A knowledge graph-based data asset intelligent exploration method and system

Abstract

The application relates to the technical field of data asset exploration, in particular to a data asset intelligent exploration method and system based on a knowledge graph, which comprises the following steps: acquiring enterprise data assets and dynamically labeling to generate a labeled data set; performing semantic analysis based on the labeled data set to obtain a semantic correlation graph; constructing a knowledge graph model, calculating node weights, correlation path lengths and path contribution degrees, and generating a simulated correlation distribution graph; segmenting the semantic correlation graph through node density and relationship strength to obtain an actual correlation distribution graph; and adjusting the knowledge graph model based on the actual and simulated correlation distribution histograms. The application can improve the intelligent level and accuracy of data asset exploration.

Description

Technical Field

[0001] This invention belongs to the field of data asset exploration technology, specifically a data asset intelligent exploration method and system based on knowledge graph. Background Technology

[0002] As data assets become increasingly important in enterprise operations and decision-making, efficient management and exploration of these assets has become a critical issue. Existing data asset management and exploration methods largely rely on traditional data processing techniques, lacking intelligent and automated capabilities, and thus failing to meet the governance needs of modern enterprises facing complex data environments. For example, patent CN114022270B proposes a data processing method based on asset knowledge graphs. This method generates feature vectors for training and predicting risk prediction models by constructing an asset knowledge graph and combining it with the importance data of asset entities. However, this technical solution primarily focuses on asset risk prediction in the financial sector and fails to comprehensively cover the needs of data asset exploration. Furthermore, it does not fully consider the dynamic relationships and contextual information between data assets during the knowledge graph construction process, potentially leading to insufficient depth and accuracy in the exploration results. Simultaneously, this solution has low efficiency in processing large-scale heterogeneous data, making it difficult to adapt to the real-time exploration needs in complex data environments.

[0003] Another patent, CN118886647B, proposes a data asset governance method based on standardized processes. It extracts descriptions of data governance steps and matches them with standard documents to construct a standard data governance rule engine for standardized data asset management. However, this technical solution primarily focuses on the standardization and process-orientation of data governance, lacking intelligent exploration capabilities and failing to automatically identify implicit relationships and potential value between data assets. Furthermore, this method has limited support for unstructured data and may have compatibility issues when handling diverse data assets. Simultaneously, the application of knowledge graphs in this solution is superficial, failing to fully utilize the semantic reasoning capabilities of knowledge graphs to enhance the intelligence level of data asset exploration.

[0004] The aforementioned issues indicate that existing data asset exploration technologies still have certain shortcomings in terms of intelligence, dynamic relationship mining, heterogeneous data compatibility, and real-time processing capabilities. Especially when facing complex and diverse enterprise data environments, existing technologies struggle to achieve comprehensive, dynamic, and intelligent exploration of data assets. Therefore, there is an urgent need for a solution that combines advanced knowledge graph technology and large-scale AI algorithms to improve the efficiency and accuracy of data asset exploration and meet the needs of modern enterprises for efficient data asset management. This invention is based on this background, aiming to solve the key problems existing in current technologies by introducing intelligent exploration methods and systems, providing enterprises with more comprehensive, dynamic, and intelligent data asset exploration capabilities. Summary of the Invention

[0005] This invention provides a knowledge graph-based intelligent data asset exploration method and system, the main purpose of which is to improve the intelligence level and accuracy of data asset exploration. To achieve the above objective, the knowledge graph-based intelligent data asset exploration method provided by this invention includes: acquiring enterprise data assets; setting data type range, time range, association strength threshold, and context weight distribution; dynamically labeling the data assets based on the enterprise data assets, data type range, time range, association strength threshold, and context weight distribution to obtain a labeled dataset; performing semantic analysis based on the labeled dataset to obtain a semantic association graph; constructing a knowledge graph model based on the enterprise data assets; calculating node weights; using node weights to calculate the association path length and path contribution; and calculating the association path length and path contribution. Construct a simulated association distribution graph; calculate node density, set a dynamic density threshold, and segment the semantic association graph according to node density and the dynamic density threshold to obtain a density segmentation graph; set a dynamic relationship threshold, calculate relationship strength, and segment the density segmentation graph according to the dynamic relationship threshold and relationship strength to obtain an actual association distribution graph; mark regions based on the actual association distribution graph to obtain marked regions, calculate the association degree of marked regions, and construct an actual association distribution histogram based on the association degree; adjust the knowledge graph model based on the actual association distribution histogram and the simulated association distribution histogram to obtain an adjusted knowledge graph model, thus completing intelligent exploration.

