Scene reconstruction method and system based on historical knowledge

Abstract

The invention provides a scene reconstruction method and system based on historical knowledge, and relates to the technical field of virtual modeling. The method comprises the steps of obtaining a historical database of a target historical period, wherein the historical database at least comprises historical text data and historical image data; constructing a historical time axis of the target historical period based on the historical database, wherein the historical time axis comprises a plurality of time nodes and historical element features corresponding to the time nodes; based on the historical element features corresponding to the time nodes, determining target historical scenes corresponding to the time nodes; and generating a dynamic evolution graph of the target historical period based on the time sequence of each time node on the historical time axis and the target historical scene of each time node. By implementing the technical scheme provided by the invention, the continuous evolution process of a historical scene can be truly reflected, and the application value of historical knowledge in cultural transmission is improved.

Description

Technical Field

[0001] This application relates to the field of virtual modeling technology, and particularly to a method and system for scene reconstruction based on historical knowledge. Background Art

[0002] With the development of digital technology, the digital protection and display of historical and cultural heritages have gradually become an important way of cultural inheritance. Especially in the process of urban renewal and cultural relic protection, how to accurately restore the spatio-temporal evolution process of historical scenes is of great significance for understanding the urban development process and protecting cultural heritages.

[0003] Currently, historical scene reconstruction is mainly achieved by collecting historical documents, old photos and other materials and combining with 3D modeling technology. Usually, manual recognition and extraction of scene features in historical materials are adopted, and 3D models are constructed based on these features. Since the evolution of historical scenes is often a gradual process, however, in practical applications, the existing methods mainly focus on the reconstruction of static scenes in a specific historical period, and it is difficult to truly reflect the continuous evolution process of historical scenes, resulting in a relatively low application value of its historical knowledge in cultural dissemination. Summary of the Invention

[0004] This application provides a method, system, storage medium and electronic device for scene reconstruction based on historical knowledge, which can truly reflect the continuous evolution process of historical scenes and improve the application value of its historical knowledge in cultural dissemination.

[0005] In a first aspect, this application provides a method for scene reconstruction based on historical knowledge, and the method includes: Obtain a historical database of a target historical period, where the historical database at least includes historical text materials and historical image materials; Construct a historical timeline of the target historical period based on the historical database, where the historical timeline includes multiple time nodes and historical element features corresponding to each of the time nodes; Determine a target historical scene corresponding to each of the time nodes based on the historical element features corresponding to each of the time nodes; Generate a dynamic evolution map of the target historical period based on the time sequence of each of the time nodes on the historical timeline and the target historical scenes of each of the time nodes.

[0006] By adopting the above technical solution, a historical database containing historical text materials and historical video materials is obtained, a historical timeline including multiple time nodes and their corresponding historical element features is constructed, and the corresponding target historical scenes are determined based on the historical element features of each time node. Furthermore, a dynamic evolution map is generated based on the chronological order of the time nodes on the historical timeline and the target historical scenes, thus realizing the continuous reconstruction of historical scenes. This solution uses the historical element features in the historical database to construct the historical timeline, making the reconstructed historical scenes have reliable historical basis, and shows the gradual change process of historical scenes between different time nodes through the dynamic evolution map, truly reflecting the continuous evolution law of historical scenes, and effectively improving the application value of historical knowledge in cultural dissemination.

[0007] In the second aspect of the present application, a historical knowledge-based scene reconstruction system is provided. The system includes: A database acquisition module, configured to acquire a historical database of a target historical period, where the historical database includes at least historical text materials and historical video materials; A timeline construction module, configured to construct a historical timeline of the target historical period based on the historical database, where the historical timeline includes multiple time nodes and the historical element features corresponding to each time node; A scene determination module, configured to determine the target historical scenes corresponding to each time node based on the historical element features corresponding to each time node; An evolution map generation module, configured to generate a dynamic evolution map of the target historical period based on the chronological order of the time nodes on the historical timeline and the target historical scenes corresponding to each time node.

[0008] In the third aspect of the present application, a computer storage medium is provided. The computer storage medium stores multiple instructions, and the instructions are suitable for being loaded and executed by a processor to perform the above method steps.

[0009] In the fourth aspect of the present application, an electronic device is provided, including: a processor and a memory; wherein, the memory stores a computer program, and the computer program is suitable for being loaded and executed by the processor to perform the above method steps.

[0010] In summary, one or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages: This application realizes the continuous reconstruction of historical scenes by obtaining a historical database containing historical text materials and historical video materials, constructing a historical timeline including multiple time nodes and their corresponding historical element features, determining the corresponding target historical scenes based on the historical element features of each time node, and then generating a dynamic evolution map based on the chronological order and target historical scenes on the historical timeline. This solution constructs a historical timeline using the historical element features in the historical database, making the reconstructed historical scenes have reliable historical basis, and shows the gradual change process of historical scenes between different time nodes through the dynamic evolution map, truly reflecting the continuous evolution law of historical scenes and effectively enhancing the application value of historical knowledge in cultural dissemination. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] Figure 1 is a schematic flowchart of a historical knowledge-based scene reconstruction method provided by an embodiment of the present application; Figure 2 is a schematic block diagram of a historical knowledge-based scene reconstruction system provided by an embodiment of the present application; Figure 3 is a schematic structural diagram of an electronic device provided by an embodiment of the present application.

[0012] Description of the reference numerals: 300, electronic device; 301, processor; 302, communication bus; 303, user interface; 304, network interface; 305, memory. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0013] In order to enable those skilled in the art to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below with reference to the accompanying drawings in the embodiments of this specification. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments.

