Communication engineering informatization system and method based on big data

Abstract

The invention discloses a communication engineering informatization system and method based on big data, and relates to the technical field of engineering informatization, and the method comprises the steps: accessing an engineering management system, a sensor network and a user operation log in real time, and constructing a dynamic knowledge graph comprising a sub-project topological relation, data generation spatial-temporal distribution and a cross-project call chain; generating a classification scheme through a sliding window clustering algorithm based on historical sub-project quantity distribution characteristics, and dynamically calibrating a critical threshold of data storage priority integration in combination with an engineering complexity factor; performing sub-project dependency analysis on the new project, and activating an optimization process when a sub-project number and topology complexity joint index exceeds a threshold value; and based on the spatial-temporal correlation and business semantic features of the historical call data, analyzing the sub-project association score, and generating a storage integration strategy. The clustering efficiency is improved, manual configuration requirements are reduced, and the engineering deployment efficiency is improved.

Description

Technical Field

[0001] The present invention relates to the field of engineering information technology, and in particular to a communication engineering information system and method based on big data. Background Art

[0002] With the continuous development and popularization of information technology, the status and role of communications engineering have become increasingly important. As the foundation and pillar of the information society, communications engineering faces increasing pressure and challenges as the economy continues to grow and the pace of informatization accelerates.

[0003] Existing technologies for determining project complexity often rely on fixed thresholds or single metrics, making them difficult to dynamically adapt to communications projects of varying scales and types. For example, when clustering high-complexity subprojects, traditional methods often use a preset global threshold. This fails to distinguish between large-scale core network projects and small base station projects, and also ignores the actual interaction intensity and topological characteristics between subprojects. This results in a lack of targeted resource optimization strategies, leading to over-optimization of simple projects and waste of resources, while truly complex projects face performance bottlenecks due to missed classifications.

[0004] Therefore, the present invention discloses a communication engineering information system and method based on big data to solve the above problems. Summary of the Invention

[0005] The purpose of the present invention is to provide a communication engineering information system and method based on big data to solve the problems raised in the prior art.

[0006] To achieve the above-mentioned purpose, the present invention provides the following technical solution: a communication engineering informatization method based on big data, the method comprising the following steps:

[0007] S1: Real-time access to the engineering management system, sensor network, and user operation logs to build a dynamic knowledge graph that includes sub-project topological relationships, data generation spatiotemporal distribution, and cross-project call chains;

[0008] S2: Based on the historical distribution characteristics of the number of sub-projects, a classification scheme is generated through a sliding window clustering algorithm, and the critical threshold for data storage priority integration is dynamically calibrated in combination with the project complexity factor;

[0009] S3: Analyze sub-project dependencies for new projects and activate the optimization process when the combined indicator of the number of sub-projects and topological complexity exceeds a threshold;

[0010] S4: Based on the spatiotemporal correlation and business semantic characteristics of historical call data, analyze the sub-project association scores and generate a storage integration strategy.

[0011] According to the above, S1 includes the following:

[0012] S101: Collect historical communication engineering projects and decompose them into a set of sub-project quantities, denoted as P = {P1, P2, ..., P i ..., P I}, where P i represents the number of sub-projects decomposed into the i-th historical communication engineering project; i∈[1,I]; I represents the total number of historical communication engineering projects; synchronously obtain the sub-project name information, project type label, data volume information, call information and construction duration of the decomposed historical communication engineering project; the call information of the sub-project data includes the number of calls, the amount of data called and the standard deviation of the call delay, and the number of calls, the amount of data called and the standard deviation of the call delay are normalized; based on the call information of the processed sub-project data, a sub-project call spatiotemporal matrix is ​​constructed, and the sub-project call spatiotemporal matrix of the i-th historical communication engineering project is recorded as T i ;

[0013]

[0014] Where M is equal to the number of sub-projects into which the i-th historical communication engineering project is decomposed; the sub-project calls the time-space matrix T i Contains elements (C (m，n) ,q (m，n) , △t (m，n) ), m, n∈[1, M], m and n are both positive integers; C (m，n) Indicates the number of times project m is called when subproject n initiates a call instruction; q (m，n) Indicates the average amount of data called by project m when project n initiates a call instruction, △t (m，n) It represents the standard deviation of the delay when project m is called when project n initiates a call instruction;

[0015] S102: Analyze data similarity based on the engineering space-time matrix of each historical communication engineering project; extract the call data of each historical communication engineering project containing sub-project pairs with the same name, and analyze the data similarity based on the call data combined with the data similarity function; in the data similarity function, if q (j，ab) Greater than or equal to q thr The output is 1, otherwise the output is 0; (j，ab) q represents the average amount of data called by project a in a single call when project b initiates a call instruction in the jth historical communication engineering project that contains both sub-projects a and b with the same name, j∈[1,J]; J represents the total number of historical communication engineering projects that contain both sub-projects a and b with the same name, J<I; thr Indicates the threshold of the amount of data called, which is preset by the system;

[0016] Analyze text similarity based on a collection of text reports from historical communication engineering projects. Mean text similarity analysis includes: using BERT to generate vectors for the text reports of subprojects a and b, calculating the cosine similarity between the vectors based on the cosine function, and calculating the mean.

