A method, device and computer equipment for automatic matching of dynamic symbols

Abstract

The present application relates to a method, device and computer equipment for automatic matching of dynamic symbols. The method comprises: clustering spatiotemporal trajectories according to an equal time interval segmentation model to obtain trajectory cluster characteristics; reading an initial representative trajectory from a representative trajectory set, and generating a final representative trajectory having the same starting point and the same trajectory length as the initial representative trajectory according to the initial representative trajectory; determining whether the final representative trajectory matches the assembly area symbol according to the shape characteristics corresponding to the trajectory length and the distance between the first and last points of the final representative trajectory, and the association characteristics corresponding to the cluster association matrix; if not, calculating the starting point distance and the end point distance of the neighbor representative trajectory closest to the starting point of the initial representative trajectory in the final representative trajectory; matching and outputting with different types of curved arrow symbols according to the shape characteristics corresponding to the starting point distance and the end point distance. The present method can automatically match dynamic symbols.

Description

Technical Field

[0001] The present application relates to the technical field of symbol matching, and in particular to a method, device, computer equipment and storage medium for automatic dynamic symbol matching. Background Art

[0002] Dynamic symbols have certain geographical scope, meaning and form, and their graphic composition is relatively complex. They cannot be drawn using simple basic primitives, and users are required to manually input some control points. Symbols are drawn by calling sub-functions and using related algorithms. After drawing, control points can be added, deleted, adjusted, and the color, transparency, and line type of the symbol can be changed in the style panel. At the same time, corresponding text annotations can be added to assist in the explanation. Due to their shape variability and flexibility, dynamic symbols can be used to represent rescue and evacuation routes, assembly areas, and other situations. In traditional semi-automatic marking, the matching of dynamic symbols often requires manual work because it involves the interpretation of situation information. However, the complex situation information that is constantly updated in a dynamic environment increases the difficulty of interpretation for map markers and reduces the efficiency and timeliness of marking results. In order to realize the automatic marking of dynamic symbols, it is necessary to design corresponding symbol automatic matching algorithms.

[0003] However, since most dynamic symbols have certain geographical scope, meaning and form, the automatic matching of dynamic symbols requires the use of situation information combined with the structural form and representational meaning of the symbols for analysis. The matching of some symbols also needs to be linked to the previous and subsequent temporal and spatial change trends and associations. This is the difficulty of the problem. Summary of the invention

[0004] Based on this, it is necessary to provide a dynamic symbol automatic matching method, device, computer equipment and storage medium that can automatically match dynamic symbols in response to the above technical problems.

[0005] A dynamic symbol automatic matching method, the method comprising:

[0006] Obtain a spatiotemporal trajectory dataset, and use the spatiotemporal trajectory dataset to construct an equal time interval segmentation model;

[0007] The spatiotemporal trajectories are clustered according to the equal time interval segmentation model to obtain trajectory cluster features; the trajectory cluster features include representative trajectory set, cluster correlation matrix and window cluster trajectory point set;

[0008] Reading an initial representative trajectory from the representative trajectory set, and generating a final representative trajectory having the same starting point and the same trajectory length as the initial representative trajectory according to the initial representative trajectory;

[0009] According to the shape features corresponding to the trajectory length and the distance between the first and the last points of the final representative trajectory, and the association features corresponding to the cluster association matrix, it is determined whether the final representative trajectory matches the symbol of the assembly area;

[0010] If not, then the neighbor representative trajectory closest to the starting point of the initial representative trajectory in the final representative trajectory is calculated to obtain the starting point distance and the end point distance of the neighbor representative trajectory;

[0011] According to the shape features corresponding to the starting point distance and the end point distance, different types of curved arrow symbols are matched and output; the curved arrow symbols include: single arrow symbol, symmetrical double arrow symbol and asymmetrical double arrow symbol.

