Fire-fighting emergency resource intelligent allocation method and equipment based on big data, and medium

Abstract

The invention relates to the technical field of resource scheduling, and discloses a fire emergency resource intelligent allocation method and device based on big data and a medium, and the method comprises the steps: carrying out the semantic situation reconstruction of a target disaster event, and obtaining the structural event description of the target disaster event; performing spatio-temporal topological relation mining on the structured event description, and constructing a dynamic evolution association graph of the structured event description; performing reverse backtracking on the dynamic evolution association graph to obtain a disaster-causing causal chain of the dynamic evolution association graph; performing coupling quantitative evaluation on the target fire-fighting emergency resource to obtain an effectiveness weight of the target fire-fighting emergency resource; performing path planning on the target fire-fighting emergency resource, and performing collaborative coding on the planned path to obtain a collaborative scheduling instruction of the target fire-fighting emergency resource; issuing the cooperative scheduling instruction to the target fire-fighting emergency resource, and generating an emergency disposal scheme of the target disaster event; according to the invention, the efficiency of the fire emergency resource intelligent allocation method based on big data can be improved.

Description

Technical Field

[0001] This invention relates to the field of resource scheduling technology, and in particular to a method, equipment and medium for intelligent allocation of fire emergency resources based on big data. Background Technology

[0002] In the field of fire emergency resource allocation, existing technologies rely on single-modal reporting information to understand disaster events, lacking in-depth integration and structured consolidation of multi-dimensional information. This results in fragmented representation of event elements, biased understanding of the context, difficulty in accurately identifying the core needs of the disaster, insufficient targeting of resource allocation decisions, and inability to achieve precise matching of resources with disaster scenarios.

[0003] Existing technologies in resource scheduling do not delve deeply into the dynamic evolution patterns of disaster events. Resource effectiveness assessments are mostly based on static assignment of inherent attributes, without considering real-time changes in disaster scenarios and causal relationships. Furthermore, path planning does not adequately address the spatiotemporal conflicts of multiple resources, resulting in poor scheduling coordination and delayed response times. This makes it difficult to meet the requirements of efficiency and accuracy in disaster emergency response. Therefore, improving the generation efficiency of intelligent allocation of fire emergency resources has become an urgent problem to be solved. Summary of the Invention

[0004] This disclosure provides a method, equipment, and medium for intelligent allocation of fire emergency resources based on big data.

[0005] Firstly, this disclosure provides a method for intelligent allocation of fire emergency resources based on big data, including: S01. Reconstruct the semantic context of the target disaster event to obtain a structured event description of the target disaster event; S02. Perform spatiotemporal topological relationship mining on the structured event description to construct a dynamic evolutionary association graph of the structured event description; S03. Backtrack the key driving paths of the dynamic evolution association graph to obtain the disaster-causing causal chain of the dynamic evolution association graph. S04. Based on the disaster causal chain, the target fire emergency resources are coupled and quantitatively evaluated to obtain the effectiveness weight of the target fire emergency resources; S05. Based on the effectiveness weight, implement path planning for the target fire emergency resources, and collaboratively encode the planned path to obtain the collaborative dispatch instructions for the target fire emergency resources. S06. Issue the coordinated dispatch instruction to the target fire emergency resources to generate an emergency response plan for the target disaster event.

[0006] In a preferred embodiment, the step of semantic context reconstruction of the target disaster event to obtain a structured event description of the target disaster event includes: Multimodal information fusion is performed on the original reported information of the target disaster event to obtain a consistent contextual representation of the original reported information; Based on consistent contextual representation, the intent of the target disaster event is inferred, resulting in a contextual understanding of the target disaster event; Structured extraction of contextual understanding yields a discretized set of event elements for contextual understanding; Semantic aggregation is performed on the discretized event element set to obtain a structured event description of the target disaster event.

[0007] In a preferred embodiment, the step of mining spatiotemporal topological relationships in the structured event description to construct a dynamic evolutionary association graph of the structured event description includes: The coordinates of the event elements in the structured event description are normalized to obtain the baseline element set of the structured event description; Based on the preset relationship strength measurement criteria, the relationship strength between elements in the benchmarked element set is structurally integrated to obtain the association strength matrix of the benchmarked element set. Within a continuous time window, the cross-slice transitivity of the correlation strength matrix is ​​verified, and the verified matrix is ​​subjected to pattern extraction to obtain the key transitivity pattern set of the correlation strength matrix. A topological mapping is performed on the key transmission pattern set to obtain a dynamic evolutionary relationship graph describing structured events.

[0008] In a preferred embodiment, the step of reverse tracing the key driving paths of the dynamic evolutionary association graph to obtain the causal chain of disaster in the dynamic evolutionary association graph includes: By performing multi-level influence intensity screening on the nodes in the dynamic evolution correlation graph, the key node sequence of the dynamic evolution correlation graph is obtained. Based on the dynamic evolutionary association graph, the connection edges between key node sequences are backtracked by temporal logic dual importance to obtain the key connection edge set of key node sequences; Based on the preset confidence standard, the causal confidence value is assigned to the key connection edge set to obtain the directed causal edge set of the key connection edge set; Based on the confidence criterion, the directed causal edge set is filtered by the confidence threshold to obtain the credible causal edge set of the directed causal edge set; By integrating the path integrity of the credible causal edge set, the disaster-causing causal chain of the dynamic evolutionary association graph is obtained.

[0009] In a preferred embodiment, the coupled quantitative evaluation of the target fire emergency resources based on the disaster causal chain to obtain the effectiveness weight of the target fire emergency resources includes: Vulnerability quantification is performed on the disaster-causing causal chain to obtain the node sensitivity of the disaster-causing causal chain; Based on node sensitivity, the resource attributes of the target fire emergency resources are aligned bidirectionally to obtain the node alignment relationship of the target fire emergency resources. The correlation degree of the node alignment relationship is calibrated to obtain the original blocking effect of the target fire emergency resources; Based on the real-time status of the target fire emergency resources, the original blocking effectiveness is corrected for timeliness, and the confidence boundary of the corrected effectiveness is defined to obtain the dynamic effectiveness range of the original blocking effectiveness. Based on node sensitivity, the core effectiveness values ​​of the dynamic effectiveness range are normalized and fused across nodes to obtain the effectiveness weight of the target fire emergency resources.

[0010] In a preferred embodiment, the step of adjusting the original blocking effectiveness based on the real-time status of the target fire emergency resources and defining the confidence boundary of the adjusted effectiveness to obtain the dynamic effectiveness range of the original blocking effectiveness includes: Multi-dimensional parameter separation is performed on the real-time status of the target fire emergency resources to obtain the time deviation parameter and reliability parameter of the real-time status; Based on node sensitivity, the core links of the disaster-causing causal chain are identified to obtain the ideal intervention time point of the disaster-causing causal chain. Calculate the time-fit correction coefficient for the original blocking efficacy; Based on the time-fit correction coefficient, the original blocking efficacy is modified and transformed to obtain the time-calibrated value of the original blocking efficacy; Based on reliability parameters, the dynamic range of the aging calibration value is extrapolated to obtain the dynamic effectiveness range of the corrected effectiveness.

[0011] In a preferred embodiment, the step of implementing path planning for the target fire emergency resources based on effectiveness weights and co-coding the planned paths to obtain co-scheduling instructions for the target fire emergency resources includes: The effectiveness weights are dynamically prioritized to obtain the resource scheduling sequence based on effectiveness weights; Based on the resource scheduling sequence, multi-constraint shortest path analysis is performed on the target fire emergency resources to obtain the initial path of the target fire emergency resources; Spatiotemporal occupancy conflict detection is performed on the initial path to obtain the conflict coordinate set of the initial path; Based on the conflict coordinate set, the initial path is spatiotemporally conflicted and resolved to obtain a conflict-free path. By structurally encoding conflict-free paths, coordinated dispatch instructions for target fire emergency resources are obtained.