[0006] Optionally, the calculation of node weights and the calculation of associated path length using node weights include: setting a feature extraction unit, wherein the feature extraction unit includes a context parsing unit, a time series unit, and a weight allocation unit; parsing context information based on the context parsing unit and recording context importance and context relevance; analyzing time span and time weight using the time series unit; allocating node weights using the weight allocation unit, obtaining association parameters, damping factors, and path coefficients; calculating the associated path length based on the context importance, context relevance, time span, time weight, node weight, damping factor, and path coefficients; setting a maximum weight and a minimum weight; and calculating the associated path length based on the association strength threshold, node weights, context weight distribution, maximum weight, minimum weight, and time span.

[0007] Optionally, the step of calculating the association path length based on the association strength threshold, node weight, context weight distribution, maximum weight, minimum weight, and time span includes: obtaining data asset diversity, data asset complexity, association sensitivity, and decay factor, and calculating the association path length based on the association strength threshold, node weight, context weight distribution, maximum weight, minimum weight, time span, data asset diversity, data asset complexity, association sensitivity, and decay factor.

[0008] Optionally, the calculation of path contribution includes: obtaining heterogeneous data compatibility, data flow direction and data dependency, and calculating path contribution based on the node weight, associated path length, context weight distribution, heterogeneous data compatibility, data flow direction and data dependency.

[0009] Optionally, constructing a simulated association distribution map based on the association path length and path contribution includes: setting an association identifier and obtaining the total number of nodes; identifying nodes based on the association identifier; obtaining the association path range; dividing the association path range into intervals to obtain association path intervals; constructing corrected weight parameters based on the path contribution and node weights; constructing a mapping function; calculating interval association contribution values ​​based on the corrected weight parameters, mapping function, association identifier, total number of nodes, association path intervals, and association path lengths; constructing an association horizontal axis and an association vertical axis, identifying the association path intervals as the association horizontal axis and the interval association contribution values ​​as the association vertical axis; and constructing an association distribution map based on the association path intervals, the association horizontal axis, the interval association contribution values, and the association vertical axis.

[0010] Optionally, the step of constructing the modified weight parameters based on the path contribution and node weight includes: obtaining the maximum weight and maximum contribution, setting the weight factor and contribution factor, and constructing the modified weight parameters based on the association identifier, time span, path contribution, node weight, maximum weight, maximum contribution, weight factor and contribution factor.

[0011] Optionally, the step of calculating node density, setting a dynamic density threshold, and segmenting the semantic association graph based on the node density and the dynamic density threshold to obtain a density segmentation graph includes: setting the horizontal and vertical coordinates of nodes; calculating horizontal density, vertical density, and normal density; obtaining the normal angle, normal direction parameter, horizontal axis sparsity parameter, and vertical axis sparsity parameter; calculating node density based on the node horizontal coordinate, node vertical coordinate, horizontal density, vertical density, normal density, normal angle, normal direction parameter, horizontal axis sparsity parameter, and vertical axis sparsity parameter; calculating the density mean and density standard deviation based on the node density; setting dynamic parameters; setting a dynamic density threshold based on the density mean, density standard deviation, and dynamic parameters; constructing a segmentation function based on the node density and the dynamic density threshold; and segmenting the semantic association graph based on the segmentation function to obtain a density segmentation graph.

