynamic threshold of the historical style sequence.

[0057] In some embodiments, the input of the generative large model also includes: attribute difference score definition: describing the mapping relationship between the score and the font / layout adjustment range; pattern difference score definition: describing the mapping relationship between the score and the color / layout adjustment range; wherein, the large model generates adjustment plans for the attribute dimension and the pattern dimension based on the two scores, and then combines them into a complete alternative style.

[0058] The degree model is trained through the following steps: obtaining a historical dataset: including user basic information update messages and the updated target style; extracting style features, which may include attribute features and pattern features; using the before and after values ​​of each information update and the manually annotated degree scores between the new and old styles as samples; training a dual-path model: the first path learns the attribute difference score; the second path learns the pattern difference score.

[0059] The historical data set may include historical update messages, updated styles, and manual annotation scores corresponding to the update messages. The historical data set may be obtained through manual annotation.

[0060] In some embodiments, the weight distribution of attribute difference scores and pattern difference scores is dynamically adjusted according to the user scenario: when the basic information update involves a business and social scenario, the weight of the pattern difference score is increased; when the update involves a recruitment and job-seeking scenario, the weight of the attribute difference score is increased.

[0061] In some embodiments, when multiple basic information fields are updated simultaneously: the attribute / pattern difference score is calculated independently for each field; when a score conflict is detected, an arbitration strategy is initiated; the arbitration strategy includes: giving priority to responding to changes in fields with higher weights, or taking the geometric mean of the conflicting field scores as the final value.

[0062] In some embodiments, the core goal of the degree model can be to receive update messages of user basic information (value before modification, value after modification) and output a numerical "degree score" to quantify the importance of this information change to the overall visual effect and core information conveyed by the business card.

[0063] Scoring purpose: To guide the generative large model (LLM) on how much visual adjustment should be made when generating new styles (fine tuning, moderate tuning, major reconstruction).

[0064] Specific scheme of degree model:

[0065] Model input:

[0066] change_type: The type of the information field being changed (string enumeration). For example: "name", "title", "company", "company_logo", "phone", "email", "address", "website", "social_media", "tagline", "headshot", etc.

[0067] change_magnitude: The magnitude of the change, which can be a numerical value or a categorical value. Calculation method:

[0068] Text fields: Calculate the semantic similarity (using models such as lightweight Sentence-BERT) or edit distance (Levenshtein distance) between the text before and after modification. The lower the similarity (or the larger the edit distance), the greater the magnitude.

[0069] Image fields (such as logos / headshots): Calculate the perceptual hash (pHash) difference or structural similarity (SSIM) index of the image before and after modification. The greater the difference, the greater the magnitude.

[0070] Enumeration or classification field: directly determine whether it has changed.

[0071] Numeric fields: Calculate absolute differences or relative rates of change.

[0072] Output: can be normalized to the interval [0, 1], or discretized into {tiny, small, medium, large, huge}.

[0073] field_importance: The default basic importance weight of the information field (a numeric value in the range [0, 10]). For example: Company Logo: 10; Company: 9; Name: 8; Position: 7; Photo: 6; Phone / Email: 5; Website / Social Media: 4; Address: 3; Slogan: 2.

[0074] user_context (optional, to improve personalization): user historical behavior or attributes.

[0075] user_industry: The user's industry (some industries are more sensitive to job titles / company names).

[0076] user_role: User role (sales vs. engineers may have different priorities for information display).

[0077] avg_style_change_frequency: How often on average did the user actively change their style in the past (reflecting their sensitivity to style updates).

[0078] last_change_impact: The adjustment range of the style finally selected by the user after the user last modified the same type of information (if recorded).

[0079] Model core and calculation logic (Core Logic):

[0080] Core idea: Degree score = f(field type basic importance, change magnitude, [user context]);

[0081] Solution 1: This can be achieved using a rule-based scoring engine.

[0082] Solution 2: It can be implemented based on a lightweight machine learning model (Light ML Model).

[0083] It can record every change of user information and the new style finally selected by the user.

[0084] When creating a historical dataset, the degree score corresponding to each update message can also be generated in the following way, and then the degree model is trained based on the created historical dataset:

[0085] Method 1: Use a computer vision model (such as a pre-trained Siamese network or a network consisting of an image feature extractor and a distance calculation module). Compare the original business card style image with the new business card style image selected by the user and calculate the visual difference (such as the eigenvector cosine distance or LPIPS perceptual distance). Normalize / map this distance to [0, 10] to quantify the actual degree of change.

