A multi-source heterogeneous data intelligent processing and situation visualized analysis method and system

Abstract

The application discloses a kind of multi-source heterogeneous data intelligent processing and situation visual analysis method and system, it is related to dynamic visual analysis technical field, comprising the following steps: S1, unified state index construction is carried out to multi-source heterogeneous operation data;S2, using unified state index set carries out cross-source state mapping analysis;S3, using heterogeneous associated state graph is carried out space-time coupling propagation analysis;S4, using dynamic situation evolution matrix carries out regional situation aggregation analysis;S5, dynamic visual mapping analysis.The application is by setting cross-source state mapping analysis based on unified state index set, and based on unified state index set, state node set, cross-source state connection edge set and state propagation path set are constructed, so that the state data in different data sources forms continuous associated propagation structure, so as to be able to support subsequent space-time coupling propagation analysis, regional situation aggregation analysis and dynamic visual mapping analysis.

Description

Technical Field

[0001] This invention relates to the field of dynamic visualization analysis technology, specifically to a method and system for intelligent processing and situation visualization analysis of multi-source heterogeneous data. Background Technology

[0002] With the continuous growth of data scale in scenarios such as urban operation monitoring, industrial equipment supervision, traffic operation analysis, and cyberspace situational awareness, data from different sources exhibit significant differences in data structure, collection cycle, state expression methods, and correlation relationships, forming a typical multi-source heterogeneous data environment. Existing technologies typically process heterogeneous data by unifying data formats or establishing single data analysis models. However, in complex operational scenarios, there are often cross-level, cross-time, and cross-regional state correlations between different data sources. Relying solely on static data integration methods is insufficient to accurately reflect the state propagation process and situational evolution.

[0003] In existing technologies, association analysis of multi-source heterogeneous data usually uses fixed field matching, unified label mapping, or simple graph structure connection to establish the relationship between data. The analysis process mainly focuses on the construction of correspondence between static data, and it is difficult to uniformly map the state propagation path, state connection edge, and cross-source propagation continuity relationship in different data sources. Summary of the Invention

[0004] To address the shortcomings of existing technologies, this invention provides a method and system for intelligent processing and situation visualization analysis of multi-source heterogeneous data, in order to solve the problems mentioned in the background.

[0005] To achieve the above objectives, the present invention provides the following technical solution:

[0006] In a first aspect, embodiments of the present invention provide a method for intelligent processing and situation visualization analysis of multi-source heterogeneous data, comprising the following steps:

[0007] S1. Construct a unified state index for multi-source heterogeneous operational data to obtain a unified state index set;

[0008] S2. Use a unified state index set to perform cross-source state mapping analysis to obtain a heterogeneous correlation state map;

[0009] S3. Use heterogeneous correlation state graphs to perform spatiotemporal coupling propagation analysis to obtain the dynamic situation evolution matrix;

[0010] S4. Use the dynamic situation evolution matrix to perform regional situation aggregation analysis to obtain a multi-level situation distribution set;

[0011] S5. Use multi-level situation distribution sets and heterogeneous correlation state maps to perform dynamic visualization mapping analysis to obtain a time-series situation visualization result set.

[0012] To further optimize this technical solution, step S1 establishes a unified state representation basis for multi-source heterogeneous operating data, resulting in a unified state index set:

[0013] ;

[0014] in:

[0015] Indicates the first 1 state index node ;

[0016] This represents the total number of state nodes in the unified state index set;

[0017] Each state index node include:

[0018] ;

[0019] in:

[0020] Indicates the first The time window number corresponding to each status node;

[0021] Indicates the first The spatial region number corresponding to each state node;

[0022] Indicates the first The state category number corresponding to each state node;

[0023] Indicates the first The event source number corresponding to each status node;

[0024] Indicates the first The position number of each state node in the state sequence.

[0025] To further optimize this technical solution, step S2 is used to generate the unified state index set in step S1. Based on this, cross-source association relationships are established for state nodes from different heterogeneous sources, and a heterogeneous association state map that can characterize state propagation relationships and state connection structures is formed.

[0026] Step S2, when performing cross-source state mapping analysis, includes the following steps:

[0027] State node synchronization mapping analysis;

[0028] Analysis of cross-source state connection edge construction;

[0029] State association path construction analysis;

[0030] Analysis of heterogeneous association state map generation.

[0031] To further optimize this technical solution, in step S2, during the state node synchronization mapping analysis, the unified state index set output in step S1 is read. The synchronization correlation between different state nodes is calculated, and the state synchronization correlation degree is:

[0032] ;

[0033] In the formula:

[0034] State node With state nodes The degree of state synchronization correlation between them;

[0035] Indicates the adjacency relationship of time windows. Indicates the time window association weight;

[0036] Indicates the adjacency relationship of spatial regions. Indicates the spatial region association weight;

[0037] Indicates the relationship between status categories. Indicates the weight associated with the state category;

[0038] Indicates the source and relationship of the event. Indicates the weight of the association between the event source and the event;

[0039] Represents the adjacency relationship of state sequences. This represents the weight associated with the state sequence.

[0040] To further optimize this technical solution, in step S2, when performing cross-source state connection edge construction analysis, cross-source state connection edges are established between state nodes, and the set of state connection edges is set as follows:

[0041] ;

[0042] in:

[0043] Represents the set of cross-source state connection edges;

[0044] State node With state nodes The connecting edges between them;

[0045] Indicates the threshold for state synchronization association;

[0046] The event co-occurrence relationships in the state connection edges are then calculated, and the event co-occurrence strength is expressed by the following formula:

[0047] ;

[0048] In the formula:

[0049] State node With state nodes The intensity of event co-occurrence between them;

[0050] State node With state nodes Number of cross-source co-occurrences within the same time window;

[0051] State node With state nodes Total number of occurrences.

[0052] To further optimize this technical solution, in step S2, when performing state association path construction analysis, the state propagation paths in the state connection structure are constructed, and the following set of state propagation paths is set as follows:

[0053] ;

[0054] in:

[0055] Represents the set of state propagation paths;

[0056] Indicates the first State propagation path;

[0057] Indicates the total number of state propagation paths;

[0058] Each state propagation path satisfies:

[0059] ;

[0060] After constructing the state propagation path, the propagation continuity in the path is calculated using the following formula:

[0061] ;

[0062] In the formula:

[0063] Indicates the first The path continuity of each state propagation path;

[0064] This represents the number of nodes in the path that satisfy the continuous-time propagation relationship;

[0065] This indicates the total number of nodes in the path.

[0066] To further optimize this technical solution, in step S2, during the heterogeneous association state graph generation and analysis, state nodes, state connection edges, and state propagation paths are uniformly aggregated to generate a heterogeneous association state graph, the expression of which is:

[0067] ;

[0068] in:

[0069] Represents a heterogeneous association state map;

[0070] Represents a set of state nodes;

[0071] Represents the set of cross-source state connection edges;

[0072] This represents the set of state propagation paths.

[0073] To further optimize this technical solution, step S3, based on the heterogeneous correlation state map generated in step S2, performs spatiotemporal coupled propagation analysis on the cross-source connections and state propagation paths already established between state nodes, thereby forming a dynamic situational evolution matrix that can characterize the state temporal propagation process, regional diffusion relationships, and propagation continuity. .

