Fusion semantic driven ceramic handicraft ai exhibition system

Abstract

The application discloses a fusion semantic driven ceramic handicraft AI exhibition system and relates to the field of virtual-real interaction, comprising: an analysis module, which is used for receiving the natural language description of ceramic handicraft exhibition input by a user, extracting core semantic elements therein, and generating a standardized exhibition demand semantic graph; and a mapping module, which is used for establishing a mapping relationship between semantic elements and ceramic culture symbols and handicraft intangible cultural heritage elements based on the exhibition demand semantic graph, and outputting a cultural element set adapted to the exhibition theme; the application can accurately capture the core semantics of the natural language demand related to ceramic handicraft exhibition, deeply connect ceramic culture symbols and intangible cultural heritage elements, generate digitalized decorative resources that retain core cultural connotations and can be flexibly adjusted, realize spatial accurate adaptation, time sequence synchronous echo and process logic fitting of process behavior and decorative presentation, and guarantee the cultural accuracy and process rationality of the exhibition content through multidimensional verification.

Description

Technical Field

[0001] This invention relates to the field of virtual-real interaction technology, specifically to a semantically driven AI-powered ceramic handicraft exhibition system. Background Technology

[0002] Handcrafted ceramics use natural clay as raw material. After selecting materials and kneading to remove impurities, the clay is shaped by throwing, hand-shaping, or printing. After drying, it is glazed (by pouring, brushing, spraying, etc.) and then fired in a kiln at a high temperature of 800-1300℃. The process utilizes the reaction of raw minerals and the melting of glaze to form a dense texture, unique glaze color, and wear resistance.

[0003] Patent application number 202510405129.9 discloses an AI-based VR display system, which aims to solve the problem that "when a user uses an AI-based VR display system, they want to view the natural lighting conditions of a room. Due to the diversity of natural language, the user may express this need in multiple ways, but the user's intention is to see the effect of the room under natural light. However, the user's input may be vague or ambiguous, causing the system to be unable to accurately understand the customer's needs. This may lead to cognitive confusion, resulting in the system failing to provide the view the user expects or providing incorrect answers."

[0004] However, for the scenario of handcrafted ceramics, existing technologies have key problems such as the disconnect between behavior and pattern generation, the inability to match the display sequence with cultural elements, and the difficulty in providing real-time feedback on user input. This would improve the accuracy of expression, generation flexibility, and interactive responsiveness of traditional handcrafted ceramics in a virtual environment.

[0005] Therefore, there is an urgent need for a semantically driven AI-powered ceramic handicraft exhibition system. Summary of the Invention

[0006] In view of the above-mentioned shortcomings of the existing technology, the present invention provides a semantically driven AI exhibition system for ceramic handicrafts, which can effectively solve the problems of the existing technology.

[0007] To achieve the above objectives, the present invention is implemented through the following technical solutions; This invention discloses a semantically driven AI-powered ceramic handicraft performance system, comprising: The parsing module is used to receive natural language descriptions related to ceramic handicraft exhibitions input by users, extract the core semantic elements, and generate a standardized semantic graph of exhibition requirements. The mapping module is used to establish the mapping relationship between semantic elements and ceramic cultural symbols and intangible cultural heritage elements based on the semantic graph of exhibition and performance needs, and output a set of cultural elements that are adapted to the exhibition and performance theme. The generation module is used to traverse the set of cultural elements, generate digital patterns of ceramic decorations that fit the set, and create a dynamically adjustable pattern resource library. The fusion module is used to receive digital representations of process behaviors and decorative resource libraries, establish a correlation mapping relationship between the two, and fuse them to generate a dataset of ceramic handicraft exhibition content. The scheduling module is used to perform time-series planning on the fused performance content data according to the presentation logic in the demand semantic graph, and generate collaborative scheduling instructions for process behavior and pattern presentation. The rendering module is used to respond to scheduling instructions, construct virtual scenes for ceramic handicraft exhibitions, and load exhibition content data to complete dynamic rendering synchronously.

[0008] Furthermore, the core semantic elements extracted by the parsing module include four categories: exhibition theme keywords, craft type limitations, presentation style requirements, and cultural connotation orientation. The standardized exhibition demand semantic graph is constructed using semantic element subjects, relationships, and attribute constraints triples, with semantic confidence attached to each node.

