A spatial geographic data processing method and apparatus

Abstract

This application relates to a spatial geographic data processing method and apparatus. The method includes: acquiring spatial geographic data corresponding to dynamic geographic entities, the spatial geographic data including location change sequences, attribute label sequences, and external event records; performing cross-domain nested encoding processing on the spatial geographic data to obtain a multi-domain entity relationship encoding set with multi-dimensional unstructured temporal features and heterogeneous semantic relationship dimensions; in the multi-domain entity relationship encoding set, performing residual graph generation processing on the temporal nodes of geographic entities exhibiting label drift and state jumps to obtain a set of residual graphs spanning temporal periods; and performing semantic transition compression processing on unstructured deterministic regions based on the residual graph set to obtain a semantic chain set, which is used to characterize the spatiotemporal semantic reconstruction expression model of dynamic geographic entities in a multi-stage evolution process. This method can compress and model the state mutation patterns of dynamic geographic entities in unstructured deterministic regions.

Description

Technical Field

[0001] This application relates to the field of data processing technology, and in particular to a spatial geographic data processing method and apparatus. Background Technology

[0002] In the field of data processing technology, it involves processing relevant spatial geographic data of geographic entities in order to achieve spatiotemporal evolution modeling of the state of geographic entities.

[0003] In related data processing methods, the evolution process of geographic entities is described by constructing time-series location trajectories. However, when faced with dynamic geographic entities that have frequent state jumps and obvious semantic label mutations, this method is difficult to effectively capture the inherent semantic connections between discontinuous states. As a result, the model has a simple expression structure, weak semantic continuity, and insufficient ability to model abnormal evolution stages, making it difficult to adapt to the expression needs of highly dynamic geographic phenomena. Summary of the Invention

[0004] Based on this, it is necessary to provide a spatial geographic data processing method, apparatus, computer equipment, and computer-readable storage medium to address the aforementioned technical problems. This method is used to compress and semantically model the state mutation patterns of dynamic geographic entities in non-structurally defined regions, thereby improving the ability to extract and interpret complex geographic evolution processes.

[0005] Firstly, this application provides a spatial geographic data processing method, including:

[0006] Acquire spatial geographic data corresponding to dynamic geographic entities, wherein the spatial geographic data includes location change sequences, attribute label sequences, and external event records;

[0007] The spatial geographic data is subjected to cross-domain nested encoding processing to obtain a multi-domain entity relationship encoding set with multi-dimensional unstructured temporal features and heterogeneous semantic relationship dimensions;

[0008] In the multi-domain entity relationship encoding set, residual graph generation processing is performed on the temporal nodes of geographic entities with label drift and state jump to obtain a set of residual graphs spanning temporal periods. Each residual graph in the set represents a residual semantic relationship pattern of the dynamic geographic entity under discontinuous semantic paths.

[0009] Based on the residual map set, the unstructured deterministic regions corresponding to the dynamic geographic entities are subjected to semantic transition compression processing to obtain a semantic chain set, which is used to characterize the spatiotemporal semantic reconstruction expression model of the dynamic geographic entities in the multi-stage evolution process.

[0010] Secondly, this application also provides a spatial geographic data processing apparatus, comprising:

[0011] The acquisition module is used to acquire spatial geographic data corresponding to dynamic geographic entities. The spatial geographic data includes location change sequences, attribute label sequences, and external event records.

[0012] The encoding module is used to perform cross-domain nested encoding processing on the spatial geographic data to obtain a multi-domain entity relationship encoding set with multi-dimensional unstructured temporal features and heterogeneous semantic relationship dimensions;

[0013] The residual module is used to generate residual graphs for temporal nodes of geographic entities with label drift and state jump in the multi-domain entity relationship encoding set, so as to obtain a set of residual graphs spanning the temporal period. Each residual graph in the set represents a residual semantic relationship pattern of the dynamic geographic entity under discontinuous semantic paths.

[0014] The compression module is used to perform semantic transition compression processing on the unstructured deterministic regions corresponding to the dynamic geographic entities based on the residual map set, to obtain a semantic chain set, which is used to characterize the spatiotemporal semantic reconstruction expression model of the dynamic geographic entities in the multi-stage evolution process.

[0015] Thirdly, this application also provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to perform the above steps.

[0016] Fourthly, this application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, performs the above steps.

[0017] The aforementioned spatial geographic data processing methods, apparatus, computer equipment, and computer-readable storage media firstly achieve unified acquisition and temporal organization of multidimensional evolutionary information of dynamic geographic entities by constructing spatial geographic data containing location change sequences, attribute label sequences, and external event records. Secondly, by performing cross-domain nested encoding processing on the spatial geographic data to obtain a multi-domain entity relationship encoding set, an entity expression form covering multidimensional structural relationships between spatial location, semantic labels, and event effects is established. Thirdly, by identifying and extracting jump nodes from the multi-domain entity relationship encoding set to construct a residual map set, discontinuous state mutations in the evolution process of dynamic geographic entities are captured, and quantifiable semantic deviation information is formed. Fourthly, semantic transition compression processing is performed on unstructured regions based on the residual map set, thereby extracting a semantic chain set with stage characteristics and trend consistency. Based on this, the state mutation patterns of dynamic geographic entities in unstructured regions can be compressed and semantically modeled, thereby improving the ability to extract and interpret complex geographic evolution processes. Attached Figure Description

[0018] To more clearly illustrate the technical solutions in the embodiments or related technologies of this application, the accompanying drawings used in the description of the embodiments or related technologies will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0019] Figure 1 This is a flowchart illustrating a spatial geographic data processing method in one embodiment;

[0020] Figure 2 This is a structural block diagram of a spatial geographic data processing device in one embodiment. Detailed Implementation

[0021] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0022] In one embodiment, such as Figure 1 As shown, a spatial geographic data processing method is provided. This embodiment illustrates the method by applying it to a server. It is understood that the method can also be applied to a terminal, or to a system including a terminal and a server, and is implemented through the interaction between the terminal and the server. In this embodiment, the method includes the following steps S101 to S104.

[0023] Step S101: Obtain the spatial geographic data corresponding to the dynamic geographic entity. The spatial geographic data includes location change sequences, attribute label sequences, and external event records.

[0024] Dynamic geographic entities refer to geographic objects with spatial location and attribute characteristics that change over time, such as shared bicycles in a city, moving typhoon systems, seasonally changing river boundaries, or construction areas.

[0025] Spatial geographic data refers to a set of data used to describe the relationship between the spatial location, attribute characteristics and the environment of dynamic geographic entities, such as a set of time-series data fragments containing coordinate trajectories, land use categories and traffic event information.

[0026] Among them, the location change sequence represents a time series of data related to the spatial location changes of dynamic geographic entities in a preset geographic coordinate system. That is, it is used to describe the movement trajectory and spatial range evolution of dynamic geographic entities in the time dimension, such as the GPS positioning coordinate sequence of a bus continuously recorded from 7 am to 9 am.

[0027] Among them, the attribute label sequence represents the time series data set of attribute categories or status identifiers of dynamic geographic entities at different points in time. That is, it is used to describe the characteristic changes of dynamic geographic entities in the time evolution. For example, the label of a river changes from "frozen state" to "melted state" and then to "flooded state" at different periods.

[0028] Among them, external event records refer to the set of event information related to the spatial area of ​​dynamic geographic entities and caused by changes in the external environment. That is, the external driving causes used to explain or assist in judging the changes in the state of dynamic geographic entities. For example, "the rainfall intensity reached 100 mm / h on July 15, 2021" is an important event record affecting changes in surface runoff.

