Safe intelligent auxiliary system for fiber art color recognition and matching

Abstract

The invention discloses a safe intelligent auxiliary system for fiber art color identification and matching, and relates to the technical field of industrial internet data, the system comprises a user interaction data acquisition module, the input information of a creator in miniature ceramic sculpture creation is acquired through a pre-established user interaction data storage library, and the input information of the creator in miniature ceramic sculpture creation is sent to the user interaction data acquisition module; for text description and operation behavior records in the input information, key descriptors and behavior patterns are extracted by adopting a semantic analysis technology, and an initial creation intention feature set is obtained; according to the safe intelligent auxiliary system for fiber art color recognition and matching, the emotion and culture background of a creator are fused into ceramic creation, accurate and personalized guidance is provided, and the creation quality and culture expression of a miniature ceramic sculpture are effectively improved.

Description

Technical Field

[0001] The present invention relates to the field of industrial Internet data technology, and in particular to a safe intelligent auxiliary system for fiber art color recognition and matching. Background Art

[0002] In the field of artistic creation and personalized guidance, research on how to provide creators with customized support is of vital importance. This area not only concerns the diversity of artistic expression but also directly impacts the growth and innovation capabilities of creators at varying skill levels. With the widespread adoption of digital tools, art guidance has become a crucial bridge connecting creators and technology, playing a crucial role in improving the quality and efficiency of creative work.

[0003] However, current approaches suffer from significant shortcomings when addressing creators' needs. Many solutions often overlook the dynamic nature of user creative intent, lack a deep understanding of the creator's subjective expression, and struggle to integrate material properties with visual presentation. These limitations often lead to superficial guidance solutions that fail to truly meet the creator's individual needs and provide targeted inspiration during the creative process. Focusing on specific challenges, the most challenging aspect of this field lies in accurately analyzing user creative intent and effectively integrating it with material properties and visual effects. First, identifying creative intent is a complex process that requires a comprehensive understanding of the creator's emotions, goals, and cultural background, and existing technologies often struggle to capture these nuances. This inadequacy in intent recognition further leads to issues with adaptability in material selection and color matching, particularly for creators of varying skill levels, making it difficult to tailor guidance to their abilities. These two factors are closely intertwined, with the former directly influencing the latter, creating a technical bottleneck that urgently needs to be addressed. Summary of the Invention

[0004] The purpose of this invention is to provide a safe and intelligent auxiliary system for fiber art color recognition and matching. Based on the understanding of the creator's intention and combined with the knowledge of material properties and color matching, a dynamic and adaptive personalized guidance plan is designed for creators of different skill levels.

[0005] To achieve the above-mentioned object, the present invention provides the following technical solution: a safe and intelligent auxiliary system for fiber art color recognition and matching, the system comprising:

[0006] The user interaction data acquisition module obtains the creator's input information during the creation of miniature ceramic sculptures through a pre-established user interaction data repository. Based on the text descriptions and operation behavior records in the input information, it uses semantic parsing technology to extract key descriptive words and behavior patterns to obtain the initial creative intention feature set;

[0007] The guidance framework generation module generates a sculpture guidance framework suitable for different skill levels based on the initial creative intention feature set. This module, combined with a dynamic emotional update mechanism, obtains real-time feedback from the creator during the creative process. If the feedback indicates a change in creative intent, the module calculates the numerical difference between the presented result and the required standard through the demand preference weight adjustment and deviation quantification evaluation formula to determine the adjusted guidance direction.

[0008] The visual effect mapping module integrates the micro-sculpture visual effect presentation module with the adjusted guidance direction, maps the guidance content with the visual effect data, and uses visual presentation correction rules to generate an intuitive sculpture effect preview image, and determines whether the preview image meets the content matching detection standards;

[0009] The deviation analysis and optimization module calls the deviation source tracing path based on the sculpture effect preview image and analyzes the specific links where the deviation occurs. If there is a gap between the preview image and the user's demand standard, the guidance content is adjusted in a targeted manner through the secondary optimization iteration limit and optimization result verification standard to obtain the final personalized miniature ceramic sculpture guidance plan.

