Visual analysis method and system for motif evolution tracking

Abstract

The present invention relates to the field of motif evolution analysis, and relates to a visual analysis method and system for motif evolution tracking. The method comprises: on the basis of the characteristics of motifs to be analyzed, selecting one or more motifs as analytic entry points, and then on the basis of the analytic entry points, searching for and matching similar motifs to obtain a group of motifs having an evolution relationship; organizing selected motifs to determine an evolution sequence of the selected motifs, and on the basis of the degree of change, determining whether to divide the selected motifs into motif subgroups; and recording discoveries and insights in the motif evolution analysis process. By means of the method disclosed in the present invention, a special analysis system is established, to intelligently perform motif evolution tracking, provide an interface for a user to organize evolution tracking processes and results, and provide a full-process support for experts to perform motif evolution analysis and research, thereby remarkably improving the analysis efficiency and laying a foundation for the development of cultural relics archaeology.

Description

A visual analysis method and system for pattern evolution tracking Technical Field

[0001] The present invention belongs to the field of pattern evolution analysis, and in particular relates to a visual analysis method and system for pattern evolution tracking. Background Art

[0002] Patterns were often used as decoration on artifacts such as utensils, clothing, and buildings. Patterns from the same period generally followed common norms and styles. In-depth analysis of pattern evolution can help reveal the characteristics of the spread and development of culture across different eras and regions. Therefore, pattern evolution analysis is often the primary and key method used by archaeologists to study ancient Chinese painted pottery, clothing, and architecture.

[0003] However, there are no tools specifically designed for analyzing pattern evolution in existing technologies. Archaeologists have to manually select patterns with the same theme and evolutionary relationships from hundreds of patterns. After completing the screening, they can only record the overall evolution trend and pairwise changes in text. The entire analysis process relies entirely on manual labor, which is very tedious and time-consuming.

[0004] Summary of the Invention

[0005] In response to the defects in the existing technology, the purpose of the present invention is to provide a visual analysis method and system for tracking pattern evolution, establish a special analysis system that can intelligently track pattern evolution, and provide an interface for users to organize the process and results of evolution tracking, thereby improving the convenience and efficiency of pattern evolution analysis, providing reliable support for archaeologists in the entire process of pattern evolution analysis, and laying the foundation for the development of cultural relics archaeology.

[0006] In order to achieve the above purpose, the technical solution adopted by the present invention is:

[0007] In a first aspect, a visual analysis method for pattern evolution tracking is provided, the method comprising the following steps:

[0008] S1. Select one or more patterns as analysis entries based on the characteristics of the pattern to be analyzed, then perform similar pattern matching based on the analysis entries to select a complete pattern set with an evolutionary relationship;

[0009] S2, organizing the selected patterns to establish a pattern evolution sequence and evolution stages;

[0010] S3. Receive and save annotation records input by users in various forms.

[0011] Furthermore, step S1 includes taking the appearance information, time information and spatial information of the pattern to be analyzed as input, generating a pattern overview with adjustable similarity weight measurement indicators of the pattern to be analyzed, selecting one or more patterns for search and matching based on the pattern overview of the pattern to be analyzed, and selecting patterns with evolutionary relationships based on the different similarities of the patterns.

[0012] Furthermore, the similarity weight measurement index of the patterns in step S1 includes appearance similarity, temporal similarity, and spatial similarity between the patterns.

[0013] Furthermore, the pattern overview in step S1 includes the pattern image, time distribution, and spatial distribution of the pattern to be analyzed.

[0014] Furthermore, in step S2, the evolution order of the patterns is determined according to the appearance similarity, time attribute and space attribute of the selected patterns.

[0015] Furthermore, in step S2, when the pattern evolution includes multiple different stages, the pattern is divided into several subgroups, each subgroup corresponding to a stage.

[0016] Furthermore, step S1 includes checking similar pattern results matched according to different similarities according to user input.

[0017] Furthermore, step S2 includes organizing the established pattern evolution sequence according to user input.

[0018] Furthermore, when the user inputs the annotation record in step S3, the pattern layout is displayed as a sequence-based layout and a space-based layout.

