A multi-dimensional detection data intelligent collection analysis document generation system

Abstract

This invention discloses a multi-dimensional detection data intelligent aggregation and analysis document generation system, belonging to the field of intelligent document generation technology, including the following steps: S1, constructing a multi-dimensional detection object association basis; S2, using the detection association basis set to construct a cross-dimensional aggregation propagation chain; S3, using the cross-dimensional aggregation set to construct a state coupling expression set; S4, using the state association expression matrix to generate a document paragraph mapping sequence; S5, using the document structure association set and the state association expression matrix to construct a multi-dimensional detection aggregation and analysis document. This invention, by setting a detection association basis set to construct a cross-dimensional aggregation propagation chain, enables the system to continuously organize the propagation process in different detection dimensions based on the propagation connection relationship, propagation order relationship, and state synchronization relationship between detection objects, forming a cross-dimensional aggregation propagation chain structure, thereby allowing subsequent state association expression analysis to establish continuous state propagation relationships.

Description

Technical Field

[0001] This invention relates to the field of intelligent document generation technology, specifically to a multi-dimensional detection data intelligent aggregation and analysis document generation system. Background Technology

[0002] As the number of objects to be detected in industrial inspection, environmental monitoring, equipment operation monitoring, and comprehensive condition assessment scenarios continues to increase, multi-source detection equipment will continuously generate large-scale condition data from different detection dimensions. Among these, there are usually temporal, spatial, and state propagation relationships between different detection data. Therefore, it is difficult to reflect the continuous propagation process and state correlation process between multi-dimensional detection objects by analyzing only a single detection result independently.

[0003] In existing technologies, multidimensional detection and analysis systems typically classify and summarize different detection data based on fixed detection categories. When there are continuous state propagation relationships between different detection dimensions, it is difficult to continuously organize the cross-dimensional state propagation process. In particular, it is difficult to uniformly collect the propagation order relationship, state continuation relationship, and cross-dimensional correlation relationship between different detection objects. As a result, the subsequent analysis documents can only describe isolated detection results and cannot form a correlation analysis structure under continuous propagation logic. Summary of the Invention

[0004] To address the shortcomings of existing technologies, this invention provides a multi-dimensional detection data intelligent aggregation and analysis document generation system 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 multi-dimensional detection data intelligent aggregation and analysis document generation system, comprising the following steps:

[0007] S1. Construct a multidimensional detection object association basis to obtain a set of detection association basis bases;

[0008] S2. Construct a cross-dimensional set propagation chain using the detection association basis set to obtain the cross-dimensional set;

[0009] S3. Construct a state coupling representation set using a cross-dimensional aggregation set to obtain the state association representation matrix;

[0010] S4. Use the state association expression matrix to generate a document paragraph mapping sequence, and obtain a document structure association set;

[0011] S5. Construct multidimensional detection aggregation analysis documents using document structure association set and state association expression matrix to obtain aggregation analysis document results.

[0012] To further optimize this technical solution, step S1 constructs the basic association structure in the multi-dimensional detection data intelligent aggregation and analysis document generation system. This is achieved by uniformly identifying and mapping the detection objects in different detection dimensions, and uniformly organizing the temporal correspondence, spatial adjacency, and state synchronization relationships among the detection objects to form a unified detection association structure. This structure is represented by a detection association basis set, and its expression is:

[0013] ;

[0014] in,

[0015] Represents a set of associated nodes;

[0016] This represents a set of associated connections.

[0017] To further optimize this technical solution, step S2, based on the detection association basis set B constructed in step S1, further establishes a continuous propagation relationship between different detection dimensions and forms a corresponding cross-dimensional aggregation propagation chain structure.

[0018] Step S2, in constructing the cross-dimensional aggregation propagation chain, includes the following steps:

[0019] Extraction of cross-dimensional related nodes;

[0020] Cross-dimensional propagation relationship analysis;

[0021] Construction of cross-dimensional propagation paths;

[0022] Construction of cross-dimensional aggregation and propagation chain.

[0023] To further optimize this technical solution, in step S2, when extracting cross-dimensional related nodes, the related connection set is used as the basis. Based on the temporal correspondence, spatial adjacency, and state synchronization relationships, the detection object nodes with continuous correlations are extracted; then, according to the detection dimension to which the detection object belongs, the detection object nodes are classified by dimension to form a corresponding cross-dimensional correlation node set.

[0024] To further optimize this technical solution, in step S2, during cross-dimensional propagation relationship analysis, the temporal correlation continuity, spatial connection continuity, and state change continuity between different detection objects are identified using correlation propagation analysis technology. When the correlation between multiple detection objects persists within a continuous time window, a cross-dimensional propagation relationship is identified between the corresponding detection objects, and a cross-dimensional propagation correlation value is constructed to describe the degree of propagation correlation between different detection objects. Its expression is:

[0025] ;

[0026] in:

[0027] Indicates the object to be detected With the test object Cross-dimensional propagation correlation values ​​between them;

[0028] Indicates the object to be detected With the test object Time-related matching values ​​between them;

[0029] Indicates the object to be detected With the test object Spatial adjacency matching values ​​between them;

[0030] Indicates the object to be detected With the test object The state synchronization matching values ​​between them;

[0031] Indicates the time correlation coefficient;

[0032] Indicates the spatial adjacency coefficient;

[0033] This represents the state synchronization coefficient.

[0034] To further optimize this technical solution, in step S2, when constructing the cross-dimensional propagation path, the cross-dimensional propagation correlation value between the detected objects is used. For detected objects with continuous propagation relationships, sequential connections are made. Based on the temporal order, spatial connection order, and state change order of the propagation relationship, multiple propagation association segments are continuously organized to construct the following propagation continuity values, which describe the degree of propagation continuity in different propagation paths:

[0035]

[0036] in:

[0037] Indicates the first The propagation continuity value of each propagation path;

[0038] Indicates the first in the propagation path Cross-dimensional propagation correlation values ​​between segment detection objects;

[0039] This indicates the number of propagation segments in the current propagation path.