[0029] For example, to support modeling the evolution of dynamic geographic entities, it is necessary to first construct a set of related spatial geographic data. This set should accurately and comprehensively reflect the location, attribute status, and external influences of the specified dynamic geographic entity at different time stages. To this end, data sources related to the dynamic geographic entity need to be systematically collected, and a location change sequence needs to be compiled according to time order. This location change sequence reflects the spatial coordinates of the dynamic geographic entity at different time points, expressing the trajectory changes experienced by the dynamic geographic entity through the correspondence between timestamps and coordinates. Furthermore, an attribute label sequence needs to be constructed simultaneously. This attribute label sequence is a tagged description of the dynamic geographic entity's own characteristics (such as category, function, status, etc.) within each time period. The labels are comparable and support temporal analysis, aiming to reveal the evolution path of the dynamic geographic entity's attributes over time. Furthermore, records of external events within the activity range of dynamic geographic entities should also be included in the data system. This data can include event information that may affect the evolution of dynamic geographic entities. By setting elements such as event occurrence time, affected area, and event type, the temporal and spatial correspondence between events and dynamic geographic entities can be clarified.

[0030] Step S102: Perform cross-domain nested encoding processing on the spatial geographic data to obtain a multi-domain entity relationship encoding set with multi-dimensional unstructured temporal features and heterogeneous semantic relationship dimensions.

[0031] Among them, the multi-domain entity relationship coding set represents the coded data structure that integrates multiple types of spatial geographic data and is organized in a unified structure. It is used to describe the semantic and temporal structural relationships of dynamic geographic entities at various time nodes under the cross-action of multi-source information. For example, the coded data structure that a main traffic artery is assigned every hour, including information such as location, traffic flow, and accident level, can reflect the dynamic evolution behavior of the road under the dimensions of traffic and events.

[0032] Among them, multidimensional unstructured temporal features represent data features composed of multiple time series data from different sources or of different types, lacking regular grid arrangement and having temporal order association; heterogeneous semantic relationship dimension represents dimensional features where multiple semantic interpretation sources constituting the dynamic geographic entity coding data structure differ in terms of attribute category, event type, spatial scale, etc.

[0033] For example, to extract information related to multidimensional unstructured temporal features and heterogeneous semantic relationships from collected spatial geographic data, cross-domain nested encoding processing needs to be performed on the spatial geographic data. In this process, firstly, the location change sequence, attribute label sequence, and external event records are unfolded on the same timeline according to chronological order, constructing a set of time nodes for dynamic geographic entities with a unified temporal granularity. Then, the three types of data corresponding to each time node are combined to construct a data unit. By setting a nested structure, the geographic location status is taken as the main dimension, and attribute label status and event response information within the corresponding time period are embedded within it, thus forming a nested expression form with location change as the main line and attributes and events as branches. Based on this, these nested data units are integrated according to the chronological evolution order, forming a multi-domain entity relationship encoding set covering the entire evolution process through temporal connections. This multi-domain entity relationship encoding set not only has temporal continuity but also preserves the cross-dependency structure between location, attributes, and events in the semantic dimension.

[0034] Step S103: In the multi-domain entity relationship encoding set, residual graph generation processing is performed on the time-series nodes of geographic entities with label drift and state jump to obtain a set of residual graphs spanning time periods. Each residual graph in the residual graph set represents a residual semantic relationship pattern of a dynamic geographic entity under discontinuous semantic paths.

[0035] Among them, the geographic entity time-series nodes with label drift and state jump indicate that in the time-series evolution of dynamic geographic entities, the node data corresponding to a specific point in time shows a significant change in attribute label or a discontinuous jump in the overall state. In other words, it is used to identify abrupt behavior or abnormal change signals in the evolution of dynamic geographic entities. For example, if the state label of a certain area is "farmland" for several consecutive days, but suddenly changes to "construction land" on a certain day, and there is no matching external event to explain it, the node data of this abrupt change is considered to have label drift and state jump.

[0036] Among them, the set of residual maps spanning time periods represents a set of residual pattern maps covering multiple time intervals, constructed based on the identified mutation node data. Each residual map reflects the residual structure of the corresponding dynamic geographic entity due to semantic changes in different time periods, in order to characterize a residual semantic relationship pattern of the corresponding dynamic geographic entity under discontinuous semantic paths.

[0037] Among them, a residual semantic relationship pattern of dynamic geographic entities under discontinuous semantic paths represents a structural pattern in which some semantic attributes of a dynamic geographic entity still maintain continuity or form new dependencies after the entity undergoes a state change. For example, an industrial area may quickly change from an "active enterprise area" to an "idle land" under policy adjustment, but some semantic elements related to enterprise names and infrastructure categories remain stable. These semantic fragments that are not completely broken constitute the residual semantic relationship pattern.

[0038] For example, to identify the state discontinuities experienced by dynamic geographic entities during their evolution, it is necessary to locate temporal nodes with label drift and state jumps in the multi-domain entity relationship encoding set, and construct a residual map set reflecting semantic anomalies accordingly. In this process, firstly, based on the temporal change trend of attribute labels and event response characteristics, the degree of deviation in semantic expression between each temporal node and its preceding and following nodes is calculated. This deviation not only reflects changes in label content but also needs to be combined with the magnitude of spatial location changes and event types to determine whether there is a non-linear jump trend. When a sudden difference is found in the semantic expression of a temporal node compared to its historical nodes, and this sudden difference cannot be reasonably explained by event triggers, the temporal node can be marked as a potential jump node. Next, centered on this jump node, an encoded data segment containing several time steps before and after it is extracted, and the semantic composition of each temporal node in the encoded data segment is compared and calculated to solve the residual semantic differences between each dimension. Finally, this residual semantic difference is used to construct a residual map reflecting jump characteristics. Based on this, the residual map set gradually accumulated in this way constitutes a structured dataset that expresses different residual semantic relationship patterns of dynamic geographic entities in the multi-stage evolution process.

[0039] Step S104: Based on the residual map set, perform semantic transition compression processing on the unstructured deterministic regions corresponding to dynamic geographic entities to obtain a semantic chain set, which is used to characterize the spatiotemporal semantic reconstruction expression model of dynamic geographic entities in the multi-stage evolution process.

[0040] Among them, unstructured deterministic regions represent spatial or temporal segments in the spatiotemporal evolution of dynamic geographic entities that cannot be described by stable rules due to factors such as discontinuous labels, event interference, or semantic jumps.

[0041] Among them, the semantic chain set refers to the set of semantic chain segments formed by connecting the key semantics of dynamic geographic entities at different time nodes according to the time sequence and evolutionary logic. It is used to extract a semantic expression structure with coherence and derivability from complex changes. For example, the evolution chain of a river can sequentially include a series of semantic nodes with causal relationships such as "source enhancement, water volume increase, flood risk increase, intervention of governance projects, and water body shrinkage". A set of multiple such semantic chain segments constitutes the semantic chain set.

[0042] Among them, the spatiotemporal semantic reconstruction expression model represents a comprehensive model that can characterize the evolution process of dynamic geographic entities by utilizing the temporal order and spatial change relationship of the semantic chain set. That is, it is used to express and reconstruct the evolution process of dynamic geographic entities in the context of complex and nonlinear state migration.

[0043] For example, in order to extract a set of semantic chains with structured evolutionary significance from a set of residual maps with significant jump characteristics, the residual map set needs to be centrally analyzed first, especially for semantic trajectory extraction of residual nodes located in non-structurally defined regions. Since these residual nodes are often located in segments of label mutation or state transition, they themselves lack continuous structural support and are difficult to be directly incorporated into a unified model expression. Therefore, starting from each residual node marked as unstable in the residual map, the process is expanded forward and backward along the time dimension node by node to retrieve jump paths that are consistent with the direction of change of their attribute labels, thereby restoring the possible trends of the dynamic geographic entity in local evolution.

[0044] Next, to further reduce the complexity of the transition paths, it is necessary to aggregate the parts of all transition paths that have similar semantic trends. Specifically, transition paths with similar semantic span characteristics are merged, that is, residual nodes with consistent label migration directions and similar state transition rhythms are merged into a single semantic chain segment, and then connected and spliced ​​in chronological order. Finally, by integrating all semantic chain segments, a semantic chain set covering the entire unstructured deterministic region can be constructed. This semantic chain set is used to replace the scattered transition data in the original residual map that does not have structural representation capabilities, and becomes the key structural unit representing dynamic geographic entities in the irregular evolution stage.