[0019] In a second aspect, a visual analysis system for tracking pattern evolution uses a visual analysis method for tracking pattern evolution as described in the first aspect of the present invention and any optional embodiment thereof to track and analyze the evolution process of a pattern to be analyzed.

[0020] The beneficial technical effects of the present invention are as follows: using the disclosed visual analysis method and system for pattern evolution tracking, one or more patterns are selected as analysis entry points based on the characteristics of the pattern to be analyzed, and then similar patterns are searched and matched based on the analysis entry points to obtain a group of patterns with evolutionary relationships. The selected patterns are organized, the evolutionary sequence of the selected patterns is determined, and whether to divide the patterns into subgroups is determined based on the degree of change; and the findings and insights obtained during the pattern evolution analysis are recorded. Using the method disclosed in the present invention, a specialized analysis system is established that can intelligently track pattern evolution, visualize the evolution tracking process, and provide an interface for users to organize the evolution tracking process and results. This system can provide full-process support for experts in pattern evolution analysis and research, significantly improve analysis efficiency, and lay the foundation for the development of cultural relics archaeology. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] FIG1 is a flow chart of a visual analysis method for pattern evolution tracking disclosed in Embodiment 1 of the present invention;

[0022] FIG2 is a schematic diagram of a working process interface of a visual analysis system for pattern evolution tracking disclosed in a second embodiment of the present invention;

[0023] FIG3 is a diagram illustrating an interface of a pattern selection module in a visual analysis system for pattern evolution tracking disclosed in a second embodiment of the present invention;

[0024] FIG4 is a diagram illustrating an interface for a pattern search interaction process of a pattern selection module in a visual analysis system for pattern evolution tracking disclosed in a second embodiment of the present invention;

[0025] FIG5 is a diagram illustrating an interface of a pattern organization module in a visual analysis system for pattern evolution tracking disclosed in a second embodiment of the present invention;

[0026] FIG6 is an interface diagram of an evolution process recording module in a visual analysis system for pattern evolution tracking disclosed in the second embodiment of the present invention. DETAILED DESCRIPTION

[0027] The present invention will be further described below with reference to the accompanying drawings and specific embodiments.

[0028] Example 1

[0029] As shown in FIG1 , an embodiment of the present invention provides a visual analysis method for pattern evolution tracking, the method comprising the following steps:

[0030] S1. Select one or more patterns as analysis entries based on the characteristics of the pattern to be analyzed, then perform similar pattern matching based on the analysis entries, and select a complete pattern set with an evolutionary relationship.

[0031] Patterns with an evolutionary relationship are typically similar in appearance, spatially close, or temporally adjacent. In this embodiment, the appearance, temporal, and spatial information of the pattern to be analyzed are used as input to generate a pattern overview with adjustable similarity weighting metrics. Based on the pattern overview, one or more patterns are selected for search and matching. Patterns with an evolutionary relationship are selected from these patterns based on their appearance similarity, temporal relationships, and spatial relationships.

[0032] The similarity weight measurement indicators of patterns include appearance similarity, temporal similarity and spatial similarity between patterns. The specific values ​​of the similarity weight measurement indicators are determined based on user input.

[0033] The pattern overview includes images of all patterns to be analyzed and their temporal and spatial distribution to help users select one or more similar patterns.

[0034] Step S1 includes checking similar pattern results matched according to different similarities according to user input.

[0035] S2. Organizing the selected patterns to establish pattern evolution sequences and evolution stages.

[0036] An evolution sequence is established based on the relationship between the selected patterns, and the patterns can be divided into different subgroups according to the degree of change.

[0037] Step S2 includes determining the evolution order of the patterns based on the appearance similarity and time and space attributes of the selected patterns.

[0038] When the pattern evolution includes multiple different stages, the pattern is divided into several subgroups, each corresponding to a stage. After the division is completed, the user can also add a description of each subgroup.

[0039] Step S2 includes organizing the established pattern evolution sequence according to user input.

[0040] S3. After completing the pattern selection and organization, receive and save the user's observations and insights recorded in various forms of annotations.