[0017] Combining data similarity, text similarity, and time decay coefficient, we construct a cross-project knowledge graph, denoted as G = (V, E); where V represents a node set containing subproject names and corresponding project type labels; E represents an edge set, and the weight of the edge connecting subproject a and subproject b is denoted as W. (a，b) :

[0018]

[0019] Among them, η j represents the time decay coefficient of the jth historical communication engineering project, η j =exp(-t j );where t j = equal to the quotient of the difference between the completion time of the historical communication engineering project and the current time and the preset constant; λ is the weight coefficient, which is a system preset constant; S sem (a, b) represents the mean text similarity between subitem a and subitem b.

[0020] By normalizing call information (call count, data volume, and latency standard deviation), we eliminate dimensional differences in the data, making subsequent analysis more fair and reliable. The subproject call spatiotemporal matrix (Ti) provides a structured representation that accurately captures the spatiotemporal dependencies between subprojects (such as call frequency and data transfer patterns), avoiding the ambiguity inherent in traditional dependency modeling.

[0021] The combination of data similarity analysis (based on a threshold function) and text similarity analysis (BERT vectors and cosine similarity) enables multimodal data fusion. This not only identifies behavioral similarities (such as frequently called sub-items) but also captures semantic similarities (such as engineering terminology in report text), thereby generating a more comprehensive knowledge graph. The time decay coefficient (ηj) assigns higher weight to newer items, ensuring the knowledge graph is dynamically updated, improving the timeliness of recommendations or predictions (reducing the interference of outdated data).

[0022] The edge weight formula of the Knowledge Graph (G) (W(a,b) = λ*S_sem(a,b) + (1-λ)*(1 / J)*Σ(ηj*data similarity output)) balances text, data, and timing factors. The parameter λ (a system-preset weight coefficient) allows for flexible adjustment of the contribution of text and data similarity to suit different engineering scenarios (e.g., a higher λ can be set for projects with rich text reports). This enables the graph to adaptively integrate heterogeneous data, supporting efficient querying of sub-project associations in subsequent modules (such as S4 storage optimization), reducing the need for manual intervention.

[0023] According to the above, S2 contains the following:

[0024] S201: Grouping historical communication engineering projects according to project type labels; arranging each project type in ascending order according to the number of sub-projects to generate a sequence of historical communication engineering projects; and calculating a sliding window size for each project type, where the sliding window size is equal to the square root of the number of historical communication engineering projects in the project type, rounded upwards.

[0025] A sliding window is used to split the historical communication engineering project sequence; if the difference in the number of sub-projects of a historical communication engineering project greater than a threshold number within a single sliding window does not exceed a preset constant, the sliding window to which it belongs is marked as a high-density window, where the threshold number is equal to the product of the sliding window size and a preset coefficient rounded up; the high-density windows are merged according to the overlapping relationship of the intervals to generate clusters, and the cluster center of each cluster is analyzed. The cluster center is equal to the average number of sub-project calls within the cluster, where the sub-project call count includes the number of times the call is initiated and the number of times the call is received, and a cluster center set is generated;

[0026] S202: Obtain the number of adjacent edges of each knowledge graph node, and add the e-th knowledge graph node v e The number of adjacent edges is recorded as A e , from the knowledge graph node v e The sub-project calls the spatiotemporal matrix to extract the knowledge graph node v e Related elements, for knowledge graph node v e The call initiation instruction and the called data are analyzed to obtain the total number of call initiation instructions, the total number of called instructions, the average amount of data for a single call initiation, the average amount of data for a single call initiation, the average standard deviation of the call initiation delay, and the average standard deviation of the call initiation delay. Based on the total number of call initiation instructions, the total number of called instructions, the average amount of data for a single call initiation, the average amount of data for a single call initiation, the average standard deviation of the call initiation delay, and the average standard deviation of the call initiation delay, the feature vector V is generated. e ; For knowledge graph node v e Execute PageRank calculation and obtain the PageRank value, which is recorded as PageRank(v e), calculate the complexity factor for each cluster; the fth cluster I f The complexity factor is denoted as θ f :

[0027]

[0028] Among them, |I f | represents cluster I f Number of neutron items, t e Represents the knowledge graph node v e The construction time of ||V e || represents the eigenvector V e Length of the module;

[0029] S203: Obtain the number of adjacent edges corresponding to all sub-projects under the same project type, and calculate the median of the number of adjacent edges, recorded as median(A); Based on the median of the number of adjacent edges, the cluster center set and the complexity factor set, analyze the node dynamic threshold Z = α1×median(A)+α2×max(θ f ×C f ); where C f represents the cluster center of the f-th cluster.

[0030] A sliding window mechanism and high-density window marking automatically identify similar patterns in historical projects. This avoids the drawback of traditional clustering methods (such as K-means) that require a preset number of clusters, improving clustering efficiency. Clusters are generated by merging overlapping windows and calculating cluster centers, enabling the system to focus on frequently interacting sub-projects and providing a basis for resource allocation. The complexity factor integrates cluster size, node importance, eigenvector modulus, and construction time. This highlights complex clusters with tight construction schedules, helping prioritize high-risk projects.

[0031] Dynamic node thresholds combine the statistical median and the maximum complexity-cluster center product. This allows the threshold to adapt to different project types, avoiding the misjudgment caused by fixed thresholds. After marking high-complexity clusters, the system can automatically trigger alerts or optimizations to prevent resource bottlenecks (such as storage or computing overloads), potentially reducing the risk of project delays.