[0012] In one embodiment, determining whether the final representative trajectory matches the assembly area symbol according to the shape features corresponding to the trajectory length and the distance between the first and last points of the final representative trajectory and the association features corresponding to the cluster association matrix includes:

[0013] Set the track length threshold and the track start and end point distance threshold; the track start and end point distance threshold includes the upper and lower distance limits;

[0014] If the trajectory length of the final representative trajectory is greater than the trajectory length threshold, and the distance between the first and last points is less than the distance between the first and last points of the trajectory, then it meets the shape characteristics of the assembly area symbol;

[0015] Then, according to the association features corresponding to the cluster association matrix, it is determined whether there is an associated cluster. If so, it meets the association features of the assembly area symbol, and the final representative trajectory is matched and output with the assembly area symbol.

[0016] In one embodiment, according to the shape features corresponding to the start distance and the end distance, different types of curved arrow symbols are matched and output, including:

[0017] If the starting point distance is greater than the lower limit of the distance threshold between the first and last points of the trajectory, or the final representative trajectory is empty, the final representative trajectory will be matched as a single arrow symbol and output.

[0018] In one embodiment, if the starting point distance and the ending point distance are both less than the lower limit of the distance threshold of the starting and ending points of the trajectory, the final representative trajectory is matched and output as a symmetrical double arrow symbol.

[0019] In one embodiment, if the starting point distance is less than the lower limit of the distance in the track start-end point distance threshold and the end point distance is between the lower limit and the upper limit of the distance in the track start-end point distance threshold, the final representative track is matched as an asymmetric double arrow symbol output.

[0020] In one embodiment, spatiotemporal trajectories are clustered according to an equal time interval segmentation model to obtain trajectory cluster features, including: segmenting the trajectories according to the equal time interval segmentation model to obtain cluster spatiotemporal correlations between adjacent time windows; and quantifying the correlation relationship between clusters using the cluster spatiotemporal correlations to obtain a cluster correlation matrix.

[0021] In one embodiment, an initial representative trajectory is read from a representative trajectory set, and a final representative trajectory having the same starting point and the same trajectory length as the initial representative trajectory is generated based on the initial representative trajectory, including: reading the initial representative trajectory from the representative trajectory set, calculating the trajectory length and the distance between the first and last points of the initial representative; and generating a final representative trajectory different from the initial representative trajectory based on the trajectory length and the distance between the first and last points of the initial representative.

[0022] A dynamic symbol automatic matching device, the device comprising:

[0023] A segmentation model building module is used to obtain a spatiotemporal trajectory dataset and build an equal time interval segmentation model using the spatiotemporal trajectory dataset;

[0024] The spatiotemporal trajectory clustering module is used to cluster spatiotemporal trajectories according to the equal time interval segmentation model to obtain trajectory cluster features; the trajectory cluster features include representative trajectory set, cluster correlation matrix and window cluster trajectory point set;

[0025] A final representative trajectory generating module is used to read the initial representative trajectory from the representative trajectory set, and generate a final representative trajectory having the same starting point and the same trajectory length as the initial representative trajectory according to the initial representative trajectory;

[0026] The assembly area symbol matching module is used to determine whether the final representative trajectory matches the assembly area symbol according to the shape features corresponding to the trajectory length and the distance between the first and last points of the final representative trajectory, and the association features corresponding to the cluster association matrix;

[0027] The neighbor representative trajectory calculation module is used to calculate the neighbor representative trajectory closest to the starting point of the initial representative trajectory in the final representative trajectory to obtain the starting point distance and the end point distance of the neighbor representative trajectory.

[0028] The curved arrow symbol matching module is used to match and output different types of curved arrow symbols according to the shape features corresponding to the starting point distance and the end point distance; the curved arrow symbols include: single arrow symbol, symmetrical double arrow symbol and asymmetrical double arrow symbol.