[0009] Furthermore, the parsing module supports dynamic expansion of core semantic elements. When receiving new natural language descriptions, it identifies the types of uncovered elements through semantic similarity comparison, synchronously adds them to the core element set, and updates the semantic graph triplet association relationships.

[0010] Furthermore, the mapping module establishes mapping relationships based on two-dimensional rules: connotation matching and application scenario adaptation. Ceramic cultural symbols are divided into three categories: objects, patterns, and folk symbols. Craft intangible cultural heritage elements are classified according to the raw material preparation, shaping, decoration, and firing process. The mapping module calculates the matching degree scores between semantic elements and various cultural elements, and selects elements that meet the preset threshold to form a cultural element set.

[0011] Furthermore, in the stage of generating digital patterns of ceramic decorations, the generation module extracts the visual and structural features of each element in the cultural element set, and then completes the construction according to the feature recombination logic. The feature recombination prioritizes the preservation of cultural connotations and ensures the visual recognizability of core cultural symbols. The dynamic adjustment dimensions of the patterns include pattern density, line thickness, color saturation, and element combination. The pattern resource library uses a tag indexing mechanism that includes cultural origin information, visual feature keywords, and appropriate craft types. Among them, the visual characteristics of elements include line shape, color tone, and composition logic, while the structural characteristics include the arrangement rules of elements, proportional relationships, and hierarchical relationships.

[0012] Furthermore, the digital representation of process behavior includes process action sequence data, dynamic process parameter data, and time-related data: The process action sequence data records the action trajectory, limb posture characteristics and operation priority ranking of the core operation steps, and confirms the start node, execution path and termination status of each action; The dynamic data recorder of process parameters includes real-time change curves of key process parameters such as raw material ratio, molding pressure, decoration intensity, and firing temperature, along with parameter acquisition timestamps. Time-related data uses a unified timeline to mark the timing of process actions and parameter changes, confirming the sequential logic and time interval between action initiation and parameter adjustment; The association mapping relationship established by the fusion module includes three dimensions: spatial adaptation mapping, timing synchronization mapping, and process logic mapping.

[0013] Furthermore, after the fusion module generates the performance content dataset, it verifies it through three dimensions: accuracy of cultural elements, rationality of process logic, and consistency of semantic matching. The accuracy of cultural elements is verified by comparing with the ceramic culture standard database, the rationality of process logic is verified by referring to the process specification knowledge base, and the consistency of semantic matching is verified based on the semantic graph of performance requirements. If the verification fails, a linkage correction mechanism is triggered to optimize the mapping relationship and adjust the pattern generation parameters, and the correction is repeated until the dataset meets the requirements of cultural accuracy and process rationality.

[0014] Furthermore, the timing planning of the scheduling module aims at the process flow logic and visual presentation priority in the semantic graph of performance requirements: First, the integrated performance content data is divided into several independent data units according to the process steps. Then, based on the semantic association strength and presentation duration requirements of each data unit, the start order, runtime and connection method of each unit are determined to construct a complete time-series scheduling sequence. The scheduling module includes collaborative scheduling instructions such as process behavior execution timing parameters, pattern presentation trigger conditions, and data synchronization transmission instructions. When different data units present conflicting requirements, they are first coordinated according to semantic confidence priority, and then processed according to process logic priority when the semantic confidence is consistent.

[0015] Furthermore, the rendering module constructs a virtual scene based on the real operation scene of ceramic handicraft, and incorporates cultural atmosphere elements corresponding to the theme. The core construction elements include spatial dimension, light and shadow simulation, material restoration, and scene interaction logic. Among them, dynamic rendering adjusts the rendering resolution, frame rate and level of detail according to the terminal performance and the requirements of perspective switching.

[0016] Furthermore, the parsing module is interconnected with a mapping module via a wireless network, the mapping module is interconnected with a generation module via a wireless network, the generation module is interconnected with a fusion module via a wireless network, the fusion module is interconnected with a scheduling module via a wireless network, and the scheduling module is interconnected with a rendering module via a wireless network.

