Knowledge-guided urban physical examination scene dynamic expression method

Abstract

The invention provides a knowledge-guided city physical examination scene dynamic expression method, which comprises the following steps: acquiring business demand data of a target city based on target city spatio-temporal data, and constructing a scene knowledge graph according to the target city spatio-temporal data and the business demand data; analyzing the target city spatio-temporal data and the scene knowledge graph to obtain an analysis result, combining semantic constraint and primitive combination to guide the analysis result to recombine, and driving scene generation and updating by means of scene narrative logic to obtain a city physical examination scene; enhancing object semantics in the city physical examination scene by adopting a dynamic and static combination mode to obtain an enhanced city physical examination scene, and performing data priority scheduling presentation on the enhanced city physical examination scene to obtain a dynamic expression result of the city physical examination scene; the problems that in the prior art, businesses and data are disjointed, adaptability of scene dynamic expression is insufficient, and visual presentation is single are solved.

Description

Technical Field

[0001] The present invention relates to the technical field of urban physical examination scene expression, and particularly relates to a method for dynamically expressing urban physical examination scenes guided by knowledge. Background Art

[0002] The core task of urban physical examination is to perform quantitative calculations, analysis, and evaluation on various data such as urban spatial structure, population distribution, resource supply and demand, and environmental quality, so as to reveal the health status and development trend of the urban system and serve urban planning and management. In this process, the dynamic changes of urban signs are presented through urban physical examination scenes, that is, the urban digital application context composed of specific geographical attributes and humanistic attributes, which is coordinated with knowledge, vision, and operation during the physical examination process. By establishing a two-way coupling between the decision-makers' understanding of the urban physical examination scenario and the refined expression of urban signs, the urban physical examination scene converts complex spatio-temporal data into various presentation forms such as intuitive and easy-to-understand dynamic visualization maps, interactive information charts, and refined and accurate texts, providing decision-making support for formulating urban planning and management measures.

[0003] However, most existing urban scene models still adopt a data-centric mode with insufficient knowledge links, making it difficult to fully link the knowledge of urban physical examination scenes required by decision-makers, resulting in the complexity of urban physical examination spatio-temporal data. At the same time, as urban signs continue to change, the elements of urban physical examination scenes need to be dynamically adjusted, such as events, processes, states, and related things and people in the scenes. However, the current visualization expression of these dynamic changes is not satisfactory, and the presentation effect of spatio-temporal data will also be poor.

[0004] In fact, in urban digital governance, urban physical examination scenes have both dynamic and static characteristics. The static characteristics are reflected in some relatively stable basic elements in the scene, such as the geographical location of the city, topography, and long-established functional areas, etc.; while the dynamic characteristics are manifested as the continuous changes of urban signs and the resulting dynamic expression of scene elements. From a technical perspective, knowledge graphs can effectively integrate the business requirements and spatio-temporal data of urban physical examination scenes, realizing the association between business and data; spatio-temporal narrative endows the semantic information of urban physical examination scenes with time and logical clues, connecting isolated urban phenomena into a coherent story and enhancing readability and comprehensibility; while maps and virtual geographical environments provide an intuitive visualization display method for the geographical spatial scene information in urban physical examination scenes, making complex information more easily acceptable. The comprehensive application of these technologies provides strong support for the dynamic expression of urban physical examination scenes. However, in the actual application process, there are many problems, such as: (1) Disconnection between data and business requirements: In the design and implementation of existing knowledge graph methods, there is a greater emphasis on the association with data, lacking the scenario knowledge for business collaboration. As a result, the expression results are disconnected from business requirements. Due to the lack of scenario knowledge, many potential semantic relationships between urban physical examination data and knowledge cannot be effectively mined and extracted, affecting the accuracy and integrity of scenario expression.

[0005] (2) Insufficient adaptability for dynamic expression: When facing these diverse scenario changes, existing scenario expression methods often show obvious insufficient adaptability. They are usually based on fixed choreography patterns and data-driven frameworks, lacking sufficient flexibility and scalability. Secondly, traditional urban physical examination reports mostly list static data, lacking plot and coherence. Even in the narrative of certain urban phenomena, the time and space dimensions are often fragmented, making it difficult to clearly present the spatio-temporal causal relationship and not conducive to in-depth analysis of urban problems.

[0006] (3) Relatively single visualization presentation: Maps can present basic urban physical examination information, but the information carried by its two-dimensional map is limited and difficult to support the dynamic visualization of urban physical examination scenarios. In addition, when the human eye extracts information, it has a certain dependence on perceptual salience. Dynamic visual phenomena such as flashing, jumping, and changing can attract more attention than static presentation. Therefore, traditional static visualization methods have obvious limitations in information transmission effects. Summary of the Invention

[0007] The present invention provides a method for dynamically expressing urban physical examination scenarios guided by knowledge, aiming to solve the problems of disconnection between business and data, insufficient adaptability for dynamic expression of scenarios, and relatively single visualization presentation in the prior art.

[0008] To achieve the above object, the present invention provides a method for dynamically expressing urban physical examination scenarios guided by knowledge, including: Step 1: Obtain the business requirement data of the target city based on the spatio-temporal data of the target city, and construct a scenario knowledge graph according to the spatio-temporal data of the target city and the business requirement data. The business requirement data includes knowledge-based evaluation data, spatio-temporal analysis data, and diversified evidence data; Step 2: Analyze the spatio-temporal data of the target city and the scenario knowledge graph to obtain the analysis results, recombine the analysis results by combining semantic constraints and graphic element combinations, and drive the generation and update of the scenario with the help of scenario narrative logic to obtain the urban physical examination scenario; Step 3: Enhance the object semantics in the urban physical examination scenario in a combination of static and dynamic ways to obtain the enhanced urban physical examination scenario, and perform data-priority scheduling presentation on the enhanced urban physical examination scenario to obtain the dynamic expression result of the urban physical examination scenario.