[0029] A computer device comprises a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0030] Obtain a spatiotemporal trajectory dataset, and use the spatiotemporal trajectory dataset to construct an equal time interval segmentation model;

[0031] The spatiotemporal trajectories are clustered according to the equal time interval segmentation model to obtain trajectory cluster features; the trajectory cluster features include representative trajectory set, cluster correlation matrix and window cluster trajectory point set;

[0032] Reading an initial representative trajectory from the representative trajectory set, and generating a final representative trajectory having the same starting point and the same trajectory length as the initial representative trajectory according to the initial representative trajectory;

[0033] According to the shape features corresponding to the trajectory length and the distance between the first and the last points of the final representative trajectory, and the association features corresponding to the cluster association matrix, it is determined whether the final representative trajectory matches the symbol of the assembly area;

[0034] If not, then the neighbor representative trajectory closest to the starting point of the initial representative trajectory in the final representative trajectory is calculated to obtain the starting point distance and the end point distance of the neighbor representative trajectory;

[0035] According to the shape features corresponding to the starting point distance and the end point distance, different types of curved arrow symbols are matched and output; the curved arrow symbols include: single arrow symbol, symmetrical double arrow symbol and asymmetrical double arrow symbol.

[0036] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the following steps:

[0037] Obtain a spatiotemporal trajectory dataset, and use the spatiotemporal trajectory dataset to construct an equal time interval segmentation model;

[0038] The spatiotemporal trajectories are clustered according to the equal time interval segmentation model to obtain trajectory cluster features; the trajectory cluster features include representative trajectory set, cluster correlation matrix and window cluster trajectory point set;

[0039] Reading an initial representative trajectory from the representative trajectory set, and generating a final representative trajectory having the same starting point and the same trajectory length as the initial representative trajectory according to the initial representative trajectory;

[0040] According to the shape features corresponding to the trajectory length and the distance between the first and the last points of the final representative trajectory, and the association features corresponding to the cluster association matrix, it is determined whether the final representative trajectory matches the symbol of the assembly area;

[0041] If not, then the neighbor representative trajectory closest to the starting point of the initial representative trajectory in the final representative trajectory is calculated to obtain the starting point distance and the end point distance of the neighbor representative trajectory;

[0042] According to the shape features corresponding to the starting point distance and the end point distance, different types of curved arrow symbols are matched and output; the curved arrow symbols include: single arrow symbol, symmetrical double arrow symbol and asymmetrical double arrow symbol.

[0043] The above-mentioned dynamic symbol automatic matching method, device, computer equipment and storage medium, the present application performs spatiotemporal trajectory clustering by establishing an equal time interval segmentation model, extracts trajectory cluster features from the generated trajectory clusters, determines the shape features and association features of the trajectories based on the trajectory cluster features, analyzes the discrimination basis of the symbol type in combination with the spatiotemporal distribution and spatiotemporal association between clusters, and uses the shape features and association features of the trajectories and the discrimination basis to perform symbol automatic matching on the trajectories. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] Figure 1 A schematic diagram of a flow chart of a dynamic symbol automatic matching method in one embodiment;

[0045] Figure 2 A schematic diagram of a trajectory represented by symbols in a gathering area in one embodiment;

[0046] Figure 3 A schematic diagram of a gathering area symbol in another embodiment;

[0047] Figure 4 is a schematic diagram of a curved arrow symbol in another embodiment;

[0048] Figure 5 is a structural block diagram of a dynamic symbol automatic matching device in one embodiment;

[0049] Figure 6 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0050] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0051] In one embodiment, Figure 1 As shown, a dynamic symbol automatic matching method is provided, comprising the following steps:

[0052] Step 102: Obtain a spatiotemporal trajectory dataset, and use the spatiotemporal trajectory dataset to construct an equal time interval segmentation model.

[0053] In order to fully explore the distribution of situation information in space and time and its correlation, the trajectory is divided into segments of different granularities according to data conditions and application requirements when clustering trajectory data. This is called a spatiotemporal segmentation model. Using trajectory segments as units to describe the spatiotemporal local morphology and local semantic attributes of the trajectory can, to a certain extent, take into account the discreteness and continuity of the trajectory and better reflect the regional situation information. The matching of dynamic symbols needs to be linked to the previous and subsequent spatiotemporal change trends and correlations. In order to compare the degree of correlation between trajectory clusters, this application chooses to use an equal time interval segmentation model to segment the trajectory. The equal time interval segmentation model refers to segmenting the trajectory at equal intervals starting from the first point or a certain point in the spatiotemporal trajectory dataset.