[0045] The aforementioned spatial geographic data processing method firstly constructs spatial geographic data containing location change sequences, attribute label sequences, and external event records, thereby achieving unified acquisition and temporal organization of multidimensional evolutionary information of dynamic geographic entities. Secondly, it obtains a multi-domain entity relationship encoding set by performing cross-domain nested encoding processing on the spatial geographic data, thus establishing an entity expression form covering multidimensional structural relationships between spatial location, semantic labels, and event effects. Thirdly, it identifies and extracts jump nodes from the multi-domain entity relationship encoding set to construct a residual map set, thereby capturing discontinuous state mutations in the evolution process of dynamic geographic entities and forming quantifiable semantic deviation information. Fourthly, it performs semantic transition compression processing on non-structurally deterministic regions based on the residual map set, thereby extracting a semantic chain set with stage characteristics and trend consistency. Based on this, it is possible to compress and model the state mutation patterns of dynamic geographic entities in non-structurally deterministic regions, thereby improving the ability to extract and interpret complex geographic evolution processes.

[0046] In an exemplary embodiment, spatial geographic data is subjected to cross-domain nested encoding processing to obtain a multi-domain entity relationship encoding set with multi-dimensional unstructured temporal features and heterogeneous semantic relationship dimensions, including steps S201 to S203.

[0047] Step S201: In the spatial geographic data, perform time alignment processing on the location change sequence, attribute label sequence, and external event records to obtain a temporally aligned sequence set.

[0048] Among them, the temporal alignment sequence set represents a multi-dimensional synchronization sequence set formed by aligning the position change sequence, attribute label sequence, and external event records with the same time granularity after unified processing in the time dimension. It is used to ensure that the content of data from different sources is comparable and synchronized at each time node.

[0049] For example, using the evolution timeline of dynamic geographic entities as a benchmark, location change sequences, attribute label sequences, and external event records (Australia) are mapped to a unified time axis at the same time granularity to achieve time alignment of the above three types of data. Specifically, since there are differences in the data collection frequency, start time, and time interval of different data sources, each data sequence needs to be timestamped before performing time alignment. That is, all original time labels are converted into a unified format and relocated to a common reference time set. Then, interpolation, pruning, or repetition padding operations are performed on the original data according to the common reference time set to ensure that each time node can obtain complete values ​​in the three data dimensions. Based on this, the final aligned temporal sequence set has synchronous temporal order, which can ensure that at any time node, spatial location, attribute labels, and event status are within a comparable unified framework.

[0050] Step S202: Based on the temporal alignment sequence set, perform association modeling on the spatial location, attribute label and event state corresponding to different time nodes to obtain a composite entity node set with time index, spatial label state and event response scalar.

[0051] The composite entity node set represents a set of structured composite expression units (i.e., composite entity nodes) that combine the spatial location, attribute labels, and event states of the corresponding time node at each aligned time node. This set is used to describe the complete state of a dynamic geographic entity at each composite entity node, including time index, spatial label state, and event response scalar.

[0052] Among them, the time index represents the time stamp used to uniquely identify each composite entity node, and is used as a reference axis in constructing sequence structures or performing operations such as sorting and searching; the spatial label status represents the attribute category or status label of a dynamic geographic entity on a certain composite entity node, and is used to express the semantic meaning of the entity at the corresponding time node; the event response scalar represents the response result of an external event corresponding to a certain composite entity node to the entity status, and is used to quantify the intensity or scope of the event's effect.

[0053] For example, to achieve the joint expression of semantic information and spatial behavior based on the aligned temporal sequence set, it is necessary to structurally combine the spatial location, attribute labels, and event states corresponding to each time node to construct a set of composite entity nodes with time indexes. Specifically, at each time node, the projection area of ​​the dynamic geographic entity in the geographic space is determined according to its spatial location and used as the geographic reference field of the time node; at the same time, the attribute labels of the corresponding time node are extracted as semantic state fields and incorporated into the node content in a structured manner; then, combined with the event state information recorded at that time point, such as impact type, scope of action, or event level, it is expressed as an event response scalar reflecting changes in the external environment, and combined with other fields to form a complete node representation, that is, the complete state of a composite entity node; furthermore, all composite entity nodes are arranged with time index as the primary key to ensure the structural continuity of dynamic geographic entities in the evolution process. Based on this, the resulting set of composite entity nodes has both spatial distribution attributes and embedded semantic state and event impact structures, and can express the full state of dynamic geographic entities at a specific moment.

[0054] Step S203: By extracting the semantic connection relationship, temporal adjacency relationship and event causal relationship between composite entity nodes, the composite entity node set is processed to perform nested structure construction to obtain a multi-domain entity relationship encoding set.

[0055] Among them, semantic connection relationship represents the semantic-level association relationship formed by the trend of attribute label change between adjacent composite entity nodes, such as the label change relationship of "agricultural land" gradually changing into "urban construction land".

[0056] Among them, temporal adjacency relationship represents the temporal relationship between consecutive composite entity nodes connected in chronological order. For example, if the time index of a node is "2023-06-01", its next adjacent node's time is "2023-06-02".

[0057] Among them, the event causal relationship represents the causal connection between different composite entity nodes due to the state change caused by a certain event. For example, if the "flood event" corresponding to a certain node causes the label of another entity to change from "farmland" to "bare land", then there is an event causal relationship between the two nodes.

[0058] For example, to enable a set of composite entity nodes to express the cross-domain relationship structure of dynamic geographic entities throughout the entire temporal process, multiple structural connection mechanisms need to be introduced to construct nested relationships based on this set of composite entity nodes. First, semantic connection relationships are established by analyzing the similarity and trend changes of attribute label values ​​between adjacent composite entity nodes to reflect the semantic evolution logic of dynamic geographic entities in the temporal dimension. Second, temporal adjacency relationships are established by calculating the time intervals and positional displacement information between temporally continuous composite entity nodes to reflect the spatiotemporal evolution logic of dynamic geographic entities in the spatial trajectory and temporal progression. Furthermore, event causal relationships are constructed by using the common causal characteristics and correlations of response results among the event states of composite entity nodes to reflect the state transition logic between different composite entity nodes caused by event influences.

[0059] After the above relational structure is constructed, the three relational structures are embedded in the topological description of each composite entity node, and the relationship between composite entity nodes is encapsulated into a computable data unit in the form of a nested structure, thereby constructing a multi-domain entity relational encoding set. This multi-domain entity relational encoding set retains the information features of each composite entity node in terms of space, semantics, and events, and clarifies the cross-dimensional connection method between composite entity nodes.

[0060] In this embodiment, firstly, a temporally aligned sequence set is obtained by uniformly aligning the location change sequence, attribute label sequence, and external event records, thereby ensuring the synchronous expression structure of various types of data at the same time node and improving the foundation for the fusion of multi-source information. Secondly, a composite entity node set is obtained by associating the spatial location, attribute label, and event state corresponding to different time nodes based on the temporally aligned sequence set, thereby realizing a structured representation of the complete state characteristics of dynamic geographic entities at each specific moment on the time axis. Furthermore, the composite entity node set is nested and constructed based on the semantic connection relationship, temporal adjacency relationship, and event causal relationship between composite entity nodes, thereby establishing a multi-domain entity relationship encoding set that expresses the information characteristics of each node and the connection relationship between nodes across dimensions. Based on this, it is possible to achieve unified modeling and association organization of multi-source and multi-dimensional temporal information of dynamic geographic entities.

[0061] In an exemplary embodiment, by extracting the semantic connection relationship, temporal adjacency relationship and event causal relationship between composite entity nodes, the set of composite entity nodes is processed to perform nested structure construction to obtain a multi-domain entity relationship encoding set, including steps S301 to S302.

[0062] Step S301: Based on the semantic connection relationship, temporal adjacency relationship and event causal relationship between composite entity nodes, perform relation triplet extraction processing on the composite entity node set to obtain a multi-source relation graph containing semantic connection edge set, temporal adjacency edge set and event causal edge set.