[0017] Compared with the known prior art, the technical solution provided by this invention has the following beneficial effects: This invention can accurately capture the core semantics of natural language requirements related to ceramic handicraft performances, deeply connect ceramic cultural symbols and intangible cultural heritage elements, generate digital decorative resources that retain core cultural connotations and can be flexibly adjusted, achieve precise spatial adaptation, temporal synchronization and consistency of craft behavior and decorative presentation, and ensure the cultural accuracy and craft rationality of the performance content through multi-dimensional verification. Meanwhile, a virtual exhibition environment is constructed based on real operating scenarios, dynamically adapting to terminal performance and perspective switching requirements. It supports dynamic expansion of demand elements and optimization based on historical feedback, allowing the exhibition to inherit the essence of traditional craft culture while having a smooth and natural presentation effect. At the same time, it enhances the interactivity and diversification of the exhibition, effectively promoting the display and promotion of ceramic handicrafts. Attached Figure Description

[0018] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the accompanying drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are merely some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without any creative effort.

[0019] Figure 1 A schematic diagram of the structure of a semantically driven AI-powered ceramic handicraft exhibition system. Detailed Implementation

[0020] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative effort are within the scope of protection of the present invention.

[0021] The present invention will be further described below with reference to embodiments.

[0022] Example: This embodiment integrates a semantically driven AI-powered ceramic handicraft exhibition system, such as... Figure 1 As shown, it includes: The parsing module is used to receive natural language descriptions related to ceramic handicraft exhibitions input by users, extract the core semantic elements, and generate a standardized semantic graph of exhibition requirements. The core semantic elements extracted by the parsing module include four categories: exhibition theme keywords, craft type limitations, presentation style requirements, and cultural connotation orientation. The extraction is completed through semantic word segmentation, dependency parsing analysis, and core element weight ranking. The standardized exhibition demand semantic graph is constructed with semantic element subject, relationship, and attribute constraint triplet, with semantic confidence attached to each node. Among them, semantic confidence is calculated by combining the frequency of occurrence of elements in natural language descriptions with the strength of semantic association; The parsing module supports dynamic expansion of core semantic elements. When receiving new natural language descriptions, it identifies the types of elements that are not covered by semantic similarity comparison, and simultaneously adds them to the core element set and updates the semantic graph triplet association relationship. Furthermore, the semantic graph can optimize the element weight allocation and association strength determination rules based on the mapping feedback results of historical performances. The mapping module is used to establish the mapping relationship between semantic elements and ceramic cultural symbols and intangible cultural heritage elements based on the semantic graph of exhibition and performance needs, and output a set of cultural elements that are adapted to the exhibition and performance theme. The mapping module establishes mapping relationships based on two-dimensional rules: connotation matching and application scenario adaptation. Ceramic cultural symbols are divided into three categories: objects, patterns, and folk customs. Craft intangible cultural heritage elements are classified according to the raw material preparation, shaping, decoration, and firing process. The mapping module calculates the matching degree scores between semantic elements and various cultural elements, and selects elements that meet the preset threshold to form a cultural element set. The generation module is used to traverse the set of cultural elements, generate digital patterns of ceramic decorations that fit the set, and create a dynamically adjustable pattern resource library. In the stage of generating digital patterns of ceramic decorations, the generation module extracts the visual and structural features of each element in the cultural element set, and then completes the construction according to the feature recombination logic. The feature recombination prioritizes the preservation of cultural connotations and ensures the visual recognizability of core cultural symbols. The dynamic adjustment dimensions of the patterns include pattern density, line thickness, color saturation, and element combination. The pattern resource library supports quick retrieval and calling by tags through a tag indexing mechanism containing cultural origin information, visual feature keywords, and adapted craft types. The tags are dynamically supplemented according to the new pattern types. Among them, the visual features of