[0054] Step 104 , clustering the spatiotemporal trajectories according to the equal time interval segmentation model to obtain trajectory cluster features; the trajectory cluster features include a representative trajectory set, a cluster association matrix, and a window cluster trajectory point set.

[0055] After the equal time interval segmentation model is established, it is necessary to explore the degree of cluster association between adjacent time windows and use the equal time interval segmentation model to cluster spatiotemporal trajectories. The spatiotemporal trajectory clustering based on the equal time interval segmentation model can discover richer situation information. The clustering result outputs trajectory cluster features including representative trajectory set, cluster association matrix and window cluster trajectory point set. The cluster association matrix represents the degree of association between trajectory clusters and can provide matching basis for dynamic symbols with association features such as differentiation, fusion and aggregation.

[0056] Step 106 , reading an initial representative trajectory from the representative trajectory set, and generating a final representative trajectory having the same starting point and the same trajectory length as the initial representative trajectory according to the initial representative trajectory.

[0057] For the assembly area symbol, since the objects in the assembly area have a small range of movement and a relatively fixed position, the overall movement trend is not obvious, such as Figure 2 As shown in the figure, the characteristic reflected in the representative trajectory is that the representative trajectory is "clustered", with a long trajectory length and a short distance between the start and end points. For the symbol in the curved arrow symbol, the start distance and the end distance have their own characteristics. Based on this characteristic, the symbol matching can be performed using the start point distance of the representative trajectory generated by clustering, and a representative trajectory is read from the representative trajectory set as the initial representative trajectory. Based on the initial representative trajectory, multiple final representative trajectories with the same start point and the same trajectory length as the initial representative trajectory can be generated.

[0058] Step 108 , determining whether the final representative trajectory matches the assembly area symbol based on the shape features corresponding to the trajectory length and the distance between the first and last points of the final representative trajectory and the association features corresponding to the cluster association matrix.

[0059] The assembly area symbol is used to indicate the gathering area of ​​people, animals, vehicles or equipment. It is generally represented by an area enclosed by a closed curve. The size of the symbol covers the gathering area, such as Figure 3 As shown in the figure, the assembly area symbols can be divided into two types: arbitrary assembly area symbols and assembly area symbols with specific shape characteristics. Among them, the arbitrary assembly area symbols are as follows: Figure 3 As shown in (a), it is a region symbol formed by a closed curve formed by connecting control points in sequence using a spline curve. Its shape is flexible and can mark any area. The assembly region symbol with specific shape characteristics needs to generate a control polygon of a specific shape based on the input control points, such as Figure 3 As shown in (b), the spline curve is then used for fitting. The fitting result has obvious shape features. Since the assembly area is formed by the convergence of moving objects or the fusion of clusters, there are often associated clusters in time and space. The above two features can be combined to match the cluster with the assembly area symbol. According to the shape features corresponding to the trajectory length and the distance between the first and last points of the final representative trajectory, as well as the association features corresponding to the cluster association matrix, it can be determined whether the final representative trajectory matches the assembly area symbol.

[0060] Step 110: If not, then calculate the neighbor representative trajectory in the final representative trajectory that is closest to the starting point of the initial representative trajectory to obtain the starting point distance and the end point distance of the neighbor representative trajectory.

[0061] Step 112, matching and outputting different types of curved arrow symbols according to shape features corresponding to the starting point distance and the end point distance; the curved arrow symbols include: single arrow symbol, symmetrical double arrow symbol and asymmetrical double arrow symbol.

[0062] In emergency rescue command and dispatch, curved arrow symbols are often used to indicate the direction of travel, trend of change and other situation information, such as Figure 4 As shown in the figure, commonly used curved arrows include single arrows, symmetrical double arrows and asymmetrical double arrows. Curved arrow symbols are generally composed of an arrow body and an arrow head, and sometimes they can be combined with other symbols to form arrows with specific meanings. Figure 4 As shown in (a), the body of the single arrow is the main body of the curved arrow, and its shape is mainly composed of curves. Its symbolic meaning mainly indicates the movement trend of a single mobile cluster. It has no interaction with other clusters in the same time window, and may have spatiotemporal correlation with the adjacent time windows before and after, such as Figure 4 As shown in (b), the shape structures of double arrows and other multi-arrows are based on single arrows. The main difference lies in the connection of the arrow body curves. The Euclidean distance between the start and end points of the two single arrows that form a symmetrical double arrow is relatively close, as shown in Figure 4As shown in (c), the two single arrows that make up the asymmetric double arrow have a closer starting point distance and a farther ending point distance. Based on this feature, the distance between the starting points of the representative trajectories generated by clustering can be used for symbol matching.