[0040] To further optimize this technical solution, in step S2, when constructing the cross-dimensional aggregation propagation chain, the detection objects with continuous propagation paths are aggregated in a chain using chain-based association organization technology; then, a corresponding cross-dimensional aggregation propagation chain is established based on the detection object nodes, propagation association relationships, and propagation order relationships in the propagation path.

[0041] Construct a cross-dimensional set to describe the set structure between different propagation chains; its expression is:

[0042] ;

[0043] in:

[0044] Represents a cross-dimensional set;

[0045] Indicates the first A cross-dimensional aggregation and propagation chain, ;

[0046] This represents the total number of cross-dimensional aggregation propagation chains.

[0047] To further optimize this technical solution, step S3 involves the cross-dimensional aggregation set formed in step S2. Based on this, the state relationships in the propagation chain are continuously organized and structurally expressed, and a state relationship expression matrix that can describe the state context relationships is established. .

[0048] To further optimize this technical solution, step S4 involves converting the state association expression matrix formed in step S3 into a more comprehensive representation. This is converted into a structured set of paragraph relationships that can be used for document organization, forming the document structure relationship set required for subsequent document content generation. .

[0049] To further optimize this technical solution, step S5 involves the document structure association set formed in step S4. and the state association expression matrix formed in step S3 Based on this, the relationship between content associated with different states and document structure is jointly mapped, and corresponding multidimensional detection and aggregation analysis documents are generated.

[0050] 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, wherein: when the computer program instructions are executed by the processor, they implement the steps of a multi-dimensional detection data intelligent collection and analysis document generation system as described in the first aspect of the present invention.

[0051] 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 a multi-dimensional detection data intelligent collection and analysis document generation system as described in the first aspect of the present invention.

[0052] Compared with existing technologies, this invention provides a multi-dimensional detection data intelligent collection and analysis document generation system, which has the following beneficial effects:

[0053] This multi-dimensional detection data intelligent aggregation and analysis document generation system constructs a cross-dimensional aggregation propagation chain by setting a detection association base set. The system can continuously organize the propagation process in different detection dimensions based on the propagation connection relationship, propagation order relationship, and state synchronization relationship between detection objects, and form a cross-dimensional aggregation propagation chain structure. This enables subsequent state association expression analysis to establish continuous state propagation relationships, further improving the association aggregation capability between multi-dimensional detection data and the continuous propagation logic expression capability in the aggregation analysis document. Attached Figure Description

[0054] 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.

[0055] Figure 1 This is a flowchart illustrating a multi-dimensional detection data intelligent collection and analysis document generation system proposed in this invention.

[0056] Figure 2 This is a schematic diagram of the cross-dimensional aggregation and propagation chain process for constructing a multi-dimensional detection data intelligent aggregation and analysis document generation system proposed in this invention;

[0057] Figure 3 This is a schematic diagram of the construction state coupling expression set process of the document generation system for intelligent collection and analysis of multi-dimensional detection data proposed in this invention;

[0058] Figure 4 This is a schematic diagram illustrating the construction process of a multi-dimensional detection data intelligent aggregation and analysis document generation system proposed in this invention. Detailed Implementation

[0059] 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.

[0060] 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.

[0061] 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.

[0062] Example 1:

[0063] Reference Figures 1-4 This is the first embodiment of the present invention, which provides a multi-dimensional detection data intelligent collection and analysis document generation system, including the following steps:

[0064] S1. Construct a multidimensional detection object association basis to obtain a set of detection association basis bases;

[0065] Step S1 constructs the basic association structure in the multi-dimensional detection data intelligent aggregation and analysis document generation system. By uniformly identifying and mapping the detection objects in different detection dimensions, and uniformly associating and organizing the temporal correspondence, spatial adjacency, and state synchronization relationships between the detection objects, a unified detection association structure is formed. Among them, the temporal correspondence is used to describe the temporal association between different detection objects, the spatial adjacency is used to describe the regional connection between different detection objects, and the state synchronization relationship is used to describe the consistency of state changes between different detection objects, thereby obtaining the detection association base set.

[0066] Step S1, in constructing the multidimensional detection object association basis, includes the following steps:

[0067] Unified identifier mapping for multidimensional detection objects:

[0068] It accesses raw detection data from different detection dimensions, including multidimensional detection data such as time-dimensional detection data, spatial-dimensional detection data, behavioral-dimensional detection data, and state-dimensional detection data.

[0069] The system employs a unified identifier mapping for detection objects across different detection dimensions: Utilizing mature entity identifier mapping technology, it uniformly matches detection numbers, region numbers, node numbers, and status identifiers across different detection dimensions, and establishes corresponding detection object nodes based on the unified detection object number. Detection objects represent the basic detection units participating in multidimensional detection correlation analysis. Detection objects include: equipment detection nodes, region detection nodes, behavior detection nodes, and status detection nodes. When multiple detection records correspond to the same detection object, they are merged using the unified detection object number, ensuring that detection records across different detection dimensions can correspond to the same associated entity.

[0070] After completing the unified identifier mapping, the corresponding set of detection object nodes is obtained, which is used for subsequent time correspondence analysis.

[0071] Time correspondence analysis:

[0072] Using mature time series alignment technology, a unified time window interval is established based on the sampling period of different detection data; a time correspondence is established for detection records within the same time window interval; after completing the time correspondence analysis, the corresponding time association results are obtained; this time association result is used for subsequent spatial adjacency analysis.