[0012] Optionally, the step of constructing the actual association distribution histogram based on the degree of association includes: summarizing based on the degree of association to obtain the actual association set; constructing the actual association horizontal axis and the actual association vertical axis, identifying the association path interval as the actual association horizontal axis, and identifying the actual association set as the actual association vertical axis; and constructing the actual association distribution histogram based on the actual association horizontal axis and the actual association vertical axis.

[0013] Optionally, adjusting the knowledge graph model based on the actual association distribution histogram and the simulated association distribution histogram to obtain an adjusted knowledge graph model includes: setting a difference threshold and model state; obtaining the graph resolution; marking the association path intervals to obtain an association index; calculating the total number of intervals and the actual association contribution value based on the actual association distribution histogram and the simulated association distribution histogram, wherein the model state includes: a normal state and a deviation state; calculating a contribution difference value based on the association index, the total number of intervals, the interval association contribution value, and the actual association contribution value; determining whether the contribution difference value is greater than the difference threshold; if the contribution difference value is not greater than the difference threshold, then confirming that the model state of the knowledge graph model is a normal state; if the contribution difference value is greater than the difference threshold, then confirming that the model state of the knowledge graph model is a deviation state, and increasing the graph resolution by 10% to obtain an adjusted resolution; completing the adjustment based on the adjusted resolution to obtain the adjusted knowledge graph model.

[0014] To achieve the above objectives, the present invention also provides a knowledge graph-based intelligent data asset exploration system, comprising: a semantic analysis module, used to acquire enterprise data assets, set data type range, time range, association strength threshold, and context weight distribution, dynamically annotate the data assets based on the enterprise data assets, data type range, time range, association strength threshold, and context weight distribution to obtain an annotated dataset, and perform semantic analysis based on the annotated dataset to obtain a semantic association graph; and a simulated distribution construction module, used to construct a knowledge graph model based on the enterprise data assets, calculate node weights, calculate the association path length using the node weights, and calculate the path contribution; and based on the association path length and path contribution... A simulated association distribution graph is constructed. An actual distribution construction module is used to calculate node density, set a dynamic density threshold, and segment the semantic association graph based on node density and the dynamic density threshold to obtain a density segmentation graph. A dynamic relationship threshold is set, relationship strength is calculated, and the density segmentation graph is segmented based on the dynamic relationship threshold and relationship strength to obtain an actual association distribution graph. The actual association distribution graph is then labeled to obtain labeled regions, and the association degree of the labeled regions is calculated. An actual association distribution histogram is constructed based on the association degree. A knowledge graph adjustment module is used to adjust the knowledge graph model based on the actual association distribution histogram and the simulated association distribution histogram to obtain an adjusted knowledge graph model, thus completing intelligent exploration.

[0015] To address the aforementioned issues, the present invention also provides an electronic device comprising: a memory storing at least one instruction; and a processor executing the instructions stored in the memory to implement the aforementioned knowledge graph-based intelligent data asset exploration method.

[0016] To address the aforementioned issues, the present invention also provides a computer-readable storage medium storing at least one instruction, which is executed by a processor in an electronic device to implement the aforementioned knowledge graph-based intelligent data asset exploration method.