[0063] In the above-mentioned dynamic symbol automatic matching method, the present application performs spatiotemporal trajectory clustering by establishing an equal time interval segmentation model, extracts trajectory cluster features from the generated trajectory clusters, determines the shape features and association features of the trajectories based on the trajectory cluster features, analyzes the judgment basis of the symbol type in combination with the spatiotemporal distribution and spatiotemporal association between clusters, and uses the shape features, association features and judgment basis of the trajectories to perform symbol automatic matching on the trajectories.

[0064] In one embodiment, determining whether the final representative trajectory matches the assembly area symbol according to the shape features corresponding to the trajectory length and the distance between the first and last points of the final representative trajectory and the association features corresponding to the cluster association matrix includes:

[0065] Set the track length threshold and the track start and end point distance threshold; the track start and end point distance threshold includes the upper and lower distance limits;

[0066] If the trajectory length of the final representative trajectory is greater than the trajectory length threshold, and the distance between the first and last points is less than the distance between the first and last points of the trajectory, then it meets the shape characteristics of the assembly area symbol;

[0067] Then, according to the association features corresponding to the cluster association matrix, it is determined whether there is an associated cluster. If so, it meets the association features of the assembly area symbol, and the final representative trajectory is matched and output with the assembly area symbol.

[0068] Let the length of the representative trajectory be l, and the distance between its starting and ending points be d se , the trajectory length threshold is l am , the distance threshold between the first and last points of the trajectory is d amin ,The symbol features of the assembly area are summarized in Table 1.

[0069] Table 1 Symbolic features of the assembly area

[0070]

[0071] In one embodiment, according to the shape features corresponding to the start distance and the end distance, different types of curved arrow symbols are matched and output, including:

[0072] If the starting point distance is greater than the lower limit of the distance threshold between the first and last points of the trajectory, or the final representative trajectory is empty, the final representative trajectory will be matched as a single arrow symbol and output.

[0073] In one embodiment, if both the starting point distance and the ending point distance are less than the lower distance limit in the trajectory start and end point distance threshold, the final representative trajectory is matched as a symmetric double arrow symbol and output.

[0074] In one embodiment, if the starting point distance is less than the lower distance limit in the trajectory start and end point distance threshold and the ending point distance is between the lower distance limit and the upper distance limit in the trajectory start and end point distance threshold, the final representative trajectory is matched as an asymmetric double arrow symbol and output.

[0075] Let the parameter d min be the lower limit of the start and end point distance between trajectories, d max be the upper limit of the start and end point distance between trajectories, the starting point distance between the representative trajectories be d s , and the ending point distance be d e , and the specific shape features are shown in Table 4.1.

[0076] Table 4.1 Curved arrow symbol features

[0077]

[0078] If the ending point distance is greater than the upper limit of the start and end point distance between trajectories, determine whether the final representative trajectory is empty. If so, match it as a single arrow and output. If not, recalculate the starting point distance and the ending point distance of the neighbor representative trajectory in the final representative trajectory that is closest to the starting point of the initial representative trajectory for judgment.

[0079] In one embodiment, spatio-temporal trajectory clustering is performed according to the equal time interval segmentation model to obtain the trajectory cluster class features, including: segmenting the trajectory according to the equal time interval segmentation model to obtain the cluster class spatio-temporal correlation degree between adjacent time windows; quantifying the correlation relationship between cluster classes using the cluster class spatio-temporal correlation degree to obtain the cluster class correlation degree matrix.