[0041] The system receives user-entered summaries of pattern evolution, recording and storing their observations and insights. To support flexible recording, the system displays pattern layouts in two formats: sequence-based and space-based. It also supports various annotation formats, including text descriptions, outlines for highlighting local patterns, and labels.

[0042] Example 2

[0043] An embodiment of the present invention provides a visual analysis system for tracking pattern evolution. The system uses a visual analysis method for tracking pattern evolution as described in Example 1 of the present invention and any optional implementation manner thereof to track and analyze the evolution process of the pattern to be analyzed.

[0044] As shown in Figure 2, a visual analysis system for pattern evolution tracking disclosed in an embodiment of the present invention is used to track and analyze the evolution of a pattern to be analyzed, using pattern information, temporal information, and spatial information as system inputs. The system includes a pattern selection module a, a pattern organization module b, and an evolution process recording module c. The pattern selection module a selects a group of patterns with an evolutionary relationship; the pattern organization module b determines the evolution sequence of the selected patterns and groups them; and the evolution process recording module c records findings and insights during the evolution process.

[0045] As shown in Figure 3, the pattern selection module includes the following five units.

[0046] The space tree view Used to display the spatial distribution of patterns. Provinces and cities are represented by rectangles, with horizontal indentations used to distinguish between provinces and cities. Each rectangle contains a name label and an icon consisting of a shaded ring and a number inside. The icon represents the proportion and total number of patterns associated with that province or city. To ensure data visibility, the proportion displayed within each city is based on the total number of patterns in its province, rather than the total number of patterns.

[0047] Timeline view This view shows the temporal distribution of patterns. Solid rectangles represent types, while dashed rectangles represent cultures. Similar to the spatial tree view, each rectangle contains a shaded ring with a number indicating the proportion and number of patterns associated with that culture or type.

[0048] Triprojection View It is used to integrate the appearance similarity and temporal and spatial proximity of patterns using a weight mechanism. The weights of the three parts are controlled by a triangle control. to control. Users can modify the weight by moving the anchor points inside the control, and the weight corresponding to each vertex will increase as the anchor points get closer. When the appearance similarity weight is 1, the view will show the similarity of the pattern images. The similarity is obtained by the perception-based measurement method LPIPS, and then the pattern layout is obtained by t-SNE. When the spatial weight is 1, the view is displayed as an abstract map with the pattern image superimposed on its corresponding city. When the time weight is set to 1, the pattern image will be aligned along the x-axis with the type center in the timeline view, and its y-axis position is determined by the appearance similarity weight and the spatial weight in the previous step.

[0049] Pattern Group View This displays created pattern groups with evolving relationships. Each row represents a pattern group, and the columns indicate the pattern group name, subgroups, and number of patterns. Users can delete, organize, and access the record interface using the three icons from left to right.

[0050] Diffusion lens Because projected views can be obscured by patterns, a diffusion lens is introduced to mitigate this issue. Once activated, users can click on a specific area in the view they wish to examine more closely. The pattern then automatically expands outward from the clicked location, with the direction of diffusion determined by the clicked location and the image's center.

[0051] As shown in Figure 4, the pattern search interaction process in the pattern selection module is detailed in the pie menu. The pie menu is triggered by clicking on the pattern image. It contains two parts: filter and create, which are used to perform pattern-based search and pattern group operations respectively. The filter part is divided into three operations: similarity search Spatial Search and time search The outermost layer of the filter consists of concentric rings that act as parameter controllers. For similarity, these control the number of patterns displayed based on their similarity to the target pattern. For spatial and temporal filtering, they determine the number of cities and types displayed that are close to the target pattern. All interactions within the pie menu are triggered by hovering the mouse. This provides a more fluid interaction experience than clicking. Hovering over the concentric rings also displays a text tooltip explaining the specific action to be performed.

[0052] Similarity Search Considering that global projection distortion may affect the user's perception of pattern similarity, the system uses ego-centric projection to provide a more reliable similarity relationship between the target pattern and patterns that meet the search criteria. The target pattern is located at the center of the view and is distinguished by a solid brown outline. The radial distance between other patterns and the target pattern indicates their precise similarity. In addition, the angular difference between other patterns represents their similarity. These similarities are calculated using simulated annealing, a global optimization method.