[0009] Furthermore, Step 1 includes: Step 11, obtain the business demand data of the target city based on the spatio-temporal data of the target city; Step 12, construct a hypergraph-based architecture layer according to the business demand data and the spatio-temporal data of the target city; Step 13, perform entity classification and entity relationship construction on the architecture layer, and use hypernode links and hyperedge links to perform knowledge fusion on different entities to obtain an initial scenario knowledge graph, where the scenario knowledge graph includes a semantic layer, a data layer, and a scenario layer; Step 14, adopt a hierarchical storage architecture to store each semantic entity in the semantic layer as a node of the scenario knowledge graph, store the original data in the data layer, and store the data in the scenario layer in the form of an attribute table. Establish an association between the data in the semantic layer, the data layer, and the scenario layer through a unique identifier and an indexing mechanism. When the spatio-temporal data of the target city changes, dynamically update the initial scenario knowledge graph to obtain the scenario knowledge graph.

[0010] Furthermore, the formal expression of the architecture layer is: ; ; ; ; Among them, represents the architecture layer, represents the semantic set, represents the theme node, represents the connotation node, represents the knowledge node, represents the index node, represents the data set, represents the working stage of urban physical examination, represents the data type, represents the data source, represents the data attribute, represents the relationship between data, represents the set of application scenarios, represents the type of application scenario, represents the hierarchical structure of data in the process of urban physical examination, represents a data subgraph composed of a group of nodes and edges, represents the high-order relationship of the data hypergraph.

[0011] Furthermore, when the spatio-temporal data of the target city changes, dynamically update the initial scenario knowledge graph to obtain the scenario knowledge graph, including: When the spatio-temporal data of the target city changes, based on the existing structure and semantic rules of the initial scene knowledge graph, incremental updates are used to adjust the entities, relationships, and attributes in the initial scene knowledge graph. After performing conflict or consistency checks on the adjusted initial scene knowledge graph, a scene knowledge graph is obtained; When the spatio-temporal data of the target city needs to be comprehensively revised, the architecture layer and the initial scene knowledge graph are updated and stored based on the revised spatio-temporal data of the target city to obtain a scene knowledge graph.

[0012] Furthermore, step 2 includes: Step 21, parse the spatio-temporal data of the target city and the scene knowledge graph to obtain multiple material primitives, and integratively manage all the material primitives to form a scene material library; Step 22, decompose the scenes in the scene knowledge graph to obtain multiple basic modules, and perform primitive mapping on all the basic modules, all the material primitives in the scene material library, and the semantic relationships in the scene knowledge graph in combination with semantic constraints to obtain multiple mapping results, and assemble based on all the mapping results to obtain a scene model; Step 23, perform dynamic evolution on the scene model through scene narrative logic modeling to obtain an evolution result, transform the evolution result through expression processing to obtain an initial urban physical examination scene, and update the initial urban physical examination scene through a dynamic update mechanism to obtain an urban physical examination scene.

[0013] Furthermore, updating the initial urban physical examination scene through a dynamic update mechanism to obtain an urban physical examination scene includes: Through the formula perform dynamic update on the material primitives to obtain an updated scene material library, where represents the material primitive, represents the parsing method, represents the spatio-temporal data of the target city, represents the scene knowledge graph; Through the formula perform dynamic update on the scene model to obtain an updated scene model, where represents the scene model, represents the synthesis operation, represents the th mapped primitive; Through the formula perform update on the initial urban physical examination scene to obtain an urban physical examination scene, where represents the initial urban physical examination scene, represents the visualization operation, represents the timeline, represents the geospatial scene.

[0014] Furthermore, step 3 includes: Step 31, enhancing the object semantics in the urban physical examination scenario based on the combination of static and dynamic visual variables to obtain an enhanced urban physical examination scenario; Step 32, dividing the data in the enhanced urban physical examination scenario according to the importance of the data and business requirements in the urban physical examination scenario to obtain a division result; Step 33, scheduling and presenting the data in the enhanced urban physical examination scenario according to the division result to obtain a dynamic expression result of the urban physical examination scenario.

[0015] Furthermore, the formal expression for enhancing the object semantics in the urban physical examination scenario based on the combination of static and dynamic visual variables is: ; wherein, represents the set of visual variables, represents the dynamic visual variable, represents the static visual variable, represents the enhanced scene features, represents the feature information of the scene object, represents the spatial location information, represents the attribute information, represents the relevant information.

[0016] Furthermore, the formal expression for dividing the data in the enhanced urban physical examination scenario according to the importance of the data and business requirements in the urban physical examination scenario is: ; ; wherein, represents the high-priority data, represents the feature information of the geographical scene object, represents the feature information of the video object, represents the feature information of the dynamic symbol, represents the low-priority data, represents the feature information of the icon object, represents the feature information of the text object.

[0017] Furthermore, the formal expression for scheduling and presenting the data in the enhanced urban physical examination scenario according to the division result is: ; wherein, represents the object feature data of the scene, represents the scene scheduling and presentation method, Indicates the priority division result, Indicates the data display mode, Indicates the release mode.

[0018] The above solution of the present invention has the following beneficial effects: Based on the spatio-temporal data of the target city, the present invention obtains the business demand data of the target city, and constructs a scenario knowledge graph according to the spatio-temporal data and business demand data of the target city; analyzes the spatio-temporal data and scenario knowledge graph of the target city to obtain an analysis result, combines semantic constraints and graphic element combinations to guide the recombination of the analysis result, and drives the generation and update of the scenario with the help of scenario narrative logic to obtain a city physical examination scenario; enhances the object semantics in the city physical examination scenario in a combination of static and dynamic ways to obtain an enhanced city physical examination scenario, and performs data priority scheduling and presentation on the enhanced city physical examination scenario to obtain a dynamic expression result of the city physical examination scenario; compared with the prior art, the present invention constructs a scenario knowledge graph by introducing a knowledge graph to deeply associate the spatio-temporal data and business demand data of the city, solves the problem of the disconnection between business and data in the prior art, combines semantic constraints and graphic element combinations to guide the recombination of the analysis results of the spatio-temporal data and scenario knowledge graph of the target city, drives the generation and update of the scenario with the help of scenario narrative logic, solves the problem of insufficient adaptability of scenario dynamic expression, enhances the object semantics in the city physical examination scenario in a combination of static and dynamic ways to obtain an enhanced city physical examination scenario, and performs data priority scheduling and presentation on the enhanced city physical examination scenario, significantly improving the visualization result of the city physical examination scenario and solving the problem of relatively single visualization presentation.