[0032] Based on the above, S3 contains the following:

[0033] Obtain the sub-project set of the current communication project, and construct a directed acyclic graph based on the sub-project set of the current communication project. The node set in the directed acyclic graph is equal to the sub-project set of the current communication project, and the directed edge indicates that dependencies exist only when the sub-projects have them. Divide the nodes into several modules according to the community discovery algorithm and analyze the modularity. Analyze the topological complexity, which is equal to the critical path length multiplied by the modularity divided by the total number of sub-projects. If the number of sub-projects and the topological complexity of the current communication project are both greater than the corresponding thresholds, activate the storage optimization process, and the corresponding threshold for the number of sub-projects of the current communication project is equal to the node dynamic threshold.

[0034] DAG construction visually represents sub-project dependencies (such as data flow or task sequence). Community discovery algorithms (such as the Louvain method) divide modules and calculate modularity (a measure of module cohesion), effectively identifying functional units within a project. The topological complexity formula integrates structural characteristics: critical path length reflects the longest dependency chain (affecting project duration), modularity reflects the degree of modularization (high values ​​indicate ease of management), and the total number of sub-projects normalizes complexity. This provides an objective complexity metric, replacing subjective assessments and improving management precision.

[0035] According to the above, S4 includes the following:

[0036] S401: Extract the sub-project set of the current communication project, search for the corresponding node for each sub-project name in the cross-project knowledge graph, extract all associated edges connected to the corresponding node and their weights, and form a sub-graph edge set;

[0037] S402: Analyze the correlation scores for each pair of sub-projects and their weights, and record the correlation scores of the current communication engineering sub-project u and sub-project v as 0. (u，v) :

[0038]

[0039] Among them, X (u，v) Indicates the number of historical call records of sub-project u and sub-project v in the current communication project, b x Indicates the data volume of the xth call record, △t x represents the standard deviation of the call delay of the xth call record, ξ() represents the Sigmoid function; Sim sem (u, v) represents the mean text similarity between subitem u and subitem v;

[0040] If the correlation score is greater than the corresponding threshold, the corresponding sub-project pair is marked as a physical storage co-location candidate; the data and services of the corresponding sub-projects are deployed on the same storage partition in descending order of the correlation score of the candidate pairs.

[0041] The association scoring formula combines historical call behavior (data volume bx and latency standard deviation Δtx) with semantic similarity. The Sigmoid function normalizes the call data to enhance robustness (avoid interference from extreme values). High-scoring sub-project pairs (such as pairs that are frequently called and have large data volumes) are preferentially co-located in the same storage partition, reducing data access latency (especially for high-real-time communication projects) and potentially improving I / O performance. Deploying candidate pairs in descending order of score enables the system to prioritize high-impact sub-projects (such as core modules) and maximize storage resource utilization. Combined with S3's activation mechanism, this claim forms a closed-loop optimization, reduces manual configuration requirements, and improves project deployment efficiency.

[0042] Another aspect of the present application provides a communication engineering information system based on big data, which is applied to the above-mentioned communication engineering information method based on big data, and includes a call data analysis module, a cluster analysis module, a real-time project screening module and an association storage module;

[0043] The call data analysis module is used to access the project management system, sensor network and user operation logs in real time to build a dynamic knowledge graph including sub-project topological relationships, data generation spatiotemporal distribution and cross-project call chains;

[0044] The cluster analysis module is used to generate a classification scheme based on the historical sub-project quantity distribution characteristics through a sliding window clustering algorithm, and dynamically calibrate the critical threshold for data storage priority integration in combination with the project complexity factor;

[0045] The real-time project screening module is used to analyze sub-project dependencies for new projects and activate the optimization process when the combined index of the number of sub-projects and topological complexity exceeds a threshold;

[0046] The associated storage module is used to analyze the sub-project association scores based on the spatiotemporal correlation and business semantic features of historical call data and generate a storage integration strategy.

[0047] According to the above content, the call data analysis module includes a spatiotemporal matrix analysis unit and a cross-engineering knowledge graph analysis unit;

[0048] The spatiotemporal matrix analysis unit is used to collect a set of sub-project numbers decomposed into historical communication engineering projects, and simultaneously obtain sub-project name information, project type label, data volume information, call information and construction duration of the decomposed historical communication engineering projects. The call information of the sub-project data includes the number of calls, the amount of data called and the standard deviation of the call delay, and normalize the number of calls, the amount of data called and the standard deviation of the call delay; and construct a sub-project call spatiotemporal matrix based on the call information of the processed sub-project data;

[0049] The cross-engineering knowledge graph analysis unit is used to analyze data similarity based on the engineering spatiotemporal matrix of each historical communication engineering project; analyze text similarity based on a set of text reports of historical communication engineering projects; and construct a cross-engineering knowledge graph by combining data similarity, text similarity and time decay coefficient.

[0050] According to the above content, the cluster analysis module includes a clustering unit and a dynamic threshold analysis unit;

[0051] The clustering unit is used to group various historical communication engineering projects according to engineering type labels; perform sliding window density clustering and output a cluster center set;

[0052] The dynamic threshold analysis unit is used to obtain the number of adjacent edges of each knowledge graph node, analyze the calling instructions and called data of the knowledge graph node, and calculate the complexity factor in each cluster; based on the median of the number of adjacent edges, the cluster center set and the complexity factor set, the node dynamic threshold is analyzed.