[0063] Among them, the multi-source relation graph represents a set of graph structures composed of multiple composite entity nodes and their different types of semantic and temporal associations. It is used to uniformly organize the interaction structure between multi-source information such as spatial location, attribute labels and event influence. For example, a node in the multi-source relation graph represents the urban area status at one hour, and the edges represent the relationship connections between attribute evolution, time progression and event-driven relationships, respectively.

[0064] Among them, the semantic connection edge set represents the set of edges in the multi-source relation graph that connect two composite entity nodes, where the semantic labels have an evolutionary trend or association change. For example, the semantic connection edge between the "agricultural land" node and the "construction land" node represents the trend of land function change at the semantic level.

[0065] Among them, the temporal adjacency edge set represents the set of edges established in chronological order between adjacent composite entity nodes in the multi-source relation graph. For example, the temporal adjacency edge between two nodes on June 1, 2023 and June 2, 2023 represents the diurnal evolution direction of the dynamic geographic entity state.

[0066] Among them, the event causal edge set represents the set of edges in a multi-source relation graph where an event occurring at a certain composite entity node drives the change of attributes of another composite entity node. For example, the event causal edge between the "heavy rainfall event" node and its subsequent "flooded surface" node represents the evolution path triggered by the event.

[0067] For example, firstly, for each pair of composite entity nodes, the similarity of their semantic labels is calculated. If the semantic labels are related or have an evolutionary trend at the semantic level, a semantic connection edge is established between the two composite entity nodes. This semantic connection edge is used to represent the change path of the attribute labels. Then, a connection operation is performed on temporally adjacent composite entity nodes, that is, each group of composite entity nodes that are consecutive in time index is connected through temporal adjacency edges to ensure that the constructed graph structure has the traceability of time progression. Next, in the event dimension, the mutual influence of the event response scalars in the two composite entity nodes is analyzed to determine whether the state of a node is triggered or influenced by the event information carried by the preceding and following nodes. If a specific causal condition is met, an event causal edge is established to describe the state jump caused by the event. After completing the generation of the above three types of edges, all composite entity nodes and the three types of edges are uniformly constructed into a multi-source relation graph containing a set of semantic connection edges, a set of temporal adjacency edges, and a set of event causal edges. This multi-source relation graph not only retains the temporal order and spatial semantic information of the original nodes, but also establishes cross-dimensional association paths at the structural level.

[0068] Step S302: In the multi-source relation graph, perform two-layer association clustering on the semantic connection edge set and the event causal edge set to construct a nested subgraph of label events. Then, perform nested graph fusion processing on the topological skeleton constructed by the temporal adjacency edge set of each nested subgraph of label events to obtain a multi-domain entity relation encoding set.

[0069] Among them, the nested subgraph of label events represents a local graph structure obtained by dual clustering of semantic connection edges and event causal edges in a multi-source relation graph. It is used to express the co-evolutionary relationship of a group of nodes in terms of label state changes and event influence. For example, if a group of nodes changes from "forest land to wasteland and then to development land" and is related to "land acquisition event", then it constitutes a nested subgraph of label events.

[0070] Among them, the topological skeleton constructed by the temporal adjacency edge set represents the main structure with temporal order formed in the entire multi-source relation graph based on the temporal adjacency edge. It is used to carry the temporal organization framework of the nested subgraphs of various labeled events. For example, nested subgraphs of labeled events representing different evolutionary stages are embedded sequentially on the time main graph constructed by consecutive days to form a complete evolutionary process.

[0071] For example, firstly, in the multi-source relationship graph, based on the attribute label change paths covered by semantic connection edges, a preliminary clustering is performed on the set of nodes with highly similar semantic trends. Then, based on the presence of event causal edges among these nodes, the preliminary clustering results are further subdivided to ensure that the nodes within the clustering unit are related in both semantic and event dimensions. Based on this, the result of this two-layer clustering process is a set of nested label-event subgraphs. Each nested label-event subgraph aggregates a subset of nodes that are interconnected in terms of semantic evolution and event-driven behavior, forming a nested unit that expresses the local evolution structure of dynamic geographic entities.

[0072] Then, at the overall topological level of the multi-source relation graph, a topological skeleton on the complete timeline is extracted based on temporal adjacency edges. Each nested subgraph of labeled events is then sequentially superimposed on this skeleton, ensuring that the nested subgraphs maintain both their internal structural independence and consistency with the global temporal progression. Finally, through nested graph fusion processing, the nested subgraphs of each labeled event are integrated into a unified topological framework, forming a multi-domain entity relation encoding set with multi-dimensional structural hierarchy and semantic evolution expression capabilities.

[0073] In this embodiment, firstly, triplet extraction is performed on the semantic connection relationships, temporal adjacency relationships, and event causal relationships between composite entity nodes to construct a multi-source relationship graph that simultaneously reflects semantic evolution, temporal progression, and event-driven mechanisms, thereby enhancing the structural expressive ability between nodes. Secondly, by performing double-layer clustering on semantic connection edges and event causal edges and fusing them into the topological skeleton constructed by temporal adjacency edges, nested integration of multi-dimensional evolutionary relationships is achieved, forming a multi-domain entity relationship encoding set with temporal organization and semantic nesting. Based on this, unified modeling of multi-dimensional structural relationships of dynamic geographic entities in a complex evolutionary background can be realized.

[0074] In an exemplary embodiment, in the multi-domain entity relationship encoding set, residual graph generation processing is performed on the time-series nodes of geographic entities with label drift and state jump to obtain a set of residual graphs spanning time periods, including steps S401 to S403.

[0075] Step S401: Perform difference measurement processing on the attribute label status and event response status of each geographic entity time sequence node in the multi-domain entity relationship encoding set under continuous time index to obtain the label drift intensity matrix and the state jump probability matrix.

[0076] The tag drift intensity matrix is ​​a two-dimensional numerical matrix used to measure the degree of change in the attribute tag status of dynamic geographic entities over time. For example, if the tag of a certain area changes from "farmland" to "industrial land" between 2020 and 2021, a higher tag drift intensity value is recorded at the matrix position corresponding to that time interval.

[0077] Among them, the state transition probability matrix represents a two-dimensional numerical matrix used to reflect the strength of the possibility of an external event causing a state transition. For example, if a "flood disaster" occurs in a certain area at a certain time point, and then a "bare land" state occurs immediately afterward, a higher state transition probability value is recorded at the matrix position corresponding to that time interval.

[0078] For example, based on a timeline, the changes in attribute label states of dynamic geographic entities at adjacent time nodes are compared item by item. Combined with their corresponding event response states, a joint index of label change magnitude and state transition significance is calculated, namely, the label drift intensity matrix and the state transition probability matrix. Specifically, firstly, the semantic distance between the current attribute label and the attribute label of the previous time node is extracted for each time-series node, and this is used to construct the original label drift intensity matrix describing the label drift intensity. Subsequently, the event response state changes of the current node are correlated and compared with the event response states of its historical periods, and this is used to construct the original state transition probability matrix describing the transition probability.

[0079] To ensure the comparability of label differences and event transitions within a unified evaluation framework, the original label drift intensity matrix and the original state transition probability matrix need to be normalized and weighted. This allows for a clear characterization of state changes between any pair of time points under the dual contexts of semantic mutation and event-induced events. Based on this, the resulting label drift intensity matrix and state transition probability matrix are used to characterize the drastic evolution of dynamic geographic entities at the label level and the probability of transitions at the event level, respectively, providing a quantitative basis for subsequent anomaly trajectory identification.

[0080] Step S402: Based on the label drift intensity matrix and the state transition probability matrix, perform abnormal trajectory identification processing on each geographic entity time-series node to obtain a set of abnormal trajectory nodes labeled with semantic offset nodes.

[0081] Among them, the set of abnormal trajectory nodes labeled with semantic offset nodes represents the set of time-series nodes with significant semantic variation characteristics identified in the temporal trajectory analysis of dynamic geographic entities based on the label drift intensity matrix and the state jump probability matrix. It is used to mark the key time points in the evolution path of dynamic geographic entities where there are jump, abnormal or mutation behaviors.