[0086] Method 2: If the business card style is defined by structured data (such as CSS properties, template IDs, component configurations), you can design rules to calculate the differences between the old and new style configurations (e.g., has the layout changed? Has the primary color changed? Has the font changed? Have elements been added or deleted?), and combine these differences to obtain an actual degree of change score.

[0087] Target variable definition: The training objective of the degree score is the calculated actual degree of change. Model learning prediction: Based on this information change, how much the user actually adjusted the style.

[0088] Training: Use the collected (change features, actual change degree) data pairs to train the GBDT model.

[0089] Prediction: Given new change features as input, the model outputs a predicted degree score (i.e., the degree of adjustment the user might expect).

[0090] Model output (Output):

[0091] Severity Rating: A numerical value (e.g., in the range [0, 10]) indicating the degree of impact this information change will have on the visual style of the business card. 0-3 indicates a minimal impact, suggesting minor adjustments (e.g., updating text, adjusting font size and position). 4-6 indicates a moderate impact, suggesting moderate adjustments (e.g., changing the color scheme, adjusting partial layout, replacing minor elements). 7-10 indicates a significant impact, suggesting a significant redesign (e.g., changing the overall layout, visual style, or core elements like the logo area).

[0092] Output Definition (input to LLM): Define the scoring range and the corresponding expected adjustment level. For example:

[0093] "The severity rating (range: 0-10) indicates the extent to which this information change suggests a visual adjustment to the business card style. 0-3 points: Minor adjustment (only the content is updated, and the style remains basically unchanged); 4-6 points: Moderate adjustment (update the content and adjust some visual elements such as color and minor layout); 7-10 points: Major adjustment (it is recommended to explore a significantly different layout, style or core visual elements)."

[0094] After deployment, actual change data is collected. After accumulating sufficient data, a lightweight ML model (Solution B-GBDT) is trained to replace the rule engine, achieving more accurate and personalized scoring.

[0095] The rule engine doesn't rely on historical style data at all. The ML model relies on the actual adjustment data after users ultimately choose a new style, which is much more feasible than labeling the degree of difference between all historical style pairs.

[0096] The rule engine is naturally interpretable. The GBDT model also provides feature importance, which is more interpretable than black-box deep learning models.

[0097] Compatible with LLM input: The output degree score and its clear definition can effectively guide LLM to control the degree of variation of generated styles.

[0098] S130 , inputting the current style definition of the current user, the modified first basic information, the first basic information before modification, the degree score, and the definition of the degree score into the generative large model to obtain a plurality of candidate styles.

[0099] The current user's style definition refers to the style features that the user currently uses or expects. For example, in software interface design, this may include the interface's color scheme, layout structure, font style, etc. It provides the model with the user's basic preferences and requirements for style.

[0100] First, basic information may change after modification, and these changes may be data updates, additions and deletions of attributes, etc. This part of information reflects the adjusted situation at a certain basic level and provides new basic data basis for the model.

[0101] It is necessary to retain the basic information before the modification. It allows the model to understand the initial state before the modification, facilitates the model to compare the differences before and after the modification, and thus more accurately understand the trend and focus of the change.

[0102] Definition of degree score: This clarifies the specific meaning and standards of the degree score, allowing the model to accurately understand the information conveyed by the score and thus reasonably apply this score when processing data.

[0103] This information is fed into the generative big model to provide it with a comprehensive understanding of the current situation and context, including user preferences, the state of underlying data, and evaluation of the existing situation. Based on this input, the generative big model can perform complex data processing, analysis, and generation tasks, resulting in multiple candidate styles. These alternative styles may include a variety of different design options, layout methods, and stylistic choices for users to further select and utilize.

[0104] For example, a "Style Generation Prompt Template" might include the following: [Current User Description], [Current Style Definition], [First Basic Information After Modification], [First Basic Information Before Modification], and [Level Rating]: Definition of the level rating. Consider all of the above information, including the user's current style preference, the changes to the basic information, and the current status reflected by the level rating. Based on these inputs, utilize the generation capabilities to generate [X] related alternative styles. These alternative styles should be diverse, offering different visual effects, layout arrangements, or functional presentations while maintaining a certain degree of rationality and relevance to the original style. For each generated alternative style, generate a detailed description, including key design elements such as the organization of interface elements, color schemes, and font styles, to ensure a clear understanding and assessment of the characteristics and applicability of these styles.

[0105] S140: Display multiple candidate styles so that the current user can select a target style from the candidate styles.