[0053] According to the above, the real-time project screening module includes a topological complexity analysis unit and an optimization activation unit;

[0054] The topological complexity analysis unit is used to obtain a set of sub-projects of the current communication project, construct a directed acyclic graph based on the set of sub-projects of the current communication project, wherein the set of nodes in the directed acyclic graph is equal to the set of sub-projects of the current communication project, and a directed edge indicates that there is a dependency relationship between the sub-projects if and only if there is a dependency relationship between the sub-projects; divide the nodes into several modules according to the community discovery algorithm and analyze the modularity; analyze the topological complexity, wherein the topological complexity is equal to the critical path length multiplied by the modularity divided by the total number of sub-projects;

[0055] The optimization activation unit is used to activate the storage optimization process if the number of sub-projects and the topological complexity of the current communication project are both greater than the corresponding thresholds, and the corresponding threshold of the number of sub-projects of the current communication project is equal to the node dynamic threshold.

[0056] According to the above content, the association storage module includes a subgraph edge set analysis unit and an optimization deployment unit;

[0057] The subgraph edge set analysis unit is used to extract the sub-project set of the current communication project, retrieve the corresponding node for each sub-project name in the cross-project knowledge graph, extract all associated edges connected to the corresponding node and their weights, and form a subgraph edge set;

[0058] The optimization deployment unit is used to analyze the association score of each pair of sub-projects and their weights. If the association score is greater than the corresponding threshold, the corresponding sub-project pair is marked as a physical storage co-location candidate; and the data and services of the corresponding sub-projects are deployed on the same storage partition in descending order of the association scores of the candidate pairs.

[0059] Compared with existing technologies, the present invention offers the following advantages: By normalizing call information, data dimension differences are eliminated, making subsequent analysis more fair and reliable. The spatiotemporal matrix of subproject calls provides a structured representation that accurately captures the spatiotemporal dependencies between subprojects, avoiding the ambiguity inherent in traditional dependency modeling. Data similarity analysis and text similarity analysis combine to achieve multimodal data fusion. This not only identifies behavioral similarities but also captures semantic similarities, thereby generating a more comprehensive knowledge graph. A time decay coefficient assigns higher weights to newer projects, ensuring dynamic updates of the knowledge graph and improving the timeliness of recommendations or predictions. The edge weight formula of the knowledge graph balances text, data, and temporal factors. Parameters allow for flexible adjustment of the contributions of text and data similarity to adapt to different project scenarios. This enables the graph to adaptively integrate heterogeneous data, supporting efficient querying of subproject associations by subsequent modules and reducing the need for manual intervention. A sliding window mechanism and high-density window tagging automatically identify similar patterns in historical projects. This avoids the drawback of traditional clustering methods that require a preset number of clusters, improving clustering efficiency. Overlapping windows are merged to generate clusters and cluster centers are calculated, enabling the system to focus on frequently interacting subprojects and providing a basis for resource allocation. The complexity factor integrates cluster size, node importance, eigenvector modulus, and construction duration. This highlights complex clusters with tight construction schedules, helping prioritize high-risk projects. The dynamic node threshold combines the statistical median and the product of maximum complexity and cluster center. This allows the threshold to adapt to different project types, avoiding misjudgments caused by fixed thresholds. After marking high-complexity clusters, the system can automatically trigger alerts or optimize, preventing resource bottlenecks and potentially reducing the risk of project delays. The DAG construct intuitively represents subproject dependencies, while the community discovery algorithm divides modules and calculates modularity, effectively identifying functional units within a project. The topological complexity formula integrates structural features: critical path length reflects the longest dependency chain, modularity reflects the degree of modularization, and the total number of subprojects normalizes complexity. This provides an objective complexity metric, replacing subjective assessments and improving management accuracy. The association scoring formula integrates historical call behavior and semantic similarity. The sigmoid function normalizes call data for enhanced robustness. High-scoring subproject pairs are preferentially co-located in the same storage partition, reducing data access latency and potentially improving I / O performance. Deploying candidate pairs in descending order of score allows the system to prioritize high-impact subprojects and maximize storage resource utilization. Combined with S3's activation mechanism, this claim forms a closed-loop optimization loop, reducing manual configuration requirements and improving project deployment efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0060] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0061] Figure 1Schematic diagram of the process of the communication engineering informatization method based on big data of the present invention;

[0062] Figure 2 This is a schematic diagram of the structure of the communication engineering information system based on big data of the present invention. DETAILED DESCRIPTION

[0063] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0064] Example 1: Please refer to Figure 1 The present invention provides a technical solution: a communication engineering informationization method based on big data, which includes the following steps:

[0065] S1: Real-time access to the engineering management system, sensor network, and user operation logs to build a dynamic knowledge graph that includes sub-project topological relationships, data generation spatiotemporal distribution, and cross-project call chains;

[0066] In S1, the following are included:

[0067] S101: Collect historical communication engineering projects and decompose them into a set of sub-project quantities, denoted as P = {P1, P2, ..., P i ..., P I}, where P i represents the number of sub-projects decomposed into the i-th historical communication engineering project; i∈[1,I]; I represents the total number of historical communication engineering projects; synchronously obtain the sub-project name information, project type label, data volume information, call information and construction duration of the decomposed historical communication engineering project; the call information of the sub-project data includes the number of calls, the amount of data called and the standard deviation of the call delay, and the number of calls, the amount of data called and the standard deviation of the call delay are normalized; based on the call information of the processed sub-project data, a sub-project call spatiotemporal matrix is ​​constructed, and the sub-project call spatiotemporal matrix of the i-th historical communication engineering project is recorded as T i ;

[0068]