[0012] In a preferred embodiment, the step of issuing collaborative dispatch instructions to target fire emergency resources to generate an emergency response plan for the target disaster event includes: Based on the coordinated scheduling instructions, the driving parameters of the target fire emergency resources are converted to obtain the executable driving instructions of the target fire emergency resources; The executable drive commands are delivered in a hierarchical manner, and the target fire emergency resources are tracked in real time to obtain the status feedback of the executable drive command sequence; Based on status feedback, the initial response actions of the target fire emergency resources are synchronized to obtain the emergency response plan for the target disaster event.

[0013] Compared with the prior art, the present invention has the following beneficial effects: 1. This invention achieves structured and accurate representation of disaster events through semantic context reconstruction. Combined with spatiotemporal topological relationship mining and disaster causal chain backtracking, it can accurately locate the core evolution path of disasters. The coupled quantitative assessment based on the disaster causal chain can dynamically adapt to the correlation needs of resources and disaster scenarios, significantly improve the accuracy of fire emergency resource effectiveness weight assessment, and ensure the scientific and targeted nature of resource allocation decisions.

[0014] 2. This invention optimizes the allocation of resource implementation paths through multi-constraint path planning and spatiotemporal conflict resolution. Combined with collaborative coding to generate precise collaborative scheduling instructions, it can significantly improve the coordination and efficiency of multi-resource scheduling. At the same time, by driving parameter conversion and real-time status tracking, it ensures the effective execution of scheduling instructions, significantly improves the generation efficiency and feasibility of emergency response plans, and strengthens the timeliness and reliability of disaster emergency response. Attached Figure Description

[0015] The present disclosure will be described in more detail below based on embodiments and with reference to the accompanying drawings: Figure 1 The flowchart of the intelligent allocation method for fire emergency resources based on big data according to Embodiment 1 of the present invention is shown. Figure 2 The diagram shows the structural composition of the intelligent fire emergency resource allocation device based on big data, as implemented in Embodiment 2 of the present invention. Detailed Implementation

[0016] To enable those skilled in the art to better understand the technical solutions of this disclosure, and to fully understand and implement the process of how this disclosure applies technical means to solve technical problems and achieve corresponding technical effects, the technical solutions in the embodiments of this disclosure will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this disclosure, not all embodiments. The embodiments of this disclosure and the various features within them can be combined with each other without conflict, and the resulting technical solutions are all within the protection scope of this disclosure. All other embodiments obtained by those skilled in the art based on the embodiments of this disclosure without creative effort should fall within the protection scope of this disclosure.

[0017] It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and although a logical order is shown in the flowchart, in some cases the steps shown or described may be executed in a different order than that shown here.

[0018] Example 1 Figure 1 This is a flowchart illustrating a method for intelligent allocation of fire emergency resources based on big data, provided in an embodiment of this disclosure. Figure 1 As shown, a method for intelligent allocation of fire emergency resources based on big data includes: S01. Reconstruct the semantic context of the target disaster event to obtain a structured event description of the target disaster event; In this embodiment of the invention, the step of semantic context reconstruction of the target disaster event to obtain a structured event description of the target disaster event includes: Multimodal information fusion is performed on the original reported information of the target disaster event to obtain a consistent contextual representation of the original reported information; Based on consistent contextual representation, the intent of the target disaster event is inferred, resulting in a contextual understanding of the target disaster event; Structured extraction of contextual understanding yields a discretized set of event elements for contextual understanding; Semantic aggregation is performed on the discretized event element set to obtain a structured event description of the target disaster event.

[0019] To achieve a consistent contextual representation of the original reported disaster information, multimodal information fusion is required. This necessitates first classifying and organizing the different types of information in the original reports, distinguishing between text, image, and audio modalities. Text information undergoes word segmentation and semantic annotation to clarify disaster-related information. Image information undergoes key visual feature extraction, transforming the disaster scene details presented in the images into understandable textual descriptions. Audio information undergoes transcription, converting the audio content into text before semantic analysis. After processing each modality individually, the information is matched and integrated according to the core disaster content described. This core disaster content includes key dimensions such as disaster type, exact location, scale, time of occurrence, current situation, affected objects, on-site environmental characteristics, and the reliability of the information source. This process eliminates duplicate or contradictory information, organically combining information from different modalities to form a consistent contextual representation that comprehensively reflects the core content of the original reported information.

[0020] To achieve contextual understanding of a target disaster event, intent inference is performed based on a consistent contextual representation. This requires extracting key information about the disaster's occurrence from the consistent contextual representation, including the location characteristics of the disaster, its specific manifestations, and its initial development trend. This key information is a focus and refinement of various dimensions within the core content of the disaster, typically prioritizing key indicators that directly influence emergency decision-making, such as disaster type, exact location, current situation, affected parties, and core demands. By analyzing the inherent relationships between these key pieces of information—specifically, by querying a pre-defined disaster element association database to establish information connections, using disaster impact assessment rules and geographic information data for hazard simulation and scope assessment, and referring to an emergency response strategy mapping table to match event characteristics—the potential scope and degree of harm caused by the disaster event are determined, identifying the direction of emergency response needs corresponding to the disaster event, and clarifying whether the core demand of the event is personnel rescue, property protection, or disaster control. Combining these analytical results, a comprehensive and clear understanding of the overall situation of the disaster event is formed, ultimately resulting in a contextual understanding that accurately reflects the essential needs and overall situation of the disaster event.

[0021] To obtain a discretized event element set, structured extraction is performed on the context understanding. This requires extracting corresponding information from the context understanding one by one according to predefined event element categories. Event element categories include disaster type, disaster occurrence time, disaster location, affected area, number of people trapped, and existing protective measures. During the extraction process, for each element category, the specific information corresponding to it in the context understanding is precisely located, and the specific content of each element is separated to ensure that each extracted element information has a clear direction and independence. After all elements are extracted, they are integrated to form a discretized event element set composed of multiple independent elements.

[0022] To obtain a structured event description by semantically aggregating a set of discrete event elements, it is necessary to first clarify the semantic relationships between the elements in the set. These semantic relationships are established based on pre-defined fire emergency standards and specifications, association patterns in historical disaster case databases, and element relationship definitions in a domain expert knowledge base, clarifying the roles and interrelationships of different elements in the disaster event. Semantically related elements are then categorized and integrated; for example, the location and impact range of the disaster are categorized as spatially related elements, and the time and development trend of the disaster are categorized as temporally related elements. Following a unified information organization standard, the integrated element information is arranged in an orderly manner, clearly presenting the logical relationships between elements, ensuring that the integrated information is clear, logically coherent, and logically sound. Through this semantic aggregation process, a structured event description that systematically and comprehensively reflects the complete information of the target disaster event is ultimately formed.

[0023] The beneficial effects are as follows: By fusing multimodal information from the original reported information of the target disaster event, the system integrates different types of information and eliminates duplicate and contradictory content, forming a consistent contextual expression that comprehensively reflects the core information, ensuring the completeness and accuracy of disaster-related information. Based on this consistent contextual expression, intent inference is carried out, key disaster information is accurately extracted and its internal connections are sorted out, clarifying the scope of disaster harm, the degree of impact, and the direction of emergency response needs, forming a clear contextual understanding of the essential needs and overall situation of the disaster event. Independent elements are accurately extracted from the contextual understanding according to preset categories to construct a set of discrete event elements with clear direction and complete information, ensuring the independence and accuracy of each disaster element. By sorting out the semantic relationships between elements and classifying and integrating them, various elements are arranged in an orderly manner according to unified standards, forming a clear, logical, and comprehensive structured event description, realizing the accurate representation of the target disaster event information, and providing a solid and reliable information foundation for subsequent analysis and decision-making related to fire emergency resource allocation.