[0019] Other beneficial effects of the present invention will be described in detail in the subsequent specific implementation part. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 Is a flowchart of an embodiment of the present invention; Figure 2 Is a flowchart of the modeling method in an embodiment of the present invention; Figure 3 Is a flowchart of the knowledge graph construction in an embodiment of the present invention; Figure 4 Is a flowchart of the city physical examination scenario generation in an embodiment of the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0021] To make the technical problems, technical solutions and advantages to be solved by the present invention clearer, the following will be described in detail with reference to the accompanying drawings and specific embodiments. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all of the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0022] In the description of the present invention, it should be noted that the terms "first", "second", "third" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance.

[0023] In the description of the present invention, it should be noted that unless otherwise clearly specified and defined, the terms "connected" and "connected" should be understood in a broad sense. For example, it can be a locking connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be directly connected or indirectly connected through an intermediate medium, and it can be the communication inside two components. For those of ordinary skill in the art, the specific meanings of the above terms in the present invention can be understood according to specific situations.

[0024] In addition, the technical features involved in different embodiments of the present invention described below can be combined with each other as long as they do not conflict with each other.

[0025] The present invention provides a method for dynamically expressing a knowledge-guided urban physical examination scenario in view of existing problems.

[0026] As Figure 1 、 Figure 2 shown, an embodiment of the present invention provides a method for dynamically expressing a knowledge-guided urban physical examination scenario, including: Step 1: Obtain the business demand data of the target city based on the spatio-temporal data of the target city, and construct a scenario knowledge graph according to the spatio-temporal data and business demand data of the target city. The business demand data includes knowledge-based evaluation data, spatio-temporal analysis data, and diversified evidence data; Step 2: Analyze the spatio-temporal data of the target city and the scenario knowledge graph to obtain an analysis result, recombine the analysis result by combining semantic constraints and graphic element combinations, and drive the generation and update of the scenario with the help of the scenario narrative logic to obtain an urban physical examination scenario; Step 3: Enhance the object semantics in the urban physical examination scenario in a combination of static and dynamic ways to obtain an enhanced urban physical examination scenario, and perform data-priority scheduling and presentation on the enhanced urban physical examination scenario to obtain a dynamic expression result of the urban physical examination scenario.

[0027] Due to the complex and diverse business processes of urban physical examinations, which cover multiple key links such as data processing, indicator calculation, evaluation and analysis, result reporting and feedback, and there are significant differences in the forms and content requirements of knowledge expression in each link. In the embodiments of the present invention, to cope with the complex spatio-temporal data and business requirements of urban physical examinations, by utilizing the high-order relationship expression ability of hypergraphs, multiple nodes are directly connected by hyperedges to construct a scenario knowledge graph, as Figure 3 shown, including the following steps: Step 11, obtaining the business requirement data of the target city based on the spatio-temporal data of the target city; Step 12, constructing a hypergraph-based architecture layer according to the business requirement data and the spatio-temporal data of the target city; Step 13, performing entity classification and entity relationship construction on the architecture layer, and using hypernode links and hyperedge links to perform knowledge fusion on different entities to obtain an initial scenario knowledge graph, where the scenario knowledge graph includes a semantic layer, a data layer, and a scenario layer; Step 14, adopting a hierarchical storage architecture to store each semantic entity in the semantic layer as a node of the scenario knowledge graph, store the original data in the data layer, and store the data in the scenario layer in the form of an attribute table. Establish associations between the data in the semantic layer, the data layer, and the scenario layer through a unique identifier and an indexing mechanism. When the spatio-temporal data of the target city changes, dynamically update the initial scenario knowledge graph to obtain the scenario knowledge graph.

[0028] Specifically, the spatio-temporal data, i.e., the spatio-temporal data of the target city, comes from multiple channels, such as the urban statistical yearbooks issued by relevant government departments, project documents of urban planning and construction departments, and environmental data reports provided by environmental monitoring agencies, etc.; the spatio-temporal data covers a relatively long time period, such as records of urban-related data in the past ten years or even longer, which enables the analysis of urban physical examination indicators in a time series, such as the growth trend of invention patents in the city, the change of economic development speed, etc.; from the spatial dimension, the spatio-temporal data covers different regions of the target city, helping to analyze the differences and distribution laws of urban physical examination indicators in different regions, such as the differences in urban greenway density and construction level in different regions, etc.

[0029] Specifically, the business requirement data includes knowledge-based evaluation data, spatio-temporal analysis data, and diversified evidence data. Among them, the knowledge-based evaluation data includes descriptive, diagnostic, predictive, and solution-based knowledge for building greenways. These knowledge sources come from urban planning documents, expert opinions, and the analysis of historical data, aiming to provide theoretical support and decision-making basis for building greenways. The data acquisition methods include literature research, expert interviews, and historical data mining, with high accuracy, which can provide strong support for the scientific planning and management of building greenways. The spatio-temporal analysis data includes urban greenway density, per capita density length, average 1-hour walking greenway accessibility rate, average 5-minute vehicle driving greenway accessibility rate, etc. These data are mainly obtained through on-site measurement, geographic information system analysis, and remote sensing technology, with high spatio-temporal resolution and accuracy, and can effectively reflect the current situation and dynamic changes of building greenways. The diversified evidence data includes geographic information data, population data, traffic data, urban planning documents, and multimedia data. The geographic information data includes topographic maps, road networks, rivers and lakes, greenway locations, greenway lengths, surrounding environments, etc. These data are mainly obtained through satellite remote sensing and on-site measurement. The population data includes demographic statistics such as population distribution and population density in the area where the greenway is built. The traffic data includes the time and location of accidents, etc. The urban planning documents include the overall urban planning, special planning for building greenways, etc., which are document data used to provide the background, goals, and specific implementation plans for building greenways. The multimedia data includes satisfaction surveys feedback by citizens, online video reports, etc.