[0017] To address the problems described in the background art, this invention first dynamically labels data assets based on enterprise data assets, data type ranges, time ranges, association strength thresholds, and context weight distributions, obtaining a labeled dataset. By setting data type ranges, time ranges, association strength thresholds, and context weight distributions, it provides data support consistent with actual needs for subsequent operations. Obtaining the labeled dataset ensures the reliability of the data source, laying the foundation for the verification and optimization of intelligent exploration. Second, semantic analysis is performed based on the labeled dataset to obtain a semantic relationship graph. Semantic analysis technology can accurately capture the semantic relationships between data assets, avoiding the limitations of traditional methods and improving the reliability of data processing. The semantic relationship graph provides accurate input data for subsequent node analysis, density segmentation, and relationship evaluation. Third, a knowledge graph model is constructed based on enterprise data assets, calculating node weights, association path lengths, and path contributions. The calculation of node weights, association path lengths, and path contributions, along with the construction of the knowledge graph model, provides the foundation for constructing a simulated association distribution graph. By calculating path contributions, it is possible to... This invention quantifies the contribution of associations between data assets. Further, it constructs a simulated association distribution map based on association path length and path contribution, which visually represents the association contribution value of data assets within the association path interval. Then, the semantic association map is segmented to obtain a density segmentation map. Segmentation of the semantic association map using node density and dynamic density thresholds accurately identifies strong and weak association regions, effectively removing noise interference. Next, the density segmentation map is segmented based on dynamic relationship thresholds and relationship strength to obtain an actual association distribution map. Further segmentation of the density segmentation map using relationship strength and dynamic relationship thresholds improves the accuracy of the actual association distribution map, facilitating the subsequent construction of the actual association distribution histogram. Finally, the actual association distribution histogram is constructed, and the knowledge graph model is adjusted based on the actual and simulated association distribution histograms. By comparing the actual and simulated association distribution histograms, the knowledge graph model is adjusted so that its output gradually approaches the actual association results, achieving closed-loop optimization and significantly improving the accuracy of intelligent data asset exploration. Therefore, this invention can improve the intelligence level and accuracy of data asset exploration. Attached Figure Description

[0018] Figure 1 This is a flowchart illustrating a knowledge graph-based intelligent data asset exploration method according to an embodiment of the present invention.

[0019] Figure 2 This is a functional module diagram of a knowledge graph-based intelligent data asset exploration system provided in an embodiment of the present invention.

[0020] Figure 3This is a schematic diagram of the structure of an electronic device that implements the knowledge graph-based intelligent data asset exploration method according to an embodiment of the present invention. Detailed Implementation

[0021] This invention provides a knowledge graph-based intelligent data asset exploration method and system. By combining semantic analysis, knowledge graph modeling, node weight calculation, path contribution evaluation, and association distribution graph construction, it achieves intelligent exploration of data assets. The specific embodiments of this invention will be described in detail below with reference to the accompanying drawings and their reference numerals.

[0022] like Figure 1 As shown, the core process of this invention includes several key steps, which together form a complete closed loop from data acquisition to knowledge graph adjustment. First, in step S1, the system acquires enterprise data assets through a semantic analysis module and sets the data type range, time range, association strength threshold, and context weight distribution. Setting these parameters is crucial for ensuring that subsequent operations align with actual needs. For example, the data type range can be limited to structured and unstructured data, the time range can be set to data records from the past year, and the association strength threshold is used to filter out data assets with significant associations. Furthermore, the setting of the context weight distribution reflects the importance of different contextual information, thus providing a basis for dynamic annotation. In this stage, the system generates an annotated dataset by dynamically annotating the data assets. The annotated dataset not only contains the original data but also includes semantic tags to clarify the category, time attribute, and contextual relationship of each data point. This annotation method provides reliable data support for subsequent semantic analysis.

[0023] In step S2, the system performs semantic analysis based on the labeled dataset to generate a semantic association graph. The core of semantic analysis lies in using natural language processing techniques and machine learning algorithms to identify semantic relationships between data assets. For example, for a transaction record describing "Customer A purchased Product B," the semantic analysis module extracts the purchase relationship between "Customer A" and "Product B" and transforms it into a node connection in the semantic association graph. The construction process of the semantic association graph involves various algorithms, one typical method being to calculate the similarity between words based on word embedding models (such as Word2Vec or BERT) to determine the strength of the association between nodes. Assuming the semantic vectors of two nodes are v1 and v2, their similarity can be calculated using the cosine similarity formula cosθ=(v1·v2) / (|v1|·|v2|). Ultimately, the semantic association graph provides high-precision input data for subsequent knowledge graph modeling.