[0014] In the description of the embodiments of the present application, words such as "for example" or "for illustration" are used to represent examples, illustrations or explanations. Any embodiment or design solution described as "for example" or "for illustration" in the embodiments of the present application should not be construed as being more preferred or having more advantages than other embodiments or design solutions. Exactly speaking, using words such as "for example" or "for illustration" is intended to present relevant concepts in a specific manner.

[0015] In the description of the embodiments of the present application, the term "a plurality of" means two or more. For example, a plurality of systems means two or more systems, and a plurality of screen terminals means two or more screen terminals. In addition, the terms "first" and "second" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance or implicitly specifying the indicated technical features. Thus, the features defined with "first" and "second" may explicitly or implicitly include one or more of such features. The terms "comprising", "including", "having" and their variants all mean "including but not limited to", unless otherwise specifically emphasized in other ways.

[0016] Next, the technical solutions in the embodiments of the present application will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments.

[0017] Please refer to Figure 1 , and a flowchart of a method for scene reconstruction based on historical knowledge is specifically proposed. This method can be implemented depending on a computer program, can be implemented depending on a single-chip microcomputer, or can run on a scene reconstruction system based on historical knowledge. This computer program can be integrated in a computer device or can run as an independent tool-class application. Specifically, this method includes steps 10 to 40, and the above steps are as follows: Step 10: Obtain a historical database of the target historical period, where the historical database includes at least historical text materials and historical image materials.

[0018] In the embodiments of the present application, the target historical period refers to a specific historical time range that needs to be reconstructed, which can be a certain dynasty, the time interval when a certain important historical event occurred, or the time period of the development and evolution of a certain historical building or historical block. For example, it can be the Kangxi period of the Qing Dynasty, the Republic of China period, or the development period of a certain ancient city from the Ming Dynasty to the Qing Dynasty, etc.

[0019] In the embodiments of the present application, the historical database refers to a collection of historical materials related to the target historical period, including but not limited to historical text materials such as historical literature records, local chronicles, ancient books and classics, old photos, historical maps, archaeological excavation reports, and historical image materials such as historical images, paintings, and architectural drawings. These materials record historical information such as the architectural style, environmental characteristics, and cultural landscapes of the target historical period.

[0020] Specifically, in order to accurately restore the scene features of the target historical period, it is first necessary to establish a complete historical knowledge base. Historical materials related to the target historical period can be collected through various channels such as digital archives, historical literature databases, and on-site investigations. Among them, historical text materials mainly include written historical materials such as local chronicles, historical literature records, and archaeological excavation reports. These materials detail information such as the architectural layout, environmental characteristics, and human activities in the target historical period; historical image materials include image historical materials such as old photos, historical maps, architectural surveying and mapping drawings, and historical paintings. These materials visually display the visual characteristics of historical scenes. During the acquisition process, historical researchers first conduct a preliminary screening of various historical materials to ensure that their time attributes belong to the target historical period. Subsequently, optical character recognition technology is used to digitally process historical text materials and convert them into searchable electronic texts; at the same time, historical image materials are subjected to high-definition scanning and image enhancement processing to improve image clarity and recognizability. The processed historical text materials and historical image materials are uniformly stored in the historical database, and data indexes and association relationships are established to facilitate the subsequent extraction of historical element features. The historical database constructed in this way not only ensures the comprehensiveness and reliability of historical materials but also realizes the structured storage and efficient utilization of historical materials, laying a solid data foundation for subsequent scene reconstruction based on the historical timeline.

[0021] Step 20: Construct a historical timeline of the target historical period based on the historical database. The historical timeline includes multiple time nodes and the historical element features corresponding to each time node.

[0022] In the embodiments of the present application, the historical timeline refers to a data structure that chronologically organizes the evolution process of historical scenes within the target historical period. It records the critical moments and transitional stages of scene changes in chronological order. For example, for the development process of an ancient city from the Ming Dynasty to the Qing Dynasty, the historical timeline can include key nodes such as important reconstruction periods and periods when major historical events occurred, as well as the gradual change process between these key nodes.

[0023] In the embodiments of the present application, a time node refers to a specific time point on the historical timeline, including core time nodes and transitional time nodes. Among them, the core time node corresponds to the moment when a major change occurs in the historical scene or there is a complete historical record, such as the year when an important building was completed or the period when the regional pattern changed; the transitional time node is an intermediate time point added between adjacent core time nodes to depict the gradual change process of the scene.

[0024] The historical element features in the embodiments of the present application refer to the set of key constituent elements and their attribute features of a historical scene at a certain time node, mainly including architectural features (such as building scale, style, material, etc.), environmental features (such as topography, vegetation distribution, etc.), and humanistic features (such as functional layout, usage method, etc.). These features are extracted from the historical database and are used to describe the specific state of the historical scene at that time node.

[0025] Specifically, time information is extracted from historical text materials through natural language processing technology to identify time markers such as dynasties, seasons, etc. in the text. At the same time, time information such as shooting time and creation era is extracted from historical image materials using image recognition technology. The extracted time information is clustered according to time attributes, and historical text materials and historical image materials with the same or similar time attributes are associated and combined to form an initial time node sequence. Subsequently, historical events and scene features recorded in each initial time node are analyzed, and time nodes containing key historical events such as major building renovations and regional pattern changes or important historical features are selected as core time nodes. Between adjacent core time nodes, the time interval is dynamically determined according to the influence degree of historical events, and transitional time nodes are supplemented. For each determined time node, its corresponding historical element features are further extracted, including architectural features such as building scale and material type from historical text materials, environmental features such as topography and vegetation distribution from historical image materials, and humanistic features such as functional layout and usage method from comprehensive materials. The historical timeline constructed in this way not only reflects the critical moments of historical scene evolution but also fills in the process details of scene changes through reasonable transitional time nodes, realizing a systematic description of the historical scene evolution process and providing a clear time sequence framework and rich feature information for subsequent scene reconstruction.