[0106] In some embodiments, the above-mentioned step S120 can be specifically implemented through the following steps: determining a historical target style sequence; determining a degree score through a pre-trained degree model based on the historical target style sequence, the modified first basic information, and the first basic information before modification.

[0107] The input of the model that integrates information change and style sequence constraints is as follows: Information change: before modification value, after modification value. Style change sequence: an ordered list of the user's historical business card styles (e.g., [Style A, Style B, Style C]), represented by structured features.

[0108] Output: Severity score (range 0-10), subject to the following: Higher scores: Information changes require more significant styling adjustments (e.g., changing a company logo requires significant adjustments). Lower scores: Information changes require only minor styling adjustments (e.g., updating a phone number).

[0109] Key Constraint: Scoring must reference historical style sequences to ensure that new and recent styles do not suddenly change (e.g., avoid a sudden shift from minimalist to retro).

[0110] A dual-path evaluation model can be designed: the model is divided into two paths, respectively addressing the impact of information changes and style sequence coherence, and ultimately combining them to output a score. The style sequence path (constraining the extent of style evolution) calculates the maximum allowable style change threshold based on historical style sequences to suppress sudden changes. Input features (styles must be converted into structured features) include: feature type - extraction method - sample value; layout complexity - calculated distribution dispersion of the main areas (name / company / contact information) - 0.2 (low) → 0.8 (high); dominant color - extract the main peak of the HSV color histogram and encode it as a hue value - [120, 0.7] (green); font style - classification code (e.g., 0 = serif, 1 = sans serif, 2 = handwriting) - 1 (sans serif); element density - the proportion of non-blank area on the business card - 0.6; brand element proportion - the proportion of brand elements such as logos / slogans occupied by the business card - 0.3.

[0111] When information changes require drastic adjustments but historical sequences indicate low incremental changes in user preferences, the degree difference will be significantly suppressed, thus avoiding the generation of mutation solutions.

[0112] In some embodiments, the dynamic threshold constraint is implemented by calculating the average attribute difference and average pattern difference of consecutive styles in the historical style sequence; if the current attribute difference score is greater than the historical average attribute difference × 1.5, it is suppressed to 60% of the original value; if the current pattern difference score is greater than the historical average pattern difference × 1.8, it is suppressed to 40% of the original value.

[0113] Example scenario:

[0114] User A (historical style sequence: minimalist style → fine-tuning color → adding new icons):

[0115] If phone number is updated → info_impact = 2 → final score ≈ 2 (only text update required);

[0116] If the company logo is changed, info_impact = 9, but the historical max_threshold only allows moderate adjustments. Final score = 9 × 0.5 = 4.5. Generate a progressive new style (keep the minimalist framework and only update the logo area).

[0117] User B (frequently switches styles: minimalist → retro → tech):

[0118] Same logo replacement → Final score = 9×1.0=9 → Substantial redesign allowed.

[0119] This embodiment uses a degree model to map basic information updates (before and after values) into style difference scores, driving a generative model to output alternative styles. The update is then completed upon user selection. This creates an automated closed loop from information changes to style updates, improving efficiency by automatically responding to information changes through the degree model.

[0120] The severity score quantifies the intensity of the change request (e.g., changing a phone number → low score, changing a company logo → high score). By using constraints, we avoid over-design or under-adjustment, reduce user cognitive load, and enable users to choose only from a limited number of AI-generated alternatives, thus reducing decision-making time.

[0121] Establish a structured style description framework, decouple attributes and patterns, lay the foundation for two-dimensional scoring, cover multi-source information-driven scenarios, and support updates triggered by behavioral data and environmental information in addition to basic information.

[0122] The degree model must be combined with historical target style sequences to calculate scores and suppress sudden changes. This ensures brand image consistency. The direction of new style generation is constrained based on the historical style evolution path to avoid style jumps.

[0123] By extracting historical style features in a structured manner and relying on manually labeled difference scoring to train the model, the problem of "style differences are difficult to quantify" in traditional methods is solved, the degree scoring is made interpretable, and the model's generalization ability is significantly improved.

[0124] Figure 2 This is a schematic diagram of a device structure for changing business card styles based on information synchronization provided in an embodiment of the present application. Figure 2 As shown, the device includes:

[0125] The receiving module 201 is configured to receive a current update message of the basic information of the current user, where the current update message includes the modified first basic information and the first basic information before the modification.