[0024] S02. Perform spatiotemporal topological relationship mining on the structured event description to construct a dynamic evolutionary association graph of the structured event description; In this embodiment of the invention, the step of mining spatiotemporal topological relationships in the structured event description to construct a dynamic evolutionary association graph of the structured event description includes: The coordinates of the event elements in the structured event description are normalized to obtain the baseline element set of the structured event description; Based on the preset relationship strength measurement criteria, the relationship strength between elements in the benchmarked element set is structurally integrated to obtain the association strength matrix of the benchmarked element set. Within a continuous time window, the cross-slice transitivity of the correlation strength matrix is ​​verified, and the verified matrix is ​​subjected to pattern extraction to obtain the key transitivity pattern set of the correlation strength matrix. A topological mapping is performed on the key transmission pattern set to obtain a dynamic evolutionary relationship graph describing structured events.

[0025] To obtain a benchmark element set by coordinate normalization of event elements in a structured event description, it is necessary to first clarify the types of spatiotemporal information contained in the event elements, including the specific time and spatial location of the event. A unified spatiotemporal reference standard must be established. For the time dimension, a fixed time measurement system is adopted, converting the occurrence time of all event elements into a unified representation under this system to eliminate differences caused by different time recording formats. For the spatial dimension, a universal geographic coordinate system is adopted, converting the spatial location of all event elements into standard coordinate values ​​under this coordinate system to ensure consistency in the description methods of different locations. Each event element in the structured event description is then transformed one by one according to the above unified spatiotemporal reference standard, ensuring that the spatiotemporal coordinates of each element are under the same measurement dimension. All event elements after comprehensive transformation are integrated to form the benchmark element set.

[0026] To obtain a correlation strength matrix, a structured integration of the relationship strength between elements in a benchmark element set is performed based on a pre-defined relationship strength measurement criterion. This requires first clarifying the core evaluation dimensions of the criterion and its coverage of the temporal and spatial correlation strength between elements. For temporal correlation strength, the shorter the interval between the occurrences of two elements, the stronger the temporal correlation. For spatial correlation strength, the closer the spatial locations of two elements, the stronger the spatial correlation. Following this criterion, each pair of elements in the benchmark element set is analyzed individually. By combining the results of temporal and spatial correlation assessments, the relationship strength level of each pair of elements is determined. Specifically, a time-space correlation coupling lookup table derived from historical disaster data is used to map the combination of time intervals and spatial distances to predefined relationship strength levels, and this level is quantified using a specific expression. All elements are arranged in a fixed order as rows and columns of a matrix, and the quantified relationship strength result for each pair of elements is filled into the corresponding position in the matrix, forming a complete correlation strength matrix.

[0027] To perform cross-slice transitivity verification of the association strength matrix within a continuous time window, and to extract the key transitivity pattern set from the verified matrix, the overall time axis must first be divided into multiple continuous and non-overlapping time windows. Each time window corresponds to an association strength matrix slice, and each slice reflects the relationship strength state between elements within that time window. For matrix slices corresponding to two adjacent time windows, the relationship between elements in the previous slice is checked one by one to see if it can be transmitted to the subsequent slice through intermediate elements, thereby verifying the transmissibility of relationships across slices. The intermediate element refers to an element that appears in the benchmark element set of both the previous and subsequent time windows. The judgment process is as follows: for any pair of elements A and B in the previous slice whose relationship strength level is higher than a preset direct association threshold, if there exists an intermediate element C such that the relationship strength level between A and C in the previous slice is higher than the preset transmission threshold, and the relationship strength level between C and B in the subsequent slice is higher than the preset transmission threshold, then it is determined that the relationship between elements A and B can be transmitted from the previous slice to the subsequent slice through the intermediate element C. The judgment is based on the preset direct association threshold and transmission threshold, which are determined based on the statistical distribution of relationship strength in historical disaster data. After completing the transitivity verification of all adjacent slices, all verified matrix slices are systematically sorted out, and the frequency of occurrence of each element relationship combination and the variance of its relationship strength level are statistically analyzed in all slices. Based on preset frequency thresholds and variance thresholds, which are set based on the statistical characteristics of relationship combinations in historical disaster data, element relationship combinations with a frequency higher than the frequency threshold and a relationship strength level variance lower than the variance threshold are selected as relationship combinations with stable characteristics. Those scattered and irregular relationships with a frequency lower than the frequency threshold or a relationship strength level variance higher than the variance threshold are removed, and these stable relationship combinations are extracted to form a key transitivity pattern set.

[0028] To obtain a dynamic evolutionary relationship graph describing structured events by performing topological mapping on a set of key transmission patterns, the core logic of topological mapping must first be clarified: transforming each event element in the set of key transmission patterns into an independent node in the graph, and converting the strength of the relationships between elements into the attribute characteristics of the connecting edges between nodes. Based on the relationship combinations of the elements in the set of key transmission patterns, the nodes corresponding to each element are placed in appropriate spatial positions. The presentation of the connecting edges between nodes is determined according to the strength of the relationships between elements; the stronger the relationship, the more prominent the connecting edge. Simultaneously, by combining the temporal sequence of continuous time windows, the evolutionary trajectory of the relationships between elements over time is reflected in the graph; that is, the changes in element relationships under different time windows are displayed through the dynamic characteristics of the connecting edges. By organically integrating all node connecting edges and temporal evolution trajectories, a dynamic evolutionary relationship graph is formed that clearly reflects the spatiotemporal relationships and dynamic changes of event elements.

[0029] The beneficial effects include: normalizing the coordinates of event elements in structured event descriptions, unifying spatiotemporal reference standards, converting different formats of time information and different expressions of spatial location into a consistent measurement dimension, eliminating various spatiotemporal differences, forming a benchmark element set, and ensuring the accuracy and consistency of subsequent relationship analysis. Based on preset criteria, the strength of the relationship between each pair of elements in the benchmark element set is evaluated and quantified one by one, and a relationship strength matrix is ​​formed through structured integration, comprehensively and accurately presenting the relationship status between elements. Cross-slice transitivity verification is carried out within a continuous time window. The verified matrix slices are systematically sorted out, stable and repetitive element relationship combinations are identified, and scattered and irregular relationships are eliminated to obtain a key transmission pattern set, effectively capturing the dynamic transmission characteristics of element relationships. Through topological mapping, event elements are transformed into independent nodes, and the relationship strength between elements is transformed into node connection edge attributes. Combined with the time sequence, the relationship evolution trajectory is displayed, and a dynamic evolutionary relationship graph is constructed, clearly and systematically presenting the spatiotemporal topological relationship and dynamic evolution law of event elements, providing a solid relationship foundation for the accurate mining of subsequent disaster causal chains.

[0030] S03. Backtrack the key driving paths of the dynamic evolution association graph to obtain the disaster-causing causal chain of the dynamic evolution association graph. In this embodiment of the invention, the step of reverse tracing the key driving paths of the dynamic evolutionary association graph to obtain the causal chain of disaster in the dynamic evolutionary association graph includes: By performing multi-level influence intensity screening on the nodes in the dynamic evolution correlation graph, the key node sequence of the dynamic evolution correlation graph is obtained. Based on the dynamic evolutionary association graph, the connection edges between key node sequences are backtracked by temporal logic dual importance to obtain the key connection edge set of key node sequences; Based on the preset confidence standard, the causal confidence value is assigned to the key connection edge set to obtain the directed causal edge set of the key connection edge set; Based on the confidence criterion, the directed causal edge set is filtered by the confidence threshold to obtain the credible causal edge set of the directed causal edge set; By integrating the path integrity of the credible causal edge set, the disaster-causing causal chain of the dynamic evolutionary association graph is obtained.