[0074] To further optimize this technical solution, step S4 performs regional situation aggregation analysis on the dynamic situation evolution matrix generated in step S3, so that the dynamic propagation results form a multi-level situation distribution set with regional hierarchical structure and time stage structure.

[0075] Step S5: Based on the multi-level situation distribution set generated in step S4, and combined with the heterogeneous correlation state map generated in step S2, perform dynamic visualization mapping analysis on the situation propagation process, thereby forming a time-series situation visualization result set that can reflect the temporal evolution relationship, regional propagation relationship, and state propagation path relationship.

[0076] A multi-source heterogeneous data intelligent processing and situation visualization analysis system is constructed based on the aforementioned multi-source heterogeneous data intelligent processing and situation visualization analysis method. The system includes the following modules: a unified state index construction module, a heterogeneous correlation state map construction module, a dynamic situation evolution analysis module, a multi-level situation aggregation module, and a time-series situation visualization mapping module.

[0077] In a second aspect, embodiments of the present invention provide a computer device, including a memory and a processor, wherein the memory stores a computer program, and the computer program instructions, when executed by the processor, implement the steps of the method and system for intelligent processing and situational visualization analysis of multi-source heterogeneous data as described in the first aspect of the present invention.

[0078] Thirdly, embodiments of the present invention provide a computer-readable storage medium having a computer program stored thereon, wherein: when the computer program instructions are executed by a processor, they implement the steps of the method and system for intelligent processing and situational visualization analysis of multi-source heterogeneous data as described in the first aspect of the present invention.

[0079] Compared with existing technologies, this invention provides a method and system for intelligent processing and situation visualization analysis of multi-source heterogeneous data, which has the following beneficial effects:

[0080] This method and system for intelligent processing and situation visualization analysis of multi-source heterogeneous data sets establishes a cross-source state mapping analysis based on a unified state index set. It also constructs a set of state nodes, a set of cross-source state connection edges, and a set of state propagation paths based on the unified state index set. This enables state data from different data sources to form a continuous and interconnected propagation structure, thereby supporting subsequent spatiotemporal coupled propagation analysis, regional situation aggregation analysis, and dynamic visualization mapping analysis. This solves the problem in existing technologies that it is difficult to establish a cross-source state propagation association structure and form a continuous situation propagation relationship. Attached Figure Description

[0081] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0082] Figure 1 This is a flowchart illustrating a method for intelligent processing and situational visualization analysis of multi-source heterogeneous data proposed in this invention.

[0083] Figure 2This is a schematic diagram of the cross-source state mapping analysis process of a multi-source heterogeneous data intelligent processing and situation visualization analysis method proposed in this invention.

[0084] Figure 3 This is a schematic diagram of the spatiotemporal coupling propagation analysis process of a multi-source heterogeneous data intelligent processing and situation visualization analysis method proposed in this invention.

[0085] Figure 4 This is a schematic diagram of the dynamic visualization mapping analysis process of a multi-source heterogeneous data intelligent processing and situation visualization analysis method proposed in this invention. Detailed Implementation

[0086] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

[0087] Many specific details are set forth in the following description in order to provide a full understanding of the invention. However, the invention may also be practiced in other ways different from those described herein, and those skilled in the art can make similar extensions without departing from the spirit of the invention. Therefore, the invention is not limited to the specific embodiments disclosed below.

[0088] Secondly, the term "an embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The phrase "in one embodiment" appearing in different places throughout this specification does not necessarily refer to the same embodiment, nor is it a single embodiment or an embodiment selectively excluded from other embodiments.

[0089] Example 1:

[0090] Reference Figures 1-4 This is the first embodiment of the present invention, which provides a method for intelligent processing and situational visualization analysis of multi-source heterogeneous data, including the following steps:

[0091] S1. Construct a unified state index for multi-source heterogeneous operational data to obtain a unified state index set;

[0092] Step S1 establishes a unified state representation basis for multi-source heterogeneous operational data, solving the problem of expression differences in time scale, spatial identification and state category between different data sources, so that the state results in different heterogeneous data can be mapped to the same state index system, providing a unified state positioning basis for cross-source state mapping analysis in the subsequent step S2.

[0093] Step S1, during the construction of the unified state index, includes the following steps:

[0094] Heterogeneous runtime data status analysis:

[0095] Data type identification is performed on operational data from different data sources, and corresponding status parsing structures are established; among them, multi-source heterogeneous operational data includes sensor time series data, log event data, video detection result data, and business operation node status data;

[0096] For sensor time-series data, mature time-series data parsing technology is used to extract sampling time, device number, and status values ​​to form a sensor status sequence;

[0097] For log event data, mature log structure parsing technology is used to extract event trigger time, event category and node identifier to form a log event status set;

[0098] Based on the video detection results data, mature target detection and event recognition technologies are used to extract the target state, region location, and behavioral results in the video frames, forming a set of visual state results.

[0099] For the status data of business operation nodes, mature business status parsing technology is used to extract node status, task number and status change time to form a set of business node status.

[0100] After completing the state parsing of data from different sources, the sensor state sequence, log event state set, visual state result set, and business node state set are integrated to obtain the original state node set.

[0101] Unified time-scale mapping processing:

[0102] Mature time synchronization technology is adopted, using a unified time base as the time reference, to correct the time offset of timestamps from different data sources. The unified time base adopts a central time synchronization base, and each state node is mapped to the unified time reference axis. Then, the state nodes are processed by time slicing according to the preset time window granularity, so that state nodes from different sources can be mapped to the unified time window structure. The time window granularity is divided according to the system operation cycle, and the time window length is kept consistent throughout the entire state sequence, resulting in a unified time state node set.

[0103] Unified spatial region mapping processing:

[0104] After time unification is completed, the spatial information in the unified time status node set is mapped to a unified spatial region. Mature spatial coordinate mapping technology is used to perform unified spatial region conversion on device number, video area position and service node position. The spatial region adopts a preset grid area structure, and the spatial identifiers from different sources are mapped to the corresponding grid area numbers. After the spatial mapping is completed, a unified spatial status node set is obtained.

[0105] For video area locations, a mature area coordinate mapping technology is used to map video pixel areas to physical space areas; for device node identifiers, a mature topology area mapping technology is used to map device numbers to corresponding area nodes.

[0106] Unified state category mapping processing:

[0107] After completing spatial unification, the state content in the unified spatial state node set is mapped to a unified state category. Mature state label mapping technology is used to merge state descriptions from different sources into a unified category. Specifically, by using a preset state category mapping table, synonymous states from different sources are mapped to a unified state category identifier to obtain a unified category state node set.

[0108] For state nodes with conflicting states, the state category with higher priority is retained according to the preset state priority order; the state priority is divided according to the state anomaly level.