[0126] The scoring module 202 is used to determine the degree score based on the modified first basic information and the first basic information before modification through a pre-trained degree model. The degree model is used to predict the degree score corresponding to the current update message based on historical update messages, the degree scores corresponding to each historical update message and the updated style. The degree score is used to indicate the difference between styles. The style of the business card includes attributes and patterns. The degree score includes an attribute difference score and a pattern difference score. The attribute difference score is used to quantify the impact of changes in text fields in the basic information on style attributes. The pattern difference score quantifies the impact of changes in visual fields in the basic information on style patterns.

[0127] The generation module 203 is used to input the current style definition of the current user, the modified first basic information, the first basic information before modification, the degree score and the definition of the degree score into the generative large model to obtain multiple candidate styles.

[0128] The display module 204 is configured to display a plurality of candidate styles so that the current user can select a target style from the candidate styles.

[0129] In some embodiments, the attributes include fonts and layouts; the user's basic information includes user personal information, user behavior information, and user scenario information; the user's personal information includes position information; the first basic information before modification includes the position information before modification; and the first basic information after modification includes the position information after modification.

[0130] In some embodiments, the final degree score takes the maximum value of the attribute difference score and the pattern difference score, and both scores are constrained by a dynamic threshold of the historical pattern sequence.

[0131] In some embodiments, the scoring module 202 is specifically configured to include:

[0132] Determine the historical target style sequence;

[0133] Based on the historical target style sequence, the modified first basic information, and the first basic information before modification, a degree score is determined by a pre-trained degree model.

[0134] In some embodiments, a training module is used to obtain a historical data set: including user basic information update messages, corresponding historical style change sequences, and updated target styles; extract style features: for each style in the historical style sequence, extract attribute features and pattern features; construct training samples: use the before and after values ​​of each information update, the corresponding style sequence features, and the manually annotated difference scores between the new and old styles as samples; train a dual-path model: the first path learns the attribute difference score; the second path learns the pattern difference score.

[0135] In some embodiments, dynamic threshold constraints are implemented by:

[0136] Calculate the average attribute difference and average pattern difference of consecutive styles in the historical style sequence;

[0137] If the current attribute difference score is greater than the historical average attribute difference × 1.5, it will be suppressed to 60% of the original value;

[0138] If the current pattern difference score is greater than the historical average pattern difference × 1.8, it will be suppressed to 40% of the original value.

[0139] In some embodiments, the input to the generative large model also includes:

[0140] Attribute Difference Score Definition: Describes the mapping relationship between the score and the font and layout adjustment range;

[0141] Definition of pattern difference score: describes the mapping relationship between the score and the degree of color and layout adjustment;

[0142] Among them, the large model generates adjustment plans for the attribute dimension and pattern dimension based on the two scores, and then combines them into a complete alternative style.

[0143] In some embodiments, the weight distribution of attribute difference scores and pattern difference scores is dynamically adjusted according to the user scenario:

[0144] When basic information updates involve business and social scenarios, the weight of the pattern difference score is increased;

[0145] When the update involves recruitment and job-seeking scenarios, the weight of attribute difference scores is increased.

[0146] In some embodiments, the scoring module is used to: independently calculate the attribute and pattern difference score for each field; when a score conflict is detected, initiate an arbitration strategy; the arbitration strategy includes: giving priority to responding to changes in fields with higher weights, or taking the score of the conflicting field Figure 3 The geometric mean of the structural schematic diagrams of the electronic device for implementing the embodiment of the present invention is shown as the final value.

[0147] like Figure 3 As shown, electronic device 300 includes a central processing unit (CPU) 301, which can perform various appropriate actions and processes according to programs stored in read-only memory (ROM) 302 or programs loaded from storage unit 308 into random access memory (RAM) 303. RAM 303 also stores various programs and data required for the operation of electronic device 300. CPU 301, ROM 302, and RAM 303 are connected to each other via bus 304. Input / output (I / O) interface 305 is also connected to bus 304.

[0148] The following components are connected to the I / O interface 305: an input section 306 including a keyboard, mouse, and the like; an output section 303 including devices such as a cathode ray tube (CRT), a liquid crystal display (LCD), and speakers; a storage section 308 including a hard disk; and a communication section 309 including a network interface card such as a LAN card or a modem. The communication section 309 performs communication processing via a network such as the Internet. A drive 310 is also connected to the I / O interface 305 as needed. Removable media 311, such as a magnetic disk, an optical disk, a magneto-optical disk, or a semiconductor memory, is installed in the drive 310 as needed, so that computer programs read from the media can be installed in the storage section 308 as needed.