[0031] To obtain a sequence of key nodes by screening nodes in a dynamic evolutionary correlation graph using multi-level impact intensity, the core evaluation dimensions of impact intensity must first be defined. These dimensions include the number of direct connections between nodes and the scale of nodes that can influence other nodes through these connections. By assigning preset weights to the number of direct connections and the coverage of the influence, the normalized values ​​are weighted and combined to calculate the comprehensive impact intensity value of each node. The weights and normalization benchmarks are derived from historical disaster data. Multiple screening levels are established from high to low impact intensity, each level corresponding to an impact intensity value range, with higher levels corresponding to higher intensity ranges. The upper and lower boundaries of these ranges are defined based on the statistical distribution of node impact intensity values ​​in historical disaster data. The highest level corresponds to the node with the widest impact range and the largest number of direct connections, with subsequent levels progressively lowering the screening criteria. Starting from all nodes in the dynamic evolutionary correlation graph, nodes meeting the highest level criteria are first screened, then the remaining nodes are screened sequentially according to the criteria of subsequent levels. All screened nodes are arranged in descending order of their respective levels, and adjustments are made based on the temporal order of their appearance to form an ordered sequence of key nodes.

[0032] To obtain a set of key connection edges, a temporal logic dual importance backtracking is performed on the connecting edges between key node sequences based on a dynamic evolutionary association graph. The core basis of temporal logic is the chronological order in which nodes appear in the node sequence. Dual importance refers to the structural importance of the connecting edge to the association between nodes and the duration of the connecting edge over time. Starting from the final node of the key node sequence, the preceding nodes are traced back in reverse chronological order, and the connecting edges between adjacent key nodes are checked one by one. The structural importance of each connecting edge is determined, i.e., whether the edge is the core link maintaining the association between two nodes, and the duration of the connecting edge from its formation to its current state is recorded. Connecting edges with high structural importance and duration meeting preset requirements are retained. All connecting edges meeting the conditions during the backtracking process are collected and integrated to form a set of key connection edges.

[0033] To obtain a directed causal edge set, a causal confidence score is assigned to the key connection edge set based on a preset confidence score standard. First, the core reference criteria for the confidence score standard must be clearly defined, including the frequency of occurrence of the node associations corresponding to the connection edges in similar historical scenarios and the degree of fit between the associations carried by the connection edges and the disaster evolution patterns. Each connection edge in the key connection edge set is analyzed individually. The stability of the association is judged based on the frequency of occurrence of this type of node association in similar historical scenarios; the higher the frequency, the stronger the stability. Combining the general laws of disaster evolution, it is judged whether the association relationship of the connection edges conforms to the logical trend of disaster development; the higher the fit, the stronger the causal correlation. Specifically, the association relationship carried by the connection edge is matched with disaster chain rules defined in a typical causal pattern library extracted from a historical disaster case library or a domain expert knowledge base. If the association relationship matches one or more of the aforementioned typical causal patterns or disaster chain rules, its fit is considered high, and the causal correlation is strong; otherwise, its fit is considered low. Based on the analysis results of stability and fit, each connection edge is assigned a corresponding confidence level label. At the same time, according to the order of node appearance and the direction of influence, the causal direction of each connection edge is clarified, that is, from the node that appears first and has an impact to the node that appears later and is affected, forming a set of directed causal edges with confidence level labels and causal directions.

[0034] To obtain a reliable causal edge set by filtering directed causal edge sets based on confidence thresholds, a clear threshold boundary must first be determined according to the confidence standard. This boundary is the core basis for distinguishing whether a causal relationship is reliable. The confidence level of each edge in the directed causal edge set is checked one by one, and the corresponding confidence level is compared with the preset threshold. Directed causal edges with confidence levels reaching or exceeding the threshold are retained, while those with confidence levels below the threshold are directly removed, ensuring that each remaining edge has a reliable causal relationship. The filtered and retained directed causal edges are then organized to ensure that the causal direction of each edge is clear and the confidence level label is complete, forming a reliable causal edge set.

[0035] To obtain the disaster-causing causal chain of the dynamic evolutionary correlation graph by integrating the set of trusted causal edges to ensure path integrity, it is necessary to first clarify the causal pointing relationships of each edge in the set of trusted causal edges, and identify the starting and ending nodes of each edge. Edges whose starting nodes have no preceding associated nodes are identified from the set of trusted causal edges; these are used as the starting points of the causal paths, and subsequent nodes are connected sequentially according to their causal pointing, ensuring that each node's subsequent nodes are associated with it through trusted causal edges. During this process, the continuity of the paths is checked. If any nodes are missing or connections are broken, the dynamic evolutionary correlation graph is checked to confirm whether any trusted causal edges are omitted. If none are missing, a reasonable way to connect the path breaks is determined based on the existing edge association logic. Following the chronological order and causal transmission logic, all trusted causal edges and their corresponding nodes are sequentially linked to form a complete, coherent disaster-causing causal chain that conforms to the disaster evolution logic.

[0036] The beneficial effects include multi-level impact intensity screening, which divides the screening levels according to the number of node connections and the coverage of associations, sequentially screening core nodes and forming a key node sequence, accurately identifying the core elements that play an important role in disaster evolution, and ensuring the relevance of subsequent causal analysis. Based on the dual importance of temporal logic, and combining the time sequence of nodes with the structural importance and duration of connection edges, key connection edges are collected and integrated to form a key connection edge set, effectively extracting the core correlation links between nodes. Based on the frequency of occurrence of historical scenarios and the degree of fit with disaster evolution patterns, key connection edges are assigned confidence labels and their causal orientation is clarified, forming a directed causal edge set, strengthening the reliability and directionality of the association. Through confidence threshold filtering, low-confidence edges are eliminated, and high-reliability directed causal edges are retained to form a credible causal edge set, ensuring the effectiveness of causal associations. The credible causal edges are integrated for path integrity, sorting out causal orientations and supplementing reasonable connections to form a complete and coherent disaster-causing causal chain that conforms to the logic of disaster evolution, accurately reconstructing the core causal path of disaster occurrence and development, and providing key decision-making basis for the precise allocation of subsequent fire and emergency resources.

[0037] S04. Based on the disaster causal chain, the target fire emergency resources are coupled and quantitatively evaluated to obtain the effectiveness weight of the target fire emergency resources; In this embodiment of the invention, the step of performing a coupled quantitative evaluation of the target fire emergency resources based on the disaster causal chain to obtain the effectiveness weight of the target fire emergency resources includes: Vulnerability quantification is performed on the disaster-causing causal chain to obtain the node sensitivity of the disaster-causing causal chain; Based on node sensitivity, the resource attributes of the target fire emergency resources are aligned bidirectionally to obtain the node alignment relationship of the target fire emergency resources. The correlation degree of the node alignment relationship is calibrated to obtain the original blocking effect of the target fire emergency resources; Based on the real-time status of the target fire emergency resources, the original blocking effectiveness is corrected for timeliness, and the confidence boundary of the corrected effectiveness is defined to obtain the dynamic effectiveness range of the original blocking effectiveness. Based on node sensitivity, the core effectiveness values ​​of the dynamic effectiveness range are normalized and fused across nodes to obtain the effectiveness weight of the target fire emergency resources.

[0038] The method involves adjusting the original blocking effectiveness based on the real-time status of the target fire emergency resources, and defining the confidence boundary of the adjusted effectiveness to obtain the dynamic effectiveness range of the original blocking effectiveness, including: Multi-dimensional parameter separation is performed on the real-time status of the target fire emergency resources to obtain the time deviation parameter and reliability parameter of the real-time status; Based on node sensitivity, the core links of the disaster-causing causal chain are identified to obtain the ideal intervention time point of the disaster-causing causal chain. Calculate the time-fit correction coefficient for the original blocking efficacy; Based on the time-fit correction coefficient, the original blocking efficacy is modified and transformed to obtain the time-calibrated value of the original blocking efficacy; Based on reliability parameters, the dynamic range of the aging calibration value is extrapolated to obtain the dynamic effectiveness range of the corrected effectiveness.