[0069] Where M is equal to the number of sub-projects into which the i-th historical communication engineering project is decomposed; the sub-project calls the time-space matrix T i Contains elements (C (m，n) ,q (m，n) , △t (m，n)), m, n∈[1, M], m and n are both positive integers; C (m，n) Indicates the number of times project m is called when subproject n initiates a call instruction; q (m，n) Indicates the average amount of data that is called by project m when project n initiates a call instruction, △t (m，n) It represents the standard deviation of the delay when project m is called when project n initiates a call instruction;

[0070] S102: Analyze data similarity based on the engineering space-time matrix of each historical communication engineering project; extract the call data of each historical communication engineering project containing sub-project pairs with the same name, and analyze the data similarity based on the call data combined with the data similarity function; in the data similarity function, if q (j，ab) Greater than or equal to q thr The output is 1, otherwise the output is 0; (j，ab) q represents the average amount of data called by project a in a single call when project b initiates a call instruction in the jth historical communication engineering project that contains both sub-projects a and b with the same name, j∈[1,J]; J represents the total number of historical communication engineering projects that contain both sub-projects a and b with the same name, J<I; thr Indicates the threshold of the amount of data called, which is preset by the system;

[0071] Analyze text similarity based on a collection of text reports from historical communication engineering projects. Mean text similarity analysis includes: using BERT to generate vectors for the text reports of subprojects a and b, calculating the cosine similarity between the vectors based on the cosine function, and calculating the mean.

[0072] Combining data similarity, text similarity, and time decay coefficient, we construct a cross-project knowledge graph, denoted as G = (V, E). V represents a node set, which contains sub-project names and corresponding project type labels. E represents an edge set, and the weight of the edge connecting sub-project a and sub-project b is denoted as W. (a，b) :

[0073]

[0074] Among them, η j represents the time decay coefficient of the jth historical communication engineering project, η j =exp(-t j ); where t j It is equal to the quotient of the difference between the completion time of the historical communication engineering project and the current time and the preset constant; λ is the weight coefficient, which is a system preset constant; S sem (a, b) represents the mean text similarity between sub-item a and sub-item b.

[0075] S2: Based on the historical distribution characteristics of the number of sub-projects, a classification scheme is generated through a sliding window clustering algorithm, and the critical threshold for data storage priority integration is dynamically calibrated in combination with the project complexity factor;

[0076] Include the following in S2:

[0077] S201: Grouping historical communication engineering projects according to project type labels; arranging each project type in ascending order according to the number of sub-projects to generate a sequence of historical communication engineering projects; calculating a sliding window size for each project type, where the sliding window size is equal to the arithmetic square root of the number of historical communication engineering projects in the project type, rounded upwards;

[0078] A sliding window is used to split the historical communication engineering project sequence. If the difference in the number of sub-projects of a historical communication engineering project greater than a threshold number within a single sliding window does not exceed a preset constant, the sliding window to which it belongs is marked as a high-density window. The threshold number is equal to the product of the sliding window size and a preset coefficient rounded up. The high-density windows are merged according to the overlapping relationship of the intervals to generate clusters. The cluster center of each cluster is analyzed. The cluster center is equal to the average number of sub-project calls within the cluster. The sub-project call count includes the number of times it initiates calls and the number of times it is called. The cluster center set is generated.

[0079] S202: Obtain the number of adjacent edges of each knowledge graph node, and add the e-th knowledge graph node v e The number of adjacent edges is recorded as A e , from the knowledge graph node v e The sub-project calls the spatiotemporal matrix to extract the knowledge graph node v e Related elements, for knowledge graph node v e The call initiation instruction and the called data are analyzed to obtain the total number of call initiation instructions, the total number of called instructions, the average amount of data for a single call initiation, the average amount of data for a single call initiation, the average standard deviation of the call initiation delay, and the average standard deviation of the call initiation delay. Based on the total number of call initiation instructions, the total number of called instructions, the average amount of data for a single call initiation, the average amount of data for a single call initiation, the average standard deviation of the call initiation delay, and the average standard deviation of the call initiation delay, the feature vector V is generated. e ; For knowledge graph node v e Execute PageRank calculation and obtain the PageRank value, which is recorded as PageRank(v e ), calculate the complexity factor for each cluster; the fth cluster I f The complexity factor is denoted as θ f :

[0080]

[0081] Among them, |I f| represents cluster I f Number of neutron items, t e Represents the knowledge graph node v e The construction time of ||V e || represents the eigenvector V e Length of the module;

[0082] S203: Obtain the number of adjacent edges corresponding to all sub-projects under the same project type, and calculate the median of the number of adjacent edges, recorded as median(A); Based on the median of the number of adjacent edges, the cluster center set and the complexity factor set, analyze the node dynamic threshold Z = α1×median(A)+α2×max(θ f ×C f ); where C f represents the cluster center of the f-th cluster.

[0083] S3: Analyze sub-project dependencies for new projects and activate the optimization process when the combined indicator of the number of sub-projects and topological complexity exceeds a threshold;

[0084] In S3, it contains the following:

[0085] Obtain the sub-project set of the current communication project, and construct a directed acyclic graph based on the sub-project set of the current communication project. The node set in the directed acyclic graph is equal to the sub-project set of the current communication project, and the directed edge indicates that dependencies exist only when the sub-projects have them. Divide the nodes into several modules according to the community discovery algorithm and analyze the modularity. Analyze the topological complexity, which is equal to the critical path length multiplied by the modularity divided by the total number of sub-projects. If the number of sub-projects and the topological complexity of the current communication project are both greater than the corresponding thresholds, activate the storage optimization process, and the corresponding threshold for the number of sub-projects of the current communication project is equal to the node dynamic threshold.