[0149] In particular, according to embodiments of the present disclosure, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of the present disclosure include a computer program product comprising a computer-readable medium carrying instructions. In such embodiments, the instructions can be downloaded and installed from a network via communication component 309 and / or installed from removable media 311. When the instructions are executed by central processing unit (CPU) 301, the various method steps described herein are performed.

[0150] Although the exemplary embodiments have been described, it will be apparent to those skilled in the art that various changes and modifications may be made without departing from the spirit and scope of the present invention. Therefore, it should be understood that the exemplary embodiments described above are not limitative, but illustrative.

Claims

1. A method for changing business card styles based on information synchronization, characterized in that: include: Receive a current update message of the basic information of the current user, where the current update message includes the modified first basic information and the first basic information before the modification; Based on the modified first basic information and the first basic information before modification, a degree score is determined using a pre-trained degree model. The degree model is used to predict the degree score corresponding to the current update message based on historical update messages, the degree scores corresponding to each historical update message, and the updated style. The degree score is used to indicate the difference between styles. The style of a business card includes attributes and patterns. The degree score includes an attribute difference score and a pattern difference score. The attribute difference score is used to quantify the impact of changes in text fields in the basic information on style attributes. The pattern difference score quantifies the impact of changes in visual fields in the basic information on the style pattern. Inputting the current style definition of the current user, the modified first basic information, the first basic information before modification, the degree score, and the definition of the degree score into a generative large model to obtain a plurality of candidate styles; A plurality of candidate styles are displayed so that the current user can select a target style from the candidate styles.

2. The method according to claim 1, characterized in that The attributes include fonts and layouts; the user's basic information includes user personal information, user behavior information, and user scenario information; the user's personal information includes position information; the first basic information before modification includes the position information before modification; and the first basic information after modification includes the position information after modification.

3. The method according to claim 1, characterized in that The final degree score takes the maximum value of the attribute difference score and the pattern difference score, and both scores are constrained by the dynamic threshold of the historical style sequence.

4. The method according to claim 1, wherein Determining a degree score based on the modified first basic information and the first basic information before the modification using a pre-trained degree model further includes: Determine the historical target style sequence; Based on the historical target style sequence, the modified first basic information, and the first basic information before modification, a degree score is determined by a pre-trained degree model.

5. The method according to claim 4, characterized in that The degree model is trained by the following steps: Obtain historical data sets: including user basic information update messages, corresponding historical style change sequences, and updated target styles; Extract style features: For each style in the historical style sequence, extract attribute features and pattern features; Construct training samples: Take the pre-modification value of each information update, the post-modification value of the information update, the corresponding style sequence features, and the manual annotation degree score between the new and old styles as samples; Training a dual-path model: the first path learns attribute difference scores; the second path learns pattern difference scores.

6. The method according to claim 1, characterized in that Dynamic threshold constraints are implemented in the following ways: Calculate the average attribute difference and average pattern difference of consecutive styles in the historical style sequence; If the current attribute difference score is greater than the historical average attribute difference × 1.5, it will be suppressed to 60% of the original value; If the current pattern difference score is greater than the historical average pattern difference × 1.8, it will be suppressed to 40% of the original value.

7. The method according to claim 1, characterized in that The input of the generative model also includes: Attribute Difference Score Definition: Describes the mapping relationship between the score and the font and layout adjustment range; Definition of pattern difference score: describes the mapping relationship between the score and the degree of color and layout adjustment; Among them, the large model generates adjustment plans for the attribute dimension and pattern dimension based on the two scores, and then combines them into a complete alternative style.

8. The method according to claim 1, characterized in that The weight distribution of the attribute difference score and the pattern difference score is dynamically adjusted according to the user scenario: When basic information updates involve business and social scenarios, the weight of the pattern difference score is increased; When the update involves recruitment and job-seeking scenarios, the weight of attribute difference scores is increased.

9. The method according to claim 1, characterized in that When multiple basic information fields are updated simultaneously: Calculate attribute difference scores and pattern difference scores independently for each field; When a scoring conflict is detected, the arbitration strategy is activated; Arbitration strategies include: Prioritize responding to changes in fields with higher weights; Alternatively, the geometric mean of the conflicting field scores can be used as the final value.

10. An electronic device, characterized in that: include: one or more processors; a memory for storing one or more programs, When the one or more programs are executed by the one or more processors, the one or more processors are caused to perform the method according to any one of claims 1 to 9.

Images