[0073] Spatial adjacency analysis:

[0074] Using mature spatial adjacency analysis technology, the spatial connectivity between different detected objects is identified based on the topological relationships of the detection regions, the node connection relationships, and the region boundary relationships. Specifically: the topological relationships of the detection regions describe the connection structure between different detection regions; the node connection relationships describe the path connections between different detection nodes; and the region boundary relationships describe the adjacency relationships between different detection regions.

[0075] Based on the spatial connectivity results, spatial adjacency relationships are established for the detected objects that have regional connectivity relationships, and corresponding spatial association results are obtained. These spatial association results are used for subsequent state synchronization relationship analysis.

[0076] State synchronization relationship analysis:

[0077] Using mature state synchronization detection technology, the state changes of different detection objects within the same time window are synchronously identified. Based on the consistency of the direction of state change and the continuity of state change, a state synchronization relationship is established between different detection objects to obtain the corresponding state synchronization result. This state synchronization result is used for subsequent detection association basis construction.

[0078] Detection of associated basis construction:

[0079] After completing the time correspondence analysis, spatial adjacency analysis, and state synchronization analysis, the above association results are uniformly organized. Using mature association organization techniques, the detected object nodes are used as association nodes, and time correspondence, spatial adjacency, and state synchronization are used as association connections to establish a corresponding association connection structure. Based on the association connections between different detected objects, a detection association basis set is established, the expression of which is:

[0080] ;

[0081] in,

[0082] This represents a set of associated nodes, used to describe different detection object nodes;

[0083] This represents a set of associated connections, used to describe the temporal correspondence, spatial adjacency, and state synchronization relationships between different detected objects.

[0084] S2. Construct a cross-dimensional set propagation chain using the detection association basis set to obtain the cross-dimensional set;

[0085] Step S2: The set of detection-related basis sets constructed in step S1 Building upon this foundation, a continuous propagation relationship between different detection dimensions is further established, forming a corresponding cross-dimensional aggregation propagation chain structure. Step S1 primarily constructs the basic association relationships between the detected objects, while step S2 further identifies the continuous association and change processes between different detection dimensions based on the temporal correspondence, spatial adjacency, and state synchronization relationships between the detected objects. Detected objects with continuous propagation relationships are then organized into corresponding propagation chain structures, thereby obtaining the cross-dimensional aggregation set. The cross-dimensional aggregation set output by step S2 This will serve as the propagation source for the state association representation construction in the subsequent step S3, enabling the subsequent state coupling analysis to be built on the basis of continuous propagation relationships.

[0086] Step S2, in constructing the cross-dimensional aggregation propagation chain, includes the following steps:

[0087] Cross-dimensional association node extraction:

[0088] Based on the set of associations Based on the temporal correspondence, spatial adjacency, and state synchronization relationships, the detection object nodes with continuous correlation relationships are extracted;

[0089] Subsequently, based on the detection dimension to which the detection object belongs, the detection object nodes are classified by dimension to form a corresponding cross-dimensional related node set, which is used to describe the related detection objects in different detection dimensions.

[0090] Cross-dimensional propagation relationship analysis:

[0091] After extracting the cross-dimensional correlation nodes, the propagation relationship between different detection dimensions is further analyzed. The cross-dimensional propagation relationship is used to describe the continuous correlation and change relationship between different detection dimensions.

[0092] The system utilizes mature correlation propagation analysis technology to identify the temporal correlation continuity, spatial connectivity continuity, and state change continuity among different detected objects, including:

[0093] Temporal correlation continuity is used to describe whether the temporal correlation between detected objects persists.

[0094] Spatial connectivity continuity is used to describe whether the spatial connectivity between detected objects is maintained continuously.

[0095] State change continuity is used to describe whether the state synchronization relationship between detected objects continues continuously.

[0096] When the correlation between multiple detected objects persists within a continuous time window, a cross-dimensional propagation relationship is established between the corresponding detected objects. A cross-dimensional propagation correlation value is constructed to describe the degree of propagation correlation between different detected objects, and its expression is:

[0097] ;

[0098] in:

[0099] Indicates the object to be detected With the test object Cross-dimensional propagation correlation values ​​between them;

[0100] Indicates the object to be detected With the test object The time correlation matching value between them comes from the time correspondence analysis results in step S1;

[0101] Indicates the object to be detected With the test object The spatial adjacency matching value between them comes from the spatial adjacency relationship analysis results in step S1;

[0102] Indicates the object to be detected With the test object The state synchronization matching value between them comes from the state synchronization relationship analysis results in step S1;

[0103] Indicates the time correlation coefficient;

[0104] Indicates the spatial adjacency coefficient;

[0105] This represents the state synchronization coefficient.

[0106] exist , , During the acquisition process, a propagation-related sample set is established based on historical detection data. Then, using mature multi-factor weighting analysis technology, statistical analysis is performed on the temporal continuity, spatial adjacency continuity, and state synchronization continuity in the historical propagation chain. Subsequently, the system further calculates the degree of contribution of different factors in the formation of the historical propagation chain, such as the frequency of the influence of temporal continuity on propagation formation, the proportion of the influence of spatial adjacency on propagation diffusion, and the degree of influence of state synchronization on state continuation. Afterwards, the system uses a mature normalized weighting calculation method to uniformly scale the contribution results of the above factors and form corresponding weight values. Finally, the formed normalized weights are used as temporal correlation coefficients. Spatial adjacency coefficient and state synchronization coefficient This allows the three coefficients to reflect the actual influence of different related factors in the process of constructing cross-dimensional propagation relationships.

