Semantic association and recommendation method for jade pendant parameterized design based on knowledge graph

Abstract

The application relates to the technical field of knowledge graphs, and discloses a jade pendant parameterized design semantic association and recommendation method based on a knowledge graph, which comprises the following steps: constructing a multi-dimensional design knowledge graph of a jade pendant; configuring a multi-source semantic association subgraph in the multi-dimensional design knowledge graph, and establishing a semantic reasoning link from the multi-source semantic association subgraph to a design parameter node; parsing a culture symbol indication and a visual style combination corresponding to the design parameter node in the semantic reasoning link; and generating a parameterized design recommendation scheme of the jade pendant by using the semantic consistency degree of the culture symbol indication and the coordination index of the visual style combination. The application can improve the cultural accuracy and visual harmony of jade pendant design results.

Description

Technical Field

[0001] This invention relates to a method for semantic association and recommendation of jade pendant parametric design based on knowledge graph, belonging to the field of knowledge graph technology. Background Technology

[0002] With the revival of traditional culture and the rise in personalized consumption demands, jade pendants, as traditional ornaments that carry cultural connotations and aesthetic values, are gradually becoming more customized, intelligent, and semantic in their design. Under this trend, the parametric design semantic association and recommendation method for jade pendants has emerged, aiming to provide designers and users with more efficient and intelligent design assistance and decision support, so as to improve design efficiency, accuracy of cultural expression, and user satisfaction.

[0003] Existing parametric design systems for jade pendants mainly rely on preset geometric constraints and basic process rules to initially identify fundamental problems such as exceeding size limits, interference conflicts, or insufficient material strength during the parametric design process. While this can ensure the technical feasibility of the design model in a specific dimension, its judgment logic is limited to the physical level and lacks an understanding of the connection between deep cultural semantics and complex styles. This can easily lead to problems of cultural inaccuracies and visual style combination disharmony in the verification process of parametric design of jade pendants. Summary of the Invention

[0004] This invention provides a method for semantic association and recommendation of jade pendant parametric design based on knowledge graph, the main purpose of which is to improve the cultural accuracy and visual harmony of jade pendant design results.

[0005] To achieve the above objectives, this invention provides a method for semantic association and recommendation of jade pendant parametric design based on knowledge graphs, the method comprising: The design parameters, cultural semantic elements, and style rules of the jade pendant are obtained to construct a multi-dimensional design knowledge graph of the jade pendant. Configure a multi-source semantic association subgraph in the multi-dimensional design knowledge graph, and establish a semantic reasoning link from the multi-source semantic association subgraph to the design parameter node; The cultural symbolic references and visual style combinations corresponding to the design parameter nodes are parsed out in the semantic reasoning chain. Calculate the semantic consistency of the cultural symbol indicators and the coordination index of the visual style combination, and generate a parametric design recommendation scheme for the jade pendant based on the semantic consistency and the coordination index.

[0006] Optionally, the cultural symbolic references corresponding to the design parameter nodes are parsed out in the semantic reasoning chain, including: Identify the transmission path from the design parameter node to the cultural symbol entity from the semantic reasoning link; Using the node type and edge relationship attributes of the traditional path, an initial symbol feature vector of the end cultural symbol entity in the transmission path is generated; Calculate the semantic association matrix between different initial symbol feature vectors, and reconstruct the optimized symbol feature group of the initial symbol feature vectors using the semantic association matrix; Based on the optimized symbol feature group, cultural symbol indicators corresponding to the design parameter nodes are generated.

[0007] Optionally, the optimized symbol feature set of the initial symbol feature vector is reconstructed using the semantic relevance matrix, including: The semantic association matrix is ​​decomposed into eigenvalues ​​to obtain a set of feature vectors; Based on a preset feature value threshold, a subset of the main feature vectors in the feature vector set is selected; Using the subset of principal feature vectors, construct the projection transformation matrix corresponding to the initial symbol feature vector; The optimized symbol feature set of the initial symbol feature vector is reconstructed using the projection transformation matrix.

[0008] Optionally, parsing the visual style combination corresponding to the design parameter node in the semantic reasoning chain includes: Extract the visual style feature vector corresponding to the design parameter node through the style propagation path in the semantic reasoning link; The visual style feature vector is compared with a preset style rule library to determine the visual style coordination degree and compositional relationship description corresponding to the design parameter node; Based on the visual style coordination degree and the compositional relationship description, the visual style combination corresponding to the design parameter node is parsed out.

[0009] Optionally, establishing the semantic reasoning link from the multi-source semantic association subgraph to the design parameter node includes: Construct an initial semantic connection network between semantic nodes and design parameter nodes in the multi-source semantic association subgraph; The propagation path from the semantic node to the design parameter node is parsed through the initial semantic connection network. The core semantic transmission path is selected from the transmission paths, and the core semantic transmission path is used as the semantic reasoning link from the multi-source semantic association subgraph to the design parameter node.

[0010] Optionally, core semantic transmission paths are selected from the transmission paths, including: The structural complexity of each of the transmission paths is evaluated based on the distribution characteristics of the number of nodes and edge types in the transmission path. Calculate the total path weight of each of the transmission paths, and combine it with the structural complexity to calculate the transmission efficiency index of each of the transmission paths; The conduction efficiency index is compared with a preset efficiency threshold, and target efficiency indices that are higher than the efficiency threshold are selected. Based on the target efficiency index, the core semantic transmission path is selected from the transmission paths.

[0011] Optionally, the multi-source semantic association subgraph includes a process constraint subgraph, a cultural symbol subgraph, and a user preference subgraph, and the multi-source semantic association subgraph is collaboratively parsed in the semantic reasoning link.