[0030] Specifically, the architecture layer in step 12 is constructed in a top-down manner. The specific process is as follows: First, based on the business requirement data of the target city's physical examination, deeply analyze the business processes, scenario elements, and associated semantics. Then, based on the spatio-temporal data of the target city, use multi-level expressions to describe the semantics of scenario modeling, including the semantic layer, scenario layer, and data layer. Among them, the semantic layer involves the knowledge content of business requirements such as the themes, connotations, knowledge points, and indicators of the target city's physical examination. The data layer describes the spatio-temporal data generated in each stage of monitoring, diagnosis, early warning, and maintenance in the target city's physical examination work. The scenario layer describes the data and knowledge sets required for the application scenarios of the target city's physical examination. Finally, use hypernode links and hyperedge links to associate complex data with knowledge application scenarios, and construct an architecture layer based on hypergraphs.

[0031] Most preferably, the formal expression of the architecture layer is: ; ; ; ; Among them, Represents the architecture layer, Represents the semantic set, Represents the theme node, Represents the connotation node, Represents the knowledge node, Represents the index node, Represents the data set, Represents the working stage of urban physical examination, Represents the data type, Represents the data source, Represents the data attribute, Represents the relationship between data, Represents the set of application scenarios, Represents the type of application scenario, Represents the hierarchical structure of data in the process of urban physical examination, , , All represent the spatio-temporal scale, Represents the physical examination stage, Represents the physical examination differentiation characteristics, Represents a data subgraph composed of a group of nodes and edges, , Represents the set of feature identifiers of the subgraph in different dimensions (such as theme dimension, knowledge dimension, index dimension, etc.), Represents the attribute name of the subgraph, Represents the high-order relationship of the data hypergraph, , Represents the spatial relationship, Represents the time relationship, Represents the physical examination stage relationship, Represents the physical examination feature relationship, Represents the dimension relationship.

[0032] Specifically, the initial scenario knowledge graph in step 13 is also created using a bottom-up method, and the specific process is as follows: First, to adapt to the application scenario of urban physical examination, the embodiments of the present invention classify entities into 3 categories: knowledge system, data system, and scenario model. Among them, in the knowledge system, a semantic conduction link is constructed with "theme - connotation - knowledge point - index" as the backbone. The data system contains spatio-temporal data generated in each stage of monitoring, diagnosis, early warning, and maintenance. The scenario model contains scenario ID, time, and spatial entities; Then, named entity recognition and attribute extraction are performed on these entities, and the relationships between them are established, such as semantic relationships such as causality, complementarity, correlation, and hierarchy, data relationships such as expression, operation, analysis, and support, and spatio-temporal relationships such as connection, sequence, topology, orientation, and distance; Finally, according to the requirements of the application scenario, knowledge fusion is carried out by using the hypernode link and hyperedge link hierarchy, data subgraphs, and high-order relationships, merging the same or similar information, and deleting the incorrect or redundant information to obtain the initial scenario knowledge graph.

[0033] In order to ensure the timeliness of the scenario knowledge graph, the embodiments of the present invention establish a storage and dynamic update mechanism for the urban physical examination knowledge graph. In terms of storage, a hierarchical storage architecture is adopted, combining the graph data integration and storage capabilities of neo4j and the storage capabilities of various database management systems.

[0034] Specifically, this storage architecture stores the semantic layer data, the raw data of the data layer, and the application data of the scenario layer separately, and establishes a close association through a unique identifier and an indexing mechanism. The specific process is as follows: First, various semantic entities in the semantic layer are stored as nodes of the knowledge graph. Each node has a unique identifier in neo4j, and the attribute and relationship information related to the entity is stored. Second, the raw data of the data layer is stored in a suitable file system or key-value store according to the data type and source. At the same time, data nodes and relationships are created in the knowledge graph, and a reference link pointing to the storage location of the raw data is established in neo4j so that the raw data can be accurately retrieved and processed when needed. Then, for the data of the scenario layer, combined with the application requirements, the scenario-related configuration information (such as the scenario type, spatio-temporal range, etc. in the scenario predefined) and user interaction data (such as the operation records of users in the scenario visualization) are stored in a file system or a relational database in the form of an attribute table. At the same time, scenario nodes and relationships are created in neo4j, and the data and knowledge in the attribute table are associated with the scenario nodes.

[0035] In terms of updating the initial scenario knowledge graph, the embodiments of the present invention adopt a strategy combining incremental update, full update, and version update. The specific process is as follows: When the spatio-temporal data of the target city changes, based on the existing structure and semantic rules of the initial scenario knowledge graph, incremental update is used to adjust the entities, relationships, and attributes in the initial scenario knowledge graph. For the newly added or modified data, according to the existing structure and semantic rules of the initial scenario knowledge graph, the relevant entities, relationships, and attributes are quickly located for local adjustment, such as adding new classes, attributes, or relationships. After performing conflict or consistency checks on the adjusted initial scenario knowledge graph, a scenario knowledge graph is obtained. Consistency checks include data type consistency (ensuring that the format of new data is compatible with existing data, such as unified time formats and consistent numerical units), semantic consistency (newly added relationships and attributes conform to the established semantic logic of the knowledge graph, such as reasonable associations between greenway construction and related accessibility indicators), and logical consistency (avoiding contradictory information, such as inconsistent infrastructure types for the same area in different data sources). If conflicts are found, semantic rules will be used to resolve the conflicts to ensure the consistency and coherence of the updated knowledge graph; When the spatio-temporal data of the target city needs to be comprehensively updated, the architecture layer and the initial scenario knowledge graph are updated and stored based on the updated spatio-temporal data of the target city, including: reconstructing the architecture layer and the initial scenario knowledge graph based on the updated data sources and business requirements, re-combing the themes, connotations, knowledge points, indicators, and data of the urban physical examination, re-identifying and extracting entities, relationships, and attributes, and organizing and storing them according to new standards. Update records of the state changes of the knowledge graph before and after each full update, and by establishing version management, trace back and analyze the development trajectory of the knowledge graph to obtain the scenario knowledge graph.