[0107] The system performs unified correlation calculations on the above correlation matching results to obtain cross-dimensional propagation correlation values ​​between corresponding detected objects. When the cross-dimensional propagation correlation value between detected objects persists in a continuous time window, the system determines that a cross-dimensional propagation relationship has been formed between the corresponding detected objects, and this cross-dimensional propagation relationship is used for subsequent propagation path construction.

[0108] Construction of cross-dimensional propagation paths:

[0109] After completing the cross-dimensional propagation relationship analysis, the system further constructs the propagation path between different detection objects. The propagation path is used to describe the single continuous propagation process between detection objects.

[0110] Based on the cross-dimensional propagation correlation value between the detected objects For detected objects with continuous propagation relationships, sequential connections are made. Based on the temporal order, spatial connection order, and state change order of the propagation relationship, multiple propagation association segments are continuously organized to construct the following propagation continuity values, which describe the degree of propagation continuity in different propagation paths:

[0111]

[0112] in:

[0113] Indicates the first The propagation continuity value of each propagation path;

[0114] Indicates the first in the propagation path Cross-dimensional propagation correlation values ​​between segment detection objects;

[0115] This indicates the number of propagation segments in the current propagation path.

[0116] The model states that by sequentially accumulating multiple cross-dimensional propagation correlation values ​​in the propagation path, the continuous propagation value of the corresponding propagation path can be obtained. ;

[0117] When multiple propagation links in a propagation path remain continuous in both temporal and spatial order, the system recognizes that a propagation path is formed between the corresponding detection objects. Subsequently, the system establishes the corresponding propagation path based on the propagation order between detection dimensions. The propagation path includes: a propagation path from the time dimension to the spatial dimension, a propagation path from the spatial dimension to the behavioral dimension, and a propagation path from the behavioral dimension to the state dimension. This propagation path is used for subsequent propagation chain aggregation analysis.

[0118] Construction of cross-dimensional aggregation and propagation chain:

[0119] Using mature chain-based association organization technology, detection objects with continuous propagation paths are chain-based aggregated; then, a corresponding cross-dimensional aggregation propagation chain is established based on the detection object nodes, propagation associations, and propagation order relationships in the propagation path.

[0120] Construct a cross-dimensional set to describe the set structure between different propagation chains; its expression is:

[0121] ;

[0122] in:

[0123] Represents a cross-dimensional set;

[0124] Indicates the first A cross-dimensional aggregation and propagation chain, ;

[0125] Indicates the total number of cross-dimensional aggregation propagation chains;

[0126] Every cross-dimensional aggregation and propagation chain All include:

[0127] The propagation node set describes the detection objects participating in the propagation.

[0128] The propagation connection set is used to describe the propagation relationships between different detection objects;

[0129] The propagation order set is used to describe the propagation direction relationship between different detection objects.

[0130] Existing mature aggregation analysis techniques typically aggregate detection results based on fixed classification rules, static label relationships, or one-dimensional association structures, focusing on classifying or summarizing detection data. However, in step S2, the system does not simply perform static aggregation based on the categories of detection results. Instead, it further identifies the continuous association and change processes between different detection dimensions based on the temporal correspondence, spatial adjacency, and state synchronization relationships identified in step S1. Furthermore, it constructs propagation paths and propagation chain structures based on continuous propagation relationships, thereby forming a cross-dimensional aggregation set oriented towards continuous propagation relationships. .

[0131] S3. Construct a state coupling representation set using a cross-dimensional aggregation set to obtain the state association representation matrix;

[0132] Step S3: The cross-dimensional set generated in step S2 Based on this, the state relationships in the propagation chain are continuously organized and structurally expressed, and a state relationship expression matrix that can describe the state context relationships is established. .

[0133] Step S3, in constructing the state-coupled representation set, includes the following steps:

[0134] State coupling analysis:

[0135] According to the set The following fields are used in the propagation node set: state identifier field, state change field, and state record field. State nodes are extracted, and the coupling relationship between different state nodes is further analyzed. The state coupling relationship is used to describe the continuous association and change relationship between different state nodes.

[0136] Using mature state association analysis technology, we identify the continuity of state origin, state propagation, and state continuation between state nodes. Among them, the continuity of state origin describes whether the current state originates from the previous state; the continuity of state propagation describes whether the state change continues to propagate along the propagation sequence; and the continuity of state continuation describes whether the state change continues within a continuous time window.

[0137] When multiple state nodes in the propagation path simultaneously satisfy the following conditions: there is a source-to-source relationship between the preceding and following states, the state changes continue along the propagation sequence, and the state changes remain consistent within a continuous time window, then it is determined that a state coupling relationship is formed between the corresponding state nodes.

[0138] Subsequently, based on the results corresponding to the state source, the state propagation, and the state continuation, an association matching result is established for the corresponding state relationships.

[0139] A state coupling association value is constructed to describe the degree of coupling association between different state nodes, and its expression is:

[0140] ;

[0141] in:

[0142] State node With state nodes The state coupling associated values ​​between them;

[0143] This indicates the state source matching value, which originates from the result corresponding to the state source;

[0144] This indicates that the state propagation matching value originates from the propagation connection relationship in step S2;

[0145] This indicates the state continuation matching value, which is derived from the state continuation corresponding results in a continuous time window;

[0146] Indicates the state origin coefficient;

[0147] Represents the state propagation coefficient;

[0148] This represents the state continuation coefficient.

[0149] exist , , During the acquisition process, mature state association statistical techniques are used to statistically analyze the source correspondence, propagation continuation, and continuous state maintenance among different state nodes. The contribution of state source relationships to state formation, the influence of state propagation relationships on the propagation chain continuation, and the sustained influence of state continuation relationships on continuous state maintenance are statistically determined. Finally, mature weight normalization techniques are used to uniformly scale the contributions of these different association factors, forming corresponding normalized weights, which are then used as state source coefficients. State propagation coefficient and state continuity coefficient .