[0012] Optionally, the design parameters, cultural semantic elements, and style rules of the jade pendant are obtained to construct a multi-dimensional design knowledge graph of the jade pendant, including: Based on the style rules, the structural relationships of the jade pendant design parameters are categorized to obtain a set of parameter topological relationships; Based on the parameter topology relationship set and the cultural semantic elements, a core semantic constraint framework for the jade pendant design parameters is established. Using the core semantic constraint framework, key parameter features are extracted from the parameter structure classification set; Based on the key parameter features, a multidimensional design knowledge graph corresponding to the jade pendant is constructed.

[0013] Optionally, based on the parameter topology relationship set and the cultural semantic elements, a core semantic constraint framework for the jade pendant design parameters is established, including: The semantic mapping relationship between the parameter topology relationship set and the cultural semantic elements is parsed out, and the hierarchical constraint rule set of the jade pendant design parameters is generated by using the type weight of the semantic mapping relationship. Perform a logical consistency check on the hierarchical constraint rule set to obtain the target constraint rule set; The value space of the jade pendant design parameters is associated and mapped with the target constraint rule set to obtain the association mapping result; Based on the association mapping results, a core semantic constraint framework for the jade pendant design parameters is established.

[0014] Optionally, based on the semantic consistency degree and the coordination index, a parameterized design recommendation scheme for the jade pendant is generated, including: Set the optimized weight thresholds for the semantic consistency degree and the coordination index; Within the feasible domain of the parametric design of the jade pendant, a set of candidate parameters that satisfy the optimization weight threshold is searched. Extract the differential parameter combinations from the candidate parameter set; Based on the differentiated parameter combinations, a parameterized design recommendation scheme for the jade pendant is generated.

[0015] Compared to the problems described in the background art, the embodiments of the present invention, by acquiring jade pendant design parameters, cultural semantic elements, and style rules, construct a multi-dimensional design knowledge graph of the jade pendant. This allows for the complete establishment of a computable association model between parametric design and cultural semantics and stylistic aesthetics, achieving a structured mapping of the complex semantic relationship between design intent and parameter expression. Furthermore, by establishing a semantic reasoning link from the multi-source semantic association subgraph to the design parameter nodes, the embodiments of the present invention can transform subjective cultural aesthetic judgments into a traceable and verifiable graph structure reasoning process. This systematically solves the dual problems of cultural inaccuracy and visual style combination disharmony in the parametric design of jade pendants. The embodiments of the present invention also parse out the cultural symbol indicators and visual style combinations corresponding to the design parameter nodes in the semantic reasoning link, enabling automated reverse mapping from parametric data to cultural semantics and aesthetic features. This allows the parametric design system of jade pendants to not only positively constrain... The design process also allows for reverse semantic interpretation and aesthetic evaluation of any parameter combination, providing an interpretable analytical basis for design verification. Furthermore, by calculating the semantic consistency of the cultural symbol indicators and the coordination index of the visual style combinations, the jade pendant parametric design system can automatically and comprehensively evaluate any parametric design scheme, accurately identifying the specific type and degree of cultural semantic deviation and visual compositional disharmony, thus providing clear and operable technical guidance for design optimization. Finally, based on the semantic consistency and coordination index, the invention generates parametric design recommendation schemes for the jade pendant, automatically correcting design defects such as cultural inaccuracies and visual disharmony, and providing differentiated recommendation scheme sequences according to different design preferences. This transforms the experience-dependent manual adjustment process into an interpretable and reproducible automated decision-making process, significantly improving design efficiency and result quality. Therefore, the knowledge graph-based semantic association and recommendation method for jade pendant parametric design provided by this invention can improve the cultural accuracy and visual harmony of jade pendant design results. Attached Figure Description

[0016] Figure 1 This is a flowchart illustrating a knowledge graph-based method for semantic association and recommendation in the parametric design of jade pendants, as provided in an embodiment of the present invention. Figure 2 A schematic diagram of a module for implementing a knowledge graph-based semantic association and recommendation system for parametric design of jade pendants, provided as an embodiment of the present invention; Figure 3 This is a schematic diagram of a computer device for a knowledge graph-based method for the semantic association and recommendation of jade pendants in parametric design.

[0017] The objectives, features, and advantages of this invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0018] It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.

[0019] This application provides a knowledge graph-based method for semantic association and recommendation in the parametric design of jade pendants. The execution entity of this knowledge graph-based method includes, but is not limited to, at least one electronic device that can be configured to execute the method provided in this application, such as a server or a terminal. In other words, the knowledge graph-based method can be executed by software or hardware installed on a terminal device or a server device. The server includes, but is not limited to, a single server, a server cluster, a cloud server, or a cloud server cluster.

[0020] Reference Figure 1 The diagram shown is a flowchart illustrating a knowledge graph-based semantic association and recommendation method for parametric design of jade pendants according to an embodiment of the present invention. In this embodiment, the knowledge graph-based semantic association and recommendation method for parametric design of jade pendants includes: S1. Obtain the design parameters, cultural semantic elements, and style rules of the jade pendant to construct a multi-dimensional design knowledge graph of the jade pendant.

[0021] This invention, through obtaining jade pendant design parameters, cultural semantic elements, and style rules, constructs a multidimensional design knowledge graph of the jade pendant. This allows for the complete establishment of a computable association model between parametric design and cultural semantics and style aesthetics, achieving a structured mapping of the complex semantic relationship between design intent and parameter expression.