[0109] Unified State Index Construction Process:

[0110] After unifying the state categories, a state sequence is constructed and a state index is generated for the unified category state node set. A mature sequence arrangement technique is used to continuously sort the state nodes according to the time window order. When multiple state nodes are located in the same time window, they are arranged according to the spatial region number order. Then, a state index association relationship is established for the sorted state nodes, and a corresponding unified state index identifier is generated based on: time window number, spatial region number, state category number, event source number, and state sequence position number, forming a unified state index set. Among them, the state sequence position number is used to represent the arrangement position of the state node in the continuous state sequence.

[0111] Step S1 ultimately outputs a unified state index set:

[0112] ;

[0113] in:

[0114] Represents a unified state index set;

[0115] Indicates the first 1 state index node ;

[0116] This represents the total number of state nodes in the unified state index set.

[0117] Each state index node include:

[0118] ;

[0119] in:

[0120] Indicates the first The time window number corresponding to each status node;

[0121] Indicates the first The spatial region number corresponding to each state node;

[0122] Indicates the first The state category number corresponding to each state node;

[0123] Indicates the first The event source number corresponding to each status node;

[0124] Indicates the first The position number of each state node in the state sequence.

[0125] S2. Use a unified state index set to perform cross-source state mapping analysis to obtain a heterogeneous correlation state map;

[0126] Step S2 is used to establish cross-source association relationships for state nodes from different heterogeneous sources based on the unified state index set generated in step S1, and to form a heterogeneous association state map that can characterize state propagation relationships and state connection structures.

[0127] Step S2, when performing cross-source state mapping analysis, includes the following steps:

[0128] State node synchronization mapping analysis:

[0129] Read the unified state index set output in step S1 The synchronization correlation between different state nodes is calculated, and the state synchronization correlation degree is:

[0130]

[0131] In the formula:

[0132] State node With state nodes The degree of state synchronization correlation between them;

[0133] Indicates the adjacency relationship of time windows. Indicates the time window association weight;

[0134] Indicates the adjacency relationship of spatial regions. Indicates the spatial region association weight;

[0135] Indicates the relationship between status categories. Indicates the weight associated with the state category;

[0136] Indicates the source and relationship of the event. Indicates the weight of the association between the event source and the event;

[0137] Represents the adjacency relationship of state sequences. Indicates the weights associated with the state sequence;

[0138] in:

[0139] Time window adjacency The time window adjacency relationship is calculated based on the time window distance between two state nodes: when two state nodes are in the same time window, the time window adjacency relationship is taken at its maximum value; when two state nodes are in adjacent time windows, the time window adjacency relationship decays according to the time distance; when the time window distance exceeds the preset time window range, no time adjacency relationship is established.

[0140] Spatial region adjacency Based on the gridded region structure calculation in step S1: when two state nodes are located in the same grid region, the spatial region adjacency relationship takes the maximum value; when two state nodes are located in adjacent grid regions, the spatial region adjacency relationship decays according to the region distance; when two state nodes are outside the adjacent region range, no spatial adjacency relationship is established.

[0141] Status category association The calculation is performed based on the unified state category mapping table in step S1:

[0142] When two state nodes belong to the same state category, the state category association relationship is set to the maximum value; when two state nodes belong to consecutive state categories, the state category association relationship decreases according to the category distance; when there is no association relationship between state categories, the state category association relationship is set to zero.

[0143] Event source and related relationships The calculation is based on the event source number corresponding to the status node: when two status nodes come from different heterogeneous sources, the event source correlation is increased; when two status nodes come from the same data source, the event source correlation is decreased.

[0144] State sequence adjacency The adjacency relationship is calculated based on the position of the state nodes in the state sequence: when two state nodes are arranged consecutively in the state sequence, the adjacency relationship of the state sequence increases; when there are multiple gap nodes between the state nodes, the adjacency relationship of the state sequence decreases.

[0145] Association weight , , , , The degree of influence of each related item in the historical state propagation results on the stability of cross-source state synchronization is statistically determined using a mature weighted normalization analysis method, which is used to characterize the contribution ratio of different related factors in the state synchronization mapping process.

[0146] Through state synchronization correlation Establish synchronization mapping relationships for state nodes from different heterogeneous sources to obtain a set of state synchronization mappings, so that state nodes from different sources form a unified association structure, providing a synchronization association basis for the subsequent construction of cross-source state connection edges.

[0147] Analysis of cross-source state connection edge construction:

[0148] After completing the state synchronization mapping, cross-source state connection edges are established between state nodes, and the set of state connection edges is set as follows:

[0149] ;

[0150] in:

[0151] Represents the set of cross-source state connection edges;

[0152] State node With state nodes The connecting edges between them;

[0153] Indicates the threshold for state synchronization association;

[0154] Among them, the state synchronization association threshold A mature statistical threshold division method is adopted, which is determined based on the distribution of synchronization correlation degree of all states, and the nodes corresponding to the synchronization correlation degree of states that are higher than the overall correlation mean are used as connection nodes.

[0155] The co-occurrence relationships of events in the state connection edges are then calculated, and the event co-occurrence strength is expressed by the following formula:

[0156] ;

[0157] In the formula:

[0158] State node With state nodes The intensity of event co-occurrence between them;

[0159] State node With state nodes Number of cross-source co-occurrences within the same time window;

[0160] State node With state nodes Total number of occurrences;

[0161] in:

[0162] When two state nodes co-occur continuously within multiple time windows, the intensity of event co-occurrence increases;

[0163] When two state nodes originate from different heterogeneous sources and continue to co-occur, the intensity of event co-occurrence is further increased;

[0164] The intensity of event co-occurrence decreases when two state nodes only occasionally co-occur.

[0165] State association path construction analysis:

[0166] After constructing the state connection edges, the state propagation paths in the state connection structure are constructed, and the following set of state propagation paths is set as follows:

[0167] ;

[0168] in:

[0169] Represents the set of state propagation paths;

[0170] Indicates the first State propagation path;

[0171] This represents the total number of state propagation paths.

[0172] Each state propagation path satisfies:

[0173] ;

[0174] The generation of a state propagation path requires the following conditions to be met simultaneously:

[0175] There are state connection edges between adjacent state nodes;

[0176] Adjacent state nodes are located within a continuous time window;

[0177] Adjacent state nodes are located in the same region or adjacent regions;

[0178] The state synchronization correlation between adjacent state nodes is higher than the state synchronization correlation threshold. .

[0179] After constructing the state propagation path, the propagation continuity in the path is calculated using the following formula:

[0180] ;

[0181] In the formula:

[0182] Indicates the first The path continuity of each state propagation path;

[0183] This represents the number of nodes in the path that satisfy the continuous-time propagation relationship;

[0184] This indicates the total number of nodes in the path.

[0185] in:

[0186] When the state nodes in a path are consecutively located in adjacent time windows, the path continuity is improved;

[0187] When there is a time interruption in the state propagation in the path, the path continuity decreases;

[0188] When the path continuity is lower than the preset continuity threshold, the construction of the current state propagation path is terminated.

[0189] The preset continuity threshold is a path continuity determination threshold used to judge whether the state propagation path still meets the continuous propagation condition. It is based on the path continuity in the historical state propagation paths. The statistical distribution results are determined using a mature quantile interval division method, which is used to screen out state propagation paths with a high degree of propagation interruption.