[0039] To quantify the vulnerability of disaster-causing causal chains to obtain node sensitivity, an analysis needs to be conducted from three aspects: the role of each node in the disaster evolution, the degree of impact on subsequent nodes, and its irreplaceability. Clarifying the position and role of a node in the causal chain is crucial for its impact on the overall evolution. Whether a node is in a core transmission link is determined based on the number of direct connections and the size of reachable nodes, as mentioned in the previous node impact intensity assessment. If a node has a large number of direct connections and a large size of reachable nodes, it is considered to be in a core transmission link. The analysis should also determine whether the failure of a node will lead to the interruption or significant weakening of subsequent causal transmission; the more severe the impact, the higher the vulnerability. Finally, it should be checked whether there are other nodes that can replace the function of the node; nodes without substitutes are more vulnerable than those with substitutes. By combining the results of these three analyses, the vulnerability of each node can be clearly defined, forming a node sensitivity that reflects the vulnerability level of a node in the disaster-causing causal chain.

[0040] To establish node alignment relationships, a two-way alignment of the resource attributes of target fire emergency resources is performed based on node sensitivity. First, nodes are categorized according to their sensitivity, defining the classification criteria for high-sensitivity, medium-sensitivity, and low-sensitivity nodes. Different node types correspond to different key roles in disaster evolution; high-sensitivity nodes are the core triggering or transmission nodes in the disaster causal chain, while medium- and low-sensitivity nodes are secondary transmission nodes and peripheral nodes, respectively. The resource attributes of the target fire emergency resources are then analyzed, including specific characteristics such as fire extinguishing capacity, rescue efficiency, protection range, response speed, and equipment integrity. A two-way match is then performed between the disaster blocking requirements corresponding to node types and the functional characteristics of resource attributes. High-sensitivity nodes require resource attributes with rapid and efficient blocking capabilities, medium-sensitivity nodes correspond to resource attributes with conventional blocking capabilities, and low-sensitivity nodes are matched with auxiliary resource attributes. This clarifies the node type and attribute matching logic for each target fire emergency resource, thus forming the node alignment relationship.

[0041] To determine the inherent blocking effectiveness of target fire emergency resources by calibrating the correlation of node alignment relationships, an analysis is needed from two dimensions: the degree of fit between resource attributes and node type requirements, and the ability of resource attributes to inhibit node functions. It is necessary to determine whether resource attributes fully cover the vulnerabilities of the corresponding node type. Vulnerabilities refer to specific attributes or states that nodes rely on for playing a key role in disaster evolution, as identified through vulnerability quantification of the disaster causal chain, such as the accumulation state of flammable materials or the failure state of load-bearing structures. The more comprehensive the coverage, the higher the degree of fit. The more significant the inhibitory effect of resource attributes, the stronger the blocking capability. Based on the combined analysis results of fit and inhibition capability, a clear correlation level is assigned to each node alignment relationship. A higher level indicates a greater blocking potential of the resource on the corresponding node. This correlation level is then converted into an inherent blocking effectiveness that quantifies the inherent blocking capability of the resource.

[0042] To obtain time deviation and reliability parameters, multi-dimensional parameter separation is performed on the real-time status of target fire emergency resources. This requires comprehensive collection of current operational information, including the estimated arrival time at the disaster site, the quality of past mission completion, and current equipment condition and maintenance records. This information is categorized by attribute: one category is time-related parameters, namely the difference between the estimated arrival time of the resource and the ideal intervention time at key nodes in the disaster causal chain, forming the time deviation parameter; the other category is parameters related to the stability of resource execution capabilities. This involves integrating information such as the quality of past mission completion, equipment condition, and maintenance records. By comparing this information with records of resources functioning normally in historical missions, a quantitative reliability score is obtained, forming a reliability parameter reflecting whether the resource can stably perform its disruptive function.

[0043] To identify the ideal intervention time point by identifying core links in the disaster causal chain based on node sensitivity, priority should be given to the causal transmission links where highly sensitive nodes are located, as these links are the key to stopping the evolution of the disaster. The triggering sequence and interaction relationships of each node in the core links should be analyzed to determine the critical time point at which each highly sensitive node begins to play its role and pushes the causal chain downward. The ideal intervention time point is set as the period before the high-sensitivity node triggers the critical time point, ensuring that resources can be fully utilized to block the spread. This period must allow sufficient time for resources to arrive on-site and carry out response work to effectively prevent the node from triggering subsequent disaster evolution.

[0044] Calculating the timeliness correction coefficient for the effectiveness of native blocking requires a comprehensive assessment of both time deviation and reliability parameters. If the expected arrival time of the resource perfectly matches the ideal intervention time, the time deviation parameter corresponds to the highest correction coefficient level. If the expected arrival time is earlier or later than the ideal intervention time, the correction coefficient level is lowered according to the length of the deviation, with longer deviations resulting in lower levels. Simultaneously, resources with a history of high-quality service, excellent equipment condition, and complete maintenance records receive the highest reliability correction coefficient level; conversely, the correction coefficient level is gradually lowered as reliability decreases. By combining the correction coefficient levels corresponding to both the time deviation and reliability parameters, a single timeliness correction coefficient is finally determined. The formula for calculating the timeliness correction coefficient is as follows: ; In the formula, For timeliness matching correction factor, The preset attenuation constant, This refers to the estimated arrival time of resources in the time deviation parameter. For the ideal time to intervene, It is a natural exponential function. The preset attenuation constant, These are reliability parameters.

[0045] The original blocking effectiveness is modified and transformed based on the timeliness matching correction coefficient to obtain the timeliness calibration value. The original blocking effectiveness needs to be adjusted specifically according to the correction coefficient level. When the correction coefficient is at its highest level, the original blocking effectiveness is maintained at its original level or slightly increased by a fixed percentage to reflect the resource's blocking capability under optimal timeliness and high reliability. When the correction coefficient is at a medium to low level, the original blocking effectiveness is reduced by a fixed percentage corresponding to the level. The lower the correction coefficient level, the higher the reduction percentage, ensuring that the adjusted timeliness calibration value accurately reflects the resource's actual blocking capability under the current real-time condition.

[0046] The dynamic effectiveness range is derived by dynamically extrapolating the time-of-use calibration values ​​based on reliability parameters. The fluctuation range of the time-of-use calibration values ​​needs to be determined according to the level of the reliability parameters. When the reliability parameters are at a high level, the resource's performance is highly stable, the deviation between the actual effectiveness and the time-of-use calibration values ​​is small, and the upper and lower limits of the dynamic effectiveness range fluctuate slightly around the time-of-use calibration values. When the reliability parameters are at a medium to low level, the risk of fluctuation in the actual effectiveness of the resource increases, and the fluctuation range of the upper and lower limits of the dynamic effectiveness range expands accordingly. The downward adjustment of the lower limit is greater than the upward adjustment of the upper limit, forming a dynamic effectiveness range that can cover the actual effectiveness range under different reliability states of the resource.

[0047] To obtain effectiveness weights, the core effectiveness values ​​of dynamic effectiveness intervals are normalized and fused across nodes based on node sensitivity. First, the median value of each dynamic effectiveness interval is extracted as the core effectiveness value, representing the typical blocking effectiveness level of the resource at the corresponding node. A corresponding weight percentage is assigned to each core effectiveness value according to the node sensitivity, with high-sensitivity nodes having the highest weight percentage, followed by medium-sensitivity nodes, and low-sensitivity nodes having the lowest. The core effectiveness values ​​corresponding to all nodes are then integrated and calculated according to their assigned weight percentages. This integration result comprehensively reflects the overall blocking effectiveness of the resource on the entire disaster-causing causal chain, ultimately forming the effectiveness weight of the target fire emergency resource.

[0048] The estimated arrival time of resources is derived from the time deviation parameter. This parameter is obtained by collecting information such as the current location and traffic conditions of the target fire emergency resources, and combining this information with the normal movement speed of the resources to calculate the estimated arrival time of the resources at the disaster site.