[0022] The design parameter nodes refer to a set of quantified variables directly defined and controlled by the computer-aided jade pendant parametric design system. For example, the coordinates of control points on the jade pendant's outline, the repetition spacing of pattern units, the width threshold of the hollowed-out area, and the radius of curvature of the surface are all design parameters. The cultural semantic elements refer to normative descriptions and symbolic definitions related to the shape, decoration, and usage of the jade pendant, extracted from historical documents, artifact illustrations, and craft classics. For example, the "grain pattern" in a jade bi symbolizes a bountiful harvest. The style rules refer to objective clauses based on formal aesthetic principles and craft traditions, used to constrain the combination relationships of visual elements. For example, the positive correlation between pattern density and the curvature of the jade pendant's outline, the area ratio range between the main pattern and the background pattern, and the carving depth range corresponding to different dynasties' styles. The multidimensional design knowledge graph refers to a heterogeneous network data structure constructed by using the design parameters, cultural semantic elements, and style rules as nodes and connecting them through semantic relationship edges.

[0023] As an embodiment of the present invention, obtaining jade pendant design parameters, cultural semantic elements, and style rules to construct a multidimensional design knowledge graph of the jade pendant includes: classifying the structural relationships of the jade pendant design parameters according to the style rules to obtain a parameter topology relationship set; establishing a core semantic constraint framework for the jade pendant design parameters based on the parameter topology relationship set and the cultural semantic elements; extracting key parameter features from the parameter structural classification set through the core semantic constraint framework; and constructing a multidimensional design knowledge graph corresponding to the jade pendant based on the key parameter features.

[0024] The structural relationship classification refers to the technical process of classifying jade pendant design parameters according to their geometric correlation, technological dependence, and functional coupling in a parametric design system. For example, boundary control point parameters controlling the outer contour of the jade pendant are classified into the shape geometry category, while carving depth and tool angle parameters are classified into the processing technology category. The parameter topology relationship set refers to a network data set reflecting the spatial structural relationships, processing sequence relationships, and logical dependencies among various design parameters. The core semantic constraint framework refers to a rule system composed of key cultural semantic elements and style rules that normatively restricts the range and combination of design parameter values. The key parameter features refer to a few core design parameters that have a decisive influence on the final form and cultural expression of the jade pendant. For example, the diameter of the central hole of the jade pendant, the coordinates of the key control points of the main pattern outline, and the material translucency parameters are all key parameter features.

[0025] Optionally, clustering analysis algorithms can be used to classify the structural relationships of the jade pendant design parameters; the multidimensional design knowledge graph corresponding to the jade pendant can be constructed using the Neo4j graph database.

[0026] As an optional embodiment of the present invention, a core semantic constraint framework for the jade pendant design parameters is established based on the parameter topology relationship set and the cultural semantic elements, including: parsing the semantic mapping relationship between the parameter topology relationship set and the cultural semantic elements, and generating a hierarchical constraint rule set for the jade pendant design parameters using the type weights of the semantic mapping relationship; performing logical consistency verification on the hierarchical constraint rule set to obtain a target constraint rule set; associating the value space of the jade pendant design parameters with the target constraint rule set to obtain an association mapping result; and establishing the core semantic constraint framework for the jade pendant design parameters based on the association mapping result.

[0027] The semantic mapping relationship refers to the interpretative correspondence established between cultural semantic elements and the set of design parameters. For example, mapping the "auspicious beast pattern" in the cultural semantic elements to the set of animal outline control points and hair texture density parameters in the design parameters; the type weight refers to the priority coefficient assigned according to the constraint category to which the semantic mapping relationship belongs, where the constraint categories include cultural heritage constraints, functional symbol constraints, and aesthetic expression constraints; the hierarchical constraint rule set refers to a multi-level rule set divided according to the strength of constraint and the scope of application, including basic process layer constraints, cultural symbol layer constraints, and style combination layer constraints; the logical consistency verification refers to the technical process of detecting and resolving contradictions or redundant relationships among the rules in the constraint rule set; the value space refers to the set of all possible values ​​of the jade pendant design parameters under the conditions of physical realizability and technological feasibility; the association mapping result refers to the quantitative matching relationship formed between the value space of the design parameters and the target constraint rule set, used to characterize the effective value range of each design parameter under the constraint conditions.

[0028] Optionally, the hierarchical constraint rule set of the jade pendant design parameters can be generated using a decision tree model; the logical consistency of the hierarchical constraint rule set can be verified by predicate logic calculus; and the value space of the jade pendant design parameters can be associated and mapped with the target constraint rule set using a constraint solver.

[0029] S2. Configure a multi-source semantic association subgraph in the multi-dimensional design knowledge graph, and establish a semantic reasoning link from the multi-source semantic association subgraph to the design parameter node.

[0030] This invention, through configuring multi-source semantic association subgraphs in the multi-dimensional design knowledge graph, can establish a complete and traceable link from cultural semantic intent to specific parametric design, providing a structured knowledge foundation for subsequent automated semantic verification and style coordination evaluation. The multi-source semantic association subgraph refers to a set of sub-network structures extracted from the multi-dimensional design knowledge graph, with a specific semantic dimension as the core, including a process constraint subgraph, a cultural symbol subgraph, and a user preference subgraph. The process constraint subgraph is used to represent the relationship between design parameter nodes and processing feasibility, the cultural symbol subgraph is used to represent the mapping relationship between design parameter nodes and traditional cultural connotations, and the user preference subgraph is used to represent the correspondence between design parameter nodes and the aesthetic preferences of the target user group.

[0031] As an embodiment of the present invention, configuring a multi-source semantic association subgraph in the multi-dimensional design knowledge graph includes: extracting process constraint entities and their corresponding first association relationships from the multi-dimensional design knowledge graph to construct a process constraint subgraph; extracting cultural symbol entities and their corresponding second association relationships from the multi-dimensional design knowledge graph to construct a cultural symbol subgraph; extracting user preference features and their corresponding parameter mapping relationships from the multi-dimensional design knowledge graph to construct a user preference subgraph; and associating the process constraint subgraph, the cultural symbol subgraph, and the user preference subgraph through design parameter nodes in the multi-dimensional design knowledge graph to form a multi-source semantic association subgraph.