[0190] Heterogeneous Association State Map Generation and Analysis:

[0191] A unified aggregation of state nodes, state connection edges, and state propagation paths is performed to generate a heterogeneous associated state graph, the expression of which is:

[0192]

[0193] in:

[0194] Represents a heterogeneous association state map;

[0195] It represents a set of state nodes, including time window number attribute, spatial region number attribute, state category number attribute, event source number attribute, and state sequence position number attribute;

[0196] Represents a set of cross-source state connection edges, including state synchronization correlation attribute, event co-occurrence strength attribute, and cross-source connection attribute;

[0197] It represents the set of state propagation paths, including path continuity attribute, path time span attribute, and regional propagation span attribute.

[0198] The final output of step S2 is the heterogeneous correlation state map. .

[0199] Existing mature technologies typically employ fixed rules to statically correlate state data from different sources. Their analysis process mainly focuses on single-state matching, fixed field mapping, and discrete node connections, making it difficult to form a continuous state propagation structure. In contrast, this step is based on a unified state index structure and combines time window adjacency relationships, spatial region adjacency relationships, state category association relationships, event source association relationships, and state sequence adjacency relationships to construct synchronous mapping relationships, cross-source connection relationships, and continuous propagation paths for state nodes from different heterogeneous sources layer by layer. This enables state nodes from different sources to form a heterogeneous correlated state graph with temporal continuity and spatial propagation.

[0200] S3. Use heterogeneous correlation state graphs to perform spatiotemporal coupling propagation analysis to obtain the dynamic situation evolution matrix;

[0201] Step S3, based on the heterogeneous associated state map generated in step S2, performs spatiotemporal coupling propagation analysis on the cross-source connection relationships and state propagation paths established between state nodes, thereby forming a dynamic situation evolution matrix that can characterize the state temporal propagation process, regional diffusion relationships, and propagation continuity.

[0202] Step S3, in the spatiotemporal coupling propagation analysis, includes the following steps:

[0203] State propagation direction identification and analysis:

[0204] Read the heterogeneous correlation state map output in step S2 The state propagation direction in the state propagation path is identified, and the following formula is used to represent the strength of the state propagation direction:

[0205] ;

[0206] In the formula:

[0207] State node To the state node The direction and intensity of propagation;

[0208] This indicates the degree of state synchronization correlation between state nodes;

[0209] Indicates the intensity of event co-occurrence between state nodes;

[0210] Indicates the state propagation path to which the state node belongs. Path continuity;

[0211] Indicates the weight of the state synchronization correlation;

[0212] Indicates the weight of event co-occurrence intensity;

[0213] Indicates the path continuity weight;

[0214] Among them, propagation weight , , The degree of influence of each propagation factor on the continuity of propagation in the historical propagation results is statistically determined using a mature weighted normalization analysis method.

[0215] The establishment of the state propagation direction simultaneously satisfies the following conditions:

[0216] State Node With state nodes There are state-connected edges between them;

[0217] State Node With state nodes They belong to the same state propagation path;

[0218] State Node With state nodes Located in the same area or adjacent areas;

[0219] State nodes satisfy the time window increment relationship That is, the state propagation direction is always established along the increasing direction of the time window, thereby avoiding the problem of time backward propagation during the state propagation process.

[0220] When the state synchronization correlation increases, it indicates that there is a more stable propagation correlation between states;

[0221] When the intensity of event co-occurrence increases, it indicates a higher probability of synchronous propagation between state nodes;

[0222] When path continuity increases, it indicates that the state propagation process is more continuous and stable.

[0223] Analysis of the construction of time propagation chains:

[0224] After identifying the state propagation direction, a continuous-time propagation chain is constructed for the state propagation path in step S2.

[0225] Let the set of time propagation chains be:

[0226] ;

[0227] in:

[0228] Represents the set of time propagation chains;

[0229] Indicates the first A time-based propagation chain;

[0230] This represents the total number of time propagation chains.

[0231] Each time propagation chain originates from the state propagation path in step S2, and only path segments that satisfy the continuous time propagation condition are retained. Each time propagation chain satisfies the following:

[0232] ;

[0233] That is, the state nodes in the time propagation chain are connected in the order of consecutive time windows, and then the propagation stability in the time propagation chain is calculated. The time propagation stability is:

[0234] ;

[0235] In the formula:

[0236] Indicates the first The propagation stability of a time-based propagation chain;

[0237] This represents the number of state nodes in the time propagation chain that satisfy the condition for continuous propagation.

[0238] This represents the total number of nodes in the time propagation chain;

[0239] The conditions for continuous propagation include: state nodes are located within a continuous time window, there are state connection edges between adjacent state nodes, adjacent state nodes are located in the same region or adjacent regions, and the propagation direction between adjacent state nodes is consistent.

[0240] When the state nodes in the time propagation chain continuously satisfy the continuous propagation condition, the propagation stability is improved;

[0241] When there are time breakpoints or changes in the propagation direction in the time propagation chain, the propagation stability decreases.

[0242] When the propagation stability is lower than the preset stability threshold, the propagation chain extension at the current time is terminated.

[0243] The preset stability threshold is a propagation stability judgment threshold used to determine whether a time propagation chain maintains a stable propagation state. It is based on the propagation stability in historical time propagation chains. The statistical distribution results are determined by a mature stable interval division method and used to screen out time propagation chains with obvious time breaks or abnormal propagation directions.

[0244] Regional diffusion path construction analysis:

[0245] After completing the construction of the time propagation chain, the regional diffusion relationship during the state propagation process is analyzed, and the regional diffusion intensity is:

[0246] ;

[0247] In the formula:

[0248] Indicates the region To the region The diffusion intensity;

[0249] Indicates the adjacency relationship between regions;

[0250] Indicates the stability of the time propagation chain;

[0251] Indicates the intensity of the state propagation direction;

[0252] Indicates the weight of the region adjacency relationship;

[0253] Indicates the stability weight of the time propagation chain;

[0254] Indicates the intensity weight of the state propagation direction;

[0255] Among them, diffusion weight , , The degree of influence of each diffusion factor on the continuity of regional diffusion in historical regional diffusion results is statistically determined using a mature weighted normalization analysis method.

[0256] Regional diffusion is only allowed to propagate between the same region or adjacent grid regions. When there is no grid adjacency between regions, regional diffusion relationship is not established. When two regions are located in adjacent grid regions, the regional adjacency relationship is improved. When the stability of the time propagation chain is improved, the continuity of regional diffusion is improved. When the intensity of the state propagation direction is improved, the regional diffusion trend is strengthened.

[0257] Subsequently, regional diffusion paths are established based on regional diffusion intensity, and the set of regional diffusion paths is expressed as follows:

[0258] ;

[0259] In the formula:

[0260] Represents the set of regional diffusion paths;

[0261] Indicates the first A regional diffusion path;

[0262] This indicates the total number of diffusion paths in the region.

[0263] Each regional diffusion path satisfies This indicates that the regional diffusion during state propagation extends along the region adjacency direction.

[0264] When the regional diffusion intensity is lower than the preset diffusion threshold, the current regional diffusion path is terminated;

[0265] When the time propagation stability is lower than the preset stability threshold, the current region diffusion path is terminated.