the elements include line shape, color tone, and composition logic, while the structural features include the arrangement rules of the elements, proportional relationships, and hierarchical relationships. The fusion module is used to receive digital representations of process behaviors and decorative resource libraries, establish a correlation mapping relationship between the two, and fuse them to generate a dataset of ceramic handicraft exhibition content. Digital representation of process behavior includes process action sequence data, dynamic process parameter data, and time-related data: The process action sequence data records the action trajectory, limb posture characteristics and operation priority ranking of the core operation steps, and confirms the start node, execution path and termination status of each action; The dynamic data recorder of process parameters includes real-time change curves of key process parameters such as raw material ratio, molding pressure, decoration intensity, and firing temperature, along with parameter acquisition timestamps. Time-related data uses a unified timeline to mark the timing of process actions and parameter changes, confirming the sequential logic and time interval between action initiation and parameter adjustment; The association mapping relationships established by the fusion module include three dimensions: spatial adaptation mapping, timing synchronization mapping, and process logic mapping. Spatial adaptation mapping, based on the coordinate positioning rules of the process operation area, accurately matches the pattern presentation area with the physical space range of the corresponding process operation; temporal synchronization mapping, through a timestamp alignment mechanism, keeps the rhythm of pattern generation synchronized with the execution progress of process actions, ensuring that pattern changes and process operation nodes correspond precisely; process logic mapping, combined with the technical principles of ceramic handicrafts, establishes a correspondence between pattern features and process realization conditions, ensuring that the pattern presentation conforms to the objective laws of the process. Among them, the decorative features include color and texture, and the technical conditions include firing temperature and glaze thickness; After the fusion module generates the performance content dataset, it is verified through three dimensions: accuracy of cultural elements, rationality of process logic, and consistency of semantic matching. The accuracy of cultural elements is verified by comparing with the ceramic culture standard database, the rationality of process logic is verified by referring to the process specification knowledge base, and the consistency of semantic matching is verified based on the semantic graph of performance requirements. When the verification fails, a linkage correction mechanism is triggered to optimize the mapping relationship and adjust the pattern generation parameters, and the correction is repeated until the dataset meets the requirements of cultural accuracy and process rationality. The scheduling module is used to perform time-series planning on the fused performance content data according to the presentation logic in the demand semantic graph, and generate collaborative scheduling instructions for process behavior and pattern presentation. The timing planning of the scheduling module aims at the process flow logic and visual presentation priority in the semantic graph of performance requirements: First, the integrated performance content data is divided into several independent data units according to the process steps. Then, based on the semantic association strength and presentation duration requirements of each data unit, the start order, runtime and connection method of each unit are determined to construct a complete time-series scheduling sequence. The scheduling module includes collaborative scheduling instructions such as process behavior execution timing parameters, pattern presentation trigger conditions, and data synchronization transmission instructions. When different data units present conflicting requirements, they are first coordinated according to semantic confidence priority, and then processed according to process logic priority when the semantic confidence is consistent. The rendering module is used to respond to scheduling instructions, construct a virtual scene for the ceramic handicraft exhibition, and load the exhibition content data to complete dynamic rendering synchronously. The rendering module constructs virtual scenes based on real ceramic handicraft operations, incorporating cultural atmosphere elements corresponding to the theme. The core construction elements include spatial dimension, lighting simulation, material reproduction, and scene interaction logic. Among them, dynamic rendering adjusts the rendering resolution, frame rate and level of detail according to the terminal performance and the requirements of perspective switching; The parsing module interacts with the mapping module via a wireless network. The mapping module interacts with the generation module via a wireless network. The generation module interacts with the fusion module via a wireless network. The fusion module interacts with the scheduling module via a wireless network. The scheduling module interacts with the rendering module via a wireless network.