[0024] Next, in step S3, the simulated distribution construction module builds a knowledge graph model based on enterprise data assets and calculates node weights, associated path lengths, and path contributions. The knowledge graph model construction process includes three main stages: node definition, edge definition, and weight allocation. Nodes represent entities in the data assets, edges represent relationships between entities, and weights reflect the importance of those relationships. To calculate node weights, the system sets up a feature extraction unit, which includes a context parsing unit, a time series unit, and a weight allocation unit. The context parsing unit is responsible for parsing context information and recording context importance and context relevance. The time series unit is used to analyze the time span and time weights, while the weight allocation unit allocates node weights based on the above results. The formula for calculating node weights can be expressed as W = αC + βT + γP, where W represents node weight, C represents context importance, T represents time weight, P represents path coefficient, and α, β, and γ are the corresponding weight factors. Based on this, the system further calculates the associated path length. Assume that the node weights on a certain path are w1, w2, ..., w... n The path length L can be determined by the formula L = Σ(w i ·d i ) calculate, where w1 represents the weight of the i-th node, d i This represents the distance from the i-th node to the next node. To improve the accuracy of the calculation, the system also introduces parameters such as data asset diversity, complexity, association sensitivity, and decay factor. These parameters affect the final association path length through a weighted summation.

[0025] In step S4, the system constructs a simulated association distribution map based on the association path length and path contribution. The construction process of the simulated association distribution map includes the following steps: First, the system sets association identifiers and obtains the total number of nodes. Then, it marks the nodes based on the association identifiers to obtain the identified nodes. Next, the system obtains the association path range and divides the range into intervals to obtain association path intervals. The purpose of interval division is to map the association path length to different intervals to facilitate subsequent statistical analysis. To quantify the association contribution value of each interval, the system constructs a modified weight parameter based on the path contribution and node weight. The formula for calculating the modified weight parameter can be expressed as R = λW + μC, where R represents the modified weight parameter, W represents the node weight, C represents the path contribution, and λ and μ are the corresponding weight factors. Subsequently, the system constructs a mapping function f(x) and substitutes the modified weight parameter, mapping function, association identifier, total number of nodes, association path interval, and association path length into the formula Q = f(R·L) to calculate the interval association contribution value Q. Finally, the system constructs a horizontal axis and a vertical axis for correlation, identifying the correlation path intervals as the horizontal axis and the interval correlation contribution values ​​as the vertical axis, thereby generating a simulated correlation distribution map.

[0026] In step S5, the actual distribution construction module calculates the node density and sets a dynamic density threshold to segment the semantic association graph, obtaining a density segmentation map. The node density calculation process includes the following steps: First, the system sets the horizontal and vertical coordinates of the nodes and calculates the horizontal density, vertical density, and normal density respectively. Assume the node set is N = {n1, n2, ..., n}. k}, then the horizontal density Dx can be obtained through the formula D x =∑(x i -x j Calculate x^(-2), where x i and x j Representing node n respectively i and n j The x-axis is the vertical density D. y and normal density D z Alternatively, the density can be calculated using corresponding formulas. To further optimize the density calculation results, the system introduces auxiliary variables such as normal angle, normal direction parameter, horizontal axis sparsity parameter, and vertical axis sparsity parameter. These variables affect the final node density value through weighted summation. The formula for calculating node density can be expressed as D = δDx + εDy + ζDz, where δ, ε, and ζ are the corresponding weighting factors. Based on this, the system calculates the density mean and density standard deviation based on the node density and sets dynamic parameters to determine the density dynamic threshold. The formula for calculating the density dynamic threshold can be expressed as T = μ + σ·k, where μ represents the density mean, σ represents the density standard deviation, and k is the dynamic parameter. Finally, the system constructs a segmentation function based on the node density and the density dynamic threshold, and segments the semantic association graph using the segmentation function to obtain a density segmentation map.