[0036] Specifically, as Figure 4 shown, step 2 includes: Step 21, parse the spatio-temporal data of the target city and the scenario knowledge graph to obtain multiple material primitives, and integrally manage all material primitives to form a scenario material library; Specifically, in the embodiments of the present invention, in order to uniformly organize a large amount of data and knowledge such as index analysis, evaluation, and evidence collection generated in the urban physical examination business work into a scenario model, with material primitives as the main modeling unit, read the spatio-temporal data of the target city, such as urban planning documents, geographic information databases, environmental monitoring reports, social and economic statistical yearbooks, etc., extract texts, images, and maps related to the urban scenario, convert them into corresponding material primitives, and through the analysis of the knowledge graph entities, extract attribute and relationship information related to the urban physical examination scenario, and convert it into material primitives to obtain multiple material primitives; through this method, information such as spatio-temporal statistics, spatial analysis, and index analysis is encapsulated, "descriptive-diagnostic-predictive-solution" knowledge, as well as material primitives such as graphic symbols, cross-media, geographic information, and policy report evidence, allowing the assembly of "spatio-temporal analysis-knowledge-based evaluation-diverse evidence" scenario materials. By integrally managing these material primitives, a scenario material library is formed to support the scenario model and dynamic updates.

[0037] Step 22: Decompose the scenarios in the scenario knowledge graph to obtain multiple basic modules. Combine semantic constraints to perform primitive mapping on all basic modules, all primitive graphics in the scenario material library, and the semantic relationships in the scenario knowledge graph, obtaining multiple mapping results, and assemble based on all mapping results to obtain a scenario model; Step 23: Dynamically evolve the scenario model through scenario narrative logic modeling to obtain an evolution result. Transform the evolution result through expression processing to obtain an initial urban physical examination scenario, and update the initial urban physical examination scenario through a dynamic update mechanism to obtain an urban physical examination scenario.

[0038] Specifically, Step 22 includes: First, perform semantic analysis on the scenario based on the urban physical examination scenario knowledge graph, and decompose it into multiple basic modules. Its formal expression is: ; Among them, represents a basic module, represents a decomposition function, represents a theme node, which is the main theme identified in the urban physical examination scenario, such as ecological livability, convenient transportation, innovative vitality, etc., represents a connotation node, which is the connotation extracted for each theme, that is, the connotation covered by this theme. For example, the connotation of the ecological livability theme includes green and low-carbon development, ecological environment protection, living space, etc., represents a knowledge node, which is the knowledge point sorted out related to the connotation. For example, the knowledge points under the green and low-carbon development connotation include greenway construction, energy conservation and emission reduction, water resource utilization, etc., represents an index node, which determines the index used to evaluate each knowledge point. For example, greenway density, greenway pedestrian accessibility rate, greenway vehicle accessibility rate, represents a data set, which is obtained by classifying the data related to the scenario, including numerical values, tables, texts, events, etc.; Next, perform primitive mapping based on semantic constraints. Its formal expression is: ; Among them, represents the mapped primitive, represents a primitive mapping function, represents a material primitive, which is used to fill the basic module; Using the above formula, extract the primitives related to the scenario from the scenario material library, map the extracted primitives to the scenario template used to organize and display the primitives, and layout the scenario template according to the semantic relationship, adjusting the position relationship, color, and size between the primitives; Finally, assemble in the scenario template to form a scenario model , and its formal expression is: ; Among them, represents the initial urban physical examination scenario, represents the visualization operation, represents the timeline, represents the geospatial scenario.

[0039] Since the narrative of the urban physical examination scenario involves the dynamic evolution of the geospatial scenario and follows specific logic, not only is it necessary to first identify events, describe the corresponding detailed processes of the events, express the states contained in the processes and the people / things in the states, but also it is necessary to use the spatio-temporal framework to organize and present information. Therefore, through the dynamic evolution of the scenario model by means of scenario narrative logic modeling, the evolution results are obtained, including: First, identify the key events in a certain hidden danger section during the urban physical examination, such as traffic accidents and greenway construction; For each identified event, describe the process of its occurrence, development, and end. For example, a traffic accident event starts from a certain time period, the vehicle congestion gradually intensifies, bringing travel risks to people and vehicles, and finally a bicycle lane is opened on the hidden danger section at a certain time point to alleviate these problems; In the process description, express each state and the people and things it contains. For example, during the vehicle congestion process, the states involve a huge traffic flow and restricted green travel. Under the state of restricted green travel, it involves a large local population and a sharp increase in motor vehicles; Use the spatio-temporal framework to organize and present the scenario information to obtain the evolution results. The spatio-temporal framework includes the geospatial scenario and the time series. The geospatial scenario can be a 2D / 3D map of the city or a real scene image, showing the specific location where the event occurs, and the time series records the state changes of the event at different time points.

[0040] Specifically, through expression processing, the evolution results are transformed to obtain the initial urban physical examination scenario, including: Through expression processing, the scenario narrative logic model is transformed into a form of scenario information that can be understood and operated. The formal expression of the expression processing is: ; ; ; Among them, represents sorting and organizing, represents spatial layout, represents the semantic conversion method, represents the th semantics, represents the process, represents the event, Represents a state, Represents a location; Using the above formula, events, processes, and states are organized into a timeline in chronological order to facilitate decision-makers in understanding the development process and status of events. Spatial entities are organized and laid out according to the geographical space scenario. Then, the semantics are converted into understandable words, symbols, or non-physical expressions.

[0041] Specifically, the initial urban physical examination scenario is updated through a dynamic update mechanism to obtain an urban physical examination scenario, including: Through the formula Dynamically update the material primitives to obtain an updated scene material library, where Represents the material primitive, Represents the parsing method, Represents the spatio-temporal data of the target city, Represents the scene knowledge graph; Through the formula Dynamically update the scene model to obtain an updated scene model, where Represents the scene model, Represents the composition operation, Represents the th mapped primitive; Through the formula Update the initial urban physical examination scenario to obtain an urban physical examination scenario, where Represents the initial urban physical examination scenario, Represents the visualization operation, Represents the timeline, Represents the geographical space scenario.

[0042] Specifically, step 3 includes: Step 31, enhance the object semantics in the urban physical examination scenario based on the combination of static and dynamic visual variables to obtain an enhanced urban physical examination scenario; Step 32, according to the importance of the data in the urban physical examination scenario and business requirements, divide the priority of the data in the enhanced urban physical examination scenario to obtain a division result; Step 33, schedule and present the data in the enhanced urban physical examination scenario according to the division result to obtain the dynamic expression result of the urban physical examination scenario.