[0023] In the above embodiments, during system operation, the parsing module receives the natural language description related to the ceramic handicraft performance input by the user, extracts the core semantic elements, and generates a standardized semantic graph of performance requirements. The mapping module then runs based on the semantic graph of performance requirements to establish a mapping relationship between semantic elements and ceramic cultural symbols and intangible cultural heritage elements of crafts, and outputs a set of cultural elements adapted to the performance theme. The generation module further traverses the set of cultural elements to generate digital patterns of ceramic decorations adapted to the set and creates a dynamically adjustable pattern resource library. The fusion module then receives the digital representation of craft behavior and the pattern resource library, establishes the association mapping relationship between the two, and merges them to generate a dataset of ceramic handicraft performance content. The scheduling module performs time-series planning on the merged performance content data according to the presentation logic in the requirement semantic graph, and generates a collaborative scheduling instruction for craft behavior and pattern presentation. Finally, the rendering module responds to the scheduling instruction, constructs a virtual scene of the ceramic handicraft performance, loads the performance content data, and synchronously completes dynamic rendering.

[0024] It should be noted that: Regarding the semantic parsing process: The semantic similarity comparison and semantic confidence calculation mentioned in the parsing module can be supplemented with specific technical implementation paths: Semantic similarity comparison adopts a sentence vector matching algorithm based on the BERT pre-trained model. By mapping the newly added natural language description with the core element set, the cosine similarity threshold is calculated (the default value is set to 0.75, which can be adjusted by the user according to the scenario); the semantic confidence calculation adopts a weighted summation formula of "occurrence frequency weight (accounting for 40%) + semantic association strength weight (accounting for 60%)". The semantic association strength is quantified by constructing an association matrix through dependency parsing results, and the historical performance feedback will affect the element weight update with an exponential decay model (decay coefficient 0.8), ensuring that the dynamic optimization of semantic capture is more operable.

[0025] Regarding the mapping module threshold and database: The preset matching threshold of the mapping module is not a fixed value, but dynamically adapted based on the type of exhibition and performance scenario: the threshold is set to 0.8 for cultural display scenarios, 0.7 for commercial exhibition and performance scenarios, and 0.85 for educational and popular science scenarios. Users can customize and adjust this value through the system backend. The ceramic culture standard database comes from the public dataset of the National Intangible Cultural Heritage Protection Center, the digital ceramic resource database of the Palace Museum, and authorized materials from local ceramic craft inheritance institutions. The database is updated quarterly, and new cultural elements must undergo three rounds of expert review (one round each for ceramic culture scholars, intangible cultural heritage inheritors, and craft technology experts) before they can be included, ensuring the authority and accuracy of the cultural elements.

[0026] Regarding the generation module parameters and indexing mechanism: In the generation module, the parameter ranges for each dimension of dynamic pattern adjustment need to be clearly defined: the pattern density adjustment range is 5-50 patterns / square decimeter; the line thickness supports continuous adjustment from 0.1-2.0mm; the color saturation is adjusted according to the 0-100% gradient of the saturation channel in the RGB color space; the element combination method provides four basic modes: "symmetrical arrangement, random distribution, hierarchical overlay, and progressive fusion," as well as a custom combination interface; the tag indexing mechanism adopts a three-level index structure of "cultural origin - visual features - craft adaptation," with the underlying layer based on Elasticsearch to achieve millisecond-level retrieval. New pattern tags need to be automatically extracted by the feature extraction model (CNN convolutional neural network) and then manually labeled and verified before being added to the database to ensure retrieval accuracy.

[0027] Regarding the data acquisition and verification standards for the fusion module: The data acquisition equipment for the digital representation of process behavior must be clearly defined: process action sequence data is acquired jointly by a 1080P high-definition motion capture camera (sampling rate 60fps) and an inertial sensor (sampling rate 100Hz); dynamic data of process parameters are acquired in real time by high-precision sensors (raw material ratio error ±0.1%, temperature error ±5℃); the specific judgment criteria for multi-dimensional verification are: the accuracy of cultural elements must meet the requirements of "core element matching rate 100% and secondary element matching rate ≥90%"; the rationality of process logic must comply with the relevant requirements of the "Ceramic Process Technology Specification" (GB / T32993-2016); the similarity threshold of semantic matching consistency is ≥0.8; when the verification fails, the linkage correction mechanism cycles through the process of "mapping relationship optimization → pattern parameter adjustment → secondary verification", with a single cycle period of ≤3 seconds and a maximum of 5 cycles (if it still fails, manual intervention will be triggered).

[0028] Regarding the scheduling module algorithm and conflict handling: The timing planning of the scheduling module adopts a dynamic programming algorithm, with the objective function being "process logic priority (70% weight) + visual presentation priority (30% weight)". Constraints include the minimum presentation duration of each data unit (not less than 2 seconds) and the connection interval (adjustable from 0.5 to 1.5 seconds). Further details are needed for handling data unit conflicts: When semantic confidence conflicts with process logic priority, if the conflicting data unit involves core cultural elements (determined by node confidence ≥ 0.9 in the semantic graph), the process logic priority takes precedence; if it is a non-core element, the semantic confidence priority is applied. The conflict handling results will be recorded in the system log for subsequent algorithm optimization.