[0026] Based on the above embodiments, as an optional embodiment, the step of constructing a historical timeline of the target historical period based on the historical database may further include the following steps: Step 201: Extract time attributes from historical text materials and historical image materials in the historical database, and associate and combine materials with the same time attributes to obtain an initial time node sequence.

[0027] Specifically, natural language processing technology is used to segment and perform part-of-speech tagging on historical text materials, and keywords containing time information such as years, dynasties, and reign titles are identified. For example, through a preset time dictionary, text expressions such as "the 15th year of Kangxi" and "the early Republic of China" are matched and converted into the corresponding Gregorian years. For historical image materials, image recognition technology is used to extract time markers in materials such as photos and maps, such as the photo shooting time and the map drawing era. At the same time, combined with image content analysis technology, according to visual elements such as architectural styles and clothing features in the images, the time attributes of the materials are assisted in judgment. After the time attribute extraction is completed, a time similarity calculation model is established, and historical materials with time differences within a preset threshold range are divided into the same time group. Within each time group, an association mapping is established between historical text materials and historical image materials to form a set of materials describing the scene characteristics of the same historical period, that is, the initial time node. All the initial time nodes are arranged in chronological order to obtain a complete initial time node sequence. This data association method based on time attributes not only ensures the chronological integrity of historical materials but also realizes the organic combination of text materials and image materials, providing a structured data basis for subsequent extraction of historical element features.

[0028] Step 202: Screen time nodes containing key historical events or important historical features from the initial time node sequence as core time nodes, and supplement transitional time nodes between adjacent core time nodes. The time interval of the transitional time nodes is dynamically determined based on the influence degree of historical events.

[0029] Specifically, first establish a historical event importance evaluation model that comprehensively considers multi-dimensional features such as the scale of building reconstruction, the degree of regional pattern change, and the scope of human activity influence. For each time node in the initial time node sequence, extract the historical event information recorded in its corresponding data set, and calculate the importance score of the historical event through the evaluation model. Determine the core time nodes as those with importance scores exceeding the preset threshold, which usually correspond to key historical moments such as the completion of major buildings, regional reconstruction, and functional transformation. After determining the core time nodes, it is necessary to supplement transitional time nodes between adjacent core time nodes to depict the gradual change process of the scene. A historical event impact degree evaluation model can also be established, which calculates the impact degree of an event based on factors such as the duration, scope of influence, and change rate of the historical event. When the impact degree of a historical event is large, such as during a large-scale urban transformation process, use a smaller time interval (such as 1-2 years) to supplement transitional time nodes; when the impact degree of a historical event is small, such as a small-scale building repair, use a larger time interval (such as 5-10 years) to supplement transitional time nodes. This dynamic time interval setting method based on historical event characteristics not only highlights the key nodes of historical scene evolution but also describes the gradual change process of the scene through reasonable transitional nodes, achieving a refined construction of the historical timeline. The finally formed historical timeline not only retains the important time nodes of historical evolution but also realizes a complete description of the historical scene change process through transitional nodes with dynamic density.

[0030] Step 203: Take each core time node and each transitional time node as time nodes of the historical timeline, and extract the historical element features corresponding to each time node.

[0031] Specifically, for each core time node, extract building feature information from its corresponding historical text materials, including using text analysis techniques to identify attribute data such as the spatial scale, styling style, and material type of the building; extract environmental feature information from historical image materials, including using image analysis techniques to identify element information such as terrain and landform, vegetation distribution, and water system pattern; at the same time, integrate text and image materials to extract human feature information, including function layout, usage method, cultural activities, etc. For transitional time nodes, based on the historical element features of adjacent core time nodes and combined with historical evolution laws, use a feature interpolation algorithm to generate historical element features of the transitional period. For example, for building features, use linear interpolation to calculate the gradual change process of building scale; for environmental features, use morphological interpolation to simulate the evolution process of terrain and landform; for human features, design a feature transition model based on function transformation laws.

[0032] Step 204: Associate each time node with its corresponding historical element features to obtain the historical timeline.

[0033] Specifically, after extracting and generating the historical element features at each time node, a mapping relationship between the time nodes and the feature data is established, and all time nodes are arranged in chronological order to form a historical timeline data structure containing complete historical element features. This feature extraction method based on multi-source historical materials not only comprehensively depicts the features of historical scenes, but also ensures the continuity of the scene evolution process through feature interpolation, providing rich feature information and a clear chronological framework for subsequent scene reconstruction.

[0034] Based on the above embodiments, as an alternative embodiment, the step of extracting the historical element features corresponding to each time node may further include the following steps: Step 2031: Extract the initial historical element features corresponding to each time node. The initial historical element features at least include building features, environmental features, and humanistic features.

[0035] Specifically, in order to accurately evaluate the completeness of the historical element features at each time node, it is first necessary to extract the initial historical element features from historical materials. Feature extraction is performed on historical text materials through natural language processing technology to identify the building features described in the text, including attribute data such as the planar scale, spatial height, facade shape, and building materials of the building; computer vision technology is used to extract feature information from historical image materials to identify environmental features, including elements such as terrain undulation, vegetation coverage, and water system distribution; humanistic features are extracted by combining text mining and image analysis technologies, including information such as building functions, usage methods, and cultural activities.

[0036] Step 2032: Evaluate the completeness of the initial historical element features corresponding to each time node to obtain the feature completeness.