[0010] Preferably, the method of obtaining a sculpture guidance framework suitable for different skill levels based on the initial creative intention feature set includes performing a multi-dimensional sentiment analysis on the feature set based on the initial creative intention feature set in combination with the emotional semantic parsing rules and the cultural symbol mapping table, extracting emotional keywords and tone features in the text, and mapping the metaphorical associations in the cultural background to determine the creator's emotional tendency label and regional cultural difference label.

[0011] Preferably, the sculpture guidance framework suitable for different skill levels obtained based on the initial creative intention feature set also includes calling the historical context reference set and the emotion triggering scene library for emotional tendency labels and regional cultural difference labels, analyzing the correspondence between emotional expression and specific scenes and historical backgrounds, and obtaining the emotion level range and cultural background correlation description under the emotion intensity grading standard.

[0012] Preferably, the method of obtaining a sculpture guidance framework suitable for different skill levels based on the initial creative intention feature set further includes accessing a ceramic material characteristic analysis library based on the emotional level range and cultural background correlation description, obtaining material attribute data that matches the emotional tendency and cultural background, such as texture roughness, molding difficulty, etc., and judging the compatibility of the material with the creative intention. If the compatibility is lower than a preset threshold, the material is re-screened through a cross-cultural comparison framework until a ceramic material combination with a compatibility higher than the preset threshold is obtained.

[0013] Preferably, obtaining a sculpture guidance framework suitable for different skill levels based on the initial creative intention feature set also includes extracting color scheme data corresponding to material properties through a combination of ceramic materials in combination with a miniature sculpture color matching knowledge base, grouping the color schemes using an emotional intensity grading standard, and determining the color matching set that best matches the creative intention.

[0014] Preferably, obtaining a sculpture guidance framework suitable for different skill levels based on the initial creative intention feature set also includes calling a personalized guidance content generation module based on a color matching set and the creator's pottery skill level difference data, performing layered processing based on skill level differences, and classifying the guidance content according to operation difficulty and visual presentation effect in combination with a user feedback classification table to obtain a sculpture guidance framework suitable for different skill levels.

[0015] Preferably, the user interaction data acquisition module includes a text analysis unit and a behavior record processing unit, which are respectively used to perform semantic analysis on the natural language description in the input information and to extract behavior patterns from the operation trajectory.

[0016] Preferably, the dynamic emotion updating mechanism in the guidance framework generation module includes an emotion recognition model and a feedback response adjustment module, which are used to dynamically adjust the guidance strategy based on changes in the emotional characteristics of the user's language or interaction.

[0017] Preferably, in the visual effect mapping module, the visual presentation correction rule includes at least one of a color contrast balance rule, a texture consistency mapping rule or a composition ratio adjustment rule.

[0018] Preferably, the deviation analysis and optimization module includes: a deviation index evaluator and a result correction submodule, the deviation index evaluator is used to locate the deviation generation link, and the correction submodule is used to adjust parameters according to a preset number of iterations.

[0019] It can be seen from the above technical solution that the present invention has the following beneficial effects:

[0020] This safe and intelligent auxiliary system for fiber art color recognition and matching analyzes the creator's input information, extracts the characteristics of the creative intention, performs sentiment analysis and cultural background mapping, and determines the emotional tendency and cultural difference labels. Combining historical context and emotional triggering scenes, it derives the emotional level range and cultural relevance description. Based on this, suitable ceramic materials and color schemes are selected, and a hierarchical guidance framework is generated according to the creator's skill level. During the creative process, the present invention can obtain feedback in real time, dynamically adjust the guidance direction, and generate a visual effect preview. Through deviation analysis and secondary optimization, a personalized micro-ceramic sculpture guidance plan is finally formed. The present invention realizes the integration of the creator's emotions and cultural background into ceramic creation, provides accurate and personalized guidance, and effectively improves the creative quality and cultural expression of micro-ceramic sculptures. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Figure 1 This is a system connection diagram of the present invention. DETAILED DESCRIPTION