[0032] The process constraint entities refer to entity objects that characterize processing feasibility conditions, including but not limited to tool diameter range, engraving depth threshold, and material hardness grade; the first association relationship refers to the constraint relationship between the process constraint entities and design parameter nodes, such as the physical constraint relationship between the tool diameter parameter and the minimum hollowing size parameter; the process constraint subgraph refers to a sub-network structure composed of process constraint entity nodes, design parameter nodes, and edges of the first association relationship; the cultural symbol entities refer to patterns, shapes, or color elements with specific traditional cultural connotations, including but not limited to dragon patterns, cloud patterns, and grain patterns; the second association relationship refers to the semantic interpretation relationship between cultural symbol entities and design parameter nodes. For example, the morphological representation relationship between the dragon pattern entity and the set of control points for the dragon head outline; the cultural symbol subgraph refers to a sub-network structure composed of cultural symbol entity nodes, design parameter nodes, and second association relationship edges; the user preference features refer to feature vectors reflecting the aesthetic preferences of the target user group, including but not limited to style preference values, complexity preference values, and traditionality preference values; the parameter mapping relationship refers to the statistical association relationship between user preference features and design parameter nodes, such as the positive correlation between traditionality preference values ​​and pattern symmetry parameters; the design parameter nodes refer to the feature nodes in the multidimensional design knowledge graph that represent the design parameters of the jade pendant, with each node corresponding to a quantifiable design variable and its value range.

[0033] Optionally, the process constraint entities and their corresponding first association relationships can be extracted using the k-nearest neighbor subgraph mining algorithm; the process constraint subgraph, cultural symbol subgraph, and user preference subgraph can be constructed using the Neo4j indexing module; and the Jaccard similarity algorithm can be used to associate the process constraint subgraph, the cultural symbol subgraph, and the user preference subgraph.

[0034] Furthermore, by establishing a semantic reasoning link from the multi-source semantic association subgraph to the design parameter node, the embodiment of the present invention can transform subjective cultural aesthetic judgments into a traceable and verifiable graph structure reasoning process. This allows the parametric design of jade pendants to systematically solve the dual problems of cultural inaccuracy and visual style combination disharmony. The semantic reasoning link refers to the directional derivation relationship path based on graph theory and logical rules established between the multi-source semantic association subgraph and the design parameter node.

[0035] As an embodiment of the present invention, establishing a semantic reasoning link from the multi-source semantic association subgraph to the design parameter node includes: constructing an initial semantic connection network between the semantic nodes in the multi-source semantic association subgraph and the design parameter node; parsing the transmission path from the semantic node to the design parameter node through the initial semantic connection network; selecting the core semantic transmission path from the transmission path, and using the core semantic transmission path as the semantic reasoning link from the multi-source semantic association subgraph to the design parameter node.

[0036] Furthermore, by parsing the propagation path from the semantic node to the design parameter node through the initial semantic connection network, the following steps are taken: assigning weights to each connection edge in the initial semantic connection network to form a weighted semantic association graph; and parsing the propagation path from the semantic node to the design parameter node from the weighted semantic association graph.

[0037] The semantic nodes refer to knowledge entities in the multi-source semantic association subgraph used to express specific cultural elements, technological constraints, or style rules, such as nodes representing the meaning of "Ruyi" in the cultural symbol subgraph. The initial semantic connection network refers to an unweighted graph structure composed of semantic nodes, design parameter nodes, and their connections, where the connection relationship refers to the semantic association between semantic nodes and design parameter nodes, specifically manifested as relationship types such as "symbol," "constraint," and "instantiation." The weighted semantic association graph refers to the graph structure obtained by assigning numerical weights representing the association strength or importance of each connection relationship based on the initial semantic connection network. For example, the weight of the "instantiation" relationship between the "dragon pattern" node and the "dragon scale density" parameter node is set to 0.9, while the weight of the secondary "association" relationship is set to 0.3. The transmission path refers to an ordered sequence in the weighted semantic association graph that starts from a semantic node, passes through a series of connecting edges and intermediate nodes, and finally reaches one or more design parameter nodes. The core semantic transmission path refers to the set of transmission paths that perform optimally in terms of semantic transmission strength and structural effectiveness, selected according to a preset path efficiency evaluation standard.

[0038] Optionally, the initial semantic connection network can be generated using a graph database query language; a semantic similarity calculation model can be used to assign weights to each connection edge in the initial semantic connection network; and a graph traversal and path search algorithm can be used to parse the propagation path from the semantic node to the design parameter node in the weighted semantic association graph.

[0039] As an optional embodiment of the present invention, selecting core semantic transmission paths from the transmission paths includes: evaluating the structural complexity of each transmission path based on the distribution characteristics of the number of nodes and edge types of the transmission paths; calculating the total path weight of each transmission path, and combining the structural complexity to calculate the transmission efficiency index of each transmission path; comparing the transmission efficiency index with a preset efficiency threshold, and selecting target efficiency indices that are higher than the efficiency threshold; and selecting core semantic transmission paths from the transmission paths based on the target efficiency index.

[0040] The path weight total value refers to the sum of the weight values ​​of all connecting edges on a transmission path, used to quantify the overall semantic association strength of the path; the number of nodes refers to the total number of nodes contained in a transmission path; the edge type distribution feature refers to the proportion or order of occurrence of different types of connecting edges in a transmission path; the structural complexity refers to a quantitative indicator that reflects the degree of detour and heterogeneity of the transmission path in terms of topological structure, jointly determined by the number of nodes and the edge type distribution feature, wherein a path with a large number of nodes and frequent alternation of edge types usually has higher structural complexity; the transmission efficiency index refers to a comprehensive evaluation value calculated by combining the path weight total value and structural complexity, used to evaluate the effectiveness of the path in transmitting semantic information under unit structural complexity, for example, using the ratio of the path weight total value to the structural complexity as the transmission efficiency index; the preset threshold refers to the minimum required value of the transmission efficiency index for judging whether the transmission path is effective; the target efficiency index refers to the portion of the transmission efficiency index that is higher than the preset threshold, used to define effective transmission paths, for example, if the preset threshold is 0.7, then the efficiency values ​​corresponding to all paths with a transmission efficiency index greater than 0.7 constitute the target efficiency index set.