[0080] Let t m t n a certain cluster within the window be Cm x ={Tm a , Tm b ,…, Tm s}, t n t l a certain cluster within the window be Cn y ={Tn a , Tn b ,…, Tn t}(m < n < l), where Tm a and Tn a respectively represent the trajectory Tr a in the t m t n window and the t n t lThe sub-trajectory in the window, then the cluster Cm x With cluster Cn y The spatiotemporal correlation degree of clusters between is as follows:

[0081]

[0082] If about Cm x With Cn y The spatiotemporal correlation degree C of clusters xy >0, then Cm x With Cn y The cluster-related spatiotemporal correlation is used to quantify the correlation between clusters and establish a cluster-related degree matrix. The cluster-related degree matrix is ​​used to represent the correlation characteristics of the trajectory, that is, whether there is at least one associated cluster in the adjacent time window.

[0083] In one embodiment, an initial representative trajectory is read from a representative trajectory set, and a final representative trajectory having the same starting point and the same trajectory length as the initial representative trajectory is generated based on the initial representative trajectory, including: reading the initial representative trajectory from the representative trajectory set, calculating the trajectory length and the distance between the first and last points of the initial representative; and generating a final representative trajectory different from the initial representative trajectory based on the trajectory length and the distance between the first and last points of the initial representative.

[0084] According to the length of the initial representative trajectory and the distance between the first and last points, multiple final representative trajectories different from the initial representative trajectory can be generated. The final representative trajectory is included in the representative trajectory set. Using the automatic matching method of the present application, all representative trajectories in the representative trajectory set can be automatically matched with dynamic symbols.

[0085] It should be understood that although Figure 1 The steps in the flowchart are shown in sequence as indicated by the arrows, but these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified in this document, there is no strict order restriction for the execution of these steps, and these steps can be executed in other orders. Moreover, Figure 1 At least part of the steps may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily executed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be executed in turn or alternately with other steps or at least part of the sub-steps or stages of other steps.

[0086] In one embodiment, Figure 5As shown, a dynamic symbol automatic matching device is provided, including: a segment model building module 502, a spatiotemporal trajectory clustering module 504, a final representative trajectory generation module 506, a gathering area symbol matching module 508, a neighbor representative trajectory calculation module 510 and a curved arrow symbol matching module 512, wherein:

[0087] A segmentation model building module 502 is used to obtain a spatiotemporal trajectory data set and build an equal time interval segmentation model using the spatiotemporal trajectory data set;

[0088] The spatiotemporal trajectory clustering module 504 is used to cluster the spatiotemporal trajectories according to the equal time interval segmentation model to obtain trajectory cluster features; the trajectory cluster features include a representative trajectory set, a cluster association matrix and a window cluster trajectory point set;

[0089] A final representative trajectory generating module 506 is used to read an initial representative trajectory from the representative trajectory set, and generate a final representative trajectory having the same starting point and the same trajectory length as the initial representative trajectory according to the initial representative trajectory;

[0090] The assembly area symbol matching module 508 is used to determine whether the final representative trajectory matches the assembly area symbol according to the shape features corresponding to the trajectory length and the distance between the first and last points of the final representative trajectory, and the association features corresponding to the cluster association matrix;

[0091] The neighbor representative trajectory calculation module 510 is used to calculate the neighbor representative trajectory closest to the starting point of the initial representative trajectory in the final representative trajectory to obtain the starting point distance and the end point distance of the neighbor representative trajectory.

[0092] The curved arrow symbol matching module 512 is used to match and output different types of curved arrow symbols according to the shape features corresponding to the starting point distance and the end point distance; the curved arrow symbols include: single arrow symbols, symmetrical double arrow symbols and asymmetrical double arrow symbols.