[0022] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0023] like Figure 1 As shown, the present invention provides a technical solution: a safe intelligent auxiliary system for fiber art color recognition and matching, the system comprising:

[0024] The user interaction data acquisition module obtains the creator's input information during the creation of miniature ceramic sculptures through a pre-established user interaction data repository. Based on the text descriptions and operation behavior records in the input information, it uses semantic parsing technology to extract key descriptive words and behavior patterns to obtain the initial creative intention feature set;

[0025] The guidance framework generation module generates a sculpture guidance framework suitable for different skill levels based on the initial creative intention feature set. This module, combined with a dynamic emotional update mechanism, obtains real-time feedback from the creator during the creative process. If the feedback indicates a change in creative intent, the module calculates the numerical difference between the presented result and the required standard through the demand preference weight adjustment and deviation quantification evaluation formula to determine the adjusted guidance direction.

[0026] The visual effect mapping module integrates the micro-sculpture visual effect presentation module with the adjusted guidance direction, maps the guidance content with the visual effect data, and uses visual presentation correction rules to generate an intuitive sculpture effect preview image, and determines whether the preview image meets the content matching detection standards;

[0027] The deviation analysis and optimization module calls the deviation source tracing path based on the sculpture effect preview image and analyzes the specific links where the deviation occurs. If there is a gap between the preview image and the user's demand standard, the guidance content is adjusted in a targeted manner through the secondary optimization iteration limit and optimization result verification standard to obtain the final personalized miniature ceramic sculpture guidance plan.

[0028] The workflow of the system starts with the user interaction data acquisition module. First, it calls the preset user interaction data repository to read the text content (such as material preferences, style descriptions, color tendencies) and operation behaviors (such as tool usage frequency, carving order, and editing path) input by the creator in real time during the micro-ceramic sculpture creation process. By constructing a natural language processing model based on joint syntactic and semantic parsing, it performs word segmentation and entity recognition on verbs, adjectives, noun phrases, etc. involved in the text description, and extracts a creative intention feature set containing dimensions such as color, shape, and emotional tendency. Then, the guidance framework generation module uses this feature set as input and matches the adapted guidance template based on the skill level labels pre-classified in the creator's historical operation data. It constructs a personalized sculpture guidance framework including step guidance sequence, operation sequence weight, and material prompt parameters. At the same time, it integrates a dynamic emotion recognition sub-module built based on a temporal convolutional network to perform real-time analysis of non-text feedback during the creation process (such as changes in operation rhythm, interruption frequency, and command rollback) to generate an emotional state vector and intention evolution prediction results. If the system determines that the current feedback features are consistent with the initial creative intention features, the system generates an emotional state vector and intention evolution prediction results. If there is a significant deviation in the feature, the demand preference weight adjustment mechanism is implemented. The numerical deviation between the current guidance content and the target intent is evaluated based on the weighted Euclidean distance formula, and the guidance direction is automatically corrected through a dynamic reconstruction algorithm. The adjusted guidance content is input into the visual effect mapping module, which integrates multi-level texture mapping parameters and geometric deformation instructions. The module combines the image feature alignment model with a pre-trained visual correction rule library to generate a high-definition sculpture effect preview containing three views. The system further detects and scores the preview based on preset content matching index functions (such as structural similarity (SSIM) and color consistency index (CI). When the detection result falls below a set threshold, the deviation analysis and optimization module is activated, calling the deviation path identification algorithm based on decision tree backtracking. It tracks the source of the error from multiple dimensions such as parameter configuration, user operation sequence, and guidance framework recommendations. Then, without exceeding the set maximum number of iterations, a hierarchical optimization model is used to adjust the key deviation points. By comparing with optimization verification criteria (including the improvement rate of user preference matching and the value of creative efficiency improvement), a personalized sculpture guidance plan that can be directly applied to the creative process is finally generated.