[0037] Specifically, after feature extraction, a feature completeness evaluation model is established. This model is evaluated based on preset feature importance weights and feature completeness indicators. For building features, evaluate the completeness of data such as geometric attributes, material attributes, and style attributes of the building; for environmental features, evaluate the coverage of elements such as terrain data, vegetation data, and water system data; for humanistic features, evaluate the completeness of information such as functional attributes, usage attributes, and cultural attributes. The evaluation scores of various features are weighted and calculated according to preset weights to obtain the feature completeness of this time node. This integrity evaluation method based on multi-dimensional features not only considers the importance of different types of features, but also reflects the integrity requirements of feature data, providing a clear direction for subsequent feature completion and optimization. Through the quantitative evaluation of feature completeness, the missing parts of the historical element features at each time node can be effectively identified, providing a basis for subsequent feature completion and optimization, thereby ensuring the accuracy and integrity of historical scene reconstruction.

[0038] Step 2033: Obtain abnormal time nodes with feature integrity lower than the integrity threshold, and perform feature supplementation based on the historical element features of the adjacent time nodes of the abnormal time nodes.

[0039] Specifically, first set the feature integrity threshold, and mark the time nodes with feature integrity lower than this threshold as abnormal time nodes. For each abnormal time node, obtain its adjacent time nodes before and after, and extract the historical element features of these adjacent nodes. By establishing a feature supplementation model, this model performs feature interpolation and inference based on the feature data of the adjacent time nodes. For the supplementation of building features, a spatial form interpolation algorithm is used to calculate the building features of the abnormal nodes based on the building geometric data of the adjacent time nodes; for the supplementation of environmental features, a geographical element evolution model is used to deduce the environmental features of the abnormal nodes based on the environmental data of the adjacent time nodes; for the supplementation of humanistic features, a functional evolution law is used to infer the humanistic features of the abnormal nodes based on the usage features of the adjacent time nodes.

[0040] Step 2034: After obtaining the historical element features corresponding to each time point after supplementation, delete the adjacent time nodes with historical element feature similarity higher than the similarity threshold to obtain the historical element features corresponding to each time node.

[0041] Specifically, after completing the feature supplementation, establish a feature similarity calculation model, which comprehensively considers the degree of difference in building features, environmental features, and humanistic features, and calculates the feature similarity between adjacent time nodes. Set the feature similarity threshold. When the feature similarity of adjacent time nodes is higher than this threshold, it indicates that the historical scene features expressed by these nodes are highly similar, and the transitional time nodes among them can be deleted, and the core time nodes can be retained. This processing method based on feature supplementation and node optimization not only ensures the integrity of historical element features but also avoids the interference of redundant time nodes, thus obtaining a historical timeline with complete features and refined nodes, providing high-quality feature data support for subsequent scene reconstruction.

[0042] Step 30: Based on the historical element features corresponding to each time node, determine the target historical scene corresponding to each time node.

[0043] The historical element features in the embodiments of the present application refer to the set of various feature information that can characterize the target historical scene in different periods, mainly including the following three aspects: building features, environmental features, and humanistic features.

[0044] The target historical scene in the embodiments of the present application refers to the spatial environment of a specific historical period that needs to be digitally reconstructed. This scene has a clear geographical location range and time span, and can be a spatial area of different scales such as a historical building complex, a historical block, or a historical urban area.

[0045] Specifically, in a feasible embodiment, a building model can be constructed based on building features, the geometric outer contour of the building can be determined using the spatial scale data of the building, the three-dimensional form of the building can be generated according to the building shape features, the surface attributes of the model can be set based on the building material information, and the detailed construction elements can be added based on the building component data. Secondly, an environmental model can be constructed based on environmental features, a terrain surface model can be generated using the topographic data, plant models can be arranged according to the vegetation distribution information, and a water body model can be constructed based on the water system pattern data. Then, scene attributes can be set based on humanistic features, the usage attributes of the space can be determined according to the building function information, activity areas can be set based on the usage mode data, and cultural element identifiers can be added based on the cultural connotation information. After the construction of various element models is completed, a scene organization algorithm is used to spatially integrate elements such as the building model and the environmental model to form a complete target historical scene.

[0046] Based on the above embodiments, as another alternative embodiment, the step of determining the target historical scene corresponding to each time node based on the historical element features corresponding to each time node may further include the following steps: Step 301: For any two adjacent time nodes on the historical time axis, compare the historical element features between the adjacent time nodes to obtain a comparison result.

[0047] Specifically, in order to accurately identify the change characteristics of historical scenes in different periods, a systematic comparative analysis of the historical element features of adjacent time nodes is required. First, compare the building features, calculate the change values of the building plane size and building height, record the specific changes in the roof form and elevation style, count the replacement situations of wall materials and decoration materials, and the changes in components such as columns and doors and windows. Secondly, compare the environmental features, calculate the change values of the ground elevation and slope, record the adjustment situations of tree positions and types, and count the change data of river courses and water body ranges. Finally, compare the humanistic features, record the transformation process of the building usage, count the adjustment methods of the space utilization mode, and record the evolution situations of historical events and folk activities. Through the above comparative analysis, a detailed comparison result table including numerical changes, morphological changes, material changes, and functional changes is formed. The table specifically records: the increase and decrease values of building dimensions, the change descriptions of elevation shapes, the specific contents of material replacements, the detailed records of component adjustments, the numerical values of terrain changes, the positions and quantities of vegetation changes, the range data of water system adjustments, the process records of functional transformations, etc.

[0048] Step 302: Determine the evolution parameters between adjacent time nodes based on the comparison result.