[0027] In step S6, the system sets a dynamic threshold for relationships and calculates relationship strength to further segment the density segmentation map, obtaining the actual association distribution map. The calculation process for relationship strength includes the following steps: First, the system acquires parameters such as heterogeneous data compatibility, data flow direction, and data dependency, and calculates the relationship strength based on these parameters. Assuming a relationship has heterogeneous data compatibility of H, data flow direction of F, and data dependency of D, the relationship strength S can be calculated using the formula... Calculate, where ρ, ψ represents the corresponding weighting factors. Based on this, the system sets dynamic thresholds for relationships and segments the density segmentation map based on relationship strength and these dynamic thresholds. The core of the segmentation process lies in determining whether each relationship meets the requirements of the dynamic threshold; only relationships that meet the requirements are retained. Finally, the system generates an actual association distribution map, which visually displays the actual associations between data assets.

[0028] In step S7, the system labels regions based on the actual association distribution map, obtains labeled regions, and calculates the association degree of the labeled regions to construct an actual association distribution histogram. The process of generating labeled regions includes the following steps: First, the system labels strongly associated and weakly associated regions based on the actual association distribution map. The labeling criteria can be determined based on parameters such as node density and relationship strength. For example, when the node density of a region is higher than the density dynamic threshold and the relationship strength is higher than the relationship dynamic threshold, the region will be labeled as a strongly associated region. Next, the system calculates the association degree of the labeled regions. Assume that a labeled region contains m relationships, and the association contribution values ​​of each relationship are q1, q2, ..., q... m The degree of correlation C in this region can be expressed by the formula C = ∑q i / m calculation. Finally, the system constructs the actual association horizontal axis and the actual association vertical axis, confirming the association path interval as the actual association horizontal axis and the actual association set as the actual association vertical axis, thereby generating an actual association distribution histogram.

[0029] In step S8, the knowledge graph adjustment module adjusts the knowledge graph model based on the actual association distribution histogram and the simulated association distribution histogram to obtain an adjusted knowledge graph model. The adjustment process includes the following steps: First, the system sets the difference threshold and model state, and obtains the graph resolution. Assuming the total number of intervals in the actual association distribution histogram is M, and the total number of intervals in the simulated association distribution histogram is N, the system marks the association path intervals to obtain the association index. Next, the system calculates the total number of intervals and the actual association contribution value based on the actual association distribution histogram and the simulated association distribution histogram, and calculates the contribution difference value Δ based on the association index, the total number of intervals, the interval association contribution value, and the actual association contribution value. The formula for calculating the contribution difference value can be expressed as Δ=∑|Q i -P i |, where Q i P represents the actual correlation contribution value. i This represents the simulated association contribution value. The system then determines whether the contribution difference value exceeds a difference threshold. If the contribution difference value is not greater than the difference threshold, the knowledge graph model is confirmed to be in a normal state; if the contribution difference value exceeds the difference threshold, the knowledge graph model is confirmed to be in a deviated state, and the graph resolution is increased by 10% to obtain the adjusted resolution. Finally, the system completes the adjustment based on the adjusted resolution, resulting in the adjusted knowledge graph model.

[0030] To achieve the above method, the present invention also provides a knowledge graph-based intelligent data asset exploration system, such as... Figure 2As shown. The system includes a semantic analysis module, a simulated distribution construction module, an actual distribution construction module, and a knowledge graph adjustment module. The semantic analysis module is responsible for acquiring enterprise data assets, setting parameters, and generating labeled datasets and semantic association graphs; the simulated distribution construction module is responsible for building the knowledge graph model, calculating node weights and path contributions, and generating a simulated association distribution graph; the actual distribution construction module is responsible for calculating node density, setting dynamic thresholds, and generating an actual association distribution graph; the knowledge graph adjustment module is responsible for adjusting the knowledge graph model based on the actual and simulated association distribution histograms. Furthermore, as... Figure 3 As shown, the present invention also provides an electronic device including a memory and a processor. The memory stores at least one instruction, and the processor executes the instruction stored in the memory to implement the above-described method. The present invention also provides a computer-readable storage medium storing at least one instruction, which is executed by a processor in the electronic device to implement the above-described method.