[0043] Since traditional visual variables, such as shape, size, color, brightness, orientation, and texture, mainly focus on static features and are difficult to fully express the dynamic features and behavioral relationships of geographical phenomena, visualizing urban physical examination scenarios requires using visual variables to transform complex urban physical examination scenarios into intuitive and easily understandable visual information. To overcome this limitation, by introducing the time dimension, dynamic visual variables, such as time, frequency, duration, synchronization, and sequence, are proposed. These variables can more accurately and intuitively reflect the state and characteristics of spatial phenomena. Therefore, the combination of "static" and "dynamic" visual variables enhances the understanding effect and can effectively highlight the target information.

[0044] Most preferably, the formal expression for enhancing the object semantics in the urban physical examination scenario based on the combination of static and dynamic visual variables is: ; Wherein, represents the set of visual variables, represents the dynamic visual variables, represents the static visual variables, represents the enhanced scene features, represents the feature information of the scene object, represents the spatial location information, represents the attribute information, represents the relevant information, such as causal relationships and time.

[0045] Specifically, the static part is a scene evaluation story composed of multiple knowledge points and relationships. Through static visual variables (such as shape, size, color, etc.), it enhances the semantic expression of scene objects such as text descriptions and statistical charts. The dynamic part is based on the scene evaluation storyline, introducing dynamic visual variables (such as time, frequency, duration, etc.) to display the dynamic changes of scene objects such as geographical spaces or video media; through the combination of the two (such as direct rendering, dynamic rendering), scene dynamic symbols (such as highlighting, movement, flashing) are formed, making the urban physical examination scene information more comprehensive and vivid.

[0046] Since the urban physical examination scenario involves not only static data such as multi-scale geographical scenes, text descriptions, and statistical charts, but also dynamic data formed by the combination of video media, multi-scale geographical scenes, and dynamic symbols. The static data does not change frequently over time, while the dynamic data has a time dimension and changes frequently, requiring real-time update and display. According to the importance of the data and business requirements in the urban physical examination scenario, the formal expression for prioritizing the data in the enhanced urban physical examination scenario is: ; ; Wherein, represents high-priority data, Represents the feature information of the geographical scene object, Represents the feature information of the video object, Represents the feature information of the dynamic symbol, Represents low-priority data, Represents the feature information of the icon object, Represents the feature information of the text object.

[0047] For high-priority data, such as key geographical scenes and real-time monitoring videos, the preloading method is adopted to ensure that users can quickly obtain information when viewing. For low-priority data, such as detailed statistical charts and text descriptions, the on-demand loading method is adopted to ensure that business personnel can obtain concise and useful information.

[0048] Most preferably, the formal expression of scheduling and presenting the data of the enhanced urban physical examination scene according to the division result is: Wherein, Represents the object feature data of the scene, Represents the scene scheduling and presenting method, Represents the preferred division result, Represents the data display method, Represents the publishing method.

[0049] Specifically, in the display method of the embodiment of the present invention, static data is rendered as the background layer, and dynamic data is rendered as the foreground layer to avoid visual chaos caused by information superposition. Its formal expression is: ; ; Wherein, Represents the background layer data, providing basic geography, text, and statistical information, Represents the foreground layer data, showing real-time change information, Represents the rendering method.

[0050] Select a suitable transmission protocol and publishing method according to the data volume, network environment, and business requirements. Its formal expression is: ; Wherein, Represents publishing tile map data, Represents publishing dynamic map data, Represents publishing dynamic real-time video data, Represents publishing static text and chart data.

[0051] The scene object is published using the above formula. Specifically: For multi-scale geographical scenario data, it is published as a tile map service using the Web Map Tile Service protocol WMTS and visualization libraries (such as Leaflet and OpenLayers), and the map within a fixed view window range is loaded and rendered through a URL. The Web Map Service protocol WMS and ArcGIS Server are used to publish a dynamic map service, and an interactive map is loaded and rendered through a RESTful API to display urban geospatial elements with different symbols and layers. For dynamic data with high real-time requirements (such as real-time video data), the HLS protocol is used for real-time push. For static data such as small-scale text and statistical data, the HTTP protocol and visualization libraries (such as Echarts and D3.js) are used to convert the data into graphical and chart visualization forms.

[0052] In an embodiment of the present invention, a certain southern city with a complex urban structure and diverse urban functional areas is used as an experimental area, and the construction of urban greenways is used as an application scenario for urban physical examination. Three typical urban physical examination scenarios for the construction of urban greenways in this city are selected to verify the effectiveness of the provided method. The specific process is as follows: Collect and process the spatio-temporal data required for the construction scenario of urban greenways in a certain southern city, and obtain business requirement data based on this spatio-temporal data, such as knowledge-based evaluation data, spatio-temporal analysis data, and diversified evidence data. The urban physical examination greenway scenario includes multiple scales, such as the overall urban situation at the macro scale, the regional situation at the meso scale, and specific events at the micro scale. Integrate the knowledge required for the business and the occurrence, development, and end processes of events for each scale scenario to form a complete evaluation story. Extract the scenario elements with different scale structures: First, at the macro scale, extract the construction situation of urban greenways as a whole, including knowledge such as themes, connotations, total greenway length, covered areas, and per capita greenway density indicators. Secondly, at the meso scale, extract the construction situation of greenways in specific regions, such as the distribution of the Bio Island Greenway and the repair and renovation of greenways in Huangpu District. Furthermore, at the micro scale, extract detailed information about specific events, such as the construction process, usage situation, and residents' feedback of a certain greenway. By extracting material primitives (such as text, images, maps, etc.), map the material primitives into the scenario template. Finally, perform layout and adjustment according to semantic relationships to form scenario models with different scale structures. Among them, the macro scale represents an overview map of the overall urban greenway construction, the meso scale represents a detailed map of the greenway construction in a specific region, and the micro scale represents the specific greenway construction and usage process.