[0093] In one embodiment, the assembly area symbol matching module 508 is further used to determine whether the final representative trajectory matches the assembly area symbol according to the shape features corresponding to the trajectory length and the distance between the first and last points of the final representative trajectory, and the association features corresponding to the cluster association matrix, including:

[0094] Set the trajectory length threshold and the trajectory start-end distance threshold; the trajectory start-end distance threshold includes the upper and lower distance limits; if the trajectory length of the final representative trajectory is greater than the trajectory length threshold, and the start-end distance is less than the trajectory start-end distance threshold, it meets the shape characteristics of the assembly area symbol; then determine whether there is an associated cluster based on the association characteristics corresponding to the cluster association matrix. If so, it meets the association characteristics of the assembly area symbol, and the final representative trajectory is matched with the assembly area symbol for output.

[0095] In one embodiment, the curved arrow symbol matching module 512 is further used to match and output different types of curved arrow symbols according to shape features corresponding to the start distance and the end distance, including:

[0096] If the starting point distance is greater than the lower limit of the distance threshold between the first and last points of the trajectory, or the final representative trajectory is empty, the final representative trajectory will be matched as a single arrow symbol and output.

[0097] In another embodiment, if the starting point distance and the ending point distance are both less than the lower limit of the distance threshold of the starting and ending points of the trajectory, the final representative trajectory is matched and output as a symmetrical double arrow symbol.

[0098] In another embodiment, if the starting point distance is less than the lower limit of the distance in the track start-end point distance threshold and the end point distance is between the lower limit and the upper limit of the distance in the track start-end point distance threshold, the final representative track is matched as an asymmetric double arrow symbol output.

[0099] In one embodiment, the spatiotemporal trajectory clustering module 504 is further used to segment the trajectory according to the equal time interval segmentation model to obtain the spatiotemporal correlation between clusters of adjacent time windows; and to quantify the correlation between clusters using the spatiotemporal correlation between clusters to obtain a cluster correlation matrix.

[0100] In one embodiment, the final representative trajectory generating module 506 is further configured to read an initial representative trajectory from the representative trajectory set, calculate the trajectory length and the distance between the first and last points of the initial representative, and generate a final representative trajectory different from the initial representative trajectory according to the trajectory length and the distance between the first and last points of the initial representative.

[0101] The specific limitation about a kind of dynamic symbol automatic matching device can refer to the limitation of a kind of dynamic symbol automatic matching method mentioned above, which will not be repeated here. Each module in the above-mentioned dynamic symbol automatic matching device can be realized in whole or in part by software, hardware and combination thereof. Each of the above-mentioned modules can be embedded in or independent of the processor in the computer device in hardware form, or can be stored in the memory in the computer device in software form, so that the processor calls and executes the corresponding operation of each of the above modules.

[0102] In one embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as follows: Figure 6As shown. The computer device includes a processor, a memory, a network interface, a display screen and an input device connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a dynamic symbol automatic matching method is implemented. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covering the display screen, or a key, trackball or touchpad set on the computer device housing, or an external keyboard, touchpad or mouse, etc.

[0103] Those skilled in the art will understand that Figure 6 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0104] In one embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the method in the above embodiment when executing the computer program.

[0105] In one embodiment, a computer storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps of the method in the above embodiment are implemented.

[0106] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0107] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0108] The above-mentioned embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the invention patent. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the patent of the present application shall be subject to the attached claims.

Claims

1. A dynamic symbol automatic matching method, It is characterized in that The method comprises: Acquire a spatiotemporal trajectory data set, and construct an equal time interval segmentation model using the spatiotemporal trajectory data set; Performing spatiotemporal trajectory clustering according to the equal time interval segmentation model to obtain trajectory cluster features; the trajectory cluster features include a representative trajectory set, a cluster association matrix, and a window cluster trajectory point set; Reading an initial representative trajectory from the representative trajectory set, and generating a final representative trajectory having the same starting point and the same trajectory length as the initial representative trajectory according to the initial representative trajectory; Determining whether the final representative trajectory matches the assembly area symbol according to the shape features corresponding to the trajectory length and the distance between the first and last points of the final representative trajectory and the association features corresponding to the cluster association matrix; If not, then calculating the neighbor representative trajectory closest to the starting point of the initial representative trajectory in the final representative trajectory to obtain the starting point distance and the end point distance of the neighbor representative trajectory; According to the shape features corresponding to the starting point distance and the end point distance, different types of curved arrow symbols are matched and output; the curved arrow symbols include: a single arrow symbol, a symmetrical double arrow symbol and an asymmetrical double arrow symbol.