[0041] Optionally, the total path weight of each of the transmission paths can be calculated using an edge weight accumulation algorithm; the structural complexity of each of the transmission paths can be evaluated using a graph structure entropy calculation model.

[0042] S3. Parse the cultural symbol references and visual style combinations corresponding to the design parameter nodes in the semantic reasoning link.

[0043] In the embodiments of the present invention, the cultural symbol indicators and visual style combinations corresponding to the design parameter nodes are parsed in the semantic reasoning link. This enables an automated reverse mapping from parameterized data to cultural semantics and aesthetic features. As a result, the jade pendant parameterized design system can not only positively constrain the design process, but also perform reverse semantic interpretation and aesthetic evaluation of any parameter combination, providing an interpretable analysis basis for design verification.

[0044] The cultural symbol indicators refer to the set of feature identifiers that have a clear correspondence with the traditional cultural symbol system, obtained by reverse parsing from the design parameter nodes through the semantic reasoning link, such as pattern type identifiers, shape category identifiers, and symbolic association identifiers; the visual style combination refers to the visual element composition relationship system reconstructed from the jade pendant design parameters through the semantic reasoning link, specifically including the structured description of shape composition relationship, pattern arrangement relationship, and color matching relationship.

[0045] As an embodiment of the present invention, parsing the cultural symbol indices corresponding to the design parameter nodes in the semantic reasoning link includes: identifying the transmission path from the design parameter node to the cultural symbol entity in the semantic reasoning link; generating initial symbol feature vectors of the end cultural symbol entities in the transmission path using the node type and edge relationship attributes of the traditional path; calculating the semantic correlation matrix between different initial symbol feature vectors, and reconstructing an optimized symbol feature group of the initial symbol feature vectors through the semantic correlation matrix; and generating the cultural symbol indices corresponding to the design parameter nodes based on the optimized symbol feature group.

[0046] Furthermore, by utilizing the node type and edge relationship attributes of the traditional path, an initial symbol feature vector of the end cultural symbol entity in the transmission path is generated, including: using the node type and edge relationship attributes of the traditional path to calculate the path confidence weight corresponding to the transmission path; and according to the path confidence weight, performing feature weighting on the end cultural symbol entity of the transmission path to generate the initial symbol feature vector.

[0047] In this context, the design parameter node refers to a data entity in the multidimensional design knowledge graph that uniquely represents and stores a specific jade pendant design parameter and its attributes; the cultural symbol entity refers to a data entity in the multidimensional design knowledge graph that represents a fixed pattern or form category with recognized traditional cultural connotations, such as the cloud pattern entity representing the meaning of "ruyi" (a traditional Chinese auspicious symbol); the transmission path refers to a complete directed edge sequence connecting the design parameter node and the cultural symbol entity in the semantic reasoning link; the node type refers to the predefined category to which each node in the transmission path belongs, such as parameter node, process constraint node, and cultural symbol node; and the edge relationship attribute refers to the semantic relationship category represented by each edge in the transmission path, such as "constrained by". "Instantiated as" and "symbolized as"; the path confidence weight refers to a numerical index calculated based on the combination of node types and edge relationship attributes in the path, used to quantify the semantic reliability of the path; the terminal cultural symbol entity refers to the cultural symbol entity connected to the end position of the transmission path; the initial symbol feature vector refers to a multi-dimensional numerical representation composed of the basic features of the terminal cultural symbol entity and its path confidence weight; the semantic correlation matrix refers to a square matrix data structure used to quantify the semantic correlation between different initial symbol feature vectors; the optimized symbol feature group refers to a feature set with higher discriminativeness and interpretability obtained after denoising, redundancy removal and semantic fusion of the initial symbol feature vectors.

[0048] Optionally, the end-point cultural symbol entities of the transmission path can be weighted using a weighted summation algorithm; the semantic correlation matrix between different initial symbol feature vectors can be calculated using a kernel function mapping algorithm; and the cultural symbol indicators corresponding to the design parameter nodes can be generated using a symbol encoder.

[0049] As an optional embodiment of the present invention, reconstructing the optimized symbol feature group of the initial symbol feature vector through the semantic correlation matrix includes: performing eigenvalue decomposition on the semantic correlation matrix to obtain a feature vector set; selecting a subset of principal feature vectors in the feature vector set based on a preset eigenvalue threshold; constructing a projection transformation matrix corresponding to the initial symbol feature vector using the subset of principal feature vectors; and reconstructing the optimized symbol feature group of the initial symbol feature vector through the projection transformation matrix.

[0050] Further, reconstructing the optimized symbol feature group of the initial symbol feature vector through the projection transformation matrix includes: performing dimensionality reduction mapping on the initial symbol feature vector through the projection transformation matrix to obtain a low-dimensional symbol feature representation; and performing cluster analysis on the low-dimensional symbol feature representation to form an optimized symbol feature group.