[0150] By performing a unified correlation calculation on the above state matching results, the state coupling correlation values ​​between the corresponding state nodes are obtained. .

[0151] When the state coupling association value between state nodes persists during continuous propagation, it is determined that a state coupling relationship has been formed between the corresponding state nodes. This state coupling relationship is used for the construction of subsequent state expression paths.

[0152] State representation path construction:

[0153] After completing the state coupling relationship analysis, the state expression path between different state nodes is constructed to describe the single continuous state propagation process between state nodes.

[0154] The system relies on the state coupling correlation values ​​between state nodes. Sequential connection is performed on state nodes that have continuous state coupling relationships.

[0155] Subsequently, based on the propagation direction between states, the order of state continuation, and the order of state origination, multiple state coupling segments are continuously organized to construct state continuity values, which describe the degree of continuity in different state expression paths. The expression for the state continuity value is:

[0156] ;

[0157] in:

[0158] Indicates the first The state expression path represents the continuous state values;

[0159] The first state in the representation path Segment state coupling associated values;

[0160] This indicates the number of state coupling segments in the current state representation path.

[0161] The system obtains the continuous state values ​​of the corresponding state representation path by sequentially accumulating multiple coupled state values ​​in the state representation path. ;

[0162] When multiple state coupling segments in a state representation path remain continuous in the direction of propagation and the order of state continuation, the system recognizes that a state representation path is formed between the corresponding state nodes.

[0163] Construction of a set of state-coupled representations:

[0164] After the state representation path is constructed, the different state representation paths are aggregated and organized, where the state representation structure is used to describe the continuous state organization relationship between multiple state representation paths;

[0165] This process utilizes mature chain-like state organization technology to couple and aggregate state nodes with continuous state expression paths; subsequently, based on the state nodes in the state expression path, state coupling relationships, and state propagation order, corresponding state expression structures are established; a state coupling expression set is constructed to describe the organizational relationships between different state expression structures, and the expression for the state coupling expression set is:

[0166] ;

[0167] in:

[0168] Represents a set of state-coupled expressions;

[0169] Represents a set of state-coupled expressions The first in State representation structure, ;

[0170] This represents the total number of state representation structures;

[0171] Each state representation structure All include:

[0172] A set of state nodes used to describe the state nodes involved in state representation;

[0173] A set of state connections is used to describe the state coupling relationships between state nodes;

[0174] A set of state sequences is used to describe the order of state propagation between state nodes.

[0175] This state is coupled with the expression set Used for constructing subsequent state association expression matrices.

[0176] Construction of the state association representation matrix:

[0177] Complete the state coupling expression set After construction, the connection relationships between different state expression structures are further organized into a matrix; using state nodes as matrix row and column indices and the state connection relationships between state nodes as the basis for matrix mapping, the association relationships between different state nodes are mapped into a matrix.

[0178] Construct the following state association matrix to describe the association relationships between different state nodes:

[0179] ;

[0180] in:

[0181] Represents the state association matrix;

[0182] Indicates the total number of state nodes;

[0183] State node With state nodes The associated values ​​between them are used to describe the state nodes. With state nodes Does the state relationship exist between them, and what is the order of the relationships?

[0184] When there is a state coupling relationship between two state nodes, establish the associated expression value at the corresponding matrix position;

[0185] When there is no state coupling relationship between two state nodes, the empty associated state is maintained at the corresponding matrix position.

[0186] The final output of step S3 is the state association representation matrix. .

[0187] Existing mature state analysis techniques typically perform independent state identification or static state classification for single state results, focusing on the determination and classification of the state results themselves. However, in step S3, the system does not merely perform static identification of state results. Instead, based on the cross-dimensional aggregation and propagation chain structure in step S2, it further identifies the source correspondence, propagation continuation, and state continuity relationships between states, and constructs state expression paths, state expression structures, and state association expression matrices according to the state propagation order. This forms a state association expression structure for continuous state propagation processes.

[0188] S4. Use the state association expression matrix to generate a document paragraph mapping sequence, and obtain a document structure association set;

[0189] Step S4 involves generating the state association representation matrix from step S3. This is converted into a structured set of paragraph relationships that can be used for document organization, forming the document structure relationship set required for subsequent document content generation. .

[0190] Step S4, in generating the document paragraph mapping sequence, includes the following steps:

[0191] State association matrix analysis:

[0192] By employing mature graph structure traversal techniques, the state association expression matrix is ​​represented. The system iterates through the matrix association results and extracts state node pairs that have state association relationships. When there are association expression values ​​between state nodes, the system determines that there is a state propagation relationship between the corresponding state nodes. When there are no association expression values ​​between state nodes, the system maintains the empty association state between the corresponding state nodes. After completing the state association matrix parsing, the system obtains the corresponding state association node set.

[0193] Document paragraph node mapping:

[0194] Using mature state content mapping technology, corresponding document paragraph nodes are established based on the state description content, state propagation record, and state association relationship corresponding to the state node. Each document paragraph node is used to represent a document content unit associated with the corresponding state node.

[0195] Subsequently, based on the state propagation relationship between state nodes, paragraph association relationships are established for the corresponding document paragraph nodes. For state nodes with a preceding-following state propagation relationship, a paragraph reference relationship is established; for state nodes with a continuous state continuation relationship, a paragraph connection relationship is established. The paragraph reference relationship is used to describe the association and reference relationship between the preceding paragraph and the subsequent paragraph, and the paragraph connection relationship is used to describe the content connection relationship between consecutive paragraphs. After completing the document paragraph node mapping, the corresponding paragraph node set is obtained.