[0082] For example, firstly, each time-series node is used as an evaluation unit. Its tag shift intensity value in the tag drift intensity matrix and its state jump probability value in the state jump probability matrix are retrieved. If at least one of these two indicators is significantly higher than the overall change benchmark of the time series, it can be determined that the time-series node has potential semantic shift behavior. Secondly, to enhance the stability of the identification results, a sliding window mechanism is introduced to jointly analyze multiple consecutive time periods, thereby identifying areas where tags are continuously unstable or events are frequently triggered, thus avoiding interference from isolated noise points. Next, after obtaining the preliminary identification results, time-series nodes with high overlap and overlapping tag change paths are merged and reduced to generate an abnormal trajectory node set. This set retains key metadata such as the time location, tag change direction, and event activation degree of each semantic shift node. The semantic shift nodes represent key moment points in the dynamic geographic entity evolution path where there is a risk of semantic jump or an abnormal driving mechanism.

[0083] Step S403: Perform residual map generation processing on the abnormal trajectory node set across time periods to obtain a residual map spectrum set across time periods.

[0084] For example, firstly, taking each semantic offset node as the core point, an adjacency trajectory is constructed over several time periods before and after it. Continuous behavioral information during state evolution is extracted from these adjacency trajectories and compared with the ideal evolutionary trend or the historical average evolutionary trend to generate residual differences in the time series. Next, by mapping these residual differences in the time series onto a graph structure, a residual subgraph centered on the semantic offset node is obtained. Furthermore, to enable these residual subgraphs to have cross-period expressive capabilities, subgraph segments with semantic similarity or abrupt change features that recur in different time periods need to be aggregated, thereby constructing a set of residual graphs spanning temporal periods.

[0085] In this embodiment, firstly, by performing differential measurement on the attribute label state and event response state of continuous time-series nodes, a label drift intensity matrix and a state jump probability matrix are constructed to achieve a quantitative expression of the semantic changes and event-driven features of dynamic geographic entities. Secondly, by performing joint analysis on each time-series node based on the above two matrices, an abnormal trajectory node set with potential semantic mutation features is identified, enhancing the ability to locate discontinuous evolutionary behavior. Thirdly, by performing cross-period residual modeling on the abnormal trajectory node set, a residual map set reflecting the semantic offset structure is generated to achieve a map-based expression of the jump paths and abnormal structures in the evolution process of dynamic geographic entities.

[0086] In an exemplary embodiment, based on the label drift intensity matrix and the state transition probability matrix, abnormal trajectory identification processing is performed on each geographic entity time-series node to obtain a set of abnormal trajectory nodes labeled with semantic offset nodes, including steps S501 to S503.

[0087] Step S501: Perform joint anomaly measurement processing on the label drift intensity matrix and the state jump probability matrix to obtain the semantic mutation gradient sequence of each geographic entity time-series node under continuous time index.

[0088] Among them, the semantic mutation gradient sequence represents a numerical sequence composed of the joint measurement results of the label drift intensity and state jump probability of the entity geographic entity at consecutive time nodes, which is used to describe the change trend and mutation degree of the semantic state of dynamic geographic entities during the evolution process.

[0089] For example, firstly, the label offset intensity of each time-series node is sequentially extracted from the label drift intensity matrix as the basic metric for semantic variation. Simultaneously, the state transition probability of that time-series node in response to an event is numerically sampled from the state transition probability matrix as another metric. Then, these two metrics are combined using a unified time index, and a fused semantic mutation index is generated through linear weighting, distance transformation, or other standardization methods. This semantic mutation index reflects not only the drastic change of a label at a single time point but also the interference effect of the event response on the state evolution path. Based on this, the semantic mutation index sequence formed at all time-series nodes constitutes a semantic mutation gradient sequence, used to describe the semantic change density, mutation tendency, and fluctuation trajectory of dynamic geographic entities throughout the entire evolution cycle. In this way, the evolutionary trends at the label level and the event level can be merged into the same metric system, thus providing a unified structural input for subsequent clustering analysis of anomalous nodes.

[0090] Step S502: Based on the state transition direction and the time difference of mutation, cluster the time index positions with abnormal jump amplitude in the semantic mutation gradient sequence to obtain a set of mutation nodes.

[0091] Among them, the state transition direction represents the semantic change trend of the attribute label state change between adjacent time sequence nodes. It is used to determine whether the entity evolution path presents a consistent evolution logic. For example, if the attribute label of a certain area changes from "arable land" to "construction land" and then to "commercial land", the state transition direction of this state evolution path can be abstractly represented as the direction of "progressing from natural land to urban functional area".

[0092] Among them, the mutation time difference represents the interval between the corresponding time indices of adjacent time series nodes. It is used to measure the distribution density and concentration of mutation events on the time axis. For example, if two nodes occur in the third quarter and the fourth quarter of 2020 respectively, their mutation time difference is one quarter. Furthermore, if the mutation time differences of multiple nodes are relatively concentrated, it indicates that dynamic geographic entities have concentrated semantic change behavior within a certain time period.

[0093] Among them, the abnormal jump amplitude represents the degree of significant numerical jump of a certain time node in the semantic mutation gradient sequence relative to its preceding and following nodes. It is used to identify the severity of state mutation. For example, if the gradient value jumps from 0.2 to 0.95 in a continuous time series, the abnormal jump amplitude of the node is 0.75, which reflects that the node has undergone a severe label mutation or semantic shift.

[0094] Among them, the mutation node set represents a group of temporal nodes identified by clustering from the semantic mutation gradient sequence that exhibit abnormal behavior in terms of jump amplitude, mutation direction and temporal density, and is used to centrally represent the concentrated area of ​​state mutation of dynamic geographic entities in the evolution process.

[0095] For example, using time indices as the basic unit, and combining the numerical change trend of each time-series node in the semantic mutation gradient sequence, the time index positions with abnormally large jump amplitudes are identified, i.e., mutation nodes, and the state transition direction and mutation time difference within the time periods before and after them are calculated. Based on this, nodes with similar state transition directions, relatively concentrated mutation time differences, and mutation amplitudes of the same order of magnitude are grouped into the same cluster unit, thereby avoiding the interference of isolated mutation nodes on the overall evolution trend. Furthermore, clustering is used to identify time periods exhibiting continuous jumps or high-frequency mutations. Based on this, the resulting set of mutation nodes represents a cluster of nodes exhibiting relatively concentrated and consistent jump characteristics in the time series, which constitute the core mutation segments in the spatial semantic evolution structure.

[0096] Step S503: Based on the preset context threshold, perform context consistency verification and annotation processing on the mutation node set to obtain an abnormal trajectory node set annotated with semantic offset nodes.

[0097] The context threshold represents the criterion for judging the tolerance of differences in context state trends when verifying semantic consistency. It is used to distinguish between real semantic offset nodes and normal fluctuation nodes. For example, setting the context threshold to 30% means that if the state similarity between a certain time-series node and its preceding and following nodes is less than 30%, then the time-series node is identified as a semantic offset node with inconsistent context.

[0098] For example, firstly, based on a preset context threshold, for each mutation node, the state trajectory, label trend, and event changes within its preceding and following time windows are extracted, and the semantic similarity and continuity between the mutation node and its context are analyzed. If the mutation node lacks predictable connections with its corresponding preceding and following nodes in terms of semantic trend, and there is a significant causal disconnect with the event information, it is labeled as a semantic offset node. Based on this, the determination process not only considers single-point mutation features but also emphasizes the discontinuity of local semantic trends to enhance the rigor and stability of the labeling. After labeling, in the final set of abnormal trajectory nodes, all nodes that satisfy the context mutation features and exhibit semantic breakpoint behavior can be classified as semantic offset nodes.