[0051] Here, eigenvalue decomposition refers to the mathematical process of performing matrix diagonalization based on linear algebra principles on the semantic correlation matrix to obtain eigenvectors representing the main directions of change of the matrix and their corresponding eigenvalues; the eigenvalue threshold refers to a pre-set numerical boundary point used to distinguish between primary and secondary eigenvectors, and the eigenvalue threshold can be determined based on the cumulative contribution rate of eigenvalues; the primary eigenvector subset refers to the set of eigenvectors whose eigenvalues ​​are greater than the eigenvalue threshold; the projection transformation matrix refers to a mathematical transformation matrix composed of the primary eigenvector subset as column vectors, used to project high-dimensional eigenvectors to a low-dimensional space; the low-dimensional symbolic feature representation refers to the numerical representation obtained after the initial symbolic feature vectors are mapped by the projection transformation matrix, which reduces the dimension and preserves the main information; the clustering analysis refers to the calculation method of performing an unsupervised classification algorithm based on similarity measurement on the low-dimensional symbolic feature representation, thereby automatically grouping semantically similar feature points into the same group.

[0052] Optionally, the projection transformation matrix corresponding to the initial symbol eigenvector can be constructed using a principal component analysis algorithm.

[0053] As an embodiment of the present invention, parsing the visual style combination corresponding to the design parameter node in the semantic reasoning link includes: extracting the visual style feature vector corresponding to the design parameter node through the style transmission path in the semantic reasoning link; comparing the visual style feature vector with a preset style rule library to determine the visual style coordination degree and compositional relationship description corresponding to the design parameter node; and parsing the visual style combination corresponding to the design parameter node based on the visual style coordination degree and the compositional relationship description.

[0054] The style transmission path refers to the connected sub-path in the semantic reasoning chain that specifically transmits style rule constraints; the visual style feature vector refers to a multi-dimensional vector representing the numerical distribution of jade pendant design parameters in the visual composition dimension; the style rule library refers to a pre-established dataset containing various visual composition rules and their quantification thresholds; the comparison refers to comparing the numerical values ​​of each dimension in the visual style feature vector with the ideal values ​​and allowable deviation ranges of the corresponding visual composition rules stored in the style rule library, and calculating the quantification of the degree of conformity; the visual style coordination degree refers to a quantitative score value reflecting the overall visual composition harmony of the jade pendant, calculated based on the comparison results; the compositional relationship description refers to a systematic textual or structured description of the spatial arrangement relationship, logical association rules, and application of formal beauty rules among the visual composition elements of the jade pendant, specifically including qualitative or quantitative expressions of the primary and secondary relationships, proportional relationships, rhythmic relationships, and contrast and harmony relationships among the elements.

[0055] Optionally, the visual style coordination degree corresponding to the design parameter node can be determined by a weighted scoring algorithm, and the composition relationship description can be generated using a rule template filling engine.

[0056] S4. Calculate the semantic consistency of the cultural symbol indicators and the coordination index of the visual style combination, and generate a parametric design recommendation scheme for the jade pendant based on the semantic consistency and the coordination index.

[0057] By calculating the semantic consistency of the cultural symbol indicators and the coordination index of the visual style combination, the embodiment of the present invention enables the jade pendant parametric design system to automatically and comprehensively evaluate any parametric design scheme, accurately locate the specific type and degree of cultural semantic deviation and visual compositional disharmony, and thus provide clear and operable technical guidance for design optimization.

[0058] The semantic consistency degree refers to the quantitative index of conformity between cultural symbol indicators and the pre-set normative cultural semantic framework in the multidimensional design knowledge graph; the coordination index refers to the quantitative score of the harmony between the constituent elements in the visual style combination in accordance with the laws of formal beauty.

[0059] Optionally, the coordination index of the visual style combination can be determined using the method of visual style coordination described above.

[0060] For example, the degree of semantic consistency is calculated using the following formula. It should be noted that this calculation method is only one possible method and does not affect the implementation of the basic scheme above: ; in, Indicates the degree of semantic consistency, where n represents the total number of cultural semantic features in the cultural symbol reference. This represents the degree centrality of the node in the multidimensional design knowledge graph for the i-th cultural semantic feature. This represents the i-th cultural semantic feature in the design parameters of the jade pendant. This represents the normative cultural semantic feature corresponding to the predefined i-th cultural semantic feature in the multidimensional design knowledge graph. express and The matching function, This indicates the number of standardized cultural symbol entities that can be correctly associated with the design parameters of the jade pendant through semantic reasoning. This represents the total number of all cultural symbol entities related to the current design type in the multidimensional design knowledge graph.

[0061] It should be noted that the above formula, through the coupling of three key parameter terms, can achieve a multi-level quantitative assessment of cultural semantic consistency. Specifically, the matching function term... By parsing features With standard features By mapping each element to the same vector space and determining a match using a cosine similarity threshold, abstract cultural semantic consistency can be transformed into a quantitative process where "analytical features" and "graphical specifications" can be compared item by item. For example, although modern simplified variants of the "chilong pattern" differ from the standard Han dynasty sample in geometric details, if the similarity in the vector space exceeds a preset threshold (e.g., 0.85), it can still be considered a semantic match (δ=1); otherwise, it is considered a mismatch (δ=0). This mechanism ensures the assessment's inclusiveness towards reasonable design evolution; the system covers all aspects. By introducing the total number of entities related to the current design type As a benchmark, the evaluation criteria are adaptive: when the design type corresponds to a large cultural system (such as "ritual objects"), the denominator automatically increases to avoid making unrealistic demands on the breadth of coverage; when the design type corresponds to a smaller system (such as "specific pattern themes"), the denominator decreases accordingly, so that the evaluation can keenly reflect subtle cultural gaps, and ultimately ensure that the coverage assessment is always within a reasonable range of expectations.

[0062] Furthermore, this embodiment of the invention generates a parametric design recommendation scheme for the jade pendant based on the semantic consistency degree and the coordination index. This not only automatically corrects design defects such as cultural inaccuracies and visual dissonance, but also provides differentiated recommendation scheme sequences according to different design preferences. This transforms the experience-dependent manual adjustment process into an interpretable and reproducible automated decision-making process, significantly improving design efficiency and result quality.