[0029] This system significantly enhances the intelligent interaction capabilities during the creation of miniature ceramic sculptures, enabling real-time understanding and response to creators' needs. By establishing a feedback loop between creative intent and the guidance framework, the accuracy of the creative process and the personalization of guidance are significantly improved. The system demonstrates greater adaptability in identifying user preferences and operational patterns, reducing the risk of misleading operations and increasing user satisfaction with the final sculptures. The optimization module limits the number of iterations and sets verification standards to ensure system efficiency and feedback response speed, effectively improving overall guidance quality.

[0030] Based on the initial creative intention feature set, a sculpture guidance framework suitable for different skill levels is obtained, including performing multi-dimensional sentiment analysis on the feature set based on the initial creative intention feature set, combining emotional semantic parsing rules and cultural symbol mapping tables, extracting emotional keywords and tone features in the text, and mapping metaphorical associations in the cultural context to determine the creator's emotional tendency label and regional cultural difference label.

[0031] In this implementation, the construction of the guidance framework is based on multi-dimensional feature extraction and semantic modeling technology. The system first calls the keyword field in the initial creative intent feature set and, by loading a defined set of sentiment semantic parsing rules, relies on sentiment dictionaries (such as SentiWordNet) and contextual analysis models to identify high-frequency sentiment words contained in the text, their polarity (positive or negative), and intensity levels. At the same time, the system uses a tone analyzer based on syntactic structure analysis to identify tone features in sentences, such as identifying imperative sentence structures and the adjacency of sentiment words to mark the author's tone preference. On this basis, the system loads a cultural symbol mapping table, which is a database of correspondences between cultural symbols manually annotated by experts and commonly used descriptive words (for example, "dragon" is a metaphor for authority in Eastern culture, but often symbolizes danger in Western culture). The extracted keywords are compared with the cultural images defined in the mapping table. Through logical matching and a weighted scoring model, the cultural orientation and symbolic preference contained in the author's text description are identified. Finally, the system uses the extracted emotional tendency labels and regional cultural difference labels as input parameters to jointly generate corresponding emotional style templates and regional adaptation templates, and combines them with the creator's skill level mark to synthesize a specific sculpture guidance framework, which includes specific operation step suggestions, performance element selection guidance and style expression technical tips.

[0032] Based on the initial creative intention feature set, a sculpture guidance framework suitable for different skill levels is obtained, which also includes emotional tendency labels and regional cultural difference labels, calling the historical context reference set and emotional trigger scene library, analyzing the correspondence between emotional expression and specific scenes and historical backgrounds, and obtaining the emotional level range and cultural background correlation description under the emotional intensity grading standard.

[0033] In this embodiment, after obtaining the emotional tendency label and regional cultural difference label, the system first calls the pre-constructed historical context reference set, which contains data entries marked with cultural background, scene description, era style and typical emotional expression. The system uses a semantic vector calculation model (such as Word2Vec or SBERT) to convert the keywords and tone features of the current creative text into vector form, and compares the cosine similarity with each entry in the historical context reference set to screen out several context entries with the closest semantics. At the same time, the system calls the emotional trigger scene library, which records common emotional trigger factors (such as sadness, joy, tension) in typical cultural scenes (such as festivals, ceremonies, wars, family gatherings), and semantically matches the creative semantics with the scene library content. Through a discriminant model based on weighted similarity, it determines the typical cultural scene that the current emotional expression is most likely to correspond to. Then, based on the matching results, the system summarizes the intensity range of this type of emotional expression in historical creations from historical expression samples, constructs a specific emotional intensity grading standard (for example, dividing emotions into five levels, from "mild emotional fluctuations" to "extreme emotional arousal"), and combines the changing patterns of cultural symbols expressed in different historical contexts. Finally, it outputs which level range the current creative emotion belongs to, as well as its corresponding cultural background relevance description content, as an important input parameter for generating a personalized guidance framework, to assist in the precise matching of subsequent operation content, style suggestions and expression intensity.