[0053] To provide the background of greenway construction and the improvement effect of the transformation of "risk" sections, dynamic scene expression is carried out at three scales: macro, meso, and micro: First, at the macro scale, GIS and vector analysis maps are used to display the greenway network pattern in Guangzhou, and at the meso scale, three-dimensional maps and visualization charts are used to display descriptive knowledge such as the construction of park greenways; Then, at the micro scale, problem diagnosis is carried out. By identifying key events in the greenway construction of the Gangding section in this area, such as traffic accidents and the opening of greenways, the accident locations and the positions of greenway openings are marked on the map, and key events are highlighted through dynamic symbols (such as flashing text markings and icon color changes); Finally, through interactive scene switching, the dynamic update of the solution-type knowledge of "improving the safety hazards of mixed pedestrian and vehicle traffic through the opening of greenways" is realized.

[0054] To provide the construction background, problem diagnosis, and optimization measures of existing greenways, dynamic scene expression is carried out at two scales: meso and micro: First, at the meso scale, three-dimensional maps and vector analysis maps are used to display descriptive knowledge such as the overall pattern of the existing greenway network on the Biological Island; Secondly, at the micro scale, problem diagnosis is carried out. By identifying the key problems of the interruption of some greenways around the island, such as building blockages and uneven road widths. The positions of greenway interruptions are marked on the map, and the interrupted parts are expressed with dynamic symbols (such as the color change of the greenway from light green to dark green); Finally, through the interactive scene switching of the existing greenways, the update of "descriptive-diagnostic" knowledge is realized.

[0055] To provide the background of the construction of new greenways on bridges and the effectiveness of ecological traffic optimization, dynamic scene expression is carried out at two scales: meso and micro: First, at the meso scale, three-dimensional maps and visualization charts are used to display the cross-shore traffic pattern, analyze the construction status and existing problems; Then, at the micro scale, identify the cases of pedestrian bridge construction, mark the positions of new greenways on the map, and express the new parts with dynamic symbols (such as green pedestrian lines), intuitively showing the positions and connection relationships of the new greenways in the regional traffic network; Finally, through interactive scene switching, the dynamic update of the scene is realized.

[0056] In the embodiment of the present invention, a questionnaire survey is used to quantitatively analyze the cognitive evaluation of business personnel on the urban greenway scene. 80 participants in the field of urban planning participated in this comparative experiment, and they were randomly divided into two groups: Group A and Group B. 46 participants in Group A were required to read the text report, and 34 participants in Group B were required to watch the dynamic scene expression page. To evaluate the reliability and validity of this questionnaire, Cronbach Coefficient (Cronbach's ) and Kaiser - Meyer - Olkin (KMO) tests. Generally, the Cronbach coefficient is used to reflect the consistency and reliability of the questionnaire results. A value greater than 0.8 indicates high reliability; the KMO test is used to evaluate the structural validity of the questionnaire. A value greater than 0.7 indicates acceptable validity. In addition, the embodiments of the present invention use indicators such as mean, quartiles, and standard deviation to analyze the feedback. The mean reflects the user's level of understanding; quartiles are used to analyze the central tendency of user feedback; the standard deviation indicates the degree of dispersion of the test results and the stability of the preset questions.

[0057] After receiving 80 questionnaires, reliability and validity analyses were carried out on the questionnaire data. The Cronbach value was determined to be 0.85, greater than 0.8; the KMO value was 0.76, close to 0.8. These statistical data indicate that the data and results collected through the questionnaire are true, valid, and reliable.

[0058] The embodiments of the present invention use indicators such as mean, quartiles, and standard deviation for analysis, and the Mann–Whitney U test is used to compare the differences between group A and group B. The statistics are represented by u and z, and the P - value represents the corresponding probability, obtaining Table 1 below: Table 1 Statistical tests of experimental results ; As can be seen from Table 1 above, when the P - value is less than 0.01, it indicates high statistical significance. For the three evaluation indicators of practicality, understandability, and aesthetics, the P - values are all 0.000, all less than 0.01, which indicates that there are significant differences between group A and group B in these three indicators.

[0059] In an embodiment of the present invention, business requirement data of a target city is obtained based on spatio-temporal data of the target city, and a scenario knowledge graph is constructed according to the spatio-temporal data and the business requirement data of the target city; the spatio-temporal data of the target city and the scenario knowledge graph are parsed to obtain a parsing result, and the parsing result is recombined by combining semantic constraints and graphic element combinations to drive scenario generation and update with the help of scenario narrative logic, so as to obtain a city physical examination scenario; the object semantics in the city physical examination scenario are enhanced in a combination of static and dynamic ways to obtain an enhanced city physical examination scenario, and data priority scheduling presentation is performed on the enhanced city physical examination scenario to obtain a dynamic expression result of the city physical examination scenario; compared with the prior art, in the embodiment of the present invention, by introducing a knowledge graph to construct a scenario knowledge graph to deeply associate the spatio-temporal data and the business requirement data of the city, the problem of disconnection between business and data in the prior art is solved, the parsing results of the spatio-temporal data and the scenario knowledge graph of the target city are recombined by combining semantic constraints and graphic element combinations, and scenario generation and update are driven with the help of scenario narrative logic, so as to solve the problem of insufficient adaptability of scenario dynamic expression, the object semantics in the city physical examination scenario are enhanced in a combination of static and dynamic ways to obtain an enhanced city physical examination scenario, and data priority scheduling presentation is performed on the enhanced city physical examination scenario, significantly improving the visualization result of the city physical examination scenario and solving the problem of relatively single visualization presentation.

[0060] The above is the preferred embodiment of the present invention. It should be noted that for those of ordinary skill in the art in the technical field, without departing from the principle described in the present invention, several improvements and refinements can be made, and these improvements and refinements should also be regarded as the protection scope of the present invention.

Claims

1. A method for dynamically expressing urban physical examination scenarios guided by knowledge, characterized in that Including: Step 1: Obtain the business demand data of the target city based on the spatio-temporal data of the target city, and construct a scenario knowledge graph according to the spatio-temporal data and business demand data of the target city. The business demand data includes knowledge-based evaluation data, spatio-temporal analysis data, and diversified evidence data. Step 2: Analyze the spatio-temporal data of the target city and the scenario knowledge graph to obtain an analysis result, combine semantic constraints and graphic element combinations to guide the recombination of the analysis result, and drive the generation and update of the scenario with the help of scenario narrative logic to obtain a city physical examination scenario. Step 3: Enhance the object semantics in the city physical examination scenario in a dynamic and static combination manner to obtain an enhanced city physical examination scenario, and perform data-priority scheduling and presentation on the enhanced city physical examination scenario to obtain a dynamic expression result of the city physical examination scenario.