[0049] Specifically, to achieve the precise quantification of the historical scene evolution process, it is necessary to perform parametric processing and standardized calculation on the feature changes in the comparison results. First, three types of key parameters are extracted from the comparison result table: physical parameters include geometric quantities such as building length, width, height, and wall thickness; material parameters include physical quantities such as material density, strength, thermal conductivity, and reflectivity; environmental parameters include environmental quantities such as ground elevation, slope, green space rate, and water area. For each group of parameters, calculate the change amount between adjacent time nodes. For example, if the building height changes from 8 meters to 10 meters, the change amount is 2 meters; if the material density changes from 2000 kg / m³ to 2200 kg / m³, the change amount is 200 kg / m³; if the green space rate changes from 30% to 35%, the change amount is 5%. Arrange these change amounts in chronological order to form a physical parameter change sequence, a material parameter change sequence, and an environmental parameter change sequence.

[0050] To eliminate the influence of different time spans on the change amount, a weighted average method is used to calculate the time span coefficient. Specifically, set the weight of physical parameters to 0.4, the weight of material parameters to 0.3, and the weight of environmental parameters to 0.3. Divide the change amount of each type of parameter by the corresponding time interval (such as 5 years, 10 years, etc.) to obtain the change rate per unit time, and then calculate the weighted average according to the set weights to obtain the time span coefficient reflecting the change rate. For example, if the time interval between two time nodes is 10 years, the annual change rate of physical parameters is 0.2, the annual change rate of material parameters is 0.15, and the annual change rate of environmental parameters is 0.1, then the time span coefficient is 0.2×0.4 + 0.15×0.3 + 0.1×0.3 = 0.155. Then, use the calculated time span coefficient to normalize the parameter change sequence, and divide the change amount of each parameter by the time span coefficient to obtain the standardized change amount. This processing method eliminates the influence of different time spans on the change amount and makes the change amounts in different periods comparable. For example, divide the original change amount by the time span coefficient of 0.155 to obtain the standardized change amount.

[0051] Finally, calculate the evolution parameters based on the standardized change sequence. Substitute the standardized change amounts of physical parameters, material parameters, and environmental parameters into the evolution parameter calculation formula: evolution parameter = standardized physical parameter change amount × 0.4 + standardized material parameter change amount × 0.3 + standardized environmental parameter change amount × 0.3 to obtain a comprehensive index reflecting the historical scene evolution characteristics. This parametric processing method realizes the quantitative expression of the historical scene evolution process by extracting parameters, calculating changes, standardizing processing, and comprehensive calculation. It not only eliminates the influence brought by different time spans but also obtains standardized parameters that can be used for scene transition generation, providing a scientific basis for subsequent scene evolution reconstruction.

[0052] Step 303: Supplement and verify the initial historical scenes corresponding to each time node based on the evolution parameters to obtain the target historical scenes corresponding to each time node.

[0053] Specifically, supplement the building elements according to the physical parameters in the evolution parameters, and improve the building space characteristics by adjusting the geometric dimensions of the building (such as adjusting the building height from 8 meters to 10 meters), updating building components (such as adding or removing doors and windows), and correcting the spatial layout (such as adjusting room partitions). Secondly, supplement the building materials based on the material parameters in the evolution parameters, and improve the building material characteristics by updating the wall materials (such as changing from blue bricks to red bricks), adjusting the surface texture (such as changing from rough to smooth), and changing the color attributes (such as changing from grayish-white to warm yellow). Then, supplement the scene environment according to the environmental parameters in the evolution parameters, and improve the environmental element characteristics by correcting the terrain elevation (such as raising the local ground by 0.5 meters), adjusting the vegetation distribution (such as increasing the green area by 100 square meters), and updating the water system layout (such as widening the river by 2 meters). After completing the element supplement, it is necessary to verify the scene. Specifically, compare the supplemented scene with historical records such as historical documents and archaeological discoveries to verify the rationality of the scene characteristics; at the same time, calculate the mutual relationships of each element based on the evolution parameters to verify the coordination of the element combination; in addition, check the integrity of the scene to ensure that all necessary historical elements are reasonably presented. Through this process of supplement and verification, the initial historical scene is improved and optimized to form a target historical scene that accurately reflects historical characteristics.

[0054] Step 40: Generate a dynamic evolution map of the target historical period based on the time sequence of each time node on the historical timeline and the target historical scenes of each time node.

[0055] Specifically, in order to generate a dynamic evolution map that accurately reflects the evolution process of the historical scene, it is necessary to perform serialization processing and feature trajectory calculation on the target historical scene. First, arrange the target historical scenes of each time node on the historical timeline in chronological order, such as constructing an ordered scene sequence for the target historical scenes in 1900, 1920, and 1950 in sequence to ensure the correct chronological relationship of the scenes. Then, extract the key feature points of adjacent target historical scenes in the scene sequence. These feature points include building element feature points (such as building corner points, door and window position points, roof contour points) and environmental element feature points (such as terrain feature points, vegetation position points, water system boundary points).

[0056] For each feature point, its specific position is determined by calculating spatial coordinates. For example, the coordinates of building corner point A in 1900 are (x1, y1, z1), and in 1920 are (x2, y2, z2); the coordinates of terrain feature point B in 1900 are (x3, y3, z3), and in 1920 are (x4, y4, z4). Then, based on the extracted spatial coordinates of the feature points, a feature trajectory is established. By calculating the movement path of the feature points between two time nodes, the change trajectory of the scene elements is determined. For example, the feature trajectory of building corner point A is a spatial curve from (x1, y1, z1) to (x2, y2, z2), and the feature trajectory of terrain feature point B is a spatial curve from (x3, y3, z3) to (x4, y4, z4). Based on the established feature trajectory, an interpolation algorithm is used to calculate the scene transition frames. Specifically, multiple time points are evenly inserted on the feature trajectory, and the scene state corresponding to each time point is calculated.