[0034] Based on the initial creative intention feature set, a sculpture guidance framework suitable for different skill levels is obtained. It also includes accessing the ceramic material characteristic analysis library based on the emotional level range and cultural background correlation description, and obtaining material attribute data that matches the emotional tendency and cultural background, such as texture roughness, molding difficulty, etc., to judge the compatibility of the material with the creative intention. If the compatibility is lower than the preset threshold, the material is re-screened through the cross-cultural comparison framework until a ceramic material combination with a higher degree of compatibility is obtained.

[0035] The core of this implementation is to establish a semantic linkage between the material selection mechanism and creative intent. The system first reads the description of the correlation between the emotional level interval and cultural background generated in the previous step and uses this as input to index the ceramic material property analysis library. This material library records the typical properties of each ceramic material through structured data, including numerical parameters (such as Mohs hardness, mean particle size, and water absorption) and categorical descriptions (such as texture type, color expression tendency, and traditional cultural use). The system establishes an emotion-attribute mapping model, semantically matching the current emotional level (such as intense expression) with material attributes (such as surface roughness and strong color contrast) to calculate a compatibility score. The scoring function comprehensively considers the material attribute weights, semantic matching, and cultural adaptability scores. If the compatibility of the current matching material combination falls below a system-set threshold (such as 85%), the system invokes a cross-cultural comparison framework. Based on a multicultural ceramic practice database, this framework compares material solutions used in different countries or regions with similar emotional and cultural backgrounds. Alternative material combinations are identified through feature vector mapping and similarity clustering methods (such as t-SNE dimensionality reduction clustering) and the compatibility is recalculated. The system returns a list of ceramic material combinations based on the optimized adaptation results, and locks the group with the highest adaptability as the recommended material selection plan in the subsequent guidance template.

[0036] Based on the initial creative intention feature set, a sculpture guidance framework suitable for different skill levels is obtained. This also includes extracting color scheme data corresponding to material properties through the combination of ceramic materials and the knowledge base of micro-sculpture color matching, grouping the color schemes using the emotional intensity grading standard, and determining the color matching set that best matches the creative intention.

[0037] In this embodiment, the system uses a selected ceramic material combination as a basis to access a knowledge base of miniature sculpture color matching. This knowledge base is constructed from a database of actual ceramic works and color psychology experimental data, and is structured and stored according to dimensions such as material type, suitable glaze, firing conditions, and color matching experience. The system first analyzes the physical parameters of the selected materials (such as surface adsorption capacity, component iron content, particle reflectivity, etc.) and heat treatment behavior (such as color change trends under oxidizing atmospheres), and matches historical color combination records that match their characteristics in the knowledge base. The system then groups the multiple matched color schemes according to a five-level emotional intensity grading standard (mild, moderate, obvious, strong, and extremely strong). The emotional intensity labels are used to classify each group of schemes using a color emotion mapping model (e.g., blue-green is classified as "tranquil" and orange-red is classified as "passionate"). The system then uses the emotional level and cultural background labels in the creative intention as constraints, and adopts a fit scoring function (taking into account color psychological consistency, cultural color symbol adaptability, color material compatibility, etc.) to comprehensively score each group of schemes, and finally selects the color matching set with the highest score and provides color recommendations as the final guiding template.

[0038] Based on the initial creative intention feature set, a sculpture guidance framework suitable for different skill levels is obtained. It also includes calling a personalized guidance content generation module based on the color matching set and the creator's pottery skill level difference data, performing layered processing based on skill level differences, and combining the user feedback classification table to classify the guidance content according to operation difficulty and visual presentation effect, thereby obtaining a sculpture guidance framework suitable for different skill levels.