[0099] In this embodiment, firstly, a semantic mutation gradient sequence is constructed based on the joint anomaly measurement of label drift intensity and state jump probability, thereby achieving a quantitative expression of the semantic change trend of dynamic geographic entities. Secondly, cluster analysis is performed on the semantic mutation gradient sequence based on the state transition direction and mutation time difference to extract a set of mutation nodes, enhancing the ability to identify concentrated jump behaviors during the evolution process. Thirdly, consistency verification and annotation processing are performed on the set of mutation nodes based on context thresholds to screen out the set of abnormal trajectory nodes that truly exhibit semantic offset characteristics, so as to achieve accurate identification and structural calibration of jump nodes of dynamic geographic entities.

[0100] In an exemplary embodiment, semantic transition compression processing is performed on the unstructured deterministic region corresponding to the dynamic geographic entity based on the residual map set to obtain a semantic chain set, including steps S601 to S602.

[0101] Step S601: Using a preset semantic traversal algorithm, traverse the residual nodes located in the non-structurally defined region in the residual graph set, and extract the jump paths that are consistent with the mutation direction of the attribute labels of each residual node.

[0102] Among them, the semantic traversal algorithm represents a path extraction method based on the semantic and structural connections between residual nodes in the residual graph, in order to identify a sequence of nodes with coherence in the direction of attribute label variation from a non-structurally defined region, i.e., a jump path.

[0103] For example, a pre-defined semantic traversal algorithm is used to progressively search for node sequences in the residual graph that exhibit continuity or convergence in the direction of attribute label variation. Specifically, starting from each residual node, the algorithm searches forward or backward along the direction of attribute label variation for subsequent nodes with semantically coherent relationships among adjacent graph nodes. For instance, a continuous transition from "agriculture" to "construction" and then to "commerce" is considered a jump path with a consistent direction. Furthermore, when identifying jump paths, contextual information such as event response status is considered to determine whether external driving factors influence the path, ensuring that each path segment has a clear semantic transfer interpretation basis. Based on this, when a group of residual nodes exhibits consistency in the direction of attribute label variation and presents a traversable connection in the graph structure, the link corresponding to this group of residual nodes can be ultimately identified as a jump path. Therefore, a set of jump paths with clear jump directions and traceable node structures can be extracted from the irregular and fragmented residual graph.

[0104] Step S602: Based on the semantic span tensor of each transition path, compress residual nodes with consistent label migration direction and matching state transition cycles in all transition paths into the same semantic chain segment, and integrate multiple semantic chain segments to obtain a semantic chain set.

[0105] Among them, the semantic span tensor of the jump path is used to quantify the multi-dimensional structured expression of the label change range, state transition magnitude and time span in a jump path, so as to compare the overall degree of change of different jump paths in the semantic evolution process.

[0106] For example, the semantic span tensor is used to characterize factors such as the overall magnitude of label changes, the number of change dimensions, and the duration of state transitions in a jump path. By constructing a semantic span tensor for each jump path, the total amount of change experienced by the corresponding jump path in the semantic classification system and its degree of continuity in the time dimension can be obtained. Then, these tensors are compared and analyzed to select jump path groups with consistent migration directions, similar tensor magnitudes, and matching time spans, and these groups are merged and compressed into a unified semantic chain segment. Furthermore, in this process, to ensure that the compressed semantic chain segment still retains the semantic trend characteristics of the original jump path, it is necessary to regulate the node order, state start and end points, and event triggering conditions in different jump paths, so that the semantic chain segment has a unified start and end logic in structure. Based on this, after generating multiple semantic chain segments, all semantic chain segments are integrated according to the time index order and structural connection rules, redundant nodes are removed, overlapping parts are merged, and the connection order of the semantic chain segments is adjusted to finally construct a complete semantic chain set.

[0107] In this embodiment, firstly, the residual map nodes are traversed based on the consistency of the attribute label mutation direction to extract the jump path, thereby realizing the quantitative extraction of the semantic evolution trend in the non-structurally deterministic region. Secondly, the semantic span tensor of the jump path is compressed and merged to integrate jump paths with consistent label migration direction and similar state transition characteristics into semantic chain segments, thereby improving the aggregation degree and chain organization capability of the residual structure expression. Based on this, it is possible to compress and model the mutation behavior of dynamic geographic entities in semantically discontinuous regions and express it in a chain, thereby enhancing the structural clarity and analytical controllability of spatiotemporal semantic modeling.

[0108] In an exemplary embodiment, after performing semantic transition compression processing on the unstructured deterministic regions corresponding to dynamic geographic entities based on the residual map set to obtain a semantic chain set, the method further includes steps S701 to S703.

[0109] Step S701: Perform staged division processing on each semantic chain segment in the semantic chain set to obtain a staged semantic chain set containing each semantic state stage.

[0110] Among them, the set of staged semantic chains containing each semantic state stage represents a chain-like set formed by dividing each semantic chain segment into multiple semantic state stages with internal consistency and structural independence based on the original semantic chain set, according to the state change rules, event response characteristics and label turning trends. This is used to refine the staged behavioral characteristics in the dynamic geographic entity evolution process. For example, a semantic chain segment expressing "from arable land to industrial land and then to commercial land" is divided into a staged structural sequence of three semantic state stages: "agricultural development stage", "industrial transformation stage" and "commercial construction stage".

[0111] Among them, the semantic state stage represents a local state unit in a semantic chain segment that consists of several semantic state nodes, is continuous in time, and has a stable evolution direction in semantic label variation.

[0112] For example, firstly, the evolution trend of attribute labels of each node in each semantic chain segment of the semantic chain set needs to be analyzed to identify the node positions where the semantic state undergoes a significant turning point, serving as candidate nodes for stage boundary points. Next, combining the change rate of the node's time index, it is determined whether the state change has a stable trend. If the label change direction is consistent within a certain time range and there are no drastic fluctuations, it is classified as a continuous stage, i.e., a semantic state stage. Furthermore, event response status can be introduced as an auxiliary criterion. When the event triggering frequency in a semantic chain segment is concentrated and the corresponding label state changes are consistent, the semantic chain segment can also be classified as a separate semantic state stage. Based on this, after the division is completed, each semantic chain segment is organized into multiple semantic state stages. Each semantic state stage records its start and end times, core semantic labels, and change types, thus forming a staged semantic chain set containing multiple semantic state stages.

[0113] Step S702: Based on the spatial distribution and state change trends of each semantic state stage in the staged semantic chain set, the evolutionary relationship between each semantic state stage is processed by spatiotemporal causal encoding to obtain a multi-stage evolutionary relationship set.

[0114] Among them, the spatial location distribution and state change trend of a semantic state stage represent the coverage, spatial extension direction and change speed of a certain semantic state stage in geographic space, as well as its structural change path in the semantic tag evolution system.

[0115] Among them, the multi-stage evolutionary relationship set represents a set of structured associations formed by causal, sequential and spatial transmission paths constructed between multiple semantic state stages, which is used to describe the state transition logic and propagation mechanism of dynamic geographic entities between multiple semantic state stages.

[0116] For example, firstly, for each semantic state stage, its geographic location coverage and expansion direction are extracted, and the state change trend and evolution rate within each semantic state stage are modeled to clarify the spatial distribution characteristics and change trend characteristics of each semantic state stage. Next, based on the temporal sequence, the continuity relationship between successive semantic state stages is structurally established, and causal relationship judgment is made based on whether it exhibits continuous evolution. Based on this, if two semantic state stages partially overlap spatially, have a sequential evolutionary order in time, and their label change paths exhibit causal logical coherence, then they are considered to constitute a spatiotemporal causal relationship unit. Furthermore, when determining each spatiotemporal causal relationship unit, not only the main evolutionary path is considered, but also branch paths, concurrent paths, and jump paths formed due to event interruptions need to be recorded, thus forming a multi-stage evolutionary relationship set containing multiple types of causal connections; this multi-stage evolutionary relationship set structurally reflects the dependencies and influence paths between different semantic state stages, providing a causal logical basis for dynamic geographic entity modeling.

[0117] Step S703: Perform state recursive modeling on the set of multi-stage evolutionary relationships to obtain a spatiotemporal semantic reconstruction expression model representing dynamic geographic entities in the multi-stage evolution process.