[0086] S4: Based on the spatiotemporal correlation and business semantic characteristics of historical call data, analyze the sub-project association scores and generate a storage integration strategy.

[0087] In S4, include the following:

[0088] S401: Extract the sub-project set of the current communication project, search for the corresponding node for each sub-project name in the cross-project knowledge graph, extract all associated edges connected to the corresponding node and their weights, and form a sub-graph edge set;

[0089] S402: Analyze the correlation scores for each pair of sub-projects and their weights, and record the correlation scores of the current communication engineering sub-project u and sub-project v as 0. (u，v) :

[0090]

[0091] Among them, X(u，v) Indicates the number of historical call records of sub-project u and sub-project v in the current communication project, b x Indicates the data volume of the xth call record, △t x represents the standard deviation of the call delay of the xth call record, ξ() represents the Sigmoid function; Sim sem (u, v) represents the mean text similarity between subitem u and subitem v;

[0092] If the correlation score is greater than the corresponding threshold, the corresponding sub-project pair is marked as a physical storage co-location candidate; the data and services of the corresponding sub-projects are deployed on the same storage partition in descending order of the correlation score of the candidate pairs.

[0093] Example 2: Please refer to Figure 2 ,The present invention provides a technical solution: a communication engineering information system based on big data, the system includes a call data analysis module, a cluster analysis module, a real-time project screening module and an associated storage module;

[0094] The call data analysis module is used to access the project management system, sensor network and user operation logs in real time to build a dynamic knowledge graph that includes sub-project topological relationships, data generation spatiotemporal distribution and cross-project call chains;

[0095] The cluster analysis module is used to generate a classification scheme based on the historical sub-project quantity distribution characteristics through a sliding window clustering algorithm, and dynamically calibrate the critical threshold for data storage priority integration in combination with the project complexity factor;

[0096] The real-time project screening module is used to analyze sub-project dependencies for new projects and activate the optimization process when the combined indicator of the number of sub-projects and topological complexity exceeds a threshold;

[0097] The associated storage module is used to analyze the sub-project association scores and generate storage integration strategies based on the spatiotemporal correlation and business semantic characteristics of historical call data.

[0098] The calling data analysis module includes a spatiotemporal matrix analysis unit and a cross-engineering knowledge graph analysis unit;

[0099] The spatiotemporal matrix analysis unit is used to collect the number of sub-projects decomposed into historical communication engineering projects, and simultaneously obtain the sub-project name information, project type label, data volume information, call information and construction duration of the decomposed historical communication engineering projects. The call information of the sub-project data includes the number of calls, the amount of data called and the standard deviation of the call delay. The number of calls, the amount of data called and the standard deviation of the call delay are normalized; based on the call information of the processed sub-project data, a sub-project call spatiotemporal matrix is ​​constructed;

[0100] The cross-engineering knowledge graph analysis unit is used to analyze data similarity based on the engineering spatiotemporal matrix of each historical communication engineering project; analyze text similarity based on the text report set of historical communication engineering projects; and construct a cross-engineering knowledge graph by combining data similarity, text similarity and time decay coefficient.

[0101] The cluster analysis module includes a clustering unit and a dynamic threshold analysis unit;

[0102] The clustering unit is used to group each historical communication engineering project according to the engineering type label; perform sliding window density clustering and output the cluster center set;

[0103] The dynamic threshold analysis unit is used to obtain the number of neighboring edges of each knowledge graph node, analyze the calling instructions and called data of the knowledge graph node, and calculate the complexity factor in each cluster; based on the median number of neighboring edges, the cluster center set and the complexity factor set, the node dynamic threshold is analyzed.

[0104] The real-time project screening module includes a topological complexity analysis unit and an optimization activation unit;

[0105] The topological complexity analysis unit is used to obtain the sub-project set of the current communication project, construct a directed acyclic graph based on the sub-project set of the current communication project, and the node set in the directed acyclic graph is equal to the sub-project set of the current communication project. The directed edge indicates that there is a dependency relationship between the sub-projects. The nodes are divided into several modules according to the community discovery algorithm and the modularity is analyzed. The topological complexity is analyzed, and the topological complexity is equal to the critical path length multiplied by the modularity divided by the total number of sub-projects.

[0106] The optimization activation unit is used to activate the storage optimization process if the number of sub-projects and the topological complexity of the current communication project are both greater than the corresponding thresholds, and the corresponding threshold of the number of sub-projects of the current communication project is equal to the node dynamic threshold.

[0107] The association storage module includes a subgraph edge set analysis unit and an optimization deployment unit;

[0108] The subgraph edge set analysis unit is used to extract the sub-project set of the current communication project. In the cross-project knowledge graph, the corresponding node is retrieved for each sub-project name, and all associated edges connected to the corresponding node and their weights are extracted to form a subgraph edge set.

[0109] The optimized deployment unit is used to analyze the association score of each pair of sub-projects and their weights. If the association score is greater than the corresponding threshold, the corresponding sub-project pair is marked as a physical storage co-location candidate; the data and services of the corresponding sub-projects are deployed on the same storage partition in descending order of the association score of the candidate pairs.

[0110] It should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that includes a list of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, method, article, or apparatus.