[0266] Dynamic situation evolution matrix generation analysis:

[0267] After constructing the regional diffusion path, the temporal propagation chain, regional diffusion path, and propagation intensity are uniformly aggregated to generate a dynamic situation evolution matrix, the expression of which is:

[0268] ;

[0269] In the formula:

[0270] Represents the dynamic situation evolution matrix;

[0271] Indicates the first The time propagation chain in the first The overall propagation results in the regional diffusion path;

[0272] Indicates the number of time propagation chains;

[0273] Indicates the number of regional diffusion paths.

[0274] in:

[0275] The rows of the matrix correspond to the time propagation dimensions;

[0276] The matrix columns correspond to the diffusion dimensions of the regions.

[0277] The matrix elements correspond to the situation propagation intensity.

[0278] Only when the first The time propagation chain covers the first When there is a diffusion path in a region, the corresponding matrix elements are valid.

[0279] Matrix elements satisfy:

[0280] ;

[0281] In the formula:

[0282] Indicates the first The propagation stability of a time-based propagation chain;

[0283] Indicates the first The diffusion intensity of each regional diffusion path.

[0284] As the stability of time propagation increases, the corresponding situational evolution results are enhanced;

[0285] When the intensity of regional diffusion increases, the trend of situational diffusion in the corresponding region intensifies;

[0286] When both propagation stability and diffusion intensity increase simultaneously, the continuity of situational propagation in the corresponding region improves.

[0287] Finally, the dynamic situation evolution matrix is ​​obtained and input into step S4 for subsequent regional situation aggregation analysis. Step S4 mainly performs regional situation aggregation based on the regional diffusion path, regional diffusion intensity, and time propagation stability in the dynamic situation evolution matrix.

[0288] Existing mature technologies typically use fixed-time-window statistics, single-region trend analysis, or discrete-state aggregation to determine the evolution of operational states. Their analysis mainly focuses on time-series change statistics or local regional state analysis, making it difficult to form continuous propagation relationships and regional diffusion relationships between states. In contrast, this step, based on the state propagation path, cross-source state connection edges, and event co-occurrence relationships in step S2, and combining temporal propagation continuity and regional adjacency propagation relationships, performs continuous coupling analysis on the state propagation direction, temporal propagation chain, and regional diffusion path. This enables the state propagation process to possess both temporal continuity and spatial diffusion, ultimately forming a dynamic situation evolution matrix that can characterize the spatiotemporal continuous propagation structure.

[0289] S4. Use the dynamic situation evolution matrix to perform regional situation aggregation analysis to obtain a multi-level situation distribution set;

[0290] Step S4 is used to perform regional situation aggregation analysis on the dynamic situation evolution matrix generated in step S3, so that the dynamic propagation results form a multi-level situation distribution result with regional hierarchical structure and time stage structure.

[0291] Step S4, when performing regional situational aggregation analysis, includes the following steps:

[0292] Regional propagation results extraction and analysis:

[0293] Read the dynamic situation evolution matrix output in step S3 The mature matrix traversal technique is used to extract the effective matrix elements in the dynamic situation evolution matrix: when the state node in the time propagation chain is located in the corresponding region diffusion path, or when the region corresponding to the time propagation chain and the region diffusion path have a region intersection, the corresponding matrix element is retained as the effective region propagation result.

[0294] Subsequently, mature region correlation analysis technology is used to expand the region nodes of the region diffusion paths corresponding to the effective matrix elements, resulting in a set of region propagation nodes. This set includes: region ID, time window ID, region propagation intensity, region propagation continuity, and region propagation source relationship.

[0295] The regional propagation continuity is obtained by mapping the temporal propagation stability in step S3 to the corresponding regional diffusion path using a mature regional continuity mapping method. It is used to characterize the continuous propagation stability during the regional propagation process.

[0296] Regional propagation source relationships are used to characterize the upstream propagation regional relationships in the process of regional propagation.

[0297] Regional situation convergence analysis:

[0298] After extracting the regional propagation results, the regional propagation node set is processed by regional situation aggregation: using mature regional clustering analysis technology, the regional propagation intensity and regional propagation continuity in the regional propagation nodes are calculated, and regional nodes with similar propagation characteristics are assigned to the same regional situation set.

[0299] The following conditions must be met for similar propagation characteristics: the difference in regional propagation intensity is lower than a preset propagation difference threshold; the difference in regional propagation continuity is lower than a preset continuity difference threshold; regional nodes are located in consecutive adjacent regions; and regional nodes maintain a continuous time propagation relationship.

[0300] The preset propagation difference threshold is determined based on the distribution of regional propagation intensity differences in historical regional propagation results, using a mature quantile interval division method.

[0301] The preset continuous difference threshold is determined based on the distribution of regional propagation continuity difference in historical regional propagation results, using a mature continuous interval division method.

[0302] Using mature regional boundary extraction technology, continuous regional contours are extracted from the range of continuously adjacent regions and the boundary of regional propagation intensity changes in the regional situation set, forming a regional situation boundary structure.

[0303] Regional hierarchy analysis:

[0304] After completing the regional situation aggregation, the regional situation sets are hierarchically divided: using mature regional density stratification technology, based on the regional propagation intensity distribution and regional propagation continuity distribution results in the regional situation sets, different regional situation sets are hierarchically divided according to the following rules:

[0305] A set of regional situations with high regional propagation intensity and high regional propagation continuity, that is, a set of regional situations where both regional propagation intensity and regional propagation continuity are higher than a preset high intensity judgment threshold, is classified as a core situation area. The preset high intensity judgment threshold is determined by a mature hierarchical interval division method based on the joint statistical distribution of regional propagation intensity and regional propagation continuity in historical regional propagation results.

[0306] The set of regional situations that maintain a continuous adjacency with the core situation area and have a secondary propagation intensity is classified as the adjacent situation area;

[0307] The set of regional situations that maintain a continuous propagation relationship with adjacent situation areas and whose propagation intensity further decreases is classified as the peripheral situation area.

[0308] Subsequently, a mature hierarchical relationship construction technology was used to process the hierarchical relationship between the propagation relationships of different regional situation sets, forming a regional hierarchical relationship structure, including: upper-level propagation region, lower-level diffusion region, regional propagation direction relationship, and regional propagation span relationship;

[0309] The regional propagation span relationship is obtained by statistically analyzing the number of consecutive regions in the regional diffusion path, and is used to characterize the spatial diffusion range in the regional propagation process.

[0310] Time-phase situational convergence analysis:

[0311] After completing the regional hierarchical division, the regional situation results in different time windows are merged into time stages. A time stage is a continuous time propagation segment formed by merging consecutive time windows.

[0312] During the processing, a mature time series merging technique is used to perform time-stage correlation analysis on the regional situation sets in continuous time windows. When the regional situation sets in different time windows simultaneously satisfy the following conditions: continuous regional boundaries, consistent regional propagation direction, continuous changes in regional propagation intensity, and consistent regional hierarchical relationships, the corresponding regional situation sets are merged into the situation set of the same time stage.