[0057] For example, between 1900 and 1920, the positions of the feature points are calculated at 2-year intervals to generate 10 transition scenes. Finally, the target historical scene and the calculated scene transition frames are combined in chronological order on the historical time axis to generate a complete dynamic evolution map. This method for generating a dynamic evolution map based on feature trajectories realizes the continuous reproduction of the historical scene evolution process through the precise positioning and trajectory calculation of the feature points of the scene elements, making the scene changes more real and smooth. The generated dynamic evolution map not only accurately shows the spatial change process of the building elements and environmental elements, but also ensures the smoothness of the scene transition through the calculation of the feature trajectories, providing an accurate visual expression method for the dynamic display of historical and cultural heritage.

[0058] Based on the above embodiments, as another alternative embodiment, the method for reconstructing a scene based on historical knowledge may further include the following steps: Specifically, in order to provide a flexible and information-rich historical scene interaction experience, it is necessary to implement the functions of multi-dimensional exploration and detailed information query of the scene. When receiving the scene exploration operation input by the user, the user selects a specific time node (such as selecting 1920) through the time slider. The system quickly locates the target historical scene in 1920 in the dynamic evolution map and pauses the animation playback to display the scene state at this time node. At the same time, when the user performs a perspective adjustment operation by dragging the mouse, touching the screen, etc., the system calculates the multi-perspective projection images of the target historical scene in real time. Specifically, by setting the position parameters of the virtual camera (such as the camera coordinates are (x, y, z) and the viewing direction is (α, β, γ)), perspective projection algorithms are used to generate scene images from different perspectives, enabling the user to observe the scene details from multiple angles. For example, the user can observe the building layout from a top-down perspective, the facade features from a side view, and the roof details from a bottom-up perspective.

[0059] When a user performs a query operation on a specific element in a scene (such as clicking on a building), the system automatically extracts the historical literature corresponding to the element, including information such as the construction age, historical evolution, architectural features, and important events. For example, when the user clicks on an ancient building, the system extracts relevant literature records such as the construction time, historical uses, architectural style, and important historical events of the building. Subsequently, the system associates and displays the extracted historical literature with the scene projection image in the current perspective, sets up an information display area beside the scene image, presents the literature in the form of text, charts, etc., and establishes a correspondence between the literature information and the scene elements through visual annotations. For example, when displaying literature related to building components, the corresponding component positions are highlighted in the scene image. This interactive scene exploration method realizes the free switching of the time dimension of the scene through time node selection, the flexible observation of the spatial dimension of the scene through perspective adjustment, and the in-depth understanding of the information dimension of the scene through detail query. The multi-perspective projection images generated by the system provide users with an all-round scene observation perspective, and the extracted historical literature provides detailed historical background information for the scene elements. The associated display of the two not only meets the user's need to observe scene details but also meets the need to learn historical knowledge.

[0060] Please refer to Figure 2 which is a schematic diagram of the modules of a scene reconstruction system based on historical knowledge provided by an embodiment of this application. The scene reconstruction system based on historical knowledge may include: a database acquisition module, a timeline construction module, a scene determination module, and an evolution diagram generation module, where: The database acquisition module is used to acquire a historical database for a target historical period, and the historical database includes at least historical text materials and historical image materials; The timeline construction module is used to construct a historical timeline for the target historical period based on the historical database, and the historical timeline includes multiple time nodes and the historical element features corresponding to each time node; The scene determination module is used to determine the target historical scene corresponding to each time node based on the historical element features corresponding to each time node; The evolution diagram generation module is used to generate a dynamic evolution diagram for the target historical period based on the time sequence of each time node on the historical timeline and the target historical scenes of each time node.

[0061] Optionally, the timeline construction module is further used to extract time attributes from the historical text materials and historical image materials in the historical database, and associate and combine the materials with the same time attributes to obtain an initial time node sequence; Screen time nodes containing key historical events or important historical features from the initial time node sequence as core time nodes, and supplement transitional time nodes between adjacent core time nodes. The time interval of the transitional time nodes is dynamically determined based on the impact degree of historical events; Take each of the core time nodes and each of the transitional time nodes as time nodes of the historical timeline, and extract the historical element features corresponding to each of the time nodes; Associate each of the time nodes and the corresponding historical element features to obtain the historical timeline.

[0062] Optionally, the timeline construction module is further configured to extract the initial historical element features corresponding to each of the time nodes. The initial historical element features at least include architectural features, environmental features, and humanistic features; Conduct a completeness assessment on the initial historical element features corresponding to each of the time nodes to obtain the feature completeness; Obtain abnormal time nodes whose feature completeness is lower than the completeness threshold, and perform feature supplementation based on the historical element features of the adjacent time nodes of the abnormal time nodes; After obtaining the historical element features corresponding to each of the supplemented time points, delete adjacent time nodes whose historical element feature similarity is higher than the similarity threshold to obtain the historical element features corresponding to each of the time nodes.

[0063] Optionally, the scenario determination module is further configured to compare the historical element features between any two adjacent time nodes on the historical timeline to obtain a comparison result; Determine the evolution parameter between the adjacent time nodes based on the comparison result; Supplement and verify the initial historical scenarios corresponding to each of the time nodes based on the evolution parameter to obtain the target historical scenarios corresponding to each of the time nodes.

[0064] Optionally, the scenario determination module is further configured to extract the physical parameters, material parameters, and environmental parameters of each historical element feature in the adjacent time nodes from the comparison result; Calculate the change amount of each parameter between the adjacent time nodes to obtain a parameter change sequence; Based on the parameter change sequence, calculate the time span coefficient between the adjacent time nodes by using a weighted average method; Normalize the parameter change sequence according to the time span coefficient to obtain a standardized change sequence; Calculate the evolution parameter between the adjacent time nodes based on the standardized change sequence.