[0049] The ideal intervention time point is derived from the identification results of the core links in the disaster causal chain. The method is to focus on the core transmission link where the highly sensitive node is located in the disaster causal chain, analyze the triggering time sequence and interaction relationship of the nodes in this link, and determine the time point that can ensure resources can be used for disposal before the highly sensitive node drives the transmission of the causal chain.

[0050] The attenuation constant is a preset fixed value. It is obtained by combining the impact of time deviation on resource effectiveness in historical disaster response cases and determining the fixed value by statistically analyzing the correspondence between time deviation and effectiveness attenuation in historical cases.

[0051] The reliability parameters are derived from the real-time status of the target fire emergency resources. The method of obtaining them is to integrate information such as the quality of past task completion, current equipment integrity, and maintenance records, and to comprehensively determine the indicators that reflect the stability of the resource's execution capability.

[0052] The significance of this formula is to obtain the timeliness matching correction coefficient. By combining the deviation between the estimated arrival time of resources and the ideal intervention time, as well as the reliability of resources, the original blocking effectiveness is adjusted so that the adjusted result can truly reflect the actual blocking capability of resources in the current real-time state.

[0053] When the deviation between the estimated resource arrival time and the ideal intervention time increases, the corresponding Natural Index result decreases, and the timeliness matching correction coefficient decreases accordingly. When the reliability parameter increases, the corresponding Natural Index result increases, and the timeliness matching correction coefficient increases accordingly. Overall, when the estimated resource arrival time is close to the ideal intervention time and the reliability parameter is at a high level, the timeliness matching correction coefficient is high; conversely, the correction coefficient is low.

[0054] The beneficial effects include: quantifying the vulnerability of the disaster causal chain, accurately identifying core nodes and clarifying node sensitivity, providing targeted basis for resource assessment; achieving precise matching of resource functions and disaster prevention needs based on two-way alignment of node type and resource attributes, ensuring the relevance of the assessment; calibrating the correlation of node alignment relationships, clearly defining the inherent blocking effectiveness of resources, and solidifying the assessment foundation; correcting the inherent blocking effectiveness by separating the time deviation and reliability parameters of real-time status, combined with the ideal intervention time point identified in the core links, ensuring that the calibration value truly reflects the real-time blocking capability of resources; extrapolating the dynamic effectiveness range based on reliability parameters, comprehensively covering the actual effectiveness range of resources under different reliability states; and finally, normalizing and fusing the core effectiveness values ​​across nodes according to node sensitivity, comprehensively considering the blocking effect of resources on the entire disaster causal chain, forming a scientific and comprehensive effectiveness weight, ensuring that the assessment results are both consistent with the disaster evolution law and adapted to the actual resource status, providing solid quantitative support for the precise and efficient allocation of fire emergency resources.

[0055] The study clarifies the sources and acquisition methods of each parameter. It obtains the estimated arrival time of resources by accurately collecting information such as resource location and road conditions; determines the ideal intervention time point by analyzing the core links of the disaster causal chain; determines the attenuation constant by combining historical case statistics; and integrates information such as resource task completion quality to obtain reliability parameters, ensuring the accuracy and availability of the parameters. It also clearly demonstrates the significance of the formula, namely, combining time deviation and resource reliability to obtain a timeliness-fitting correction coefficient, enabling precise adjustment of the original blocking effectiveness and truly reflecting the real-time actual blocking capability of resources. Furthermore, it clarifies the trend of the formula, intuitively presenting the deviation between the estimated resource arrival time and the ideal intervention time, and the impact of reliability parameters on the correction coefficient. This ensures that the changes in the correction coefficient are highly adapted to the actual state of resources, facilitating subsequent reasonable adjustments to the original blocking effectiveness and providing an accurate and reliable basis for the effectiveness assessment of fire emergency resources.

[0056] S05. Based on the effectiveness weight, implement path planning for the target fire emergency resources, and collaboratively encode the planned path to obtain the collaborative dispatch instructions for the target fire emergency resources. In this embodiment of the invention, the step of implementing path planning for the target fire emergency resources based on effectiveness weights and co-coding the planned paths to obtain the co-scheduling instructions for the target fire emergency resources includes: The effectiveness weights are dynamically prioritized to obtain the resource scheduling sequence based on effectiveness weights; Based on the resource scheduling sequence, multi-constraint shortest path analysis is performed on the target fire emergency resources to obtain the initial path of the target fire emergency resources; Spatiotemporal occupancy conflict detection is performed on the initial path to obtain the conflict coordinate set of the initial path; Based on the conflict coordinate set, the initial path is spatiotemporally conflicted and resolved to obtain a conflict-free path. By structurally encoding conflict-free paths, coordinated dispatch instructions for target fire emergency resources are obtained.

[0057] To obtain a resource scheduling sequence, the effectiveness weights of each target fire emergency resource need to be dynamically prioritized. This requires arranging the effectiveness weights of each target fire emergency resource in descending order, while also considering the disaster causal chain node type corresponding to the resource. This ensures that among resources with the same effectiveness weight, those corresponding to highly sensitive nodes are prioritized. This sorting method clarifies the scheduling order of each resource, forming an orderly resource scheduling sequence.

[0058] To obtain the initial path for the target fire emergency resources based on the resource scheduling sequence, the constraints of the path must first be clarified, including road conditions, traffic control areas around the disaster area, and the safe range for resource passage. Then, the current location of each resource and the corresponding disaster causal chain node location are determined. All feasible routes from the current location to the target location are sorted out. After eliminating routes that do not meet the constraints, the route with the shortest distance that meets the constraints is selected as the initial path for the resource.

[0059] To obtain a conflict coordinate set, the initial path is subjected to spatiotemporal occupancy conflict detection. The position coordinates corresponding to each time node in the initial path of each resource need to be recorded one by one. Then, the path time nodes and coordinates of different resources are cross-compared to find the situation where multiple resources are at the same position coordinate at the same time node. These conflicting position coordinates are collected and organized to form the conflict coordinate set of the initial path.

[0060] To resolve spatiotemporal conflicts on the initial path based on the conflict coordinate set and obtain a conflict-free path, for each coordinate and corresponding time node in the conflict coordinate set, one resource needs to be selected to adjust its path, either by delaying the arrival time of the resource at the coordinate or by changing the coordinates of the route segment to avoid conflict time periods and locations. After the adjustment is completed, the paths of all resources are compared again to ensure that there are no new spatiotemporal occupancy conflicts, thus forming a conflict-free path for each resource.

[0061] To obtain the coordinated dispatch instructions for target fire emergency resources, the conflict-free path information of each resource needs to be organized in a unified format, including the resource's identification information, departure time, location coordinates at each stage, and corresponding target node locations. This information is then arranged sequentially according to the resource dispatch sequence to form a set of instructions with clear content and standardized format, which is the coordinated dispatch instruction for the target fire emergency resources.

[0062] The beneficial effects include: dynamically prioritizing the effectiveness weights and clarifying the scheduling order based on the type of disaster-causing causal chain node corresponding to the resource, forming an orderly resource scheduling sequence to ensure the priority deployment of core effectiveness resources. Based on the resource scheduling sequence, multi-constraint shortest path analysis is performed, fully considering constraints such as road conditions, traffic control, and safety ranges, selecting the shortest and most compliant route as the initial path to ensure feasibility and efficiency. Spatiotemporal conflict detection is performed on the initial path; by cross-comparing the path time nodes and coordinates of different resources, conflict locations are accurately identified and a conflict coordinate set is formed, providing a clear target for conflict resolution. Based on the conflict coordinate set, the path or time is adjusted in a targeted manner to completely eliminate spatiotemporal conflicts in resource scheduling, forming conflict-free paths and avoiding mutual interference between multiple resource deployments. Conflict-free paths are structured and encoded, integrating key information such as resource identifiers, departure times, and location coordinates in a unified format and arranging them in an orderly manner to generate clear and standardized collaborative scheduling instructions, ensuring consistent coordination among resource scheduling actions and significantly improving the accuracy and efficiency of fire emergency resource deployment.