[0313] Subsequently, a mature time continuity determination technology is adopted to determine the continuity of regional overlap rate and regional propagation direction consistency in adjacent time windows. When the regional overlap rate is higher than the preset overlap threshold and the propagation direction remains consistent, the correlation of the corresponding time stage is retained. The preset overlap threshold is determined by a mature method of dividing overlap intervals based on the statistical distribution of regional overlap rate in historical regional propagation results.

[0314] Finally, a mature time-stage mapping technique is used to establish a continuous time-stage correspondence for the time-stage situation set, so that the regional situation in different time stages forms a continuous evolution relationship; after the time stages are merged, a time-stage situation set is formed.

[0315] Step S4 ultimately outputs a multi-level situational distribution set, the expression of which is:

[0316] ;

[0317] in:

[0318] Represents a multi-level situational distribution set;

[0319] This represents the core situation area set, used to characterize the situation area with the highest regional propagation intensity and the most stable propagation continuity.

[0320] This represents the set of adjacent situational regions, used to characterize the diffusion region that maintains a continuous propagation relationship with the core situational region;

[0321] This represents the set of peripheral situational regions, used to characterize the peripheral diffusion area after the regional propagation gradually weakens;

[0322] This represents a set of hierarchical relationships between regions, used to characterize the hierarchical relationships of propagation between regions with different situations.

[0323] It represents a set of situations at different time stages, used to characterize the continuous evolution of situations at different time stages.

[0324] S5. Use multi-level situation distribution sets and heterogeneous correlation state maps to perform dynamic visualization mapping analysis and obtain a time-series situation visualization result set;

[0325] Step S5: Based on the multi-level situation distribution set generated in step S4, and combined with the heterogeneous correlation state map generated in step S2, perform dynamic visualization mapping analysis on the situation propagation process, thereby forming a time-series situation visualization result set that can reflect the temporal evolution relationship, regional propagation relationship, and state propagation path relationship.

[0326] Step S5, when performing dynamic visualization mapping analysis, includes the following steps:

[0327] Analysis of the construction of the regional hierarchical display structure:

[0328] Read the multi-level situation distribution set output in step S4 To establish a regional hierarchical display structure for different levels of situational areas, the regional display level value is set, and its expression is:

[0329] ;

[0330] in:

[0331] Indicates the region The display hierarchy value;

[0332] Indicates the intensity of regional transmission;

[0333] Indicates the continuity of regional propagation;

[0334] The value representing the regional propagation span is obtained by normalizing the number of continuous regions in the regional diffusion path using a mature regional span quantification method. It is used to characterize the spatial diffusion range during the regional propagation process.

[0335] Indicates the propagation strength weight;

[0336] Indicates the propagation continuity weight;

[0337] Indicates the weight of the propagation span value;

[0338] Hierarchical weight , , The degree of influence of each display factor on the continuity of regional display in the historical situation display results is statistically determined through a mature weighted normalization analysis method;

[0339] The regions are sorted according to their display level values, and then divided into corresponding display levels according to preset level intervals: the region with the highest display level value is designated as the core display layer; the regions that maintain a continuous propagation relationship with the core display layer are designated as the diffusion display layer; and the regions that maintain a continuous propagation relationship with the diffusion display layer are designated as the outer display layer.

[0340] The preset hierarchical intervals are determined based on the statistical distribution of regional display hierarchical values ​​in historical regional display results, using a mature hierarchical interval division method.

[0341] The region hierarchy display structure is represented by the following formula:

[0342] ;

[0343] In the formula:

[0344] This indicates the hierarchical display structure of the regions;

[0345] Indicates the first Each area displays a hierarchy;

[0346] Each region display level includes: region number, region boundary, region display level value, region propagation direction, and time stage number.

[0347] State propagation path mapping analysis:

[0348] After completing the construction of the regional hierarchical display structure, read the heterogeneous association state map output in step S2:

[0349] ;

[0350] In the formula:

[0351] Represents a set of state nodes;

[0352] Represents the set of cross-source state connection edges;

[0353] This represents the set of state propagation paths.

[0354] The state propagation trajectory structure is constructed based on the set of state nodes and the set of cross-source state connection edges; the state connection edges are used to construct the node connection relationship in the state propagation path and form the connection display relationship between state nodes in the subsequent state propagation trajectory graph; the set of state nodes is used to generate the node display structure in the state propagation trajectory graph.

[0355] The following formula is used to represent the state path mapping strength, and to perform regional situation mapping on the state propagation path:

[0356] ;

[0357] In the formula:

[0358] Indicates the first The path mapping strength of each state propagation path;

[0359] Indicates the first The path continuity of each state propagation path;

[0360] Indicates the first The area coverage of each state propagation path;

[0361] Indicates the first The propagation stability of a time-based propagation chain;

[0362] , , This represents the mapping weight of the corresponding path factor.

[0363] Where: path continuity The results are derived from the state propagation path continuity analysis in step S2;

[0364] When the The state propagation path is contained in the first When there are multiple time propagation chains, the stability of the corresponding time propagation chain will be propagated. As the temporal propagation stability of the state propagation path, the regional coverage is obtained by counting the number of regions covered by the state propagation path; the state nodes in the state propagation path are associated with the corresponding regional situation set through regional mapping relationship, and then the number of corresponding covered regions is counted.

[0365] Mapping weights , , The degree of influence of each path factor on the continuity of path display in the historical situation mapping results is statistically determined through a mature weight normalization analysis method.

[0366] The state propagation path is then mapped to the corresponding region-level display structure, where: state propagation paths located in the core situation area are mapped to the core display layer; state propagation paths located in adjacent situation areas are mapped to the diffusion display layer; and state propagation paths located in the outer situation area are mapped to the outer display layer. When a state propagation path simultaneously covers multiple region levels, the region display level value is used as the basis for mapping. Establish path mapping relationships in the highest region;

[0367] The final set of region-related display paths is formed:

[0368] ;

[0369] In the formula:

[0370] This indicates a set of associated display paths for a given region.

[0371] Indicates the first Display paths associated with specific regions.

[0372] Among them, the region-related display path is formed by mapping the state propagation path to the region-level display structure.

[0373] Time-phase continuous mapping analysis:

[0374] After completing the state propagation path mapping, continuous time mapping is performed on the time stage situation set in step S4; the state propagation path is mapped to the corresponding time stage situation set according to its time propagation chain; the time stage mapping continuity is set as follows:

[0375] ;

[0376] In the formula:

[0377] Indicates the continuity of the time-phase mapping;

[0378] This indicates the regional overlap rate in adjacent time periods;

[0379] Indicates the consistency of propagation direction in adjacent time periods;

[0380] Indicates the continuity of propagation intensity in adjacent time periods;

[0381] Continuous weights representing regional overlap rates;

[0382] Continuous weights representing the consistency of propagation direction;

[0383] The continuous weights represent the continuity of propagation intensity.

[0384] in:

[0385] The continuity of propagation intensity is calculated by the difference in regional propagation intensity changes between adjacent time stages, and is used to characterize the degree of continuity of propagation changes between different time stages.