[0063] The parametric design recommendation scheme refers to the set of candidate parameter configurations that achieve the optimal result under the dual requirements of semantic consistency and coordination index. Each recommendation scheme includes a complete list of parameter values, corresponding dual-index evaluation values, and specific optimization basis descriptions that can be traced back to a multi-dimensional design knowledge graph.

[0064] As an embodiment of the present invention, a parameterized design recommendation scheme for the jade pendant is generated based on the semantic consistency degree and the coordination index, including: setting an optimization weight threshold for the semantic consistency degree and the coordination index; searching for a set of candidate parameters that satisfy the optimization weight threshold in the feasible domain of the parameterized design of the jade pendant; extracting differentiated parameter combinations from the candidate parameter sets; and generating a parameterized design recommendation scheme for the jade pendant based on the differentiated parameter combinations.

[0065] The optimization weight threshold refers to the minimum satisfaction boundary value set for semantic consistency and coordination index according to design requirements; the parameterized design feasible domain refers to the multi-dimensional parameter feasible space defined by the value range of all design parameters of the jade pendant and their mutual process constraints and cultural semantic constraints; the candidate parameter set refers to the set of parameter combinations that can simultaneously satisfy the optimization weight threshold of semantic consistency and coordination index within the parameterized design feasible domain; the differentiated parameter combination refers to the key parameter difference combination extracted from the candidate parameter set that can distinguish different design tendencies, such as a high consistency parameter subset emphasizing traditional semantics and a high coordination parameter subset emphasizing modern aesthetics.

[0066] Optionally, the feasible region of the parameterized design of the jade pendant can be determined by a constraint solver; the differentiated parameter combinations of the candidate parameter set can be extracted by constructing a combinatorial optimization model using the Pyomo tool.

[0067] like Figure 2 The diagram shown is a module schematic of a knowledge graph-based semantic association and recommendation system for the parametric design of jade pendants, provided in an embodiment of the present invention.

[0068] The knowledge graph-based semantic association and recommendation system 200 for parametric design of jade pendants described in this invention can be installed in an electronic device. Depending on the functions implemented, the knowledge graph-based semantic association and recommendation system for parametric design of jade pendants may include a graph generation module 201, a link construction module 202, a semantic parsing module 203, and a scheme recommendation module 204. The module described in this invention can also be called a unit, which refers to a series of computer program segments that can be executed by the processor of an electronic device and can perform a fixed function, and which are stored in the memory of the electronic device.

[0069] In this embodiment of the invention, the functions of each module / unit are as follows: The graph generation module 201 is used to obtain the jade pendant design parameters, cultural semantic elements and style rules, so as to construct a multi-dimensional design knowledge graph of the jade pendant; The link construction module 202 is used to configure a multi-source semantic association subgraph in the multi-dimensional design knowledge graph and establish a semantic reasoning link from the multi-source semantic association subgraph to the design parameter node. The semantic parsing module 203 is used to parse out the combination of cultural symbol indicators and visual styles corresponding to the design parameter nodes in the semantic reasoning link. The scheme recommendation module 204 is used to calculate the semantic consistency degree of the cultural symbol indicators and the coordination index of the visual style combination, and generate a parametric design recommendation scheme for the jade pendant based on the semantic consistency degree and the coordination index.

[0070] In one embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as follows: Figure 3 As shown, the computer device includes a processor, memory, network interface, and database connected via a system bus. The processor provides computational and control capabilities. The memory includes non-volatile and / or volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and database. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The network interface is used to communicate with external clients via a network connection. When the computer program is executed by the processor, it implements the server-side functions or steps of a knowledge graph-based method for parametric design semantic association and recommendation of jade pendants.

[0071] In one embodiment, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to perform the following steps: The design parameters, cultural semantic elements, and style rules of the jade pendant are obtained to construct a multi-dimensional design knowledge graph of the jade pendant. Configure a multi-source semantic association subgraph in the multi-dimensional design knowledge graph, and establish a semantic reasoning link from the multi-source semantic association subgraph to the design parameter node; The cultural symbolic references and visual style combinations corresponding to the design parameter nodes are parsed out in the semantic reasoning chain. Calculate the semantic consistency of the cultural symbol indicators and the coordination index of the visual style combination, and generate a parametric design recommendation scheme for the jade pendant based on the semantic consistency and the coordination index.

[0072] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, the computer program performing the following steps when executed by a processor: The design parameters, cultural semantic elements, and style rules of the jade pendant are obtained to construct a multi-dimensional design knowledge graph of the jade pendant. Configure a multi-source semantic association subgraph in the multi-dimensional design knowledge graph, and establish a semantic reasoning link from the multi-source semantic association subgraph to the design parameter node; The cultural symbolic references and visual style combinations corresponding to the design parameter nodes are parsed out in the semantic reasoning chain. Calculate the semantic consistency of the cultural symbol indicators and the coordination index of the visual style combination, and generate a parametric design recommendation scheme for the jade pendant based on the semantic consistency and the coordination index.

[0073] It should be noted that the functions or steps that can be implemented by the computer-readable storage medium or computer device described above can be referred to the relevant descriptions on the server side and client side in the foregoing method embodiments. To avoid repetition, they will not be described one by one here.

[0074] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments of the above methods. Any references to memory, storage, databases, or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), RAMbus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0075] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional units and modules is used as an example. In practical applications, the above functions can be assigned to different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above.

[0076] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0077] Finally, it should be noted that in the above embodiments, each embodiment can be combined with each other or independent. Deleting any one of them will not affect the technical implementation of other embodiments. The above embodiments are only used to illustrate the technical solutions of the present invention and not to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention.