[0111] 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 invention can be embodied in other specific forms without departing from the spirit or essential characteristics of the invention. Therefore, the embodiments should be considered in all respects as illustrative and non-restrictive, and the scope of the invention is defined by the appended claims, not the foregoing description, and all variations within the meaning and range of equivalents of the claims are intended to be included therein. Any reference sign in a claim should not be construed as limiting the claim to which it relates.

Claims

1. A communication engineering informationization method based on big data, characterized in that: The method comprises the following steps: S1: Real-time access to the engineering management system, sensor network, and user operation logs to build a dynamic knowledge graph that includes sub-project topological relationships, data generation spatiotemporal distribution, and cross-project call chains; S2: Based on the historical distribution characteristics of the number of sub-projects, a classification scheme is generated through a sliding window clustering algorithm, and the critical threshold for data storage priority integration is dynamically calibrated in combination with the project complexity factor; S3: Analyze sub-project dependencies for new projects and activate the optimization process when the combined indicator of the number of sub-projects and topological complexity exceeds a threshold; S4: Based on the spatiotemporal correlation and business semantic characteristics of historical call data, analyze the sub-project association scores and generate a storage integration strategy.

2. The communication engineering informatization method based on big data according to claim 1, characterized in that: In S1, the following are included: S101: Collect historical communication engineering projects and decompose them into a set of sub-project quantities, denoted as P = {P1, P2, ..., P i ..., P I }, where P i represents the number of sub-projects decomposed into the i-th historical communication engineering project; i∈[1,I]; I represents the total number of historical communication engineering projects; synchronously obtain the sub-project name information, project type label, data volume information, call information and construction duration of the decomposed historical communication engineering project; the call information of the sub-project data includes the number of calls, the amount of data called and the standard deviation of the call delay, and the number of calls, the amount of data called and the standard deviation of the call delay are normalized; based on the call information of the processed sub-project data, a sub-project call spatiotemporal matrix is ​​constructed, and the sub-project call spatiotemporal matrix of the i-th historical communication engineering project is recorded as T i ; S102: Analyze data similarity based on the engineering space-time matrix of each historical communication engineering project; extract the call data of each historical communication engineering project containing sub-project pairs with the same name, and analyze the data similarity based on the call data combined with the data similarity function; in the data similarity function, if q (j，ab) Greater than or equal to q thr The output is 1, otherwise the output is 0; (j，ab) q represents the average amount of data called by project a in a single call when project b initiates a call instruction in the jth historical communication engineering project that contains both sub-projects a and b with the same name, j∈[1,J]; J represents the total number of historical communication engineering projects that contain both sub-projects a and b with the same name, J<I; thr Indicates the threshold of the amount of data called, which is preset by the system; Analyze text similarity based on a collection of text reports from historical communication engineering projects. Mean text similarity analysis includes: using BERT to generate vectors for the text reports of subprojects a and b, calculating the cosine similarity between the vectors based on the cosine function, and calculating the mean. Combining data similarity, text similarity, and time decay coefficient, we construct a cross-project knowledge graph, denoted as G = (V, E); where V represents a node set containing subproject names and corresponding project type labels; E represents an edge set, and the weight of the edge connecting subproject a and subproject b is denoted as W. (a，b) .

3. The communication engineering informatization method based on big data according to claim 2, characterized in that: Include the following in S2: S201: Grouping historical communication engineering projects according to project type labels; arranging each project type in ascending order according to the number of sub-projects to generate a sequence of historical communication engineering projects; and calculating a sliding window size for each project type, where the sliding window size is equal to the square root of the number of historical communication engineering projects in the project type, rounded upwards. Use sliding windows to split the historical communication engineering project sequence; If the difference in the number of sub-projects of historical communication engineering projects within a single sliding window is greater than a threshold number and does not exceed a preset constant, the sliding window to which it belongs is marked as a high-density window, where the threshold number is equal to the product of the sliding window size and a preset coefficient rounded up; the high-density windows are merged according to the interval overlap relationship to generate clusters, and the cluster center of each cluster is analyzed. The cluster center is equal to the average number of sub-project calls within the cluster, where the sub-project call count includes the number of calls initiated and the number of calls received, to generate a cluster center set; S202: Obtain the number of adjacent edges of each knowledge graph node, and add the e-th knowledge graph node v e The number of adjacent edges is recorded as A e , from the knowledge graph node v e The sub-project calls the spatiotemporal matrix to extract the knowledge graph node v e Related elements, for knowledge graph node v e The call initiation instruction and the called data are analyzed to obtain the total number of call initiation instructions, the total number of called instructions, the average amount of data for a single call initiation, the average amount of data for a single call initiation, the average standard deviation of the call initiation delay, and the average standard deviation of the call initiation delay. Based on the total number of call initiation instructions, the total number of called instructions, the average amount of data for a single call initiation, the average amount of data for a single call initiation, the average standard deviation of the call initiation delay, and the average standard deviation of the call initiation delay, the feature vector V is generated. e ; For knowledge graph node v e Execute PageRank calculation and obtain the PageRank value, which is recorded as PageRank(v e ), calculate the complexity factor for each cluster; the fth cluster I f The complexity factor is denoted as θ f ; S203: Obtain the number of adjacent edges corresponding to all sub-projects under the same project type, and calculate the median of the number of adjacent edges, recorded as median(A); Based on the median of the number of adjacent edges, the cluster center set and the complexity factor set, analyze the node dynamic threshold Z = α1×median(A)+α2×max(θ f ×C f ); where C f represents the cluster center of the f-th cluster.