[0063] S06. Issue the coordinated dispatch instruction to the target fire emergency resources to generate an emergency response plan for the target disaster event; In this embodiment of the invention, the step of issuing collaborative dispatch instructions to target fire emergency resources to generate an emergency response plan for the target disaster event includes: Based on the coordinated scheduling instructions, the driving parameters of the target fire emergency resources are converted to obtain the executable driving instructions of the target fire emergency resources; The executable drive commands are delivered in a hierarchical manner, and the target fire emergency resources are tracked in real time to obtain the status feedback of the executable drive command sequence; Based on status feedback, the initial response actions of the target fire emergency resources are synchronized to obtain the emergency response plan for the target disaster event.

[0064] To obtain executable driving instructions for target fire emergency resources based on collaborative dispatch instructions, the information in the collaborative dispatch instructions must first be broken down, and the identification information, departure time, location coordinates at each stage, and target node location corresponding to each resource must be extracted. Then, according to the type of resource, this information is converted into specific parameters that the resource can directly execute. For example, for rescue vehicles, the departure time is converted into a specific start time, the location coordinates are converted into route guidance for vehicle navigation, and the resource identifier is mapped to the vehicle's unique number. For rescue personnel, the departure time is converted into an assembly time, and the location coordinates are converted into an assembly point and action route. After completing the parameter conversion for each resource, executable driving instructions corresponding to each resource are formed.

[0065] The executable drive commands are delivered in a tiered manner, and the target fire emergency resources are tracked in real time to obtain status feedback. The delivery must be carried out in the priority order of the resource scheduling sequence. First, the corresponding executable drive commands are sent to the resources with the highest priority. After the resource receives the command, the command is sent to the next highest priority resource. The command delivery of all resources is completed in sequence. After the delivery is completed, the current status of each resource is continuously recorded, including whether it has been started, whether it is moving along the route, its current location, and whether it has reached the target node. These real-time status information are collected and organized to form the status feedback of the executable drive command sequence.

[0066] To obtain an emergency response plan for the target disaster event, the initial response actions of the target fire emergency resources are synchronized based on status feedback. This requires analyzing the response progress of each resource in the status feedback, comparing the current status of different resources, and coordinating the acceleration of the action pace of some resources if their response progress lags behind the preset process. If some resources have arrived at the target node ahead of schedule, they are arranged to carry out the disposal actions corresponding to the current node first, while adjusting the action pace of other resources to match the overall process. After the response action progress of all resources tends to be consistent, the information system such as the deployment location, action arrangement, and disposal tasks of each resource is integrated to form an emergency response plan for the target disaster event.

[0067] The beneficial effects are as follows: by breaking down key information in collaborative dispatch instructions and converting driving parameters based on the type of target fire emergency resources, dispatch information is accurately transformed into specific instructions that resources can directly execute. This ensures a high degree of compatibility between instructions and resource execution capabilities, guaranteeing the operability and accuracy of instructions. Executable driving instructions are delivered in a tiered manner according to the priority of the resource dispatch sequence. Subsequent delivery is only advanced after instruction reception is confirmed. Simultaneously, the real-time status of resources is continuously tracked and feedback is compiled, ensuring complete instruction delivery and dynamic monitoring of resources. Based on the status feedback, the response progress of each resource is analyzed, and resources that lag behind are coordinated to accelerate their pace, while resources that arrive early are arranged to carry out pre-emptive tasks. The deployment locations, action arrangements, and disposal tasks of all resources are integrated simultaneously to form a comprehensive emergency response plan, ensuring consistent and coordinated response actions from all resources and significantly improving the orderliness and effectiveness of disaster emergency response.

[0068] Example 2 like Figure 2 As shown, this embodiment also provides a computer device, which may include a processor 10, a memory 11, a communication bus 12 and a communication interface 13, and may also include a computer program stored in the memory 11 and capable of running on the processor 10, such as a big data-based intelligent allocation program for fire emergency resources.

[0069] In some embodiments, the processor 10 may be composed of integrated circuits, such as a single packaged integrated circuit or multiple integrated circuits with the same or different functions, including combinations of one or more central processing units (CPUs), microprocessors, digital processing chips, graphics processors, and various control chips. The processor 10 is the control unit of the device, connecting various components of the device through various interfaces and lines. It executes programs or modules stored in the memory 11 (e.g., executing a big data-based intelligent allocation program for fire emergency resources) and calls data stored in the memory 11 to perform various functions of the device and process data.

[0070] The memory 11 includes at least one type of medium, including flash memory, portable hard drive, multimedia card, card-type memory (e.g., SD or DX memory), magnetic memory, disk, optical disk, etc. In some embodiments, the memory 11 can be an internal storage unit of the device, such as the device's portable hard drive. In other embodiments, the memory 11 can be an external storage device of the device, such as a plug-in portable hard drive, Smart Media Card (SMC), Secure Digital (SD) card, Flash Card, etc. Furthermore, the memory 11 can include both internal and external storage units. The memory 11 can be used not only to store application software and various types of data installed on the device, such as the code of a big data-based intelligent allocation program for fire emergency resources, but also to temporarily store data that has been output or will be output.

[0071] The communication bus 12 can be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus, etc. This bus can be divided into an address bus, a data bus, a control bus, etc. The bus is configured to enable communication between the memory 11 and at least one processor 10, etc.

[0072] The communication interface 13 is used for communication between the aforementioned device and other devices, including a network interface and a user interface. Optionally, the network interface may include a wired interface and / or a wireless interface (such as a Wi-Fi interface, Bluetooth interface, etc.), typically used to establish communication connections between the device and other devices. The user interface may be a display, an input unit (such as a keyboard), or optionally, a standard wired or wireless interface. Optionally, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, or an OLED (Organic Light-Emitting Diode) touchscreen, etc. The display may also be appropriately referred to as a screen or display unit, used to display information processed within the device and to display a visual user interface.

[0073] The figure only shows the device with components. Those skilled in the art will understand that the structure shown in the figure does not constitute a limitation on the device and may include fewer or more components than shown, or combine certain components, or have different component arrangements.

[0074] For example, although not shown, the device may also include a power supply (such as a battery) to power the various components. Preferably, the power supply can be logically connected to the at least one processor 10 through a power management system, thereby enabling functions such as charging management, discharging management, and power consumption management through the power management system. The power supply may also include one or more DC or AC power supplies, a recharging system, a power fault detection circuit, a power converter or inverter, a power status indicator, or any other components. The device may also include various sensors, Bluetooth modules, Wi-Fi modules, etc., which will not be described in detail here.

[0075] It should be understood that the embodiments described are for illustrative purposes only and are not limited to this structure in the scope of the patent application.

[0076] The memory 11 in the device stores a big data-based intelligent allocation program for fire emergency resources, which is a combination of multiple instructions. When run in the processor 10, it can achieve the following: S01. Reconstruct the semantic context of the target disaster event to obtain a structured event description of the target disaster event; S02. Perform spatiotemporal topological relationship mining on the structured event description to construct a dynamic evolutionary association graph of the structured event description; S03. Backtrack the key driving paths of the dynamic evolution association graph to obtain the disaster-causing causal chain of the dynamic evolution association graph. S04. Based on the disaster causal chain, the target fire emergency resources are coupled and quantitatively evaluated to obtain the effectiveness weight of the target fire emergency resources; S05. Based on the effectiveness weight, implement path planning for the target fire emergency resources, and collaboratively encode the planned path to obtain the collaborative dispatch instructions for the target fire emergency resources. S06. Issue the coordinated dispatch instruction to the target fire emergency resources to generate an emergency response plan for the target disaster event.

[0077] Specifically, the specific implementation method of the processor 10 for the above instructions can be referred to the description of the relevant steps in the corresponding embodiment of the accompanying drawings, and will not be repeated here.