[0039] In this embodiment, the system extracts data on pottery skill level differences from user profile information or operation records, primarily including the user's past creative experience, tool proficiency, operation time distribution, and historical work ratings. The system determines the current creator's skill level based on a set skill grading standard (e.g., entry-level, elementary, intermediate, advanced, and expert) and passes this level information as a key input parameter to the personalized guidance content generation module. The module first evaluates the feasibility of the color combination set selected in the previous stage, combining the ceramic material properties and color processing complexity to determine whether it is suitable for the current skill level. If a combination exceeds the skill level, the system initiates a hierarchical substitution mechanism, prioritizing alternatives with strong compatibility and moderate operational difficulty. Simultaneously, the module accesses a user feedback classification table, which records the feedback and evaluation of previous guidance content by users of different skill levels. Using a naive Bayesian classifier or a weighted regression model, the system categorizes and predicts the newly generated guidance content based on two dimensions: "operational difficulty" and "visual presentation effect." This ensures that the output does not exceed the user's operational capabilities while maintaining the creative intent in terms of visual expression. Ultimately, the module outputs a sculpture guidance framework that includes specific process steps, precautions, matching color descriptions, and time node arrangements, which is a feasible implementation path suitable for the creator's personal skill conditions.

[0040] The user interaction data acquisition module includes a text analysis unit and a behavior record processing unit, which are respectively used to perform semantic analysis on the natural language description in the input information and to extract behavior patterns from the operation trajectory.

[0041] In this embodiment, the user interaction data acquisition module is subdivided into two core functional subunits: a text analysis unit and a behavior record processing unit. The text analysis unit utilizes a syntactic-semantic joint analysis model based on natural language processing (NLP) technology to perform multi-level parsing on the natural language descriptions input by the creator (e.g., "I hope my work conveys a warm feeling," "I want to use a rough surface"), including part-of-speech tagging, named entity recognition, dependency extraction, and keyword extraction. This generates a set of semantically tagged intent description vectors. This set forms an important component of the initial creative intent features. The behavior record processing unit uses an operation log collection tool to track the user's behavior trajectory on the digital sculpting tool or operation interface in real time, including data dimensions such as mouse movements, click events, sliding behavior, tool switching frequency, and operation time period. Based on behavior sequence models (such as long short-term memory networks (LSTMs) or behavior graph modeling), the system identifies typical user operation patterns and interaction habits, such as "repeatedly modifying a specific area" or "frequently switching color tools." This behavior pattern vector is then constructed, which, together with the text vector, constitutes a complete user interaction feature set, providing a data foundation for subsequent creative intent understanding, guidance framework generation, and feedback optimization.

[0042] The dynamic emotion update mechanism in the guidance framework generation module includes an emotion recognition model and a feedback response regulation module, which is used to dynamically adjust the guidance strategy based on changes in the emotional characteristics of user language or interaction.

[0043] In this embodiment, the dynamic emotion update mechanism builds a closed-loop control system by integrating the emotion recognition model and the feedback response regulation module. The emotion recognition model supports the extraction of emotional signals from two types of input: one is user text input, which uses natural language processing methods (such as polarity scoring based on the sentiment dictionary, emotion label classifier, multi-task BERT emotion recognition model, etc.) to analyze the emotional state of the creator's input text and output a variety of emotion labels and confidence scores including "joy", "confusion", "anxiety", and "satisfaction"; the other is user interaction behavior data, such as the number of operation interruptions, mouse click rhythm, interface dwell time, etc., which evaluates the user's emotional fluctuation trend through the behavior sequence model. The system compares the above-mentioned emotion labels with the initial creative intention feature set. If an emotion shift is identified (such as from "positive" to "neutral" or "anxious"), the feedback response regulation module is triggered. Based on a predefined strategy table, this module adjusts the creative guidance content for different emotional states, including increasing or decreasing the level of detail of prompt information, switching the interface interaction tone (for example, from "Please try this" to "You can consider..."), and changing the complexity level of operation suggestions (such as from advanced techniques to basic operation suggestions) to achieve a humane and adaptable guidance response mechanism, thereby improving the system's adaptability to the creator's psychological state and interaction satisfaction.

[0044] In the visual effect mapping module, the visual presentation correction rule includes at least one of a color contrast balance rule, a texture consistency mapping rule, or a composition ratio adjustment rule.