[0386] Continuous weights , , The degree of influence of each time continuity factor on the continuity of time display in the historical situation evolution results is statistically determined through a mature weighted normalization analysis method.

[0387] Subsequently, a continuous mapping relationship for time stages is established based on the continuity of the time stage mapping:

[0388] ;

[0389] in:

[0390] This indicates a continuous mapping relationship across time stages;

[0391] Indicates the first A time phase;

[0392] A continuous time phase mapping relationship is established only when there is regional overlap between adjacent time phases and the propagation direction remains consistent.

[0393] When the continuity of the time phase mapping is lower than the preset continuous mapping threshold, the continuous mapping of the current time phase is terminated.

[0394] The preset continuous mapping threshold is determined based on the statistical distribution of the mapping continuity in the time stage in the historical situation evolution results, and is determined by a mature continuous interval division method.

[0395] Dynamic situation visualization results generation and analysis:

[0396] After completing the continuous mapping of time phases, the regional hierarchical display structure, regional associated display paths, and continuous mapping relationships of time phases are uniformly aggregated to generate a time-series situation visualization result set, the expression of which is:

[0397] ;

[0398] In the formula:

[0399] This represents a set of visualization results for time-series situations;

[0400] This represents a time-series situation evolution diagram, showing the continuous mapping relationship between corresponding time stages;

[0401] This represents the set of display paths associated with different regions, and the corresponding state propagation path mapping relationship.

[0402] This represents a multi-level situational distribution map, showing the corresponding regional hierarchical display structure.

[0403] This represents a state propagation trajectory graph, corresponding to a set of state nodes, a set of state connection edges, and a set of state propagation paths, including: state nodes, state connection edges, state propagation paths, path propagation directions, and time stage correspondences;

[0404] This indicates the results of dynamic regional changes, including changes in regional boundaries, changes in regional propagation intensity, and changes in regional hierarchy.

[0405] Existing mature technologies typically use static regional display, fixed time-section display, or single-level state display to visualize situational results. Their display process mainly focuses on displaying regional distribution results or simple time series switching, making it difficult to establish a continuous mapping relationship between the underlying state propagation relationship and the regional situational structure. Furthermore, they usually only display regional results, lacking a linked display structure between state nodes, state connection edges, and state propagation paths. In contrast, this step combines the set of state nodes, cross-source state connection edges, and state propagation paths from step S2 with the multi-level situational distribution structure in step S4 for unified coupling and mapping. This results in a continuous association structure between "state nodes - state connection edges - state propagation paths - regional situational hierarchy - time stage evolution" in the final situational display, thus simultaneously possessing regional hierarchical structure, state propagation association relationship, and continuous time evolution relationship.

[0406] Example 2:

[0407] This embodiment provides a multi-source heterogeneous data intelligent processing and situation visualization analysis system, including the following functional modules:

[0408] The unified state index construction module, corresponding to step S1, performs unified parsing and state encoding on multi-source heterogeneous operational data to generate a unified state index set, forming a basic data structure that can be uniformly processed within the system. This module is responsible for standardizing the raw data, extracting state features, and mapping unified identifiers, providing basic data for subsequent cross-source analysis.

[0409] The heterogeneous relational state graph construction module, corresponding to step S2, performs cross-source relational mapping on states from different data sources based on a unified state index set, constructing a heterogeneous relational state graph containing state nodes, state connection edges, and state propagation paths. This module reveals the relationships between multi-source data, providing a network of inter-state relationships for subsequent spatiotemporal propagation analysis.

[0410] The dynamic situation evolution analysis module, corresponding to step S3, performs spatiotemporal coupled propagation analysis on the heterogeneous correlated state map to form a dynamic situation evolution matrix. This module reveals the propagation patterns of states in time and space, provides analysis results on temporal continuity and path propagation stability, and provides input for regional situation aggregation.

[0411] The multi-level situation aggregation module, corresponding to step S4, performs multi-level aggregation analysis on the region based on the dynamic situation evolution matrix, generating a multi-level situation distribution set. This module maps the spatiotemporal situation to a regional hierarchical structure, forming regional situation distributions at different levels, providing a foundation for regional display of the visualization mapping.

[0412] The temporal situation visualization mapping module, corresponding to step S5, performs joint mapping analysis between the multi-level situation distribution set and the heterogeneous associated state map, generating a temporal situation visualization result set, including state propagation trajectory map, regional association display path, multi-level situation distribution map, and dynamic regional changes. This module is used to dynamically display the situation evolution process of multi-source data, achieving continuous mapping visualization of region, state, and time.

[0413] Example 3:

[0414] This embodiment provides an application of a method and system for intelligent processing and situation visualization analysis of multi-source heterogeneous data in a real-world scenario:

[0415] In urban traffic management, road network data comes from diverse sources, with varying formats, collection cycles, and update frequencies, representing typical multi-source heterogeneous data. The traffic management department uses this solution for analysis, including the following implementation process:

[0416] Unified Status Index Construction: The system standardizes traffic data from different sources through the unified status index construction module: it converts traffic flow detected by cameras into "road segment congestion level" status; it converts sensor data into "vehicle average speed status"; and it maps public transport information into "route operation status".

[0417] This ultimately forms a unified set of state indexes, with each road segment and bus route having a corresponding state code at each point in time.

[0418] Construction of heterogeneous association state graph:

[0419] The system analyzes the relationships between different road segments, routes, and events through a heterogeneous relational state graph construction module: it connects the congestion status of adjacent road segments into paths, establishes association edges between traffic accidents or construction events and the status of affected road segments, and constructs cross-source state propagation paths to reflect the trend of congestion spreading from core road segments to the surrounding areas.

[0420] The resulting state graph displays traffic state nodes, connections between nodes, and main propagation paths.

[0421] Dynamic situational evolution analysis:

[0422] The system performs time-series analysis on the state map through the dynamic situation evolution analysis module: it analyzes the dynamic process of congestion spreading from peak road sections to adjacent road sections; it identifies the evolution trend of traffic conditions in different time periods, such as morning peak, midday relief, and evening peak; and it forms a dynamic situation evolution matrix to describe the situation evolution relationship of each road section in each time period.

[0423] Multi-level situational convergence:

[0424] The system maps dynamic situation to the regional level through a multi-level situation aggregation module: the city is divided into core urban area, secondary core urban area and peripheral area; road segment situation information is aggregated to the regional level to form a regional situation distribution set; detailed road segment situation is displayed in the core urban area and aggregated situation is displayed in the peripheral area.

[0425] Multi-level displays enable managers to quickly identify congestion hotspots in the core road network and potential risks in the peripheral road network.

[0426] Temporal situation visualization mapping:

[0427] The system generates an interactive dynamic situational interface through a time-series situational visualization mapping module: the congestion status of core road sections is displayed by color or height changes; the status propagation path is displayed by arrows, reflecting the direction of congestion spread; the traffic situation at different time periods can be observed dynamically by sliding the time axis; the combination of regional hierarchical display and path mapping allows managers to understand both the overall situation and local details.

[0428] Managers can intuitively understand congestion trends and take traffic guidance or incident response measures in advance.