[0031] In summary, this invention achieves intelligent exploration of data assets by combining semantic analysis, knowledge graph modeling, node weight calculation, path contribution evaluation, and association distribution graph construction. This method not only improves the intelligence and accuracy of data asset exploration but also provides strong technical support for enterprise data asset management.

Claims

1. A method for intelligent exploration of data assets based on knowledge graphs, characterized in that, The method includes: Acquire enterprise data assets, set data type range, time range, association strength threshold and context weight distribution, dynamically label the data assets based on enterprise data assets, data type range, time range, association strength threshold and context weight distribution to obtain labeled dataset, perform semantic analysis based on labeled dataset to obtain semantic association graph; A knowledge graph model is constructed based on the enterprise data assets, node weights are calculated, the length of the associated path is calculated using the node weights, and the path contribution is calculated. A simulated association distribution map is constructed based on the associated path length and path contribution. Calculate the node density, set a dynamic density threshold, and segment the semantic association graph based on the node density and the dynamic density threshold to obtain a density segmentation graph; Set a dynamic threshold for relationships, calculate the relationship strength, and segment the density segmentation map based on the dynamic threshold and relationship strength to obtain the actual association distribution map; Based on the actual association distribution map, the marked areas are obtained, the association degree of the marked areas is calculated, and the actual association distribution histogram is constructed based on the association degree. The knowledge graph model is adjusted based on the actual association distribution histogram and the simulated association distribution histogram to obtain an adjusted knowledge graph model, thus completing intelligent exploration.

2. The intelligent data asset exploration method based on knowledge graphs as described in claim 1, characterized in that, The calculation of node weights, and the calculation of associated path lengths using node weights, includes: A feature extraction unit is set up, which includes a context parsing unit, a time series unit, and a weight allocation unit; The context information is parsed based on the context parsing unit, and the context importance and context relevance are recorded. The time series unit is used to analyze the time span and time weight. The weight allocation unit is used to allocate node weights, obtain association parameters, damping factors and path coefficients, and calculate the association path length based on the context importance, context relevance, time span, time weight, node weight, damping factor and path coefficients. Set the maximum and minimum weights, and calculate the association path length based on the association strength threshold, node weights, context weight distribution, maximum weight, minimum weight, and time span.

3. The intelligent data asset exploration method based on knowledge graphs as described in claim 2, characterized in that, The calculation of the association path length based on the association strength threshold, node weight, context weight distribution, maximum weight, minimum weight, and time span includes: Obtain data asset diversity, data asset complexity, association sensitivity, and decay factor. Calculate the association path length based on the association strength threshold, node weight, context weight distribution, maximum weight, minimum weight, time span, data asset diversity, data asset complexity, association sensitivity, and decay factor.

4. The intelligent data asset exploration method based on knowledge graphs as described in claim 1, characterized in that, The calculation path contribution includes: Obtain heterogeneous data compatibility, data flow direction, and data dependency, and calculate path contribution based on the node weight, associated path length, context weight distribution, heterogeneous data compatibility, data flow direction, and data dependency.

5. The intelligent data asset exploration method based on knowledge graphs as described in claim 1, characterized in that, The construction of the simulated association distribution map based on the associated path length and path contribution includes: Set an association identifier and obtain the total number of nodes. Identify nodes based on the association identifier to obtain the identified nodes. Obtain the association path range and divide the association path range into intervals to obtain the association path intervals. Construct corrected weight parameters based on the path contribution and node weights; Construct the mapping function; The interval association contribution value is calculated based on the modified weight parameters, mapping function, association identifier, total number of nodes, association path interval, and association path length. Construct a horizontal axis and a vertical axis for association, identify the associated path interval as the horizontal axis and the interval association contribution value as the vertical axis, and construct an association distribution map based on the associated path interval, the horizontal axis, the interval association contribution value and the vertical axis.