[0118] For example, in a multi-stage evolutionary relationship set, the various semantic state stages and their causal, temporal, and spatial relationships are transformed into a structural system that can be used for state evolution deduction, thereby achieving overall modeling of dynamic geographic entities in the multi-stage evolution process. Specifically, a corresponding state representation structure needs to be established for each semantic state stage, clarifying its basic attributes such as spatial location, semantic label, duration, and event association, and using these as the initial nodes corresponding to that semantic state stage in the state transition graph. Then, the paths related to the various types of causal connections between semantic state stages recorded in the multi-stage evolutionary relationship set are used as directed edges of the state transition graph. Furthermore, recursive deduction is implemented based on the connected nodes in the constructed state transition graph, that is, starting from the initial state, the semantic state change process of the dynamic geographic entity is gradually advanced according to the state connection relationship, thereby deriving the complete spatiotemporal evolution path. In addition, in the recursive deduction process, not only the sequential connections between nodes are considered, but also nonlinear evolutionary behaviors such as node merging, splitting, or interruption need to be handled to express the multi-directional evolutionary trajectory of dynamic geographic entities under complex changing conditions. Finally, by iteratively expanding the initial nodes and dynamically introducing external environmental influence parameters in the process, a spatiotemporal semantic reconstruction expression model that represents the entire process of multi-stage semantic evolution of dynamic geographic entities is finally formed.

[0119] In this embodiment, firstly, the semantic chain segments are divided into stages, thereby refining the continuous semantic chain segments containing multiple semantic evolution structures into semantic state stages with internal consistency and external separability, improving the structural clarity of semantic evolution expression. Secondly, spatiotemporal causal relationships between semantic state stages are established based on the spatial location distribution and state change trends of each semantic state stage, thereby constructing a multi-stage evolutionary relationship set that can reveal semantic evolution logic and event-driven logic. Thirdly, state recursive modeling is performed based on the multi-stage evolutionary relationship set, thereby generating a spatiotemporal semantic reconstruction expression model with logical traceability and process continuity. Based on this, a structured, staged, and logical expression of the complex semantic evolution process of dynamic geographic entities can be achieved, enhancing the expressive and reasoning capabilities of geographic semantic modeling.

[0120] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0121] Based on the same inventive concept, this application also provides a spatial geographic data processing apparatus for implementing the spatial geographic data processing method described above. The solution provided by this apparatus is similar to the implementation scheme described in the above method; therefore, the specific limitations in one or more spatial geographic data processing apparatus embodiments provided below can be found in the limitations of the spatial geographic data processing method described above, and will not be repeated here.

[0122] In one exemplary embodiment, such as Figure 2 As shown, a spatial geographic data processing device is provided, comprising: an acquisition module 201, an encoding module 202, a residual module 203, and a compression module 204, wherein:

[0123] The acquisition module 201 is used to acquire spatial geographic data corresponding to dynamic geographic entities. The spatial geographic data includes location change sequences, attribute label sequences, and external event records.

[0124] Encoding module 202 is used to perform cross-domain nested encoding processing on spatial geographic data to obtain a multi-domain entity relationship encoding set with multi-dimensional unstructured temporal features and heterogeneous semantic relationship dimensions;

[0125] The residual module 203 is used to generate residual graphs for temporal nodes of geographic entities with label drift and state jump in a multi-domain entity relationship encoding set, so as to obtain a set of residual graphs spanning the temporal period. Each residual graph in the residual graph set represents a residual semantic relationship pattern of a dynamic geographic entity under discontinuous semantic paths.

[0126] Compression module 204 is used to perform semantic transition compression processing on the unstructured deterministic regions corresponding to dynamic geographic entities based on the residual map set, to obtain a semantic chain set, which is used to characterize the spatiotemporal semantic reconstruction expression model of dynamic geographic entities in the multi-stage evolution process.

[0127] In an exemplary embodiment, the encoding module 202 is further configured to: perform time alignment processing on location change sequences, attribute label sequences, and external event records in spatial geographic data to obtain a temporally aligned sequence set; perform association modeling processing on spatial locations, attribute labels, and event states corresponding to different time nodes based on the temporally aligned sequence set to obtain a composite entity node set with time index, spatial label state, and event response scalar; and perform nested structure construction processing on the composite entity node set by extracting semantic connection relationships, temporal adjacency relationships, and event causal relationships between composite entity nodes to obtain a multi-domain entity relationship encoding set.

[0128] In an exemplary embodiment, the encoding module 202 is further configured to: perform relation triplet extraction processing on the composite entity node set according to the semantic connection relationship, temporal adjacency relationship and event causal relationship between composite entity nodes, to obtain a multi-source relation graph containing a semantic connection edge set, a temporal adjacency edge set and an event causal edge set; in the multi-source relation graph, perform two-level association clustering processing on the semantic connection edge set and the event causal edge set to construct a label event nested subgraph, and perform nested graph fusion processing on each label event nested subgraph according to the topological skeleton constructed by the temporal adjacency edge set to obtain a multi-domain entity relation encoding set.

[0129] In an exemplary embodiment, the residual module 203 is further configured to: perform difference measurement processing on the attribute label state and event response state of each geographic entity time-series node in the multi-domain entity relationship encoding set under continuous time index to obtain a label drift intensity matrix and a state jump probability matrix; perform abnormal trajectory identification processing on each geographic entity time-series node according to the label drift intensity matrix and the state jump probability matrix to obtain an abnormal trajectory node set labeled with semantic offset nodes; and perform cross-time period residual map generation processing on the abnormal trajectory node set to obtain a cross-temporal period residual map set.

[0130] In an exemplary embodiment, the residual module 203 is further configured to: perform joint anomaly measurement processing on the label drift intensity matrix and the state jump probability matrix to obtain the semantic mutation gradient sequence of each geographic entity time-series node under continuous time index; perform clustering processing on the time index positions with abnormal jump amplitude in the semantic mutation gradient sequence according to the state transition direction and mutation time difference to obtain a mutation node set; and perform context consistency verification processing and annotation processing on the mutation node set according to a preset context threshold to obtain an abnormal trajectory node set annotated with semantic offset nodes.

[0131] In an exemplary embodiment, the compression module 204 is further configured to: traverse residual nodes located in non-structurally defined regions in the residual graph set using a preset semantic traversal algorithm, extract jump paths that are consistent with the attribute label mutation direction of each residual node; compress residual nodes with consistent label migration direction and matching state transition periods in all jump paths into the same semantic chain segment according to the semantic span tensor of each jump path, and integrate multiple semantic chain segments to obtain a semantic chain set.

[0132] In an exemplary embodiment, the device further includes a modeling module, which is configured to: perform staged division processing on each semantic chain segment in the semantic chain set to obtain a staged semantic chain set containing each semantic state stage; perform spatiotemporal causal encoding processing on the evolutionary relationship between each semantic state stage according to the spatial location distribution and state change trend of each semantic state stage in the staged semantic chain set to obtain a multi-stage evolutionary relationship set; and perform state recursive modeling processing on the multi-stage evolutionary relationship set to obtain a spatiotemporal semantic reconstruction expression model representing the dynamic geographic entity in the multi-stage evolution process.

[0133] Each module in the aforementioned spatial geographic data processing device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the memory of a computer device as software, so that the processor can call and execute the operations corresponding to each module.

[0134] In one exemplary embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps of any of the above embodiments.

[0135] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the steps of any of the above embodiments.