4. The communication engineering informatization method based on big data according to claim 3 is characterized in that: In S3, it contains the following: Obtain the sub-project set of the current communication project, and construct a directed acyclic graph based on the sub-project set of the current communication project. The node set in the directed acyclic graph is equal to the sub-project set of the current communication project, and the directed edge indicates that dependencies exist only when the sub-projects have them. Divide the nodes into several modules according to the community discovery algorithm and analyze the modularity. Analyze the topological complexity, which is equal to the critical path length multiplied by the modularity divided by the total number of sub-projects. If the number of sub-projects and the topological complexity of the current communication project are both greater than the corresponding thresholds, activate the storage optimization process, and the corresponding threshold for the number of sub-projects of the current communication project is equal to the node dynamic threshold.

5. The communication engineering informatization method based on big data according to claim 4 is characterized in that: In S4, include the following: S401: Extract the sub-project set of the current communication project, search for the corresponding node for each sub-project name in the cross-project knowledge graph, extract all associated edges connected to the corresponding node and their weights, and form a sub-graph edge set; S402: Analyze the correlation scores for each pair of sub-projects and their weights, and record the correlation scores of the current communication engineering sub-project u and sub-project v as 0. (u，v) ; If the correlation score is greater than the corresponding threshold, the corresponding sub-project pair is marked as a physical storage co-location candidate; the data and services of the corresponding sub-projects are deployed on the same storage partition in descending order of the correlation score of the candidate pairs.

6. A communication engineering information system based on big data, wherein the system is applied to implement the communication engineering information method based on big data according to any one of claims 1 to 5, characterized in that: The system includes a call data analysis module, a cluster analysis module, a real-time project screening module and an associated storage module; The call data analysis module is used to access the project management system, sensor network and user operation logs in real time to build a dynamic knowledge graph including sub-project topological relationships, data generation spatiotemporal distribution and cross-project call chains; The cluster analysis module is used to generate a classification scheme based on the historical sub-project quantity distribution characteristics through a sliding window clustering algorithm, and dynamically calibrate the critical threshold for data storage priority integration in combination with the project complexity factor; The real-time project screening module is used to analyze sub-project dependencies for new projects and activate the optimization process when the combined index of the number of sub-projects and topological complexity exceeds a threshold; The associated storage module is used to analyze the sub-project association scores based on the spatiotemporal correlation and business semantic features of historical call data and generate a storage integration strategy.

7. The communication engineering information system based on big data according to claim 6, characterized in that: The call data analysis module includes a spatiotemporal matrix analysis unit and a cross-engineering knowledge graph analysis unit; The spatiotemporal matrix analysis unit is used to collect a set of sub-project numbers decomposed into historical communication engineering projects, and simultaneously obtain sub-project name information, project type label, data volume information, call information and construction duration of the decomposed historical communication engineering projects. The call information of the sub-project data includes the number of calls, the amount of data called and the standard deviation of the call delay, and normalize the number of calls, the amount of data called and the standard deviation of the call delay; and construct a sub-project call spatiotemporal matrix based on the call information of the processed sub-project data; The cross-engineering knowledge graph analysis unit is used to analyze data similarity based on the engineering spatiotemporal matrix of each historical communication engineering project; analyze text similarity based on a set of text reports of historical communication engineering projects; and construct a cross-engineering knowledge graph by combining data similarity, text similarity and time decay coefficient.

8. The communication engineering information system based on big data according to claim 6, characterized in that: The cluster analysis module includes a clustering unit and a dynamic threshold analysis unit; The clustering unit is used to group various historical communication engineering projects according to engineering type labels; perform sliding window density clustering and output a cluster center set; The dynamic threshold analysis unit is used to obtain the number of neighboring edges of each knowledge graph node, analyze the calling instructions and called data of the knowledge graph node, and calculate the complexity factor in each cluster; based on the median of the number of neighboring edges, the cluster center set and the complexity factor set, the node dynamic threshold is analyzed.

9. The communication engineering information system based on big data according to claim 6, characterized in that: The real-time project screening module includes a topological complexity analysis unit and an optimization activation unit; The topological complexity analysis unit is used to obtain a set of sub-projects of the current communication project, construct a directed acyclic graph based on the set of sub-projects of the current communication project, wherein the set of nodes in the directed acyclic graph is equal to the set of sub-projects of the current communication project, and a directed edge indicates that there is a dependency relationship between the sub-projects if and only if there is a dependency relationship between the sub-projects; divide the nodes into several modules according to the community discovery algorithm and analyze the modularity; analyze the topological complexity, wherein the topological complexity is equal to the critical path length multiplied by the modularity divided by the total number of sub-projects; The optimization activation unit is used to activate the storage optimization process if the number of sub-projects and the topological complexity of the current communication project are both greater than the corresponding thresholds, and the corresponding threshold of the number of sub-projects of the current communication project is equal to the node dynamic threshold.

10. The communication engineering information system based on big data according to claim 6, characterized in that: The association storage module includes a subgraph edge set analysis unit and an optimization deployment unit; The subgraph edge set analysis unit is used to extract the sub-project set of the current communication project, retrieve the corresponding node for each sub-project name in the cross-project knowledge graph, extract all associated edges connected to the corresponding node and their weights, and form a subgraph edge set; The optimization deployment unit is used to analyze the association score of each pair of sub-projects and their weights. If the association score is greater than the corresponding threshold, the corresponding sub-project pair is marked as a physical storage co-location candidate; and the data and services of the corresponding sub-projects are deployed on the same storage partition in descending order of the association scores of the candidate pairs.

Images