[0065] Optionally, the evolution graph generation module is further configured to construct the target historical scenarios at each of the time nodes into a scenario sequence in chronological order; Extract the key feature points of adjacent target historical scenarios in the scenario sequence, and calculate the spatial coordinates of the key feature points; Establish a feature trajectory based on the spatial coordinates of the key feature points, calculate a scene transition frame based on the feature trajectory, and combine the target historical scenario and the scene transition frame in the time order of each time node on the historical time axis to generate the dynamic evolution graph.

[0066] Optionally, the evolution graph generation module is further configured to receive a user's scene exploration operation, where the scene exploration operation includes a time node selection operation and a perspective adjustment operation; In response to the time node selection operation, locate the target historical scenario corresponding to the time node in the dynamic evolution graph; In response to the perspective adjustment operation, calculate a multi-perspective projection image of the target historical scenario; Obtain a user's scene detail query operation, and extract historical literature materials of corresponding scene elements; Associate and display the historical literature materials with the multi-perspective projection image.

[0067] It should be noted that: when the system provided in the above embodiments realizes its functions, only the above-mentioned division of each functional module is used for illustration. In actual applications, the above functions can be allocated to different functional modules according to needs, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above. In addition, the system and method embodiments provided in the above embodiments belong to the same concept, and the specific implementation process can be found in the method embodiments, which will not be repeated here.

[0068] The embodiment of the present application also provides a computer storage medium, which can store multiple instructions. The instructions are suitable for being loaded and executed by a processor to perform a method for scene reconstruction based on historical knowledge in the above embodiments. The specific execution process can refer to the specific description in the above embodiments and will not be repeated here.

[0069] Please refer to Figure 3 The present application also discloses an electronic device. Figure 3 It is a schematic structural diagram of an electronic device disclosed in the embodiment of the present application. The electronic device 300 may include: at least one processor 301, at least one network interface 304, a user interface 303, a memory 305, and at least one communication bus 302.

[0070] Among them, the communication bus 302 is used to realize the connection and communication between these components.

[0071] Among them, the user interface 303 may include a display screen and a camera. Optionally, the user interface 303 may further include standard wired interfaces and wireless interfaces.

[0072] Among them, the network interface 304 may optionally include standard wired interfaces and wireless interfaces (such as WI-FI interfaces).

[0073] Among them, the processor 301 may include one or more processing cores. The processor 301 connects various parts within the entire server through various interfaces and circuits. By running or executing instructions, programs, code sets, or instruction sets stored in the memory 305, and by calling data stored in the memory 305, it executes various functions of the server and processes data. Optionally, the processor 301 may be implemented in at least one of the hardware forms of digital signal processing (DSP), field-programmable gate array (FPGA), and programmable logic array (PLA). The processor 301 may integrate one or a combination of several of a central processing unit (CPU), a graphics processing unit (GPU), and a modem, etc. Among them, the CPU mainly processes the operating system, user interfaces, and application programs, etc.; the GPU is responsible for rendering and drawing the content to be displayed on the display screen; the modem is used to process wireless communications. It can be understood that the above-mentioned modem may not be integrated into the processor 301 and may be implemented separately through a single chip.

[0074] Among them, the memory 305 may include random access memory (RAM) and may also include read-only memory. Optionally, the memory 305 includes a non-transitory computer-readable storage medium. The memory 305 can be used to store instructions, programs, code, code sets, or instruction sets. The memory 305 may include a program storage area and a data storage area. Among them, the program storage area may store instructions for implementing the operating system, instructions for at least one function (such as touch function, sound playback function, image playback function, etc.), instructions for implementing the above-mentioned various method embodiments, etc.; the data storage area may store the data involved in the above-mentioned various method embodiments. Optionally, the memory 305 may further be at least one storage device located far from the aforementioned processor 301. Refer to Figure 3In the memory 305, which is a computer storage medium, an operating system, a network communication module, a user interface module, and an application program of a method for reconstructing a scene based on historical knowledge may be included.

[0075] In Figure 3 In the electronic device 300 shown, the user interface 303 is mainly used to provide an interface for the user to input data and obtain the data input by the user; while the processor 301 can be used to call the application program of the method for reconstructing a scene based on historical knowledge stored in the memory 305. When executed by one or more processors 301, the electronic device 300 is caused to execute the method described in one or more of the above embodiments. It should be noted that for the foregoing method embodiments, for simplicity of description, they are all expressed as a series of action combinations. However, those skilled in the art should know that the present application is not limited by the described action sequence, because according to the present application, certain steps can be performed in other sequences or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily essential to the present application.

[0076] In the above embodiments, the descriptions of the respective embodiments have their own emphases. For the parts not detailed in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0077] In several implementation manners provided by the present application, it should be understood that the disclosed device can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the couplings or direct couplings or communication connections shown or discussed with each other can be through some service interfaces. The indirect couplings or communication connections of the devices or units can be in an electrical or other form.

[0078] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they can be located in one place, or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0079] In addition, in each embodiment of the present application, the functional units can be integrated in a processing unit, or each unit can exist physically alone, or two or more units can be integrated in one unit. The above integrated units can be implemented in the form of hardware or in the form of software functional units.

[0080] When the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a memory and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this application. The aforementioned memory includes various media that can store program codes, such as USB flash drives, mobile hard disks, magnetic disks, or optical discs.

[0081] The above are only exemplary embodiments of the present disclosure and should not be used to limit the scope of the present disclosure. That is, all equivalent changes and modifications made in accordance with the teachings of the present disclosure still fall within the scope covered by the present disclosure. Those skilled in the art will readily think of other implementation schemes of the present disclosure after considering the specification and the disclosure of the practical truth.