[0078] Furthermore, if the modules / units integrated into the device are implemented as software functional units and sold or used as independent products, they can be stored in a medium. The medium can be volatile or non-volatile. For example, the medium may include: any entity or system capable of carrying the computer program code, a recording medium, a USB flash drive, a portable hard drive, a magnetic disk, an optical disk, a computer memory, or a read-only memory (ROM).

[0079] In the several embodiments provided by this invention, it should be understood that the disclosed devices, systems, and methods can be implemented in other ways. For example, the system embodiments described above are merely illustrative; for instance, the division of modules is only a logical functional division, and other division methods may be used in actual implementation.

[0080] The modules described as separate components may or may not be physically separate. The components shown as modules may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0081] Furthermore, the functional modules in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or in the form of hardware plus software functional modules.

[0082] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0083] The embodiments of this application can acquire and process relevant data based on artificial intelligence technology. Artificial intelligence (AI) refers to the theories, methods, technologies, and application systems that use digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, perceive the environment, acquire knowledge, and use that knowledge to obtain optimal results.

[0084] Finally, 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.

Claims

1. A method for intelligent allocation of fire emergency resources based on big data, characterized in that, The method includes: S01. Reconstruct the semantic context of the target disaster event to obtain a structured event description of the target disaster event; S02. Perform spatiotemporal topological relationship mining on the structured event description to construct a dynamic evolutionary association graph of the structured event description; S03. Backtrack the key driving paths of the dynamic evolution association graph to obtain the disaster-causing causal chain of the dynamic evolution association graph. S04. Based on the disaster causal chain, the target fire emergency resources are coupled and quantitatively evaluated to obtain the effectiveness weight of the target fire emergency resources; S05. Based on the effectiveness weight, implement path planning for the target fire emergency resources, and collaboratively encode the planned path to obtain the collaborative dispatch instructions for the target fire emergency resources. S06. Issue the coordinated dispatch instruction to the target fire emergency resources to generate an emergency response plan for the target disaster event.

2. The intelligent allocation method for fire emergency resources based on big data as described in claim 1, characterized in that, The semantic context reconstruction of the target disaster event yields a structured event description of the target disaster event, including: Multimodal information fusion is performed on the original reported information of the target disaster event to obtain a consistent contextual representation of the original reported information; Based on consistent contextual representation, the intent of the target disaster event is inferred, resulting in a contextual understanding of the target disaster event; Structured extraction of contextual understanding yields a discretized set of event elements for contextual understanding; Semantic aggregation is performed on the discretized event element set to obtain a structured event description of the target disaster event.

3. The intelligent allocation method for fire emergency resources based on big data as described in claim 1, characterized in that, The process of mining spatiotemporal topological relationships in structured event descriptions to construct a dynamic evolutionary correlation graph of the structured event descriptions includes: The coordinates of the event elements in the structured event description are normalized to obtain the baseline element set of the structured event description; Based on the preset relationship strength measurement criteria, the relationship strength between elements in the benchmarked element set is structurally integrated to obtain the association strength matrix of the benchmarked element set. Within a continuous time window, the cross-slice transitivity of the correlation strength matrix is ​​verified, and the verified matrix is ​​subjected to pattern extraction to obtain the key transitivity pattern set of the correlation strength matrix. A topological mapping is performed on the key transmission pattern set to obtain a dynamic evolutionary relationship graph describing structured events.

4. The intelligent allocation method for fire emergency resources based on big data as described in claim 1, characterized in that, The process of reverse-tracing the key driving paths of the dynamic evolutionary association graph to obtain the causal chain of disaster in the dynamic evolutionary association graph includes: By performing multi-level influence intensity screening on the nodes in the dynamic evolution correlation graph, the key node sequence of the dynamic evolution correlation graph is obtained. Based on the dynamic evolutionary association graph, the connection edges between key node sequences are backtracked by temporal logic dual importance to obtain the key connection edge set of key node sequences; Based on the preset confidence standard, the causal confidence value is assigned to the key connection edge set to obtain the directed causal edge set of the key connection edge set; Based on the confidence criterion, the directed causal edge set is filtered by the confidence threshold to obtain the credible causal edge set of the directed causal edge set; By integrating the path integrity of the credible causal edge set, the disaster-causing causal chain of the dynamic evolutionary association graph is obtained.

5. The intelligent allocation method for fire emergency resources based on big data as described in claim 1, characterized in that, The method of coupled quantitatively evaluating target fire emergency resources based on the disaster causal chain to obtain the effectiveness weights of target fire emergency resources includes: Vulnerability quantification is performed on the disaster-causing causal chain to obtain the node sensitivity of the disaster-causing causal chain; Based on node sensitivity, the resource attributes of the target fire emergency resources are aligned bidirectionally to obtain the node alignment relationship of the target fire emergency resources. The correlation degree of the node alignment relationship is calibrated to obtain the original blocking effect of the target fire emergency resources; Based on the real-time status of the target fire emergency resources, the original blocking effectiveness is corrected for timeliness, and the confidence boundary of the corrected effectiveness is defined to obtain the dynamic effectiveness range of the original blocking effectiveness. Based on node sensitivity, the core effectiveness values ​​of the dynamic effectiveness range are normalized and fused across nodes to obtain the effectiveness weight of the target fire emergency resources.

6. The intelligent allocation method for fire emergency resources based on big data as described in claim 5, characterized in that, The method involves adjusting the original blocking effectiveness based on the real-time status of the target fire emergency resources, and defining the confidence boundary of the adjusted effectiveness to obtain the dynamic effectiveness range of the original blocking effectiveness, including: Multi-dimensional parameter separation is performed on the real-time status of the target fire emergency resources to obtain the time deviation parameter and reliability parameter of the real-time status; Based on node sensitivity, the core links of the disaster-causing causal chain are identified to obtain the ideal intervention time point of the disaster-causing causal chain. Calculate the time-fit correction coefficient for the original blocking efficacy; Based on the time-fit correction coefficient, the original blocking efficacy is modified and transformed to obtain the time-calibrated value of the original blocking efficacy; Based on reliability parameters, the dynamic range of the aging calibration value is extrapolated to obtain the dynamic effectiveness range of the corrected effectiveness.

7. The intelligent allocation method for fire emergency resources based on big data as described in claim 1, characterized in that, The process of implementing path planning for target fire emergency resources based on effectiveness weights, and then collaboratively encoding the planned paths to obtain collaborative dispatch instructions for the target fire emergency resources, includes: The effectiveness weights are dynamically prioritized to obtain the resource scheduling sequence based on effectiveness weights; Based on the resource scheduling sequence, multi-constraint shortest path analysis is performed on the target fire emergency resources to obtain the initial path of the target fire emergency resources; Spatiotemporal occupancy conflict detection is performed on the initial path to obtain the conflict coordinate set of the initial path; Based on the conflict coordinate set, the initial path is spatiotemporally conflicted and resolved to obtain a conflict-free path. By structurally encoding conflict-free paths, coordinated dispatch instructions for target fire emergency resources are obtained.

8. The intelligent allocation method for fire emergency resources based on big data as described in claim 1, characterized in that, The step of issuing coordinated dispatch instructions to target fire emergency resources to generate an emergency response plan for the target disaster event includes: Based on the coordinated scheduling instructions, the driving parameters of the target fire emergency resources are converted to obtain the executable driving instructions of the target fire emergency resources; The executable drive commands are delivered in a hierarchical manner, and the target fire emergency resources are tracked in real time to obtain the status feedback of the executable drive command sequence; Based on status feedback, the initial response actions of the target fire emergency resources are synchronized to obtain the emergency response plan for the target disaster event.

9. A computer device, comprising a memory, a processor, and a computer program stored in the memory, characterized in that, The processor executes the computer program to implement the steps of the method according to any one of claims 1 to 8.

10. A computer medium having a computer program stored thereon, characterized in that, When executed by a processor, the computer program implements the steps of the method according to any one of claims 1 to 8.

Images