[0045] In this embodiment, after receiving the guidance content, the visual effect mapping module reprocesses the initially generated preview image at the image level by calling the visual presentation correction rule. The system first applies the color contrast balance rule, which adjusts the brightness and hue angle differences between adjacent color blocks in the image based on the color saturation requirements in the emotional tendency label. It uses a calculation formula based on the CIELAB color space to maintain visual harmony while highlighting key areas of emotional expression. For example, it converts high-contrast color schemes under "intense" emotions into a contrasting layout of warm and cool colors. Next, the system executes the texture consistency mapping rule, using parameters such as "surface roughness" and "grain density" recorded in the material property analysis data as convolution kernel weights to reconstruct the image texture channel, so that the texture presented in the preview image is close to the light and shadow reflection and detailed structure of the real ceramic material, avoiding misleading caused by the large difference between the preview and the actual object. Finally, the composition proportion adjustment rule automatically optimizes the relative proportions and positional relationships of the sculpture components in the image according to the preset cultural composition norms (such as symmetry, rule of thirds, dynamic axis, etc.) and the element hierarchical relationship in the input guidance content, ensuring a stable visual center of gravity and clear expression logic, thereby enhancing the visual tension and artistic appeal of the work composition.

[0046] The deviation analysis and optimization module includes: a deviation index evaluator and a result correction submodule. The deviation index evaluator is used to locate the deviation generation link, and the correction submodule is used to adjust parameters according to the preset number of iterations.

[0047] In this embodiment, the deviation analysis and optimization module consists of two parts: a deviation index evaluator and a result correction submodule. The deviation index evaluator is responsible for comparing the sculpture effect preview image with the creative intention feature set set by the creator, and using image content analysis and semantic matching algorithms to quantitatively evaluate key expression dimensions, including but not limited to color accuracy (such as calculated by SSIM and CI indicators), morphological restoration (such as contour similarity) and cultural expression consistency (such as the degree of emotional label matching). During the evaluation process, the system constructs an error matrix, analyzes the deviation distribution, and identifies the main factors and links that lead to a decrease in overall fit (for example, it is found that the color contrast is lower than the preset emotional intensity requirement). The above information is passed to the result correction submodule, which gradually adjusts the corresponding parameters in the guidance content according to the preset maximum number of iterations (such as 3 times), including color scheme fine-tuning, composition reconstruction suggestions, material replacement suggestions, etc. After each parameter adjustment, the system automatically generates a new sculpture effect preview and calls the deviation index evaluator again to evaluate the optimization effect. If the optimization result verification standard is met (such as the deviation rate drops to within 5%), the iteration is terminated and the final guidance plan is output; otherwise, the iteration continues until the number of times is exhausted, ensuring that the system optimization process has automatic control capabilities and computational controllability.

[0048] While embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions, and variations may be made to these embodiments without departing from the principles and spirit of the invention, and that the scope of the invention is defined by the appended claims and their equivalents.

Claims

1. A safe intelligent auxiliary system for fiber art color recognition and matching, characterized by: The system comprises: The user interaction data acquisition module obtains the creator's input information during the creation of miniature ceramic sculptures through a pre-established user interaction data repository. Based on the text descriptions and operation behavior records in the input information, it uses semantic parsing technology to extract key descriptive words and behavior patterns to obtain the initial creative intention feature set; The guidance framework generation module generates a sculpture guidance framework suitable for different skill levels based on the initial creative intention feature set. This module, combined with a dynamic emotional update mechanism, obtains real-time feedback from the creator during the creative process. If the feedback indicates a change in creative intent, the module calculates the numerical difference between the presented result and the required standard through the demand preference weight adjustment and deviation quantification evaluation formula to determine the adjusted guidance direction. The visual effect mapping module integrates the micro-sculpture visual effect presentation module with the adjusted guidance direction, maps the guidance content with the visual effect data, and uses visual presentation correction rules to generate an intuitive sculpture effect preview image, and determines whether the preview image meets the content matching detection standards; The deviation analysis and optimization module calls the deviation source tracing path based on the sculpture effect preview image and analyzes the specific links where the deviation occurs. If there is a gap between the preview image and the user's demand standard, the guidance content is adjusted in a targeted manner through the secondary optimization iteration limit and optimization result verification standard to obtain the final personalized miniature ceramic sculpture guidance plan.