2. The knowledge-guided dynamic expression method for urban physical examination scenarios according to claim 1, wherein The said Step 1 includes: Step 11: Obtain the business demand data of the target city based on the spatio-temporal data of the target city. Step 12: Construct a hypergraph-based architecture layer according to the business demand data and the spatio-temporal data of the target city. Step 13: Perform entity classification and entity relationship construction on the architecture layer, and use hypernode links and hyperedge links to perform knowledge fusion on different entities to obtain an initial scenario knowledge graph. The scenario knowledge graph includes a semantic layer, a data layer, and a scenario layer. Step 14: Use a hierarchical storage architecture to store each semantic entity in the semantic layer as a node of the scenario knowledge graph, store the original data in the data layer, and store the data in the scenario layer in the form of an attribute table. Establish associations between the data in the semantic layer, the data layer, and the scenario layer through a unique identifier and an indexing mechanism. When the spatio-temporal data of the target city changes, dynamically update the initial scenario knowledge graph to obtain a scenario knowledge graph.

3. The knowledge-guided dynamic expression method for urban physical examination scenarios according to claim 2, characterized in that The formal expression of the said architecture layer is: Among them, represents the architecture layer, represents the semantic set, represents the theme node, represents the connotation node, represents the knowledge node, represents the index node, represents the data set, represents the working stage of urban physical examination, represents the data type, represents the data source, represents the data attribute, represents the relationship between data, represents the set of application scenarios, represents the type of application scenario, represents the hierarchical structure of data in the process of urban physical examination, represents a data subgraph composed of a group of nodes and edges, represents the high-order relationship of the data hypergraph.

4. The knowledge-guided dynamic expression method for urban physical examination scenarios according to claim 2, characterized in that When the spatio-temporal data of the target city changes, dynamically update the initial scenario knowledge graph to obtain a scenario knowledge graph, including: When the spatio-temporal data of the target city changes, on the basis of the existing structure and semantic rules of the initial scenario knowledge graph, use incremental update to adjust the entities, relationships, and attributes in the initial scenario knowledge graph, and perform conflict or consistency checks on the adjusted initial scenario knowledge graph to obtain a scenario knowledge graph. When the spatio-temporal data of the target city needs to be comprehensively revised, update and store the architecture layer and the initial scenario knowledge graph based on the revised spatio-temporal data of the target city to obtain a scenario knowledge graph.

5. The knowledge-guided dynamic expression method for urban physical examination scenarios according to claim 4, characterized in that, The said Step 2 includes: Step 21: Analyze the spatio-temporal data of the target city and the scenario knowledge graph to obtain multiple material graphic elements, and integrally manage all material graphic elements to form a scenario material library. Step 22: Decompose the scenarios in the scenario knowledge graph to obtain multiple basic modules, combine semantic constraints to perform graphic element mapping on all basic modules, all material graphic elements in the scenario material library, and semantic relationships in the scenario knowledge graph to obtain multiple mapping results, and assemble based on all mapping results to obtain a scenario model. Step 23: Dynamically evolve the scenario model through scenario narrative logic modeling to obtain an evolution result, transform the evolution result through expression processing to obtain an initial urban physical examination scenario, and update the initial urban physical examination scenario through a dynamic update mechanism to obtain an urban physical examination scenario.

6. The knowledge-guided dynamic expression method for urban physical examination scenarios according to claim 5, characterized in that, Updating the initial urban physical examination scenario through a dynamic update mechanism to obtain an urban physical examination scenario includes: Dynamically update the material primitive through the formula to obtain an updated scene material library, where represents the material primitive, represents the parsing method, represents the spatio-temporal data of the target city, represents the scene knowledge graph; Dynamically update the scene model through the formula to obtain the updated scene model, where represents the scene model represents the composition operation represents the th mapped primitive; Update the initial urban physical examination scenario through the formula to obtain an urban physical examination scenario, where represents the initial urban physical examination scenario,[ represents the visualization operation,[ represents the timeline,[ represents the geospatial scenario.[ 7. The knowledge-guided dynamic expression method for urban physical examination scenarios according to claim 5, characterized in that Step 3 includes: Step 31: Enhance the object semantics in the urban physical examination scenario based on visual variables combining static and dynamic elements to obtain an enhanced urban physical examination scenario; Step 32: Divide the data in the enhanced urban physical examination scenario into priorities according to the importance of the data and business requirements in the urban physical examination scenario to obtain a division result; Step 33: Schedule and present the data in the enhanced urban physical examination scenario according to the division result to obtain a dynamic expression result of the urban physical examination scenario.

8. The knowledge-guided dynamic expression method for urban physical examination scenarios according to claim 7, wherein, The formal expression for enhancing the object semantics in the urban physical examination scenario based on visual variables combining static and dynamic elements is: Among them, represents a set of visual variables, represents dynamic visual variables, represents static visual variables, represents enhanced scene features of the representation, represents the feature information of the scene object, represents spatial location information, represents attribute information, represents relevant information.

9. The knowledge-guided dynamic expression method for urban physical examination scenarios according to claim 8, wherein The formal expression for dividing the data in the enhanced urban physical examination scenario into priorities according to the importance of the data and business requirements in the urban physical examination scenario is: Among them, represents high-priority data, represents the feature information of a geographical scene object, represents the feature information of a video object, represents the feature information of a dynamic symbol, represents low-priority data, represents the feature information of an icon object, represents the feature information of a text object.

10. The knowledge-guided dynamic expression method for urban physical examination scenarios according to claim 9, wherein The formal expression for scheduling and presenting the data in the enhanced urban physical examination scenario according to the division result is: Among them, represents the object feature data of the scene, represents the scene scheduling and rendering method, represents the priority division result, represents the data display method, represents the publishing method.

Images