[0053] Spatial Search Compared to global layout adjustments controlled by triangular controls, spatial search only displays patterns within adjacent cities, resolving overlapping results by saving screen space. Specifically, the system handles overlaps within cities and between cities. The system uses circular packing technology to determine the layout of patterns within cities. When handling overlaps between cities, the patterns in the affected cities are repositioned together based on the relative orientation of the cities. Bubble Sets are used to provide clear boundaries for each city.

[0054] Time Search Similar to spatial search, the optimization of temporal search results compared to directly setting the time weight to 1 through the triangle control is also mainly reflected in solving overlaps. The initial layout of the results encodes the type of pattern through the x-direction position and the y-direction position encodes the similarity between patterns. In a type, if two patterns overlap, the lower pattern will move downward. If the pattern at the bottom is blocked, the system will ensure the visibility of all patterns by adjusting their overall position, even if this will cause slight overlap. At the same time, for overlaps between types, the system adopts a strategy similar to spatial search. The difference is that patterns are only allowed to move horizontally.

[0055] As shown in Figure 5, the interface of the pattern structure module b includes the following two parts:

[0056] Group Action List by Clicking The second icon in the dialog box is used to determine the evolution sequence of the pattern (i.e. the order of evolution). In this mode, the triple projection only displays the previously selected pattern. Their position along the x-axis indicates their type, while their position along the y-axis indicates their similarity in appearance. Due to the introduction of overlapping strategies and spacing, the positions of the patterns in both directions can only roughly reflect their temporal and similarity relationships. Each pattern displays its temporal and spatial properties directly below its image. By clicking on two patterns with a direct evolutionary relationship, the user can create a line connecting them, representing the order of evolution.

[0057] The evolution of patterns sometimes manifests itself in different stages. The system allows users to divide patterns into subgroups, with each subgroup corresponding to a specific stage. Users can use the group operation list to In this mode, the pattern layout remains the same as in the sequence building mode, and the subgroup operation panel appears. The Add icon on the far right is used to create a new subgroup. Each new subgroup is assigned a unique color. For each subgroup, the system supports three operations: modifying subgroup members, deleting a subgroup, and adding a description (the three icons from left to right). When modifying members, users can add a pattern to the subgroup by clicking the corresponding image.

[0058] As shown in Figure 6, the interface of the evolution process recording module c includes the following parts:

[0059] The spatial tree view and timeline view also exist in the pattern selection module a interface. They are simplified to only display the spatial and temporal distribution of the selected pattern and display the image thumbnails of the pattern.

[0060] The Subgroup panel is located at the top of the interface and is used to add descriptions for each subgroup.

[0061] Record View and A circular icon used to display the image, temporal and spatial attributes of each pattern, as well as user-provided information. The color of the icon indicates the subgroup to which the pattern belongs, and the number inside indicates the order of the pattern in the evolution sequence. Arrows connect adjacent patterns in the evolution sequence. The view provides sequence-based and space-based There are two layout modes, users can switch between them through the radio button in the navigation bar at the top of the interface. The pattern arrangement in the view is not like Panels showing spatiotemporal properties are represented by icons and are collapsed by default.

[0062] Sequence-based layout view The pattern follows a zigzag pattern in this layout. Space-based layout view The patterns are superimposed on a city-centered map. Each city is represented by its center and label. The patterns in each city are laid out using a force-directed strategy. This strategy involves three forces: city center force, boundary force, and collision force. Together, they ensure that: (1) patterns within a city are close to each other; (2) patterns are primarily located within the city boundaries; and (3) patterns do not overlap with each other or with the city center and label. In addition, to maintain spatial consistency with the evolving sequence, the system sets an angle for the movement of each pattern based on its order. This linear mapping ensures that adjacent patterns in the sequence move in similar directions.