6. The intelligent data asset exploration method based on knowledge graphs as described in claim 5, characterized in that, The construction of corrected weight parameters based on the path contribution and node weights includes: Obtain the maximum weight and maximum contribution, set the weight factor and contribution factor, and construct the modified weight parameters based on the association identifier, time span, path contribution, node weight, maximum weight, maximum contribution, weight factor and contribution factor.

7. The intelligent data asset exploration method based on knowledge graphs as described in claim 1, characterized in that, The calculation of node density involves setting a dynamic density threshold, segmenting the semantic association graph based on the node density and the dynamic density threshold to obtain a density segmentation graph, including: Set the node x-coordinate and node y-coordinate, calculate the horizontal density, vertical density and normal density, obtain the normal angle, normal direction parameter, horizontal axis sparse parameter and vertical axis sparse parameter, and calculate the node density based on the node x-coordinate, node y-coordinate, horizontal density, vertical density, normal density, normal angle, normal direction parameter, horizontal axis sparse parameter and vertical axis sparse parameter. Calculate the density mean and density standard deviation based on the node density, set dynamic parameters, and set a density dynamic threshold according to the density mean, density standard deviation, and dynamic parameters; A segmentation function is constructed based on the node density and the dynamic density threshold. The semantic association graph is segmented based on the segmentation function to obtain a density segmentation graph.

8. The intelligent data asset exploration method based on knowledge graphs as described in claim 5, characterized in that, The construction of the actual association distribution histogram based on the degree of association includes: Based on the degree of association, the actual association set is obtained by summarizing the data. Construct the actual association horizontal axis and the actual association vertical axis, and identify the association path interval as the actual association horizontal axis and the actual association set as the actual association vertical axis; Construct a histogram of actual association distribution based on the actual association horizontal axis and the actual association vertical axis.

9. The intelligent data asset exploration method based on knowledge graphs as described in claim 5, characterized in that, The adjustment of the knowledge graph model based on the actual association distribution histogram and the simulated association distribution histogram to obtain the adjusted knowledge graph model includes: Set the difference threshold and model state, obtain the map resolution, mark the associated path intervals to obtain the association index, and count the total number of intervals and the actual association contribution value according to the actual association distribution histogram and the simulated association distribution histogram. The model state includes normal state and deviation state. The contribution difference value is calculated based on the associated index, the total number of intervals, the interval association contribution value, and the actual association contribution value. Determine whether the contribution difference value is greater than the difference threshold; If the contribution difference value is not greater than the difference threshold, then the model state of the knowledge graph model is confirmed to be normal. If the contribution difference value is greater than the difference threshold, the model state of the knowledge graph model is confirmed to be in a bias state, and the graph resolution is increased by 10% to obtain the adjusted resolution. The adjustment is completed based on the adjusted resolution, resulting in an adjusted knowledge graph model.

10. A knowledge graph-based intelligent data asset exploration system, characterized in that, The system includes: The semantic analysis module is used to acquire enterprise data assets, set data type range, time range, association strength threshold and context weight distribution, dynamically label the data assets based on enterprise data assets, data type range, time range, association strength threshold and context weight distribution to obtain labeled dataset, and perform semantic analysis based on labeled dataset to obtain semantic association graph; The simulated distribution construction module is used to construct a knowledge graph model based on the enterprise data assets, calculate node weights, use node weights to calculate the length of associated paths, and calculate path contribution; and construct a simulated association distribution graph based on the associated path lengths and path contribution. The actual distribution construction module is used to calculate node density, set a dynamic density threshold, and segment the semantic association graph according to the node density and the dynamic density threshold to obtain a density segmentation graph; set a dynamic relationship threshold, calculate the relationship strength, and segment the density segmentation graph according to the dynamic relationship threshold and the relationship strength to obtain an actual association distribution graph; mark the actual association distribution graph to obtain marked regions, calculate the association degree of the marked regions, and construct an actual association distribution histogram based on the association degree. The knowledge graph adjustment module is used to adjust the knowledge graph model based on the actual association distribution histogram and the simulated association distribution histogram to obtain an adjusted knowledge graph model and complete intelligent exploration.

Images