2. The safe intelligent auxiliary system for fiber art color recognition and matching according to claim 1, characterized in that: The method of obtaining a sculpture guidance framework suitable for different skill levels based on the initial creative intention feature set includes performing a multi-dimensional sentiment analysis on the feature set based on the initial creative intention feature set, combining the emotional semantic parsing rules and the cultural symbol mapping table, extracting emotional keywords and tone features in the text, mapping the metaphorical associations in the cultural context, and determining the creator's emotional tendency label and regional cultural difference label.

3. The safe intelligent assistance system for fiber art color recognition and matching according to claim 2, characterized in that: The sculpture guidance framework suitable for different skill levels obtained based on the initial creative intention feature set also includes calling the historical context reference set and the emotion triggering scene library for emotional tendency labels and regional cultural difference labels, analyzing the correspondence between emotional expression and specific scenes and historical backgrounds, and obtaining the emotion level range and cultural background correlation description under the emotion intensity grading standard.

4. The safe intelligent assistance system for fiber art color recognition and matching according to claim 3, characterized in that: The method of obtaining a sculpture guidance framework suitable for different skill levels based on the initial creative intention feature set also includes accessing a ceramic material characteristic analysis library based on the emotional level range and cultural background correlation description to obtain material attribute data that matches the emotional tendency and cultural background, such as texture roughness, molding difficulty, etc., to determine the compatibility of the material with the creative intention. If the compatibility is lower than a preset threshold, the material is re-screened through a cross-cultural comparison framework until a ceramic material combination with a compatibility higher than the preset threshold is obtained.

5. The safe intelligent auxiliary system for fiber art color recognition and matching according to claim 4, characterized in that: The method of obtaining a sculpture guidance framework suitable for different skill levels based on the initial creative intent feature set also includes extracting color scheme data corresponding to material properties through a combination of ceramic materials, combining with a knowledge base of micro-sculpture color matching, grouping the color schemes using an emotional intensity grading standard, and determining the color matching set that best matches the creative intent.

6. The safe intelligent assistance system for fiber art color recognition and matching according to claim 5, characterized in that: The method of obtaining a sculpture guidance framework suitable for different skill levels based on the initial creative intention feature set further includes calling a personalized guidance content generation module based on a color matching set and data on differences in the creator's pottery skill levels, performing layered processing based on differences in skill levels, and classifying the guidance content according to operational difficulty and visual presentation effect in combination with a user feedback classification table to obtain a sculpture guidance framework suitable for different skill levels.

7. The safe intelligent assistance system for fiber art color recognition and matching according to claim 1, characterized in that: The user interaction data acquisition module includes a text analysis unit and a behavior record processing unit, which are respectively used to perform semantic analysis on the natural language description in the input information and to extract behavior patterns from the operation trajectory.

8. The safe intelligent assistance system for fiber art color recognition and matching according to claim 1, characterized in that: The dynamic emotion update mechanism in the guidance framework generation module includes an emotion recognition model and a feedback response adjustment module, which is used to dynamically adjust the guidance strategy based on changes in user language or emotional characteristics in interaction.

9. The safe intelligent assistance system for fiber art color recognition and matching according to claim 1, characterized in that: In the visual effect mapping module, the visual presentation correction rule includes at least one of a color contrast balance rule, a texture consistency mapping rule, or a composition ratio adjustment rule.

10. The safe intelligent auxiliary system for fiber art color recognition and matching according to claim 1, characterized in that: The deviation analysis and optimization module includes: a deviation index evaluator and a result correction submodule. The deviation index evaluator is used to locate the deviation generation link, and the correction submodule is used to adjust parameters according to a preset number of iterations.

Images