2. The method according to claim 1, It is characterized in that Determining whether the final representative trajectory matches the assembly area symbol according to the shape features corresponding to the trajectory length and the distance between the first and last points of the final representative trajectory and the association features corresponding to the cluster association matrix includes: Setting a track length threshold and a track start-end distance threshold; the track start-end distance threshold includes an upper distance limit and a lower distance limit; If the trajectory length of the final representative trajectory is greater than the trajectory length threshold, and the start-end point distance is less than the trajectory start-end point distance threshold, then the shape feature of the assembly area symbol is met; Then, it is determined whether there is an associated cluster according to the associated features corresponding to the cluster association matrix. If so, it meets the associated features of the assembly area symbol, and the final representative trajectory is matched and output with the assembly area symbol.

3. The method according to claim 2, It is characterized in that According to the shape features corresponding to the starting point distance and the end point distance, different types of curved arrow symbols are matched and output, including: If the starting point distance is greater than the lower limit of the distance threshold between the first and last points of the trajectory, or the final representative trajectory is empty, the final representative trajectory is matched as a single arrow symbol and output.

4. The method according to claim 3, It is characterized in that The method further comprises: If the starting point distance and the ending point distance are both less than the lower limit of the distance between the first and last points of the trajectory, the final representative trajectory is matched as a symmetrical double arrow symbol and output.

5. The method according to claim 4, It is characterized in that The method further comprises: If the starting point distance is less than the lower limit of the distance in the track start-end point distance threshold and the end point distance is between the lower limit and the upper limit of the distance in the track start-end point distance threshold, the final representative track is matched as an asymmetric double arrow symbol output.

6. The method according to claim 1, It is characterized in that The spatiotemporal trajectories are clustered according to the equal time interval segmentation model to obtain trajectory cluster features, including: Segment the trajectory according to the equal time interval segmentation model to obtain the cluster spatiotemporal correlation between adjacent time windows; The cluster spatiotemporal correlation is used to quantify the correlation relationship between clusters to obtain a cluster correlation matrix.

7. The method according to claim 6, It is characterized in that Reading an initial representative trajectory from the representative trajectory set, and generating a final representative trajectory having the same starting point and the same trajectory length as the initial representative trajectory according to the initial representative trajectory, comprising: Reading an initial representative trajectory from the representative trajectory set, and calculating the trajectory length and the distance between the first and last points of the initial representative; A final representative trajectory different from the initial representative trajectory is generated according to the trajectory length and the distance between the first and last points of the initial representative trajectory.

8. A dynamic symbol automatic matching device, It is characterized in that The device comprises: A segmentation model building module is used to obtain a spatiotemporal trajectory data set and build an equal time interval segmentation model using the spatiotemporal trajectory data set; A spatiotemporal trajectory clustering module, used to cluster spatiotemporal trajectories according to the equal time interval segmentation model to obtain trajectory cluster features; the trajectory cluster features include a representative trajectory set, a cluster association matrix and a window cluster trajectory point set; A final representative trajectory generating module is used to read an initial representative trajectory from the representative trajectory set, and generate a final representative trajectory having the same starting point and the same trajectory length as the initial representative trajectory according to the initial representative trajectory; A gathering area symbol matching module, used to determine whether the final representative trajectory matches the gathering area symbol according to the shape features corresponding to the trajectory length and the distance between the first and last points of the final representative trajectory, and the association features corresponding to the cluster association matrix; A neighbor representative trajectory calculation module is used to calculate the neighbor representative trajectory closest to the starting point of the initial representative trajectory in the final representative trajectory to obtain the starting point distance and the end point distance of the neighbor representative trajectory; The curved arrow symbol matching module is used to match and output different types of curved arrow symbols according to the shape features corresponding to the starting point distance and the end point distance; the curved arrow symbols include: single arrow symbols, symmetrical double arrow symbols and asymmetrical double arrow symbols.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program. It is characterized in that When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, It is characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images