[0136] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments described above. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

[0137] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0138] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A spatial geographic data processing method, characterized in that, The method includes: Acquire spatial geographic data corresponding to dynamic geographic entities, wherein the spatial geographic data includes location change sequences, attribute label sequences, and external event records; The spatial geographic data is subjected to cross-domain nested encoding processing to obtain a multi-domain entity relationship encoding set with multi-dimensional unstructured temporal features and heterogeneous semantic relationship dimensions; In the multi-domain entity relationship encoding set, residual graph generation processing is performed on the temporal nodes of geographic entities with label drift and state jump to obtain a set of residual graphs spanning temporal periods. Each residual graph in the set represents a residual semantic relationship pattern of the dynamic geographic entity under discontinuous semantic paths. The residual semantic relationship pattern represents a structural pattern in which some semantic attributes of the dynamic geographic entity still maintain continuity or form new dependencies after the dynamic geographic entity undergoes a state change. The semantic transition compression process is performed on the unstructured deterministic regions corresponding to the dynamic geographic entities based on the residual map set to obtain a semantic chain set, which is used to characterize the spatiotemporal semantic reconstruction expression model of the dynamic geographic entities in the multi-stage evolution process; wherein, the unstructured deterministic regions represent the spatial or temporal segments in the spatiotemporal evolution process of the dynamic geographic entities, where the evolution path of the dynamic geographic entities cannot be described by stable rules due to label discontinuity, event interference, or semantic jumps. The cross-domain nested encoding process performed on the spatial geographic data yields a multi-domain entity relationship encoding set with multi-dimensional unstructured temporal features and heterogeneous semantic relationship dimensions, including: In the spatial geographic data, the location change sequence, attribute label sequence, and external event records are time-aligned to obtain a temporally aligned sequence set. Based on the temporally aligned sequence set, the spatial location, attribute label, and event status corresponding to different time nodes are associated and modeled to obtain a composite entity node set with time index, spatial label status, and event response scalar. By extracting the semantic connection relationship, temporal adjacency relationship, and event causal relationship between the composite entity nodes, the composite entity node set is subjected to nested structure construction to obtain a multi-domain entity relationship encoding set. Specifically, by extracting semantic connections, temporal adjacency relationships, and event causal relationships between composite entity nodes, a nested structure construction process is performed on the composite entity node set to obtain a multi-domain entity relationship encoding set, including: Based on the semantic connection relationships, temporal adjacency relationships, and event causal relationships between composite entity nodes, the composite entity node set is subjected to relation triple extraction processing to obtain a multi-source relation graph containing semantic connection edge sets, temporal adjacency edge sets, and event causal edge sets. In the multi-source relation graph, the semantic connection edge sets and the event causal edge sets are subjected to two-level association clustering processing to construct a label event nested subgraph. Each label event nested subgraph is then fused into a nested graph according to the topological skeleton constructed by the temporal adjacency edge sets to obtain a multi-domain entity relation encoding set.

2. The method according to claim 1, characterized in that, In the multi-domain entity relationship encoding set, residual graph generation processing is performed on the temporal nodes of geographical entities exhibiting label drift and state transitions to obtain a set of residual graphs spanning temporal periods, including: The attribute label status and event response status of each geographic entity time-series node in the multi-domain entity relationship encoding set under continuous time index are measured to obtain the label drift intensity matrix and the state jump probability matrix. Based on the label drift intensity matrix and the state transition probability matrix, abnormal trajectory identification processing is performed on each geographic entity time-series node to obtain a set of abnormal trajectory nodes labeled with semantic offset nodes. The abnormal trajectory node set is subjected to residual map generation processing across time periods to obtain a residual map spectrum set across time periods.

3. The method according to claim 2, characterized in that, The process involves performing abnormal trajectory identification on each geographic entity's time-series node based on the label drift intensity matrix and the state transition probability matrix, resulting in a set of abnormal trajectory nodes labeled with semantic offset nodes, including: By performing joint anomaly measurement processing on the label drift intensity matrix and the state jump probability matrix, the semantic mutation gradient sequence of each geographic entity time-series node under continuous time index is obtained. Based on the state transition direction and the time difference of mutation, clustering is performed on the time index positions where there are abnormal jump amplitudes in the semantic mutation gradient sequence to obtain a set of mutation nodes. Based on a preset context threshold, the set of mutated nodes is subjected to context consistency verification and annotation processing to obtain a set of abnormal trajectory nodes annotated with semantic offset nodes.

4. The method according to claim 1, characterized in that, The step of performing semantic transition compression processing on the unstructured deterministic regions corresponding to the dynamic geographic entities based on the residual map set to obtain a semantic chain set includes: Using a preset semantic traversal algorithm, the residual nodes located in the non-structurally deterministic region in the residual map set are traversed, and the jump paths that are consistent with the attribute label variation direction of each residual node are extracted; wherein, the non-structurally deterministic region refers to the spatial or temporal segment in the spatiotemporal evolution of the dynamic geographic entity that cannot be described by stable rules due to label discontinuity, event interference or semantic jumps. Based on the semantic span tensor of each transition path, residual nodes with consistent label migration direction and matching state transition periods in all transition paths are compressed into the same semantic chain segment, and multiple semantic chain segments are integrated to obtain a semantic chain set.

5. The method according to claim 1, characterized in that, After performing semantic transition compression processing on the unstructured deterministic regions corresponding to the dynamic geographic entities based on the residual map set to obtain a semantic chain set, the method further includes: Each semantic chain segment in the semantic chain set is divided into stages to obtain a staged semantic chain set containing each semantic state stage. Based on the spatial location distribution and state change trend of each semantic state stage in the staged semantic chain set, the evolutionary relationship between each semantic state stage is processed by spatiotemporal causal encoding to obtain a multi-stage evolutionary relationship set. The set of multi-stage evolutionary relationships is subjected to state recursive modeling to obtain a spatiotemporal semantic reconstruction expression model representing dynamic geographic entities in the multi-stage evolution process.

6. A spatial geographic data processing device, characterized in that, The device includes: The acquisition module is used to acquire spatial geographic data corresponding to dynamic geographic entities. The spatial geographic data includes location change sequences, attribute label sequences, and external event records. The encoding module is used to perform cross-domain nested encoding processing on the spatial geographic data to obtain a multi-domain entity relationship encoding set with multi-dimensional unstructured temporal features and heterogeneous semantic relationship dimensions; The residual module is used to perform residual graph generation processing on the temporal nodes of geographic entities with label drift and state jump in the multi-domain entity relationship encoding set, to obtain a set of residual graphs spanning the temporal period. Each residual graph in the set represents a residual semantic relationship pattern of the dynamic geographic entity under discontinuous semantic paths. The residual semantic relationship pattern represents a structural pattern in which some semantic attributes of the dynamic geographic entity still maintain continuity or form new dependencies after the dynamic geographic entity undergoes a state change. The compression module is used to perform semantic transition compression processing on the unstructured deterministic regions corresponding to the dynamic geographic entities according to the residual map set, to obtain a semantic chain set, which is used to characterize the spatiotemporal semantic reconstruction expression model of the dynamic geographic entities in the multi-stage evolution process; wherein, the unstructured deterministic regions represent the spatial or temporal segments in the spatiotemporal evolution process of the dynamic geographic entities, where the evolution path of the dynamic geographic entities cannot be described by stable rules due to label discontinuity, event interference, or semantic jumps. The encoding module is further configured to: perform time alignment processing on location change sequences, attribute label sequences, and external event records in the spatial geographic data to obtain a temporally aligned sequence set; perform association modeling processing on spatial locations, attribute labels, and event states corresponding to different time nodes based on the temporally aligned sequence set to obtain a composite entity node set with time index, spatial label state, and event response scalar; and perform nested structure construction processing on the composite entity node set by extracting semantic connection relationships, temporal adjacency relationships, and event causal relationships between composite entity nodes to obtain a multi-domain entity relationship encoding set. The encoding module is further configured to: perform relation triplet extraction processing on the composite entity node set according to the semantic connection relationship, temporal adjacency relationship and event causality relationship between composite entity nodes, to obtain a multi-source relation graph containing a semantic connection edge set, a temporal adjacency edge set and an event causality edge set; in the multi-source relation graph, perform two-level association clustering processing on the semantic connection edge set and the event causality edge set to construct a nested subgraph of labeled events, and perform nested graph fusion processing on each nested subgraph of labeled events according to the topological skeleton constructed by the temporal adjacency edge set to obtain a multi-domain entity relation encoding set.

7. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 5.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 5.

Images