[0082] This application aims to cover any variations, uses, or adaptive changes of the present disclosure that follow the general principles of the present disclosure and include common general knowledge or conventional technical means in the technical field not recorded in the present disclosure. The specification and the embodiments are only regarded as exemplary, and the scope and spirit of the present disclosure are defined by the claims.

Claims

1. A scene reconstruction method based on historical knowledge, characterized in that: The method comprises: Acquire a historical database of a target historical period, wherein the historical database includes at least historical text data and historical video data; Constructing a historical timeline of the target historical period based on the historical database, wherein the historical timeline includes a plurality of time nodes and historical element features corresponding to each of the time nodes; Determine the target historical scene corresponding to each of the time nodes based on the historical element features corresponding to each of the time nodes; Based on the time sequence of each of the time nodes on the historical timeline and the target historical scenario of each of the time nodes, a dynamic evolution diagram of the target historical period is generated.

2. The scene reconstruction method based on historical knowledge according to claim 1, characterized in that: The constructing the historical timeline of the target historical period based on the historical database includes: Extracting time attributes from the historical text data and historical image data in the historical database, and associating and combining data with the same time attributes to obtain an initial time node sequence; Selecting time nodes containing key historical events or important historical features from the initial time node sequence as core time nodes, and supplementing transition time nodes between adjacent core time nodes, wherein the time intervals of the transition time nodes are dynamically determined based on the impact of historical events; Each of the core time nodes and each of the transition time nodes are used as a time node of the historical time axis, and the historical element features corresponding to each of the time nodes are extracted; Each of the time nodes and the corresponding historical element features are associated to obtain the historical timeline.

3. The scene reconstruction method based on historical knowledge according to claim 2, characterized in that: The extracting of the historical element features corresponding to each of the time nodes includes: Extracting initial historical element features corresponding to each of the time nodes, wherein the initial historical element features at least include architectural features, environmental features, and cultural features; Performing integrity assessment on the initial historical element features corresponding to each of the time nodes to obtain feature integrity; Acquire the abnormal time node whose feature completeness is lower than the completeness threshold, and perform feature supplementation based on the historical element features of the adjacent time nodes of the abnormal time node; After obtaining the supplemented historical element features corresponding to each of the time points, adjacent time nodes whose historical element feature similarity is higher than a similarity threshold are deleted to obtain the historical element features corresponding to each of the time nodes.

4. The scene reconstruction method based on historical knowledge according to claim 1, characterized in that: The determining, based on the historical element features corresponding to each of the time nodes, the target historical scene corresponding to each of the time nodes, includes: For any two adjacent time nodes on the historical time axis, the historical element features between the adjacent time nodes are compared to obtain a comparison result; Determine the evolution parameters between the adjacent time nodes based on the comparison result; The initial historical scenes corresponding to the time nodes are supplemented and verified based on the evolution parameters to obtain the target historical scenes corresponding to the time nodes.

5. The scene reconstruction method based on historical knowledge according to claim 4 is characterized in that: The determining the evolution parameter between the adjacent time nodes based on the comparison result includes: Extracting physical parameters, material parameters and environmental parameters of the characteristics of each historical element in the adjacent time nodes from the comparison results; Calculating the change of each parameter between the adjacent time nodes to obtain a parameter change sequence; Based on the parameter change sequence, a time span coefficient between adjacent time nodes is calculated by weighted average; Normalizing the parameter change sequence according to the time span coefficient to obtain a standardized change sequence; The evolution parameters between the adjacent time nodes are calculated based on the standardized change sequence.

6. The scene reconstruction method based on historical knowledge according to claim 1, characterized in that: The generating of the dynamic evolution diagram of the target historical period based on the time sequence of each of the time nodes on the historical timeline and the target historical scene of each of the time nodes includes: Constructing the target historical scenes of each time node into a scene sequence in chronological order; Extracting key feature points of adjacent target historical scenes in the scene sequence, and calculating the spatial coordinates of the key feature points; A feature trajectory is established according to the spatial coordinates of the key feature points, and a scene transition frame is calculated based on the feature trajectory. The target historical scene and the scene transition frame are combined according to the time sequence of each time node on the historical timeline to generate the dynamic evolution diagram.

7. The scene reconstruction method based on historical knowledge according to claim 1, characterized in that: The method further comprises: Receiving a scene exploration operation of a user, wherein the scene exploration operation includes a time node selection operation and a viewing angle adjustment operation; In response to the time node selection operation, locating a target historical scene corresponding to a time node in the dynamic evolution graph; In response to the viewing angle adjustment operation, calculating a multi-view projection image of the target historical scene; Obtain the user's scene detail query operation and extract the historical literature data corresponding to the scene elements; The historical document data is associated with the multi-view projection image and displayed.

8. A scene reconstruction system based on historical knowledge, characterized in that: The system comprises: A database acquisition module, used to acquire a historical database of a target historical period, wherein the historical database includes at least historical text data and historical image data; A timeline construction module, used to construct a historical timeline of the target historical period based on the historical database, wherein the historical timeline includes a plurality of time nodes and historical element features corresponding to each of the time nodes; A scene determination module, used to determine the target historical scene corresponding to each of the time nodes based on the historical element features corresponding to each of the time nodes; The evolution diagram generation module is used to generate a dynamic evolution diagram of the target historical period based on the time sequence of each time node on the historical timeline and the target historical scene of each time node.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a plurality of instructions, and the instructions are suitable for being loaded by a processor and executing the method according to any one of claims 1 to 7.

10. An electronic device, characterized in that: It includes a processor, a memory, a user interface and a network interface, the memory is used to store instructions, the user interface and the network interface are used to communicate with other devices, and the processor is used to execute the instructions stored in the memory so that the electronic device executes the method as described in any one of claims 1-7.

Images