[0029] Regarding rendering module terminal adaptation and parameters: The rendering module supports various terminal types, including VR devices (compatible with mainstream models such as Oculus Quest 2 and above, Pico 4, etc.), PCs (Windows 10 and above, macOS 12 and above), and mobile devices (Android 11 and above, iOS 14 and above). The minimum configuration requirements for different terminals are as follows: PCs require a CPU i5-10400 or higher, a graphics card GTX 1650 or higher, and 8GB or more of RAM; mobile devices require a Snapdragon 870 or higher processor and 6GB or more of RAM. The dynamic rendering resolution adjustment range is 720P-4K, and the frame rate supports adaptive switching from 30fps to 60fps. The detail level is divided into three levels: "Basic," "Standard," and "High Definition," corresponding to 500,000, 1.5 million, and 3 million triangles, respectively, ensuring a smooth rendering effect on different terminals.

[0030] Regarding copyright compliance and user feedback: All ceramic cultural symbols and intangible cultural heritage elements used in the system have been authorized. Public domain cultural elements are directly included in the database, while copyrighted elements are used through authorization agreements signed with cultural heritage institutions and intangible cultural heritage inheritors. The authorization information is stored in the database along with the elements, making it traceable and verifiable. The user feedback mechanism adopts a "post-performance rating + tag-based evaluation" model. Users can rate the accuracy of the culture, the presentation effect, and the interactive experience from 1 to 5 points, and select specific evaluation tags (such as "mismatch between pattern and craftsmanship" or "deviation in the presentation of cultural elements"). Feedback data is statistically analyzed monthly to optimize mapping rules, pattern generation parameters, and scheduling logic, forming a closed-loop iteration of "use-feedback-optimization".

[0031] In summary, the system in the above embodiments can accurately capture the core semantics of natural language requirements related to ceramic handicraft performances, deeply connect ceramic cultural symbols and intangible cultural heritage elements, generate digital decorative resources that retain core cultural connotations and can be flexibly adjusted, achieve precise spatial adaptation, temporal synchronization, and logical consistency between craft behaviors and decorative presentations, ensure the cultural accuracy and craft rationality of the performance content through multi-dimensional verification, and construct a virtual performance environment based on real operation scenarios. It dynamically adapts to terminal performance and perspective switching requirements, supports dynamic expansion of requirement elements and optimization based on historical feedback, so that the performances not only inherit the essence of traditional craft culture but also have a smooth and natural presentation effect. At the same time, it enhances the interactivity and diversified adaptability of the performances, effectively promoting the display and promotion of ceramic handicrafts.

[0032] The above embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions will not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A semantically driven AI-powered ceramic handicraft exhibition system, characterized in that: include: The parsing module is used to receive natural language descriptions related to ceramic handicraft exhibitions input by users, extract the core semantic elements, and generate a standardized semantic graph of exhibition requirements. The mapping module is used to establish the mapping relationship between semantic elements and ceramic cultural symbols and intangible cultural heritage elements based on the semantic graph of exhibition and performance needs, and output a set of cultural elements that are adapted to the exhibition and performance theme. The generation module is used to traverse the set of cultural elements, generate digital patterns of ceramic decorations that fit the set, and create a dynamically adjustable pattern resource library. The fusion module is used to receive digital representations of process behaviors and decorative resource libraries, establish a correlation mapping relationship between the two, and fuse them to generate a dataset of ceramic handicraft exhibition content. The scheduling module is used to perform time-series planning on the fused performance content data according to the presentation logic in the demand semantic graph, and generate collaborative scheduling instructions for process behavior and pattern presentation. The rendering module is used to respond to scheduling instructions, construct virtual scenes for ceramic handicraft exhibitions, and load exhibition content data to complete dynamic rendering synchronously.

2. The AI-powered ceramic handicraft exhibition system based on semantic-driven technology according to claim 1, characterized in that, The core semantic elements extracted by the parsing module include four categories: exhibition theme keywords, craft type limitations, presentation style requirements, and cultural connotation orientation. The standardized exhibition demand semantic map is constructed using semantic element subjects, relationships, and attribute constraints triples, with semantic confidence attached to each node.

3. The AI-powered ceramic handicraft exhibition system based on semantic-driven technology according to claim 1, characterized in that, The parsing module supports dynamic expansion of core semantic elements. When receiving new natural language descriptions, it identifies the types of elements that are not covered by semantic similarity comparison, and synchronously adds them to the core element set and updates the semantic graph triplet association relationship.