[0063] Annotation Panel Three types of annotation are provided (text description, outline of highlighted local pattern, and label) to help users record their findings and insights. Labels include overall labels and local labels, which are used to describe the overall evolution trend and pairwise changes between patterns respectively. In order to reduce the labor required to annotate the two layouts, the system adopts a semi-automatic strategy to bind and add annotations. Specifically, it can automatically identify visual elements bound to user annotations. Descriptions and labels are bound to the lines connecting adjacent patterns. They are then automatically added to the starting position of the corresponding lines in the other layout. Users can drag and adjust as needed. The outline is bound to the closest pattern. Given that the size of patterns in different layouts may vary, the system calculates the position and size of the newly added outline in the other layout based on its relative position and size to the pattern in the original layout.

[0064] As can be seen from the above embodiments, the present invention discloses a visual analysis method and system for tracking pattern evolution, which can be applied to the archaeology of cultural relics such as utensils, clothing, and buildings. By selecting one or more patterns as analysis entry points based on the characteristics of the pattern to be analyzed, and then searching and matching similar patterns based on the analysis entry points, a group of patterns with evolutionary relationships is obtained. The selected patterns are organized, the evolution sequence of the selected patterns is determined, and whether to divide the patterns into subgroups is determined based on the degree of change; and the findings and insights obtained during the pattern evolution analysis process are recorded. Using the method disclosed in the present invention, a specialized analysis system is established that can intelligently track pattern evolution and provide an interface for users to organize the evolution tracking process and results. This system can provide full-process support for experts in pattern evolution analysis and research, significantly improving analysis efficiency and laying the foundation for the development of cultural relics archaeology.

[0065] The method and system of the present invention are not limited to the embodiments described in the specific implementation manner. Those skilled in the art may derive other implementation manners based on the technical solution of the present invention, which also fall within the scope of the technical innovation of the present invention.

Claims

1. A visual analysis method for pattern evolution tracking, the method The following steps are involved: S1. Select one or more patterns as analysis entries according to the characteristics of the pattern to be analyzed, then match similar patterns according to the analysis entries, and select a complete pattern set with an evolution relationship; S2, organizing the selected patterns to establish a pattern evolution sequence and evolution stages; S3. Receive and save annotation records input by users in various forms.

2. A visual analysis method for pattern evolution tracking as claimed in claim 1, Features: Step S1 includes taking the appearance information, time information and space information of the pattern to be analyzed as input, generating a pattern overview with adjustable similarity weight measurement indicators of the pattern to be analyzed, selecting one or more patterns for search and matching according to the pattern overview of the pattern to be analyzed, and selecting patterns with evolutionary relationships according to different similarities of the patterns.

3. A visual analysis method for pattern evolution tracking as claimed in claim 2, Features: The similarity weight measurement indexes of the patterns in step S1 include appearance similarity, time similarity and space similarity between the patterns.

4. A visual analysis method for pattern evolution tracking as claimed in claim 2, Features: The pattern overview in step S1 includes the pattern image, time distribution and space distribution of the pattern to be analyzed.

5. A visual analysis method for pattern evolution tracking as claimed in claim 1, Features: In step S2, the evolution order of the patterns is determined according to the appearance similarity, time attribute and space attribute of the selected patterns.

6. A visual analysis method for pattern evolution tracking as claimed in claim 5, Features: In step S2, when the pattern evolution includes multiple different stages, the pattern is divided into several subgroups, each subgroup corresponding to a stage.

7. A visual analysis method for pattern evolution tracking as claimed in claim 1, Features: Step S1 includes checking similar pattern results matched according to different similarities according to user input.

8. A visual analysis method for pattern evolution tracking as claimed in claim 1, Features: Step S2 includes organizing the established pattern evolution sequence according to user input.

9. A visual analysis method for pattern evolution tracking as claimed in claim 1, Features: When the user inputs the annotation record in step S3, the pattern layout is displayed as a sequence-based layout and a space-based layout.

10. A visual analysis system for tracking pattern evolution, Features: The visual analysis method for pattern evolution tracking as described in any one of claims 1 to 9 is used to track and analyze the evolution process of the pattern to be analyzed.

Images