[0196] Document paragraph mapping sequence construction:

[0197] The system uses mature directed order organization technology to establish a sequential arrangement relationship for corresponding paragraph nodes based on the forward and backward propagation order in the state propagation path. When there is a propagation continuation relationship between state nodes, the system establishes a continuous arrangement relationship between corresponding paragraphs.

[0198] Based on the paragraph reference relationships, paragraph connection relationships, and paragraph arrangement relationships, different paragraph nodes are organized sequentially, and a corresponding document paragraph mapping sequence is generated. The document paragraph mapping sequence Q includes: paragraph node order, paragraph reference order, and paragraph connection order; it is used to describe the continuous organizational relationship between document paragraphs.

[0199] Document structure association collection construction:

[0200] The system utilizes mature hierarchical document structure organization technology, based on document paragraph mapping sequences. The document establishes structural connections between paragraph nodes based on their arrangement, paragraph references, connections, and arrangement. Furthermore, it organizes these paragraph nodes into a unified set of document structure relationships. ;

[0201] The document structure association set D includes:

[0202] A collection of paragraph nodes used to describe paragraph nodes in a document;

[0203] Paragraph connection set, used to describe the referencing and connection relationships between paragraphs;

[0204] Paragraph order set, used to describe the order relationship between paragraphs.

[0205] S5. Construct multidimensional detection aggregation analysis documents using document structure association set and state association expression matrix to obtain aggregation analysis document results;

[0206] Step S5: The document structure association set formed in step S4 and the state association expression matrix formed in step S3 Based on this, the relationship between content associated with different states and document structure is jointly mapped, and corresponding multidimensional detection and aggregation analysis documents are generated.

[0207] Step S5, in constructing the multidimensional detection aggregation analysis document, includes the following steps:

[0208] Document structure node extraction:

[0209] Associating sets from document structure Extract the corresponding document structure nodes, extract the corresponding document paragraph nodes based on the paragraph node set, and identify the arrangement order relationship between different paragraphs based on the paragraph order set.

[0210] Based on the paragraph connection set, the system identifies paragraph reference relationships and paragraph connection relationships between different paragraphs. Paragraph reference relationships describe the reference relationship between a preceding paragraph and a subsequent paragraph; paragraph connection relationships describe the content connection relationship between consecutive paragraphs; after extracting the document structure nodes, the system obtains the corresponding document structure node set.

[0211] State-related content mapping:

[0212] After extracting the document structure nodes, the state association expression matrix is ​​further processed. Mapping the state-related content in the matrix, and using mature state content association technology, the state association expression matrix is ​​processed. The relationships between state nodes are analyzed, and the following are extracted: state origin relationship, state propagation relationship, and state continuation relationship.

[0213] Subsequently, based on the state description record corresponding to the state node, the corresponding state content is organized into text; and according to the correspondence between state nodes and paragraph nodes, the corresponding state content is written into the corresponding document paragraph node, where:

[0214] The state source relationship is mapped to the paragraph quotation content;

[0215] State propagation relationships are mapped to paragraph propagation content;

[0216] State continuity is mapped to continuous paragraph content;

[0217] After completing the state-related content mapping, the system obtains the corresponding state content mapping result.

[0218] Collection and analysis document content generation:

[0219] After completing the mapping of state-related content, the content related to different states is further collected and organized. Using mature hierarchical document generation technology, based on the paragraph order in the paragraph sequence set, the corresponding state content is organized and written according to the structural order of the preceding paragraph, the current paragraph, and the following paragraphs. Based on the propagation direction in the state propagation path, the connection relationship between the preceding and following paragraphs is established for the corresponding state content.

[0220] Write the preceding state content into the preceding paragraph;

[0221] Subsequent status information should be written into the following paragraph;

[0222] Establish paragraph citation relationships based on state content that has a state propagation relationship;

[0223] Establish continuous paragraph connections based on the state content that has a state continuity relationship.

[0224] Construct the following document association values ​​to describe the degree of aggregation association between different paragraphs:

[0225] ;

[0226] in:

[0227] Paragraph With paragraph Document association values ​​between;

[0228] The paragraph order association value is derived from the paragraph order relationship in step S4;

[0229] This indicates the state propagation association value, which originates from the state propagation relationship in step S3;

[0230] The state continuation association value is derived from the state continuation relationship in step S3;

[0231] Indicates the paragraph order coefficient;

[0232] Represents the state propagation coefficient;

[0233] Indicates the state continuation coefficient;

[0234] Three coefficients , , The correlation contribution statistics are obtained by analyzing the paragraph organization relationship, state propagation relationship and state continuation relationship in historical aggregated analysis documents, and the contribution results of each correlation factor are uniformly scaled by using a mature normalized weight analysis method.

[0235] When paragraphs simultaneously exhibit sequential association, state propagation association, and state continuation association, a continuous aggregation analysis relationship is established between the corresponding paragraphs.

[0236] Construction of aggregated analysis document results:

[0237] After generating the aggregated analysis document content, the relationships between different paragraphs are organized in a unified manner. Through mature hierarchical content organization technology, the related content of the detection objects, cross-dimensional aggregated propagation content, state coupling related content, and paragraph reference related content in different paragraphs are uniformly aggregated and organized.

[0238] Associating sets based on document structure By establishing paragraph connections within the document, structural organization relationships are built across different document content units, resulting in aggregated analysis of document outputs.

[0239] ;

[0240] in:

[0241] This indicates the results of the document aggregation and analysis;

[0242] Indicates the results of document aggregation analysis The first in Each document content unit ;

[0243] Indicates the total number of document content units;

[0244] Each document content unit This corresponds to a structured document content segment in the aggregation analysis document, including: content related to the detection object, content related to cross-dimensional aggregation and propagation, content related to state coupling, and content related to paragraph references.