4. The AI-powered ceramic handicraft exhibition system based on semantic-driven technology according to claim 1, characterized in that, The mapping module establishes mapping relationships based on two-dimensional rules: connotation matching and application scenario adaptation. Ceramic cultural symbols are divided into three categories: objects, patterns, and folk symbols. Craft intangible cultural heritage elements are classified according to the raw material preparation, shaping, decoration, and firing process. The mapping module calculates the matching degree scores between semantic elements and various cultural elements, and selects elements that meet the preset threshold to form a cultural element set.

5. The AI-powered ceramic handicraft exhibition system based on semantic-driven technology according to claim 1, characterized in that, In the stage of generating digital patterns of ceramic decorations, the generation module extracts the visual and structural features of each element in the cultural element set, and then completes the construction according to the feature recombination logic. The feature recombination prioritizes the preservation of cultural connotations and ensures the visual recognizability of core cultural symbols. The dynamic adjustment dimensions of the patterns include pattern density, line thickness, color saturation, and element combination. The pattern resource library uses a tag indexing mechanism that includes cultural origin information, visual feature keywords, and appropriate craft types. Among them, the visual characteristics of elements include line shape, color tone, and composition logic, while the structural characteristics include the arrangement rules of elements, proportional relationships, and hierarchical relationships.

6. The AI-powered ceramic handicraft exhibition system based on semantic-driven technology according to claim 1, characterized in that, The digital representation of process behavior includes process action sequence data, dynamic process parameter data, and time-related data: The process action sequence data records the action trajectory, limb posture characteristics and operation priority ranking of the core operation steps, and confirms the start node, execution path and termination status of each action; The dynamic data recorder of process parameters includes real-time change curves of key process parameters such as raw material ratio, molding pressure, decoration intensity, and firing temperature, along with parameter acquisition timestamps. Time-related data uses a unified timeline to mark the timing of process actions and parameter changes, confirming the sequential logic and time interval between action initiation and parameter adjustment; The association mapping relationship established by the fusion module includes three dimensions: spatial adaptation mapping, timing synchronization mapping, and process logic mapping.

7. The AI-powered ceramic handicraft exhibition system based on semantic-driven technology according to claim 6, characterized in that, After the fusion module generates the performance content dataset, it verifies it through three dimensions: accuracy of cultural elements, rationality of process logic, and consistency of semantic matching. The accuracy of cultural elements is verified by comparing with the ceramic culture standard database, the rationality of process logic is verified by referring to the process specification knowledge base, and the consistency of semantic matching is verified based on the semantic graph of performance requirements. If the verification fails, a linkage correction mechanism is triggered to optimize the mapping relationship and adjust the pattern generation parameters, and the correction is repeated until the dataset meets the requirements of cultural accuracy and process rationality.

8. The AI-powered ceramic handicraft exhibition system based on semantic-driven technology according to claim 1, characterized in that, The timing planning of the scheduling module aims at the process flow logic and visual presentation priority in the semantic graph of performance requirements: First, the integrated performance content data is divided into several independent data units according to the process steps. Then, based on the semantic association strength and presentation duration requirements of each data unit, the start order, runtime and connection method of each unit are determined to construct a complete time-series scheduling sequence. The scheduling module includes collaborative scheduling instructions such as process behavior execution timing parameters, pattern presentation trigger conditions, and data synchronization transmission instructions. When different data units present conflicting requirements, they are first coordinated according to semantic confidence priority, and then processed according to process logic priority when the semantic confidence is consistent.

9. The AI-powered ceramic handicraft exhibition system based on semantic-driven technology according to claim 1, characterized in that, The rendering module constructs a virtual scene based on the real operation scene of ceramic handicraft, and incorporates cultural atmosphere elements corresponding to the theme. The core construction elements include spatial dimension, light and shadow simulation, material reproduction, and scene interaction logic. Among them, dynamic rendering adjusts the rendering resolution, frame rate and level of detail according to the terminal performance and the requirements of perspective switching.

10. The AI-powered ceramic handicraft exhibition system based on semantic-driven technology according to claim 1, characterized in that, The parsing module is interconnected with the mapping module via a wireless network. The mapping module is interconnected with the generation module via a wireless network. The generation module is interconnected with the fusion module via a wireless network. The fusion module is interconnected with the scheduling module via a wireless network. The scheduling module is interconnected with the rendering module via a wireless network.

Images