Claims

1. A knowledge graph-based jade pendant parameterization design semantic association and recommendation method, characterized in that, The method includes: The design parameters, cultural semantic elements, and style rules of the jade pendant are obtained to construct a multi-dimensional design knowledge graph of the jade pendant. Configure a multi-source semantic association subgraph in the multi-dimensional design knowledge graph, and establish a semantic reasoning link from the multi-source semantic association subgraph to the design parameter node; The cultural symbolic references and visual style combinations corresponding to the design parameter nodes are parsed out in the semantic reasoning chain. Calculate the semantic consistency of the cultural symbol indicators and the coordination index of the visual style combination, and generate a parametric design recommendation scheme for the jade pendant based on the semantic consistency and the coordination index.

2. The knowledge graph-based semantic association and recommendation method for jade pendant parameterization design according to claim 1, characterized in that, The cultural symbolic references corresponding to the design parameter nodes are parsed out in the semantic reasoning chain, including: Identify the transmission path from the design parameter node to the cultural symbol entity from the semantic reasoning link; Using the node type and edge relationship attributes of the traditional path, an initial symbol feature vector of the end cultural symbol entity in the transmission path is generated; Calculate the semantic association matrix between different initial symbol feature vectors, and reconstruct the optimized symbol feature group of the initial symbol feature vectors using the semantic association matrix; Based on the optimized symbol feature group, cultural symbol indicators corresponding to the design parameter nodes are generated.

3. The knowledge graph-based parameterized design semantic association and recommendation method for jade pendant according to claim 2, characterized in that, The optimized symbol feature set of the initial symbol feature vector is reconstructed using the semantic relevance matrix, including: The semantic association matrix is ​​decomposed into eigenvalues ​​to obtain the decomposed vectors; Based on a preset feature value threshold, a subset of the main feature vectors in the decomposition vector is selected; Using the subset of principal feature vectors, construct the projection transformation matrix corresponding to the initial symbol feature vector; The optimized symbol feature set of the initial symbol feature vector is reconstructed using the projection transformation matrix.

4. The knowledge graph-based parameterized design semantic association and recommendation method for jade pendant according to claim 1, characterized in that, The visual style combination corresponding to the design parameter node is parsed out in the semantic reasoning chain, including: Extract the visual style feature vector corresponding to the design parameter node through the style propagation path in the semantic reasoning link; The visual style feature vector is compared with a preset style rule library to determine the visual style coordination degree and compositional relationship description corresponding to the design parameter node; Based on the visual style coordination degree and the compositional relationship description, the visual style combination corresponding to the design parameter node is parsed out.

5. The method for semantic association and recommendation of jade pendant parametric design based on knowledge graph as described in claim 1, characterized in that, Establishing the semantic reasoning link from the multi-source semantic association subgraph to the design parameter node includes: Construct an initial semantic connection network between semantic nodes and design parameter nodes in the multi-source semantic association subgraph; The propagation path from the semantic node to the design parameter node is parsed through the initial semantic connection network. The core semantic transmission path is selected from the transmission paths, and the core semantic transmission path is used as the semantic reasoning link from the multi-source semantic association subgraph to the design parameter node.

6. The method for semantic association and recommendation of jade pendant parametric design based on knowledge graph as described in claim 5, characterized in that, The core semantic transmission path is selected from the transmission paths, including: The structural complexity of each of the transmission paths is evaluated based on the distribution characteristics of the number of nodes and edge types in the transmission path. Calculate the total path weight of each of the transmission paths, and combine it with the structural complexity to calculate the transmission efficiency index of each of the transmission paths; The conduction efficiency index is compared with a preset efficiency threshold, and target efficiency indices that are higher than the efficiency threshold are selected. Based on the target efficiency index, the core semantic transmission path is selected from the transmission paths.

7. The method for semantic association and recommendation of jade pendant parametric design based on knowledge graph as described in claim 1, characterized in that, The multi-source semantic association subgraph includes a process constraint subgraph, a cultural symbol subgraph, and a user preference subgraph, and the multi-source semantic association subgraph is collaboratively parsed in the semantic reasoning link.

8. The method for semantic association and recommendation of jade pendant parametric design based on knowledge graph as described in claim 1, characterized in that, To acquire the design parameters, cultural semantic elements, and style rules of the jade pendant, a multi-dimensional design knowledge graph of the jade pendant is constructed, including: Based on the style rules, the structural relationships of the jade pendant design parameters are categorized to obtain a set of parameter topological relationships; Based on the parameter topology relationship set and the cultural semantic elements, a core semantic constraint framework for the jade pendant design parameters is established. Key parameter features are extracted from the parameter structure classification set using the core semantic constraint framework. Based on the key parameter features, a multidimensional design knowledge graph corresponding to the jade pendant is constructed.

9. The method for semantic association and recommendation of jade pendant parametric design based on knowledge graph as described in claim 8, characterized in that, Based on the parameter topology set and the cultural semantic elements, a core semantic constraint framework for the jade pendant design parameters is established, including: The semantic mapping relationship between the parameter topology relationship set and the cultural semantic elements is parsed out, and the hierarchical constraint rule set of the jade pendant design parameters is generated by using the type weight of the semantic mapping relationship. Perform a logical consistency check on the hierarchical constraint rule set to obtain the target constraint rule set; The value space of the jade pendant design parameters is associated and mapped with the target constraint rule set to obtain the association mapping result; Based on the association mapping results, a core semantic constraint framework for the jade pendant design parameters is established.

10. The method for semantic association and recommendation of jade pendant parametric design based on knowledge graph as described in claim 1, characterized in that, Based on the semantic consistency level and the coordination index, a parameterized design recommendation scheme for the jade pendant is generated, including: Set the optimized weight thresholds for the semantic consistency degree and the coordination index; Within the feasible domain of the parametric design of the jade pendant, a set of candidate parameters that satisfy the optimization weight threshold is searched. Extract the differential parameter combinations from the candidate parameter set; Based on the differentiated parameter combinations, a parameterized design recommendation scheme for the jade pendant is generated.

Images