[0245] Existing mature document generation technologies typically generate corresponding analysis documents based on fixed templates, static fields, or independent detection results, focusing primarily on filling in content from existing detection results. However, in step S5, the system does not simply generate detection content based on a fixed document template. Instead, it uses the document structure relationships from step S4 and the state context relationships from step S3 to jointly map the state propagation relationships, state continuation relationships, and paragraph reference relationships between different detection contents. Furthermore, it structures the corresponding state content according to the continuous state propagation process, thereby forming a collected analysis document result with continuous detection logic, state propagation logic, and paragraph association logic. .

[0246] Example 2:

[0247] This embodiment provides a functional module for a multi-dimensional detection data intelligent aggregation and analysis document generation system, including:

[0248] Basis Association Construction Module: Corresponding to step S1, this module is used to uniformly organize the detection records, detection dimension relationships, and detection object association relationships in the multidimensional detection objects, and to establish the basic association structure between the detection objects, thereby forming a detection association basis set. This provides a basic set of related inputs for the subsequent construction of cross-dimensional aggregation and propagation chains.

[0249] Cross-dimensional aggregation construction module: corresponding to step S2, used to detect the associated basis set The relationships between detected objects, their propagation connections, and their propagation order are continuously organized to form a cross-dimensional aggregation propagation chain structure, thus yielding a cross-dimensional aggregation set. This provides the propagation structure input for subsequent state association expression analysis.

[0250] State association expression module: corresponding to step S3, used based on cross-dimensional aggregation set The propagation chain structure in the model associates and organizes the state origin relationships, state propagation relationships, and state continuation relationships between different state nodes, and establishes a state coupling expression structure, thereby forming a state association expression matrix. This provides state-related input for subsequent document structure mapping.

[0251] Document structure mapping module: corresponding to step S4, used to associate the expression matrix based on the state. The document establishes state relationships, maps document paragraph nodes to different states, and establishes paragraph arrangement, paragraph referencing, and paragraph connection relationships based on the state propagation order, thus forming a document structure association set. This provides structural and organizational input for the subsequent generation of aggregated analysis documents.

[0252] Collection and analysis document generation module: corresponding to step S5, used to associate collections based on document structure. Paragraph structure relationships and state association expression matrix The state context relationships within the data are used to jointly map and aggregate different detected content, and generate corresponding aggregation analysis document content based on paragraph arrangement relationships, state propagation relationships, and state continuation relationships, thus forming the aggregation analysis document results. .

[0253] Example 3:

[0254] This embodiment provides a scenario for the practical application of a multi-dimensional detection data intelligent aggregation and analysis document generation system:

[0255] A large industrial park includes power transmission equipment, a circulating water system, a pressure pipeline system, and an environmental monitoring system. Each system is equipped with vibration detection equipment, temperature detection equipment, current detection equipment, gas detection equipment, and pressure detection equipment. The park generates a large number of status records daily from various monitoring dimensions, including records of abnormal equipment vibration, temperature fluctuations, pressure changes, and changes in harmful gas concentrations. This industrial park has deployed a multi-dimensional monitoring data intelligent collection, analysis, and document generation system.

[0256] First, the system uses a basic association construction module to organize and associate the test records uploaded by different testing devices. Specifically, the system establishes basic associations between different test objects based on device number, testing area, testing time, and device connection relationships. For example, if the system identifies abnormal vibration of a circulating water pump and current fluctuation in a power supply cabinet as occurring in the same area, and that there is a power supply connection between them, then a basic association structure is established between the corresponding test objects.

[0257] Subsequently, the cross-dimensional aggregation construction module further organizes the anomaly propagation process in different detection dimensions based on the correlation between the aforementioned detection objects. For example, the system identifies that the power supply cabinet current fluctuation occurs before the circulating water pump vibration anomaly, and the circulating water pump vibration anomaly then leads to pressure changes in the pressure pipeline. Therefore, the system organizes the above-mentioned anomaly change process into a cross-dimensional aggregation propagation chain, so that a continuous propagation relationship is formed between multiple detection dimensions.

[0258] Next, the state association expression module further organizes the state relationships in the propagation chain. The system analyzes the source relationships, propagation relationships, and state continuation relationships between different abnormal states and forms a state association expression structure. For example, the system identifies that power supply fluctuations cause unstable water pump speed, which in turn causes pressure fluctuations to continue to expand. Therefore, it establishes continuous state association relationships between the above states and forms a corresponding state association expression matrix.

[0259] After completing the state association analysis, the document structure mapping module establishes document structure relationships based on the state association results. The system maps different state nodes to corresponding document paragraphs and organizes the paragraph arrangement according to the state propagation order. For example, the system uses "Power Supply Anomaly Analysis" as the preceding paragraph, "Water Pump Vibration Change Analysis" as the middle paragraph, and "Pressure Pipeline Fluctuation Analysis" as the following paragraph, while establishing reference relationships and content connection relationships between paragraphs, thus forming a complete document structure.

[0260] Finally, the aggregation and analysis document generation module generates the final aggregation and analysis document based on the document structure and state relationships. The generated document includes not only descriptions of the abnormal states of each detected object, but also the abnormal propagation path, state relationships, and the continuous impact process between different abnormalities. For example, the document can clearly describe the complete correlation process of "current fluctuations in the power supply cabinet causing changes in the operating state of the circulating water pump, which in turn leads to continuous pressure fluctuations in the pressure pipeline," enabling maintenance personnel to quickly locate the source and propagation path of the abnormality.

[0261] Example 4:

[0262] This embodiment also provides a computer device applicable to a multi-dimensional detection data intelligent collection and analysis document generation system, 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 multi-dimensional detection data intelligent collection and analysis document generation system proposed in the above embodiment.