[0429] Example 4:

[0430] This embodiment also provides a computer device applicable to a method and system for intelligent processing and situation visualization analysis of multi-source heterogeneous data, including a memory and a processor; the memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions to realize the method and system for intelligent processing and situation visualization analysis of multi-source heterogeneous data as proposed in the above embodiment.

[0431] This embodiment also provides a storage medium storing a computer program, which, when executed by a processor, implements a method and system for intelligent processing and situational visualization analysis of multi-source heterogeneous data as proposed in the above embodiments.

[0432] The computer device can be a terminal, comprising a processor, memory, communication interface, display screen, and input devices connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, carrier networks, NFC (Near Field Communication), or other technologies. The display screen can be an LCD screen or an e-ink screen. The input devices can be a touch layer covering the display screen, buttons, a trackball, or a touchpad on the computer device's casing, or an external keyboard, touchpad, or mouse.

[0433] If a function is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0434] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-including system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device.

[0435] More specific examples (a non-exhaustive list) of computer-readable media include: electrical connections (electronic devices) having one or more wires, portable computer disk drives (magnetic devices), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Furthermore, computer-readable media can even be paper or other suitable media on which programs can be printed, because programs can be obtained electronically, for example, by optically scanning the paper or other media, followed by editing, interpreting, or otherwise processing as necessary, and then stored in computer memory.

[0436] It should be understood that various parts of the present invention can be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0437] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.

Claims

1. A method for intelligent processing and situation visualization analysis of multi-source heterogeneous data, characterized in that, Includes the following steps: S1. Construct a unified state index for multi-source heterogeneous operational data to obtain a unified state index set; S2. Use a unified state index set to perform cross-source state mapping analysis to obtain a heterogeneous correlation state map; S3. Use heterogeneous correlation state graphs to perform spatiotemporal coupling propagation analysis to obtain the dynamic situation evolution matrix; S4. Use the dynamic situation evolution matrix to perform regional situation aggregation analysis to obtain a multi-level situation distribution set; S5. Use multi-level situation distribution sets and heterogeneous correlation state maps to perform dynamic visualization mapping analysis to obtain a time-series situation visualization result set.

2. The method for intelligent processing and situation visualization analysis of multi-source heterogeneous data according to claim 1, characterized in that, Step S1 establishes a unified state representation basis for multi-source heterogeneous operational data, resulting in a unified state index set: ； in: Indicates the first 1 state index node ; This represents the total number of state nodes in the unified state index set; Each state index node include: ； in: Indicates the first The time window number corresponding to each status node; Indicates the first The spatial region number corresponding to each state node; Indicates the first The state category number corresponding to each state node; Indicates the first The event source number corresponding to each status node; Indicates the first The position number of each state node in the state sequence.

3. The method for intelligent processing and situation visualization analysis of multi-source heterogeneous data according to claim 1, characterized in that, Step S2 is used to generate the unified state index set in step S1. Based on this, cross-source association relationships are established for state nodes from different heterogeneous sources, and a heterogeneous association state map that can characterize state propagation relationships and state connection structures is formed. Step S2, when performing cross-source state mapping analysis, includes the following steps: State node synchronization mapping analysis; Analysis of cross-source state connection edge construction; State association path construction analysis; Analysis of heterogeneous association state map generation.

4. The method for intelligent processing and situation visualization analysis of multi-source heterogeneous data according to claim 3, characterized in that, In step S2, during the state node synchronization mapping analysis, the unified state index set output in step S1 is read. The synchronization correlation between different state nodes is calculated, and the state synchronization correlation degree is: ； In the formula: State node With state nodes The degree of state synchronization correlation between them; Indicates the adjacency relationship of time windows. Indicates the time window association weight; Indicates the adjacency relationship of spatial regions. Indicates the spatial region association weight; Indicates the relationship between status categories. Indicates the weight associated with the state category; Indicates the source and relationship of the event. Indicates the weight of the association between the event source and the event; Represents the adjacency relationship of state sequences. This represents the weight associated with the state sequence.

5. The method for intelligent processing and situation visualization analysis of multi-source heterogeneous data according to claim 3, characterized in that, In step S2, when performing cross-source state connection edge construction analysis, cross-source state connection edges are established between state nodes, and the set of state connection edges is set as follows: ； in: Represents the set of cross-source state connection edges; State node With state nodes The connecting edges between them; Indicates the threshold for state synchronization association; The co-occurrence relationships of events in the state connection edges are then calculated, and the event co-occurrence strength is expressed by the following formula: ； In the formula: State node With state nodes The intensity of event co-occurrence between them; State node With state nodes Number of cross-source co-occurrences within the same time window; State node With state nodes Total number of occurrences.

6. The method for intelligent processing and situation visualization analysis of multi-source heterogeneous data according to claim 3, characterized in that, In step S2, during the state association path construction analysis, the state propagation paths in the state connection structure are constructed, and the following set of state propagation paths is set as follows: ； in: Represents the set of state propagation paths; Indicates the first State propagation path; Indicates the total number of state propagation paths; Each state propagation path satisfies: ； After constructing the state propagation path, the propagation continuity in the path is calculated using the following formula: ； In the formula: Indicates the first The path continuity of each state propagation path; This represents the number of nodes in the path that satisfy the continuous-time propagation relationship; This indicates the total number of nodes in the path.

7. The method for intelligent processing and situation visualization analysis of multi-source heterogeneous data according to claim 3, characterized in that, In step S2, during the heterogeneous association state graph generation and analysis, state nodes, state connection edges, and state propagation paths are uniformly aggregated to generate a heterogeneous association state graph, the expression of which is: ； in: Represents a heterogeneous association state map; Represents a set of state nodes; Represents the set of cross-source state connection edges; This represents the set of state propagation paths.

8. The method for intelligent processing and situation visualization analysis of multi-source heterogeneous data according to claim 1, characterized in that, Step S3, based on the heterogeneous correlation state map generated in step S2, performs spatiotemporal coupled propagation analysis on the established cross-source connections and state propagation paths between state nodes, thereby forming a dynamic situational evolution matrix that can characterize the state temporal propagation process, regional diffusion relationships, and propagation continuity. .

9. The method for intelligent processing and situation visualization analysis of multi-source heterogeneous data according to claim 1, characterized in that, Step S4 performs regional situation aggregation analysis on the dynamic situation evolution matrix generated in step S3, so that the dynamic propagation results form a multi-level situation distribution set with regional hierarchical structure and time stage structure. Step S5: Based on the multi-level situation distribution set generated in step S4, and combined with the heterogeneous correlation state map generated in step S2, perform dynamic visualization mapping analysis on the situation propagation process, thereby forming a time-series situation visualization result set that can reflect the temporal evolution relationship, regional propagation relationship, and state propagation path relationship.

10. A multi-source heterogeneous data intelligent processing and situation visualization analysis system, constructed based on the multi-source heterogeneous data intelligent processing and situation visualization analysis method according to any one of claims 1-9, characterized in that, The system includes the following modules: unified state index construction module, heterogeneous correlation state map construction module, dynamic situation evolution analysis module, multi-level situation aggregation module, and time-series situation visualization mapping module.

Images