[0263] This embodiment also provides a storage medium on which a computer program is stored. When the program is executed by a processor, it implements a multi-dimensional detection data intelligent collection and analysis document generation system as proposed in the above embodiments.

[0264] 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.

[0265] 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.

[0266] 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.

[0267] 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.

[0268] 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.

[0269] 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 multi-dimensional detection data intelligent collection and analysis document generation system, characterized in that, Includes the following steps: S1. Construct a multidimensional detection object association basis to obtain a set of detection association basis bases; S2. Use the detection association basis set to construct a cross-dimensional set propagation chain to obtain a cross-dimensional set; S3. Construct a state coupling representation set using a cross-dimensional aggregation set to obtain the state association representation matrix; S4. Use the state association expression matrix to generate a document paragraph mapping sequence to obtain a document structure association set; S5. Construct multidimensional detection aggregation analysis documents using document structure association set and state association expression matrix to obtain aggregation analysis document results.

2. The multi-dimensional detection data intelligent collection and analysis document generation system according to claim 1, characterized in that, Step S1 constructs the basic association structure in the multi-dimensional detection data intelligent aggregation and analysis document generation system. This is achieved by uniformly identifying and mapping the detection objects in different detection dimensions, and uniformly organizing the temporal correspondence, spatial adjacency, and state synchronization relationships among the detection objects to form a unified detection association structure. This structure is represented by a detection association basis set, and its expression is: ； in, Represents a set of associated nodes; This represents a set of associated connections.

3. The multi-dimensional detection data intelligent collection and analysis document generation system according to claim 1, characterized in that, The detection-related basis set constructed in step S1 in step S2 is described in step S2. Based on this, we further establish continuous propagation relationships between different detection dimensions and form corresponding cross-dimensional aggregation propagation chain structures; Step S2, in constructing the cross-dimensional aggregation propagation chain, includes the following steps: Extraction of cross-dimensional related nodes; Cross-dimensional propagation relationship analysis; Construction of cross-dimensional propagation paths; Construction of cross-dimensional aggregation and propagation chain.

4. The multi-dimensional detection data intelligent collection and analysis document generation system according to claim 3, characterized in that, In step S2, when extracting cross-dimensional related nodes, the related connection set is used as a basis. Based on the temporal correspondence, spatial adjacency, and state synchronization relationships, the detection object nodes with continuous correlations are extracted; then, according to the detection dimension to which the detection object belongs, the detection object nodes are classified by dimension to form a corresponding cross-dimensional correlation node set.

5. The multi-dimensional detection data intelligent collection and analysis document generation system according to claim 3, characterized in that, In step S2, during the cross-dimensional propagation relationship analysis, the association propagation analysis technique is used to identify the temporal continuity, spatial connection continuity, and state change continuity between different detected objects. When the association between multiple detected objects persists within a continuous time window, it is determined that a cross-dimensional propagation relationship has been formed between the corresponding detected objects. A cross-dimensional propagation association value is constructed to describe the degree of propagation association between different detected objects, and its expression is: ； in: Indicates the object to be detected With the test object Cross-dimensional propagation correlation values ​​between them; Indicates the object to be detected With the test object Time-related matching values ​​between them; Indicates the object to be detected With the test object Spatial adjacency matching value between them; Indicates the object to be detected With the test object The state synchronization matching values ​​between them; Indicates the time correlation coefficient; Indicates the spatial adjacency coefficient; This represents the state synchronization coefficient.

6. The multi-dimensional detection data intelligent collection and analysis document generation system according to claim 3, characterized in that, In step S2, when constructing the cross-dimensional propagation path, the cross-dimensional propagation correlation value between the detected objects is used as a basis. Sequential connection is performed on detection objects that have a continuous propagation relationship; Based on the temporal order, spatial connection order, and state change order of propagation relationships, multiple propagation-related segments are continuously organized to construct the following propagation continuity values, which describe the degree of propagation continuity in different propagation paths: ； in: Indicates the first The propagation continuity value of each propagation path; Indicates the first in the propagation path Cross-dimensional propagation correlation values ​​between segment detection objects; This indicates the number of propagation segments in the current propagation path.

7. The multi-dimensional detection data intelligent collection and analysis document generation system according to claim 3, characterized in that, In step S2, when constructing the cross-dimensional aggregation propagation chain, the detection objects with continuous propagation paths are aggregated in a chain using chain-based association organization technology. Subsequently, a corresponding cross-dimensional aggregation propagation chain is established based on the detected object nodes, propagation relationships, and propagation order relationships in the propagation path; Construct a cross-dimensional set to describe the set structure between different propagation chains; its expression is: ； in: Represents a cross-dimensional set; Indicates the first A cross-dimensional aggregation and propagation chain, ; This represents the total number of cross-dimensional aggregation propagation chains.

8. The multi-dimensional detection data intelligent collection and analysis document generation system according to claim 1, characterized in that, The cross-dimensional aggregation set formed in step S3 in step S2 Based on this, the state relationships in the propagation chain are continuously organized and structurally expressed, and a state relationship expression matrix that can describe the state context relationships is established. .

9. The multi-dimensional detection data intelligent collection and analysis document generation system according to claim 1, characterized in that, Step S4 involves generating the state association expression matrix formed in step S3. This is converted into a structured set of paragraph relationships that can be used for document organization, forming the document structure relationship set required for subsequent document content generation. .

10. A multi-dimensional detection data intelligent collection and analysis document generation system according to claim 1, characterized in that, The document structure association set formed in step S5 in step S4 and the state association expression matrix formed in step S3 Based on this, the relationship between content associated with different states and document structure is jointly mapped, and corresponding multidimensional detection and aggregation analysis documents are generated.

Images